Towards a model of visual recognition based on neurosciences

Abstract Cognitive sciences and computer vision have proposed diverse models to acquire, transform and interpret visual information, mainly aimed to achieve realistic, yet efficient approaches to those capacities. One of the key aspects of visual processing is the identification of objects in the scene, that entails the perceptual association of visual features with semantic information extracted from memory. In this study, we present a model for visual recognition that resembles the way the human’s brain interacts to achieve this process. The model describes the processes in V1 and V2 to extract features of lines, angles, and contours; as well as a template matching process in ITC, that uses early low spatial frequency visual information to bias the available comparisons. Operations of prefrontal areas DLPFC and VLPFC to maintain the representation and OFC to give a response are also described. Our proposal is intended to be the basis to treat visual information in a broader cognitive architecture. We find that matching of ITC templates provide a general and biologically inspired representation for objects. We also show how the use of low spatial frequency visual information can lead to a faster identification process when previous data exists. This is achieved by selecting a small number of ITC templates to handle the incoming bottom-up input.

[1]  Sanghoon Han,et al.  Ventrolateral prefrontal cortex and self-initiated semantic elaboration during memory retrieval , 2009, Neuropsychologia.

[2]  John R Anderson,et al.  An integrated theory of the mind. , 2004, Psychological review.

[3]  Donna Rose Addis,et al.  The Wiley Handbook on The Cognitive Neuroscience of Memory , 2015 .

[4]  R. Poldrack,et al.  Dissociable Controlled Retrieval and Generalized Selection Mechanisms in Ventrolateral Prefrontal Cortex , 2005, Neuron.

[5]  Hamutal Slovin,et al.  Population Responses to Contour Integration: Early Encoding of Discrete Elements and Late Perceptual Grouping , 2013, Neuron.

[6]  J. Hegdé,et al.  Selectivity for Complex Shapes in Primate Visual Area V2 , 2000, The Journal of Neuroscience.

[8]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[9]  M. Bar,et al.  Magnocellular Projections as the Trigger of Top-Down Facilitation in Recognition , 2007, The Journal of Neuroscience.

[10]  E. Rolls,et al.  A Neurodynamical cortical model of visual attention and invariant object recognition , 2004, Vision Research.

[11]  K R Gegenfurtner,et al.  Processing of color, form, and motion in macaque area V2 , 1996, Visual Neuroscience.

[12]  Pieter R Roelfsema,et al.  The role of primary visual cortex (V1) in visual awareness , 2000, Vision Research.

[13]  Vinod Venkatraman,et al.  A Parallel Functional Topography between Medial and Lateral Prefrontal Cortex: Evidence and Implications for Cognitive Control , 2011, The Journal of Neuroscience.

[14]  J. Grafman,et al.  Dorsolateral prefrontal contributions to human working memory , 2013, Cortex.

[15]  P. Brodal.  The Central Nervous System , 1992 .

[16]  Activation of the primary visual cortex (V1) related to surface brightness , 2006, Nature Reviews Neuroscience.

[17]  Simon M Stringer,et al.  Hebbian learning of hand-centred representations in a hierarchical neural network model of the primate visual system , 2017, PloS one.

[18]  Thomas L. Dean,et al.  Neural Networks and Neuroscience-Inspired Computer Vision , 2014, Current Biology.

[19]  Edmund T. Rolls,et al.  Invariant Visual Object and Face Recognition: Neural and Computational Bases, and a Model, VisNet , 2012, Front. Comput. Neurosci..

[20]  Cynthia Avila-Contreras,et al.  An Agent Cognitive Model for Visual Attention and Response to Novelty , 2014, KES-AMSTA.

[21]  A. Baddeley.  Working memory: theories, models, and controversies. , 2012, Annual review of psychology.

[22]  A. Snyder,et al.  Electromagnetic effects in the cones of the human retina , 1965 .

[23]  H. Spiers,et al.  Prefrontal and medial temporal lobe interactions in long-term memory , 2003, Nature Reviews Neuroscience.

[24]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[25]  Félix F. Ramos Corchado,et al.  Brain Architecture for Visual Object Identification , 2013, Int. J. Cogn. Informatics Nat. Intell..

[26]  Niels Taatgen,et al.  Pre-attentive and attentive vision module , 2013, Cognitive Systems Research.

[27]  Juan Luis del Valle-Padilla,et al.  A bioinspired model of early visual processing with hue-feature saliency for a cognitive architecture , 2017, BICA.

[28]  Daniel P. Bliss,et al.  Serial Dependence across Perception, Attention, and Memory , 2017, Trends in Cognitive Sciences.

[29]  M. R. Riley,et al.  Role of Prefrontal Persistent Activity in Working Memory , 2016, Front. Syst. Neurosci..

[30]  Changsong Liu,et al.  Gabor filters-based feature extraction for character recognition , 2005, Pattern Recognit..

[31]  E. Rolls.  The functions of the orbitofrontal cortex , 1999, Brain and Cognition.

[32]  Bevil R. Conway,et al.  Toward a Unified Theory of Visual Area V4 , 2012, Neuron.

[33]  Fiona Rowe,et al.  Visual Fields via the Visual Pathway , 2006 .

[34]  M. Bar.  A Cortical Mechanism for Triggering Top-Down Facilitation in Visual Object Recognition , 2003, Journal of Cognitive Neuroscience.

[35]  Minami Ito,et al.  Representation of Angles Embedded within Contour Stimuli in Area V2 of Macaque Monkeys , 2004, The Journal of Neuroscience.

[36]  Reginald B. Adams,et al.  Convergent evidence for top-down effects from the “predictive brain” 1 , 2016, Behavioral and Brain Sciences.

[37]  D. Hubel,et al.  Receptive fields and functional architecture of monkey striate cortex , 1968, The Journal of physiology.

[38]  M. Goodale,et al.  Separate visual pathways for perception and action , 1992, Trends in Neurosciences.

[39]  Edmund T. Rolls,et al.  Invariant visual object recognition: biologically plausible approaches , 2015, Biological Cybernetics.

[40]  Keiji Tanaka,et al.  Neural representation for object recognition in inferotemporal cortex , 2016, Current Opinion in Neurobiology.

[41]  Keiichi Abe,et al.  Topological structural analysis of digitized binary images by border following , 1985, Comput. Vis. Graph. Image Process..

[42]  Roberta L. Klatzky,et al.  Ventral and Dorsal Visual Stream Contributions to the Perception of Object Shape and Object Location , 2014, Journal of Cognitive Neuroscience.

[43]  Chris I. Baker,et al.  Disentangling visual imagery and perception of real-world objects , 2012, NeuroImage.

[44]  Edmund T. Rolls,et al.  Finding and recognizing objects in natural scenes: complementary computations in the dorsal and ventral visual systems , 2014, Front. Comput. Neurosci..

[45]  E. Rolls,et al.  Value, Pleasure and Choice in the Ventral Prefrontal Cortex , 2022 .

[46]  J. Wallis.  Orbitofrontal cortex and its contribution to decision-making. , 2007, Annual review of neuroscience.

[47]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[48]  Sebastian J. Crutch,et al.  Neural Basis of Semantic Memory: Semantic refractory access disorders , 2007 .

[49]  Y. Miyashita.  Inferior temporal cortex: where visual perception meets memory. , 1993, Annual review of neuroscience.

[50]  David C. Plaut,et al.  ‘What’ Is Happening in the Dorsal Visual Pathway , 2016, Trends in Cognitive Sciences.

[51]  M. Bar,et al.  Prediction, context, and competition in visual recognition , 2015, Annals of the New York Academy of Sciences.

[52]  Malte Persike,et al.  Contour integration with corners , 2016, Vision Research.

[53]  Félix F. Ramos Corchado,et al.  A Cognitive Architecture for Visual Memory Identification , 2014, Int. J. Softw. Sci. Comput. Intell..

[54]  John E. Laird,et al.  A Standard Model of the Mind: Toward a Common Computational Framework across Artificial Intelligence, Cognitive Science, Neuroscience, and Robotics , 2017, AI Mag..

[55]  Deepak Khosla,et al.  A neuromorphic system for visual object recognition , 2014, BICA 2014.

[56]  John R. Anderson,et al.  Competition and representation during memory retrieval: Roles of the prefrontal cortex and the posterior parietal cortex , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[57]  C. Connor,et al.  Population coding of shape in area V4 , 2002, Nature Neuroscience.

[58]  Dwight J. Kravitz,et al.  The ventral visual pathway: an expanded neural framework for the processing of object quality , 2013, Trends in Cognitive Sciences.

[59]  E. Rolls,et al.  The functional neuroanatomy of the human orbitofrontal cortex: evidence from neuroimaging and neuropsychology , 2004, Progress in Neurobiology.

[60]  Joshua W. Brown,et al.  A meta-analysis of executive components of working memory. , 2013, Cerebral cortex.

[61]  S. Courtney,et al.  Attention and cognitive control as emergent properties of information representation in working memory , 2004, Cognitive, affective & behavioral neuroscience.