This volume is product of the third online consciousness conference, held at http:// consciousnessonline. com in February and March 2011. Chapters range over epistemological issues in the science and philosophy of perception, what neuroscience can do to help us solve philosophical issues in the philosophy of mind, what the true nature of black and white vision, pain, auditory, olfactory, or multi-modal experiences are, to higher-order theories of consciousness, synesthesia, among others. Each chapter includes a target article, commentaries, and in most (...) cases, a final response from the author. Though wide-ranging all of the papers aim to understand consciousness both from the inside, as we experience it, and from the outside as we encounter it in our science. (shrink)

This study is to explore the gesture recognition and behavior tracking in swimming motion images under computer machine vision and to expand the application of moving target detection and tracking algorithms based on computer machine vision in this field. The objectives are realized by moving target detection and tracking, Gaussian mixture model, optimized correlation filtering algorithm, and Camshift tracking algorithm. Firstly, the Gaussian algorithm is introduced into target tracking and detection to reduce the filtering loss and make (...) the acquired motion posture more accurate. Secondly, an improved kernel-related filter tracking algorithm is proposed by training multiple filters, which can clearly and accurately obtain the motion trajectory of the monitored target object. Finally, it is proposed to combine the Kalman algorithm with the Camshift algorithm for optimization, which can complete the tracking and recognition of moving targets. The experimental results show that the target tracking and detection method can obtain the movement form of the template object relatively completely, and the kernel-related filter tracking algorithm can also obtain the movement speed of the target object finely. In addition, the accuracy of Camshift tracking algorithm can reach 86.02%. Results of this study can provide reliable data support and reference for expanding the application of moving target detection and tracking methods. (shrink)

This paper presents an implemented computational model of word acquisition which learns directly from raw multimodal sensory input. Set in an information theoretic framework, the model acquires a lexicon by finding and statistically modeling consistent cross‐modal structure. The model has been implemented in a system using novel speech processing, computer vision, and machine learning algorithms. In evaluations the model successfully performed speech segmentation, word discovery and visual categorization from spontaneous infant‐directed speech paired with video images of single objects. These (...) results demonstrate the possibility of using state‐of‐the‐art techniques from sensory pattern recognition and machine learning to implement cognitive models which can process raw sensor data without the need for human transcription or labeling. (shrink)

A new approach examined two aspects of chess skill, long a popular topic in cognitive science. A powerful computer‐chess program calculated the number and magnitude of blunders made by the same 23 grandmasters in hundreds of serious games of slow (“classical”) chess, regular “rapid” chess, and rapid “blindfold” chess, in which opponents transmit moves without ever seeing the actual position. Rapid chess led to substantially more and larger blunders than classical chess. Perhaps more surprisingly, the frequency and magnitude of (...) blunders did not differ in rapid versus blindfold play, despite the additional memory and visualization load imposed by the latter. We discuss the involvement of various cognitive processes in human problem‐solving and expertise, especially with respect to chess. Prior opposing views about the basis of general chess skill have emphasized the dominance of either (a) swift pattern recognition or (b) analyzing ahead, but both seem important and the controversy appears currently unresolvable and perhaps fruitless. (shrink)

This article investigates the concept of the ground truth as both an epistemic and technical figure of knowledge that is central to discussions of machine vision and media techniques of visuality. While ground truth refers to a set of remote sensing practices, it has a longer history in operational photography, such as aerial reconnaissance. Building on a discussion of this history, this article argues that ground truth has shifted from a reference to the physical, geographical ground to the surface of (...) the images echoing earlier points raised by philosopher Jean-Luc Nancy that there is a ground of the image that is central to the task of analysis beyond representational practices. Furthermore, building on the practices of pattern recognition, composite imaging, and different interpretational techniques, we discuss contemporary practices of machine learning that mobilizes geographical earth observation datasets for experimental purposes, including tests such as “fake geography” as well as artistic practices, to show how ground truth is operationalized in such contexts of AI and visual arts. (shrink)

1 Matching Templates and Feature Analysers. 2 Modes of Perception in Left and Right Cerebral Hemispheres. 3 Identification and Recognition. 4 Chess Plying Machines.

Deep neural networks (DNNs) have had extraordinary successes in classifying photographic images of objects and are often described as the best models of biological vision. This conclusion is largely based on three sets of findings: (1) DNNs are more accurate than any other model in classifying images taken from various datasets, (2) DNNs do the best job in predicting the pattern of human errors in classifying objects taken from various behavioral datasets, and (3) DNNs do the best job in (...) predicting brain signals in response to images taken from various brain datasets (e.g., single cell responses or fMRI data). However, these behavioral and brain datasets do not test hypotheses regarding what features are contributing to good predictions and we show that the predictions may be mediated by DNNs that share little overlap with biological vision. More problematically, we show that DNNs account for almost no results from psychological research. This contradicts the common claim that DNNs are good, let alone the best, models of human object recognition. We argue that theorists interested in developing biologically plausible models of human vision need to direct their attention to explaining psychological findings. More generally, theorists need to build models that explain the results of experiments that manipulate independent variables designed to test hypotheses rather than compete on making the best predictions. We conclude by briefly summarizing various promising modeling approaches that focus on psychological data. (shrink)

Current artificial neural network or connectionist models of music cognition embody feature-extraction and feature-weighting principles. This paper reports two experiments which seek evidence for similar processes mediating recognition of short musical compositions by musically trained and untrained listeners. The experiments are cast within a pattern recognition framework based on the vision-audition analogue wherein music is considered an auditory pattern consisting of local and global features. Local features such as inter-note interval, and global features such as melodic (...) contour, are derived from a two-dimensional matrix in which music is represented as a series of frequencies plotted over time.Manipulation of inter-note interval affected accuracy and reaction time measures in a discrimination task, whereas the same variables were affected by manipulation of melodic contour in a classification task. Musical training is thought of as a form of practice in musical pattern recognition and, as predicted, accuracy and reaction time measures of musically trained subjects were significantly better than those of untrained subjects. Given the evidence for feature-extraction and weighting processes in music recognition tasks, two connectionist models are discussed. The first is a single-layer perceptron which has been trained to discriminate between compositions according to inter-note interval. A second network, using the back-propagation algorithm and sequential input of patterns, is also discussed. (shrink)

Human motion gesture recognition is the most challenging research direction in the field of computer vision, and it is widely used in human-computer interaction, intelligent monitoring, virtual reality, human behaviour analysis, and other fields. This paper proposes a new type of deep convolutional generation confrontation network to recognize human motion pose. This method uses a deep convolutional stacked hourglass network to accurately extract the location of key joint points on the image. The generation and identification part of (...) the network is designed to encode the first hierarchy and the second hierarchy and show the spatial relationship of human body parts. The generator and the discriminator are designed as two parts in the network, and they are connected together in order to encode the possible relationship of appearance and, at the same time, the possibility of the existence of human body parts and the relationship between each part of the body and its parental part coding. In the image, the key nodes of the human body model and the general body posture can be identified more accurately. The method has been tested on different data sets. In most cases, the results obtained by the proposed method are better than those of other comparison methods. (shrink)

Computational visual perception, also known as computer vision, is a field of artificial intelligence that enables computers to process digital images and videos in a similar way as biological vision does. It involves methods to be developed to replicate the capabilities of biological vision. The computer vision’s goal is to surpass the capabilities of biological vision in extracting useful information from visual data. The massive data generated today is one of the driving factors for the tremendous growth of (...) computer vision. This survey incorporates an overview of existing applications of deep learning in computational visual perception. The survey explores various deep learning techniques adapted to solve computer vision problems using deep convolutional neural networks and deep generative adversarial networks. The pitfalls of deep learning and their solutions are briefly discussed. The solutions discussed were dropout and augmentation. The results show that there is a significant improvement in the accuracy using dropout and data augmentation. Deep convolutional neural networks’ applications, namely, image classification, localization and detection, document analysis, and speech recognition, are discussed in detail. In-depth analysis of deep generative adversarial network applications, namely, image-to-image translation, image denoising, face aging, and facial attribute editing, is done. The deep generative adversarial network is unsupervised learning, but adding a certain number of labels in practical applications can improve its generating ability. However, it is challenging to acquire many data labels, but a small number of data labels can be acquired. Therefore, combining semisupervised learning and generative adversarial networks is one of the future directions. This article surveys the recent developments in this direction and provides a critical review of the related significant aspects, investigates the current opportunities and future challenges in all the emerging domains, and discusses the current opportunities in many emerging fields such as handwriting recognition, semantic mapping, webcam-based eye trackers, lumen center detection, query-by-string word, intermittently closed and open lakes and lagoons, and landslides. (shrink)

The papers included are divided into five sections: Psychology and Philosophy of Perception and Discovery, Integrations of Experimental Findings, Theoretical Developments, Experimental Results from Neurophysiology and Psychology Pertinent to Model Building, and Computer Simulations of Complex Models. The last of these sections will probably prove most interesting to the contemporary philosopher of mind. Peirce, Cassirer, and Wittgenstein are the philosophers who make the scene in the first section; inclusion of material from the last of these is no mean editorial (...) feat. The volume aims to be comprehensive rather than intensive and while this makes it ideal for the philosopher, the psychologist may find it thin in spots.—E. A. R. (shrink)

During 2018, as part of a research project funded by the Deviant Practice Grant, artist Bruno Moreschi and digital media researcher Gabriel Pereira worked with the Van Abbemuseum collection (Eindhoven, NL), reading their artworks through commercial image-recognition (computer vision) artificial intelligences from leading tech companies. The main takeaways were: somewhat as expected, AI is constructed through a capitalist and product-focused reading of the world (values that are embedded in this sociotechnical system); and that this process of using AI (...) is an innovative way for doing institutional critique, as AI offers an untrained eye that reveals the inner workings of the art system through its glitches. This paper aims to regard these glitches as potentially revealing of the art system, and even poetic at times. We also look at them as a way of revealing the inherent fallibility of the commercial use of AI and machine learning to catalogue the world: it cannot comprehend other ways of knowing about the world, outside the logic of the algorithm. But, at the same time, due to their “glitchy” capacity to level and reimagine, these faulty readings can also serve as a new way of reading art; a new way for thinking critically about the art image in a moment when visual culture has changed form to hybrids of human–machine cognition and “machine-to-machine seeing”. (shrink)

This book attempts to marry truth-conditional semantics with cognitive linguistics in the church of computational neuroscience. To this end, it examines the truth-conditional meanings of coordinators, quantifiers, and collective predicates as neurophysiological phenomena that are amenable to a neurocomputational analysis. Drawing inspiration from work on visual processing, and especially the simple/complex cell distinction in early vision (V1), we claim that a similar two-layer architecture is sufficient to learn the truth-conditional meanings of the logical coordinators and logical quantifiers. As a prerequisite, (...) much discussion is given over to what a neurologically plausible representation of the meanings of these items would look like. We eventually settle on a representation in terms of correlation, so that, for instance, the semantic input to the universal operators (e.g. and, all)is represented as maximally correlated, while the semantic input to the universal negative operators (e.g. nor, no)is represented as maximally anticorrelated. On the basis this representation, the hypothesis can be offered that the function of the logical operators is to extract an invariant feature from natural situations, that of degree of correlation between parts of the situation. This result sets up an elegant formal analogy to recent models of visual processing, which argue that the function of early vision is to reduce the redundancy inherent in natural images. Computational simulations are designed in which the logical operators are learned by associating their phonological form with some degree of correlation in the inputs, so that the overall function of the system is as a simple kind of pattern recognition. Several learning rules are assayed, especially those of the Hebbian sort, which are the ones with the most neurological support. Learning vector quantization (LVQ) is shown to be a perspicuous and efficient means of learning the patterns that are of interest. We draw a formal parallelism between the initial, competitive layer of LVQ and the simple cell layer in V1, and between the final, linear layer of LVQ and the complex cell layer in V1, in that the initial layers are both selective, while the final layers both generalize. It is also shown how the representations argued for can be used to draw the traditionally-recognized inferences arising from coordination and quantification, and why the inference of subalternacy breaks down for collective predicates. Finally, the analogies between early vision and the logical operators allow us to advance the claim of cognitive linguistics that language is not processed by proprietary algorithms, but rather by algorithms that are general to the entire brain. Thus in the debate between objectivist and experiential metaphysics, this book falls squarely into the camp of the latter. Yet it does so by means of a rigorous formal, mathematical, and neurological exposition – in contradiction of the experiential claim that formal analysis has no place in the understanding of cognition. To make our own counter-claim as explicit as possible, we present a sketch of the LVQ structure in terms of mereotopology, in which the initial layer of the network performs topological operations, while the final layer performs mereological operations. The book is meant to be self-contained, in the sense that it does not assume any prior knowledge of any of the many areas that are touched upon. It therefore contains mini-summaries of biological visual processing, especially the retinocortical and ventral /what?/ parvocellular pathways computational models of neural signaling, and in particular the reduction of the Hodgkin-Huxley equations to the connectionist and integrate-and-fire neurons Hebbian learning rules and the elaboration of learning vector quantization the linguistic pathway in the left hemisphere memory and the hippocampus truth-conditional vs. image-schematic semantics objectivist vs. experiential metaphysics and mereotopology. All of the simulations are implemented in MATLAB, and the code is available from the book’s website. • The discovery of several algorithmic similarities between visison and semantics. • The support of all of this by means of simulations, and the packaging of all of this in a coherent theoretical framework. (shrink)

Research in the field of computer graphics and vision strives to precisely synthesize any possible human face in a way that it is perceived as a real face and to parametrically describe or analyze any existing human face. This article provides an overview of the theoretical and technical steps taken to get a model of human faces that satisfied two demands for face stimuli for experimental research: full control over the information in faces enabling precise manipulations on the one (...) hand, and high ecological validity of the stimuli, i.e. the ability to generate face stimuli that look very natural, on the other. It presents a new technology that fulfills both conditions. An important advance in the development of computer-generated face stimuli is initiated by the proposal of a theoretical face-space framework for the encoding of faces. (shrink)

This paper studies the traditional target classification and recognition algorithm based on Histogram of Oriented Gradients feature extraction and Support Vector Machine classification and applies this algorithm to distributed artificial intelligence image recognition. Due to the huge number of images, the general detection speed cannot meet the requirements. We have improved the HOG feature extraction algorithm. Using principal component analysis to perform dimensionality reduction operations on HOG features and doing distributed artificial intelligence image recognition experiments, the results (...) show that the image detection efficiency is slightly improved, and the detection speed is also improved. This article analyzes the reason for these changes because PCA mainly uses the useful feature information in HOG features. The parallelization processing of HOG features on graphics processing unit is studied. GPU is used for high parallel and high-density calculations, and the calculation of HOG features is very complicated. Using GPU for parallelization of HOG features can make the calculation speed of HOG features improved. We use image experiments for the parallelized HOG feature algorithm. Experimental simulations show that the speed of distributed artificial intelligence image recognition is greatly improved. By analyzing the existing digital image recognition methods, an improved BP neural network algorithm is proposed. Under the premise of ensuring accuracy, the recognition speed of digital images is accelerated, the time required for recognition is reduced, real-time performance is guaranteed, and the effectiveness of the algorithm is verified. (shrink)

The result of the author's extensive practical experience: a decade in computer process control using large scale systems, another decade in machine pattern-recognition for vision systems, and nearly a decade dealing with artificial intelligence and expert systems. These real-life projects have taught Vámos a critical appreciation of, and respect for, both abstract theory and the practical methodology that grows out of—and, in turn, shapes—those theories.Machine representation means a level of formalization that can be expressed by the instruments (...) of mathematics, whereas programming is not more and not less than a special linguistic translation of these mathematical formulae. How these all are related and controlled is a most practical philosophical and computation professional task. Wide experience in the practical fields of computer science, and the research of the underlying theoretical issues have led Vámos to the development of the attitude and activity of constructive skepticism. (shrink)

Understanding how look-ahead search and pattern recognition interact is one of the important research questions in the study of expert problem solving. This paper examines the implications of the template theory Gobet & Simon, 1996a , a recent theory of expert memory, on the theory of problem solving in chess. Templates are chunks Chase & Simon, 1973 that have evolved into more complex data structures and that possess slots allowing values to be encoded rapidly. Templates may facilitate search (...) in three ways: a by allowing information to be stored into LTM rapidly; b by allowing a search in the template space in addition to a search in the move space; and c by compensating loss in the minds eye due to interference and decay. A computer model implementing the main ideas of the theory is presented, and simulations of its search behaviour are discussed. The template theory accounts for the slight skill difference in average depth of search found in chess players, as well as for other empirical data. (shrink)

Forensic evidence often involves an evaluation of whether two impressions were made by the same source, such as whether a fingerprint from a crime scene has detail in agreement with an impression taken from a suspect. Human experts currently outperform computer-based comparison systems, but the strength of the evidence exemplified by the observed detail in agreement must be evaluated against the possibility that some other individual may have created the crime scene impression. Therefore, the strongest evidence comes from features (...) in agreement that are also not shared with other impressions from other individuals. We characterize the nature of human expertise by applying two extant metrics to the images used in a fingerprint recognition task and use eye gaze data from experts to both tune and validate the models. The Attention via Information Maximization model quantifies the rarity of regions in the fingerprints to determine diagnosticity for purposes of excluding alternative sources. The CoVar model captures relationships between low-level features, mimicking properties of the early visual system. Both models produced classification and generalization performance in the 75%–80% range when classifying where experts tend to look. A validation study using regions identified by the AIM model as diagnostic demonstrates that human experts perform better when given regions of high diagnosticity. The computational nature of the metrics may help guard against wrongful convictions, as well as provide a quantitative measure of the strength of evidence in casework. (shrink)

This article presents Epistemic Spatialization as a new framework for investigating the interconnected patterns of biases when identifying objects with convolutional neural networks. It draws upon Foucault’s notion of spatialized knowledge to guide its method of enquiry. We argue that decisions involved in the creation of algorithms, alongside the labeling, ordering, presentation, and commercial prioritization of objects, together create a distorted “nomination of the visible”: they harden the visibility of some objects, make other objects excessively visible, and consign yet others (...) to permanent or haphazard invisibility. Our approach differs from those who focus on high-stakes misidentifications, such as errors tied to structural racism. Examining the far more dominant series of low-stakes mistakes shows the scope of errors, destabilizing the goal of image content identification with considerable societal impact. We explore these issues by closely examining the demonstration video of a popular convnet. This examination reveals an interlocking series of biases undermining the content identification process. The picture we paint is crucial for a better understanding of the errors that result as these convnets become further embedded in everyday products. The framework is valuable for critical work on computer vision, AI studies, and large-scale visual analysis. (shrink)

Visual Agnosia is a comprehensive and up-to-date review of disorders of higher vision that relates these disorders to current conceptions of higher vision from cognitive science, illuminating both the neuropsychological disorders and the nature of normal visual object recognition.Brain damage can lead to selective problems with visual perception, including visual agnosia the inability to recognize objects even though elementary visual functions remain unimpaired. Such disorders are relatively rare, yet they provide a window onto how the normal brain might accomplish (...) the complex task of vision. Visual Agnosia reviews a century of case studies of higher-level visual deficits following brain damage, places them in the general context of current neuroscience, and draws relevant conclusions about the organization of normal visual processing. It is unique in drawing on research in cognitive psychology, computational vision, visual neurophysiology, and neuropsychology to interpret the agnosias and draw inferences from them about visual object recognition.Following a historical account of agnosia research, Visual Agnosia offers a taxonomy of a wide range of agnosia syndromes, describing and interpreting the syndromes in terms of the latest theoretical models of visual processing and ultimately bringing them to bear as evidence on a variety of questions in the study of higher vision.Martha J. Farah is Associate Professor of Psychology at Carnegie Mellon University. Visual Agnosia is included in the Issues in Biology of Language and Cognition series, edited by John Marshall. (shrink)

We present a generalization of the problem of pattern recognition to arbitrary probabilistic models. This version deals with the problem of recognizing an individual pattern among a family of different species or classes of objects which obey probabilistic laws which do not comply with Kolmogorov’s axioms. We show that such a scenario accommodates many important examples, and in particular, we provide a rigorous definition of the classical and the quantum pattern recognition problems, respectively. Our framework (...) allows for the introduction of non-trivial correlations between the different species involved, opening the door to a new way of harnessing these physical resources for solving pattern recognition problems. Finally, we present some examples and discuss the computational complexity of the quantum pattern recognition problem, showing that the most important quantum computation algorithms can be described as non-Kolmogorovian pattern recognition problems. (shrink)

What is the most important reason for using Computer Vision methods in humanities research? In this article, I argue that the use of numerical representation and data analysis methods offers a new language for describing cultural artifacts, experiences and dynamics. The human languages such as English or Russian that developed rather recently in human evolution are not good at capturing analog properties of human sensorial and cultural experiences. These limitations become particularly worrying if we want to compare thousands, millions (...) or billions of artifacts—i.e. to study contemporary media and cultures at their new twenty-first century scale. When we instead use numerical measurements of image properties standard in Computer Vision, we can better capture details of a single artifact as well as visual differences between a number of artifacts–even if they are very small. The examples of visual dimensions that numbers can capture better then languages include color, shape, texture, contours, composition, and visual characteristics of represented faces, bodies and objects. The methods of finding structures and relationships in large numerical datasets developed in statistics and machine learning allow us to extend this analysis to very big datasets of cultural objects. Equally importantly, numerical image features used in Computer Vision also give us a new language to represent gradual and continuous temporal changes—something which natural languages are also bad at. This applies to both single artworks such as a film or a dance piece and also to changes in visual characteristics in millions of artifacts over decades or centuries. (shrink)

Production and comprehension have long been viewed as inseparable components of language. The study of vision, by contrast, has centered almost exclusively on comprehension. Here we investigate drawing—the most basic form of visual production. How do we convey concepts in visual form, and how does refining this skill, in turn, affect recognition? We developed an online platform for collecting large amounts of drawing and recognition data, and applied a deep convolutional neural network model of visual cortex trained only (...) on natural images to explore the hypothesis that drawing recruits the same abstract feature representations that support natural visual object recognition. Consistent with this hypothesis, higher layers of this model captured the abstract features of both drawings and natural images most important for recognition, and people learning to produce more recognizable drawings of objects exhibited enhanced recognition of those objects. These findings could explain why drawing is so effective for communicating visual concepts, they suggest novel approaches for evaluating and refining conceptual knowledge, and they highlight the potential of deep networks for understanding human learning. (shrink)

Production and comprehension have long been viewed as inseparable components of language. The study of vision, by contrast, has centered almost exclusively on comprehension. Here we investigate drawing—the most basic form of visual production. How do we convey concepts in visual form, and how does refining this skill, in turn, affect recognition? We developed an online platform for collecting large amounts of drawing and recognition data, and applied a deep convolutional neural network model of visual cortex trained only (...) on natural images to explore the hypothesis that drawing recruits the same abstract feature representations that support natural visual object recognition. Consistent with this hypothesis, higher layers of this model captured the abstract features of both drawings and natural images most important for recognition, and people learning to produce more recognizable drawings of objects exhibited enhanced recognition of those objects. These findings could explain why drawing is so effective for communicating visual concepts, they suggest novel approaches for evaluating and refining conceptual knowledge, and they highlight the potential of deep networks for understanding human learning. (shrink)

Computer vision is widely used in manufacturing, sports, medical diagnosis, and other fields. In this article, a multifeature fusion error action expression method based on silhouette and optical flow information is proposed to overcome the shortcomings in the effectiveness of a single error action expression method based on the fusion of features for human body error action recognition. We analyse and discuss the human error action recognition method based on the idea of template matching to analyse the (...) key issues that affect the overall expression of the error action sequences, and then, we propose a motion energy model based on the direct motion energy decomposition of the video clips of human error actions in the 3 Deron action sequence space through the filter group. The method can avoid preprocessing operations such as target localization and segmentation; then, we use MET features and combine with SVM to test the human body error database and compare the experimental results obtained by using different feature reduction and classification methods, and the results show that the method has the obvious comparative advantage in the recognition rate and is suitable for other dynamic scenes. (shrink)

In step with rapid advancements in computer vision, vehicle classification demonstrates a considerable potential to reshape intelligent transportation systems. In the last couple of decades, image processing and pattern recognition-based vehicle classification systems have been used to improve the effectiveness of automated highway toll collection and traffic monitoring systems. However, these methods are trained on limited handcrafted features extracted from small datasets, which do not cater the real-time road traffic conditions. Deep learning-based classification systems have been proposed (...) to incorporate the above-mentioned issues in traditional methods. However, convolutional neural networks require piles of data including noise, weather, and illumination factors to ensure robustness in real-time applications. Moreover, there is no generalized dataset available to validate the efficacy of vehicle classification systems. To overcome these issues, we propose a convolutional neural network-based vehicle classification system to improve robustness of vehicle classification in real-time applications. We present a vehicle dataset comprising of 10,000 images categorized into six-common vehicle classes considering adverse illuminous conditions to achieve robustness in real-time vehicle classification systems. Initially, pretrained AlexNet, GoogleNet, Inception-v3, VGG, and ResNet are fine-tuned on self-constructed vehicle dataset to evaluate their performance in terms of accuracy and convergence. Based on better performance, ResNet architecture is further improved by adding a new classification block in the network. To ensure generalization, we fine-tuned the network on the public VeRi dataset containing 50,000 images, which have been categorized into six vehicle classes. Finally, a comparison study has been carried out between the proposed and existing vehicle classification methods to evaluate the effectiveness of the proposed vehicle classification system. Consequently, our proposed system achieved 99.68%, 99.65%, and 99.56% accuracy, precision, and F1-score on our self-constructed dataset. (shrink)

Algorithmic vision, the computational process of making meaning from digital images or visual information, has changed the relationship between the image and the human subject. In this paper, I explicate on the role of algorithmic vision as a technique of algorithmic governance, the organization of a population by algorithmic means. With its roots in the United States post-war cybernetic sciences, the ontological status of the computational image undergoes a shift, giving way to the hegemonic use of automated facial recognition (...) technologies towards predatory policing and profiling practices. By way of example, I argue that algorithmic vision reconfigures the philosophical links between vision, image, and truth, paradigmatically changing the way a human subject is represented through imagistic data. With algorithmic vision, the relationship between subject and representation challenges the humanistic discourse around images, calling for a critical displacement of the human subject from the center of an analysis of how computational images make meaning. I will explore the relationship between the operative image, the image that acts but is not seen by human eyes, and what Louise Amoore calls an “emergent subject,” a subject that is made visible through algorithmic techniques. Algorithmic vision reveals subjects to power in a mode that requires a new approach towards analyzing the entanglement and invisiblization of the human in automated decision-making systems. (shrink)

Emotional facial expressions can inform researchers about an individual's emotional state. Recent technological advances open up new avenues to automatic Facial Expression Recognition. Based on machine learning, such technology can tremendously increase the amount of processed data. FER is now easily accessible and has been validated for the classification of standardized prototypical facial expressions. However, applicability to more naturalistic facial expressions still remains uncertain. Hence, we test and compare performance of three different FER systems with human emotion recognition (...) for standardized posed facial expressions and for non-standardized acted facial expressions. For the standardized images, all three systems classify basic emotions accurately and they are mostly on par with human raters. For the non-standardized stimuli, performance drops remarkably for all three systems, but Azure still performs similarly to humans. In addition, all systems and humans alike tend to misclassify some of the non-standardized emotional facial expressions as neutral. In sum, emotion recognition by automated facial expression recognition can be an attractive alternative to human emotion recognition for standardized and non-standardized emotional facial expressions. However, we also found limitations in accuracy for specific facial expressions; clearly there is need for thorough empirical evaluation to guide future developments in computer vision of emotional facial expressions. (shrink)

William Gibson's 1984 cyberpunk novel Neuromancer continues to be a touchstone in cultural representations of the impact of new information and communication technologies on the self. As critics have noted, the posthumanist, capital-driven, urban landscape of Neuromancer resembles a Foucaultian vision of a panoptically engineered social space in which no activity (even unofficial and illegal activity) eludes the disciplinary gaze of power. On the other hand, William Gibson's latest novel, Pattern Recognition, marks an important ideological shift from Neuromancer. (...) Though the novel retains a deep ambivalence toward new technologies' potential impact on the self, Pattern Recognition nevertheless locates a new source for hope and agency in embodied everyday experience. This article maintains that the change can best be understood as a complex transition from the worldview of Michel Foucault to that of Michel de Certeau. (shrink)

Ballard et al.'s principle of deictic coding as exemplified in the analysis of fixation patterns relies on a functional dichotomy between foveal and extrafoveal vision based on the well-known dependency of spatial resolution on eccentricity. Experimental evidence suggests that for processes of pattern learning and recognition such a dichotomy may be less warranted because its manifestation depends on the learning state of the observer. This finding calls for an explicit consideration of learning mechanisms within deictic coding schemes.

You might reasonably surmise from the title of this paper that I will be discussing a theory of vision. After all, what is a theory of vision but a theory of how the world is connected to our visual representations? Theories of visual perception universally attempt to give an account of how a proximal stimulus (presumably a pattern impinging on the retina) can lead to a rich representation of a three dimensional world and thence to either the recognition (...) of known objects or to the coordination of actions with visual information. Such theories typically provide an effective (i.e., computable) mapping from a 2D pattern to a representation of a 3D scene, usually in the form of a symbol structure. But such a mapping, though undoubtedly the essential purpose of a theory of vision, leaves at least one serious problem that I intend to discuss here. It is this problem, rather than a theory of vision itself, that is the subject of this talk. (shrink)

Face recognition is one of the core and challenging issues in computer vision field. Compared to computer vision, human visual system can identify a target from complex backgrounds quickly and accurately. This paper proposes a new network model deriving from Where-What Networks (WWNs), which can approximately simulate the information processing pathways (i.e., dorsal pathway and ventral pathway) of human visual cortex and recognize different types of faces with different locations and sizes in complex background. To enhance the (...) recognition performance, synapse maintenance mechanism and neuron regenesis mechanism are both introduced. Synapse maintenance is used to reduce the background interference while neuron regenesis mechanism is introduced to regulate the neuron resource dynamically to improve the network usage efficiency. Experiments have been conducted on human face images of 5 types, 11 sizes, and 225 locations in complex backgrounds. Experiment results demonstrate that the proposed WWN model can basically learn three concepts (type, location and size) simultaneously. The experiment results also show the advantages of the enhanced WWN-7 model for face recognition in comparison with several existing methods. (shrink)

Just as humans can draw conclusions responsibly or irresponsibly, so too can computers. Machine learning systems that have been trained on data sets that include irresponsible judgments are likely to yield irresponsible predictions as outputs. In this paper I focus on a particular kind of inference a computer system might make: identification of the intentions with which a person acted on the basis of photographic evidence. Such inferences are liable to be morally objectionable, because of a way in which (...) they are presumptuous. After elaborating this moral concern, I explore the possibility that carefully procuring the training data for image recognition systems could ensure that the systems avoid the problem. The lesson of this paper extends beyond just the particular case of image recognition systems and the challenge of responsibly identifying a person’s intentions. Reflection on this particular case demonstrates the importance (as well as the difficulty) of evaluating machine learning systems and their training data from the standpoint of moral considerations that are not encompassed by ordinary assessments of predictive accuracy. (shrink)

In the target article, Bowers et al. dispute deep artificial neural network (ANN) models as the currently leading models of human vision without producing alternatives. They eschew the use of public benchmarking platforms to compare vision models with the brain and behavior, and they advocate for a fragmented, phenomenon-specific modeling approach. These are unconstructive to scientific progress. We outline how the Brain-Score community is moving forward to add new model-to-human comparisons to its community-transparent suite of benchmarks.

Sports energy consumption is a quantitative reflection of physical exercise effect. Combined with different sports modes and students’ physical characteristics, the calculation model of sports energy consumption is put forward. Firstly, the relationship between students’ age, height, weight, gender, and energy consumption is analyzed by using multiple linear regression method, and a linear acceleration model is proposed by combining different exercise methods. The relationship between the integral value of acceleration and energy consumption is analyzed, and a linear integral model based (...) on different motion modes is proposed. Based on the kinetic energy theorem, the student movement energy expenditure is estimated. This paper proposes a human movement recognition method based on hybrid features, which mostly can represent the curve of the second generation wavelet transform edge thinning, and from the edge and texture features of the optimal said human posture, the statistical characteristic of the second generation wavelet transform is subtly trained as image characteristics, learning and recognition of human movement. Then, the motion recognition algorithm is tested, which can effectively identify the common movement patterns of primary and middle school students. Finally, the linear relationship between the estimation results of the model and the calculation results of Meijer is analyzed. The analysis results show that the linear acceleration model proposed in this paper can estimate the energy consumption of primary and middle school students’ motion relatively accurately. (shrink)

Este trabajo surge a partir de la investigación general de las técnicas hidropónicas teniendo en cuenta sus ventajas y desventajas para de esta forma poder encontrar aquel factor determinante a través de una comparación de técnicas hidropónicas que permitan clasificarlas y escoger la mejor opción que genere menos impacto ambiental negativo y demuestre ser más productivo en los entornos urbanos. Adicionalmente, un factor determinante en las ciudades es su espacio limitado por lo que la mejor opción también deberá incluir un (...) óptimo manejo del espacio que permita a casi cualquier individuo poder aplicarlos desde su entorno sin recurrir a excesivas modificaciones. Como principal resultado se escogió a la Hidroponía recirculante como método predominante por los excelentes resultados que se obtienen con relación a los demás, adicionalmente, este puede ser fácilmente aplicado en los ambientes urbanos por su versatilidad y buen manejo de recursos. Palabras Clave: Hidroponia, ambiente, urbano, comparativa, técnicas, cultivo. Referencias [1]J. López, «La producción hidropónica de cultivos,» IDESIA, vol. 36, nº 2, pp. 139-141, 2018. [2]J. Lee, A. Rahman, J. Behrens, C. Brennan, B. Ham, H. Seok Kim, C. Won, S. Yun, H. Azam y M. Kwon, «Nutrient removal from hydroponic wastewater by a microbial consortium,» New Biotechnology, vol. 41, pp. 15-24, 2018. [3]H. Ku, C. Tiong, A. Suresh y B. Ong, «“Active” hydroponic greenhouse system to kick-start and augment reforestation program through carbon sequestration e an experimental and theoretical feasibility study,» Journal of Cleaner Production, vol. 129, pp. 637-646, 2016. [4]J. Beltrano y D. Gimenez, Cultivo en hidroponía, Buenos Aires: Universidad de la Plata, 2015. [5]L. Ramírez, M. Pérez, P. Jiménez, H. Giraldo y E. Gómez, «Evaluación preliminar de sistemas acuapónicos e hidropónicos en cama flotante para el cultivo de orégano,» Revista Facultad de Ciencias Básicas, vol. 7, nº 2, pp. 242-259, 2011. [6]S. Hosseinzadeh, D. Testai, M. BKheet y J. De Graeve, «Degradation of root exudates in closed hydroponic systems using UV/H2O2: Kinetic investigation, reaction pathways and cost analysis,» Science of the Total Environment, vol. 1, pp. 1-9, 2019. [7]N. Camarena, A. Rojas y M. Santos, «Fluoride bioaccumulation by hydroponic cultures of camellia,» Chemosphere, vol. 136, pp. 56-62, 2015. [8]W. Wang, Y. Ma, L. Fu, Y. Cui y M. Yaqoob, «Physical an mechanical properties of hydroponic lettuce for automatic harvesting,» Informatión processing in agriculture, vol. 1, pp. 2214-3173, 2020. [9]M. Zárate, Manual de Hidroponia, Coyoacán: Universidad Autónoma de Mexico, 2014. [10]S. Magwaza, L. Magwaza, A. Odindo y C. Buckley, «Partially treated domestic wastewater as a nutrient source for tomatoes grown in a hydroponic system: effect on nutrientabsorption and yield,» Heliyon, vol. 6, nº 12, pp. 2405-8440, 2020. [11]C. ARANO, «Hidroponía: Algunas paginas de historia,» Tecnología de Producción, nº 58, pp. 24-32, 2007. [12]G. Guzmán, Hidroponia en Casa: Una actividad familiar, Costa Rica: Ministerio de Agricultura y ganaderia, 2004. [13]J. Gilsanz, HIDROPONIA, Montevideo : Unidad de Comunicación y Transferencia de Tecnología, 2007. [14]C. Miller, «El debate de hidroponia orgánica: Perspectivas norteamericanas sobre si la producción hidropónica merece ser certificada como orgánica.,» Productores de Hortalizas, nº 6, pp. 36-38, 2017. [15]A. Herrera, «Manejo de la solución nutritiva en la producción de tomate en hidroponía,» Terra Latinoamericana, vol. 17, nº 3, pp. 221-229, 1999. [16]C. Espinal y D. Matulić, «Recirculating Aquaculture Technologies,» Biomedical and Life Sciences, pp. 35-76, 2020. [17]H. Resh, «Técnicas de cultivo con flujo laminar de nutrientes,» de Cultivos Hidroponicos, España, Mundi-Prensa, 2001, pp. 35-37. [18]P. Blanca y L. Teresa, «Sistemas recirculantes y su interés en el cutlivo de ornamentales,» Tecnología de producción, nº 35, pp. 34-36, 2006. [19]C. Magán, «Recirculación de las soluciones nutritivas, Manejo y Control Microbiologico,» InfoAgro, nº 2, pp. 1-2, 2016. [20]S. Goddek, A. Joyce, B. Kotzen y M. Dos-Santos, «Aquaponics and Global Food Challenges,» Aquaponics Food Production Systems. Springer, vol. 1, nº 1, pp. 3-17, 2019. [21]S. G. Verdoliva, D. Gwyn Jones, A. Detheridge y P. Robson, «Controlled comparisons between soil and hydroponic systems reveal increased water use efficiency and higher lycopene and β-carotene contents in hydroponically grown tomatoes,» Scientia Horticulturae, pp. 3002-4238, 2020. [22]A. Chaudhry y V. Mishra, «A Comparative Analysis of Vertical Agriculture Systems in Residential Apartments, » de 2019 Advances in Science and Engineering Technology International Conferences, Dubai, United Arab Emirates, United Arab Emirates, 2019. [23]T. Mazhar, G. Jianmin, L. Imran, S. Kashif, Q. Waqar, S. Sher y C. Jiedong, «Modern plant cultivation technologies in agriculture under controlled nvironment: a review on aeroponics,» Journal of Plant Interactions, vol. 13, nº 1, pp. 338-352, 2012. [24]K. Janiak, A. Jurga, J. Kuźma, W. Breś y M. Muszyński, «Surfactants effect on aeroponics and important mass balances of regenerative life support system – Lettuce case study,» Science of the Total Environment, vol. 718, nº137324, pp. 1-12, 2020. [25]F. Rahman, I. Jahan, R. Biplob, N. Farhin y J. Uddin, «Automated Aeroponics System for Indoor Farming using Arduino,» de 2018 Joint 7th International Conference on Informatics, Electronics & Vision and 2018 2nd International Conference on Imaging, Vision & Pattern Recognition, Kitakyushu, Japan, 2018. [26]M. Caldeyro Stajano, «La Hidroponía Simplificada como Tecnología apropiada, para implementar la Seguridad Alimentaria en la Agricultura Urbana.,» Cuadernos del CEAgro, nº 8, pp. 71-76, 2006. (shrink)

In the area of machine learning, different techniques are used to train machines and perform different tasks like computer vision, data analysis, natural language processing, and speech recognition. Computer vision is one of the main branches where machine learning and deep learning techniques are being applied. Optical character recognition is the ability of a machine to recognize the character of a language. Pashto is one of the most ancient and historical languages of the world, spoken in (...) Afghanistan and Pakistan. OCR application has been developed for various cursive languages like Urdu, Chinese, and Japanese, but very little work is done for the recognition of the Pashto language. When it comes to handwritten character recognition, it becomes more difficult for OCR to recognize the characters as every handwritten character’s shape is influenced by the writer’s hand motion dynamics. The reason for the lack of research in Pashto handwritten character data as compared to other languages is because there is no benchmark dataset available for experimental purposes. This study focuses on the creation of such a dataset, and then for the evaluation purpose, a machine is trained to correctly recognize unseen Pashto handwritten characters. To achieve this objective, a dataset of 43000 images was created. Three Feed Forward Neural Network models with backpropagation algorithm using different Rectified Linear Unit layer configurations were trained and tested with this dataset. The simulation shows that Model 1 achieved accuracy up to 87.6% on unseen data while Model 2 achieved an accuracy of 81.60% and 3% accuracy, respectively. Similarly, loss was the lowest for Model 1 with 0.15 and 3.17 for training and testing, followed by Model 2 with 0.7 and 4.2 for training and testing, while Model 3 was the last with loss values of 6.4 and 3.69. The precision, recall, and f-measure values of Model 1 were better than those of both Model 2 and Model 3. Based on results, Model 1 is found to be the most efficient as compared to the other two models in terms of accuracy to recognize Pashto handwritten characters. (shrink)

In lieu of an abstract, here is a brief excerpt of the content:The Journal of Aesthetic Education 37.4 (2003) 58-64 [Access article in PDF] Media Literacy Education in Art:Motion Expression and the New Vision of Art EducationThe Bauhaus, which established the foundation of modern design, has greatly influenced Japanese design and art education. It is a historical fact that the movement views "synthetic art" as an integration of the various fields and the integration of the art and machine technology experimentally. (...) However, the Bauhaus is not just of historical importance but continues to have an influence even in the integration of the art and electronic technology in today's "multimedia." In addition, it can be said that it is very much alive as "the digital Bauhaus" or "the electronic Bauhaus." 1 As we know, today's multimedia and the Internet give us a new life-environment, and expandthe possibility of expression in art. Therefore, current art education must examine how these new medias will be incorporated into the curriculum.In the cases of the photograph, video, or computer, an expression by the image media is added to the art course for the junior high school course of study. 2 Also in school art classes, image media was introduced, expanding the possibilities of self-expression through art. This result can be matched to the needs of the industrial world in Japan as well. As an educational practice, the content of this course of study is promising, even though someproblems must be solved, acquiring new equipment, re-educating the artteacher, and securing additional art school hours. The new content in art education can be summarized as follows:1. The motion picture (animation) which includes time and movement. Motion picture is asequence of continuous images, obviously different from the still images of painting. There are, of course, artworks that express motion or induce the viewer'seye movement. There are also kinetic artworks that do move, such as mobiles. Works of motion picture have, however, a fixed time shaft, and they are formed by the afterimage phenomenon. Thinking about the progress of time shaft is an indispensable element for the production. [End Page 58]2. The synchronism of image and sound. Because time is a factor in the visual expression, the works are compatible with music — the art of time. There is a synchronized relation between the motion picture and music. Image expression with multimedia became synthetic art, just as the Bauhaus looked for "architecture." Currently, this kind of expression transitions from art to entertainment, and permeates daily life.3. The method with interactive art work. Not only artworks of installation, but also TV games and web design have interactive construction as an indispensable interface. The aesthetic value of these visual works will be appreciated when the user starts the action by hitting a touchpad, pushing buttons, or clicking a mouse. To make this kind of artwork, one needs to consider the latent relationships between humans and work, and establish the input-output order for the method of construction.4. The problem of virtual reality. The term "virtual reality" is used by some art teachers as criticism against digital works such as computer graphics. These teachers insist that there is no reality there. One can, however, get an aesthetic feeling through sensory information, imagination, and sensitivity, even though what one sees is an illusion. The feeling of reality a picture of an apple gives, for example, may be equal to a computer graphic apple.Human imagination also creates "virtual reality" beyond reality in the myth, the novel, and so on. It can be said that this is the basis for human creativity.Furthermore, expression by image media raises the problem of a "reality" in which material experience is important to encounterthe world directly. Such an argument discusses multimedia as a tool of expression and a teaching material while reconsidering human reality.More recently, "media literacy" (ability to read and understand media) became an important point of discussion for Japanese educators. Usually, in this discussion, the critical ability to talk back to the television program is emphasized. However, through art... (shrink)

In lieu of an abstract, here is a brief excerpt of the content:The Journal of Aesthetic Education 37.4 (2003) 58-64 [Access article in PDF] Media Literacy Education in Art:Motion Expression and the New Vision of Art EducationThe Bauhaus, which established the foundation of modern design, has greatly influenced Japanese design and art education. It is a historical fact that the movement views "synthetic art" as an integration of the various fields and the integration of the art and machine technology experimentally. (...) However, the Bauhaus is not just of historical importance but continues to have an influence even in the integration of the art and electronic technology in today's "multimedia." In addition, it can be said that it is very much alive as "the digital Bauhaus" or "the electronic Bauhaus." 1 As we know, today's multimedia and the Internet give us a new life-environment, and expandthe possibility of expression in art. Therefore, current art education must examine how these new medias will be incorporated into the curriculum.In the cases of the photograph, video, or computer, an expression by the image media is added to the art course for the junior high school course of study. 2 Also in school art classes, image media was introduced, expanding the possibilities of self-expression through art. This result can be matched to the needs of the industrial world in Japan as well. As an educational practice, the content of this course of study is promising, even though someproblems must be solved, acquiring new equipment, re-educating the artteacher, and securing additional art school hours. The new content in art education can be summarized as follows:1. The motion picture (animation) which includes time and movement. Motion picture is asequence of continuous images, obviously different from the still images of painting. There are, of course, artworks that express motion or induce the viewer'seye movement. There are also kinetic artworks that do move, such as mobiles. Works of motion picture have, however, a fixed time shaft, and they are formed by the afterimage phenomenon. Thinking about the progress of time shaft is an indispensable element for the production. [End Page 58]2. The synchronism of image and sound. Because time is a factor in the visual expression, the works are compatible with music — the art of time. There is a synchronized relation between the motion picture and music. Image expression with multimedia became synthetic art, just as the Bauhaus looked for "architecture." Currently, this kind of expression transitions from art to entertainment, and permeates daily life.3. The method with interactive art work. Not only artworks of installation, but also TV games and web design have interactive construction as an indispensable interface. The aesthetic value of these visual works will be appreciated when the user starts the action by hitting a touchpad, pushing buttons, or clicking a mouse. To make this kind of artwork, one needs to consider the latent relationships between humans and work, and establish the input-output order for the method of construction.4. The problem of virtual reality. The term "virtual reality" is used by some art teachers as criticism against digital works such as computer graphics. These teachers insist that there is no reality there. One can, however, get an aesthetic feeling through sensory information, imagination, and sensitivity, even though what one sees is an illusion. The feeling of reality a picture of an apple gives, for example, may be equal to a computer graphic apple.Human imagination also creates "virtual reality" beyond reality in the myth, the novel, and so on. It can be said that this is the basis for human creativity.Furthermore, expression by image media raises the problem of a "reality" in which material experience is important to encounterthe world directly. Such an argument discusses multimedia as a tool of expression and a teaching material while reconsidering human reality.More recently, "media literacy" (ability to read and understand media) became an important point of discussion for Japanese educators. Usually, in this discussion, the critical ability to talk back to the television program is emphasized. However, through art... (shrink)

Image restoration is a research hotspot in computer vision and computer graphics. It uses the effective information in the image to fill in the information of the designated damaged area. This has high application value in environmental design, film and television special effects production, old photo restoration, and removal of text or obstacles in images. In traditional sparse representation image restoration algorithms, the size of dictionary atoms is often fixed. When repairing the texture area, the dictionary atom will (...) be too large to cause blurring. When repairing a smooth area, the dictionary atom is too small to cause the extension of the area, which affects the image repair effect. In this paper, the structural sparsity of the block to be repaired is used to adjust the repair priority. By analyzing the structure information of the repair block located in different regions such as texture, edge, and smoothing, the size of the dictionary atom is adaptively determined. This paper proposes a color image restoration method that adaptively determines the size of dictionary atoms and discusses a model based on the partial differential equation restoration method. Through simulation experiments combined with subjective and objective standards, the repair results are evaluated and analyzed. The simulation results show that the algorithm can effectively overcome the shortcomings of blurred details and region extension in fixed dictionary restoration, and the restoration effect has been significantly improved. Compared with the results of several other classic algorithms, it shows the effectiveness of the algorithm in this paper. (shrink)

People recognize faces of their own race more accurately than faces of other races. The “contact” hypothesis suggests that this “other‐race effect” occurs as a result of the greater experience we have with own‐ versus other‐race faces. The computational mechanisms that may underlie different versions of the contact hypothesis were explored in this study. We replicated the other‐race effect with human participants and evaluated four classes of computational face recognition algorithms for the presence of an other‐race effect. Consistent with (...) the predictions of a developmental contact hypothesis, “experience‐based models” demonstrated an other‐race effect only when the representational system was developed through experience that warped the perceptual space in a way that was sensitive to the overall structure of the model's experience with faces of different races. When the model's representation relied on a feature set optimized to encode the information in the learned faces, experience‐based algorithms recognized minority‐race faces more accurately than majority‐race faces. The results suggest a developmental learning process that warps the perceptual space to enhance the encoding of distinctions relevant for own‐race faces. This feature space limits the quality of face representations for other‐race faces. (shrink)