14 - Gaze Control for Face Learning and Recognition by Humans and Machines

In this chapter we describe an ongoing project designed to investigate gaze control in face perception, a problem of central importance in both human and machine vision. The project uses converging evidence from behavioral studies of human observers and computational studies in machine vision. The research is guided by a formal framework for understanding gaze control based on Markov decision processes (MDPs). Behavioral data from human observers provide new insight into gaze control in a complex task, and are used to motivate an artificial gaze control system using the Markov framework. Furthermore, the efficacy of a foveal Markov-based approach to gaze control for face recognition in machine vision is tested. The general goal of the project is to uncover key principles of gaze control that cut across the specific implementation of the system (biological or machine).

[1]  Trevor Darrell.  Reinforcement Learning of Active Recognition Behaviors , 1997, NIPS 1997.

[2]  Andrew Hollingworth,et al.  Eye Movements During Scene Viewing: An Overview , 1998 .

[3]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[4]  L. R Gleitman,et al.  Proceedings of the twenty-second annual conference of the cognitive science society , 2000 .

[5]  Sridhar Mahadevan,et al.  Eye Movements in Human Face Learning and Recognition , 2000 .

[6]  C. H. Graham,et al.  Vision and visual perception , 1965 .

[7]  M. Farah,et al.  Parts and Wholes in Face Recognition , 1993, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[8]  J. Henderson,et al.  The effects of semantic consistency on eye movements during complex scene viewing , 1999 .

[9]  Leslie G. Ungerleider,et al.  FMRI reveals differential activation in the ventral vision pathway during the perception of objects , 1997, Neuroscience Letters.

[10]  Katta G. Murty,et al.  On KΔ , 1986, Discret. Appl. Math..

[11]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[12]  S. Carey,et al.  Why faces are and are not special: an effect of expertise. , 1986 .

[13]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[14]  G. Underwood.  Eye guidance in reading and scene perception , 1998 .

[15]  L. Stark,et al.  Scanpaths in Eye Movements during Pattern Perception , 1971, Science.

[16]  Alex Pentland,et al.  Beyond eigenfaces: probabilistic matching for face recognition , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[17]  Steve J. Young,et al.  HMM-based architecture for face identification , 1994, Image Vis. Comput..

[18]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[19]  R. Groner,et al.  Looking at Faces: Local and Global Aspects of Scanpaths , 1984 .

[20]  Edward L. Keller.  Visual Science and Engineering: Models and Applications , 1995 .

[21]  C. Pierrot-Deseilligny,et al.  Cortical control of saccades in man. , 1991, Acta neurologica Belgica.

[22]  Nancy Millette,et al.  How People Look at Pictures , 1935 .

[23]  R. Desimone.  Face-Selective Cells in the Temporal Cortex of Monkeys , 1991, Journal of Cognitive Neuroscience.

[24]  Brian Scassellati,et al.  Alternative Essences of Intelligence , 1998, AAAI/IAAI.

[25]  A. L. Yarbus,et al.  Eye Movements and Vision , 1967, Springer US.

[26]  Brian J. Thompson.  Visual Science and Engineering: Models and Applications , 1994 .

[27]  Seong-Whan Lee,et al.  Biologically Motivated Computer Vision , 2002, Lecture Notes in Computer Science.

[28]  S M Anstis,et al.  Letter: A chart demonstrating variations in acuity with retinal position. , 1974, Vision research.

[29]  Mark H. Johnson,et al.  Newborns' preferential tracking of face-like stimuli and its subsequent decline , 1991, Cognition.

[30]  H D Crane,et al.  Generation-V dual-Purkinje-image eyetracker. , 1985, Applied optics.

[31]  Yasuo Kuniyoshi,et al.  A foveated wide angle lens for active vision , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[32]  N. Mackworth,et al.  Cognitive determinants of fixation location during picture viewing. , 1978, Journal of experimental psychology. Human perception and performance.

[33]  A. Friedman.  Framing pictures: the role of knowledge in automatized encoding and memory for gist. , 1979, Journal of experimental psychology. General.

[34]  E. Matin.  Saccadic suppression: a review and an analysis. , 1974, Psychological bulletin.

[35]  Rajesh P. N. Rao,et al.  Embodiment is the foundation, not a level , 1996, Behavioral and Brain Sciences.

[36]  Michael L. Littman,et al.  Algorithms for Sequential Decision Making , 1996 .

[37]  A. Friedman.  Framing pictures: the role of knowledge in automatized encoding and memory for gist. , 1979, Journal of experimental psychology. General.

[38]  J. Henderson,et al.  High-level scene perception. , 1999, Annual review of psychology.

[39]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[40]  O. Mimura.  [Eye movements]. , 1992, Nippon Ganka Gakkai zasshi.

[41]  Monson H. Hayes,et al.  Face Recognition Using An Embedded HMM , 1999 .

[42]  R. Yin.  Looking at Upside-down Faces , 1969 .

[43]  M. Farah,et al.  What causes the face inversion effect? , 1995, Journal of experimental psychology. Human perception and performance.

[44]  A. L. I︠A︡rbus.  Eye Movements and Vision , 1967 .

[45]  Edward H.F. de Haan,et al.  Category specificity in visual recognition , 1994 .

[46]  N. Kanwisher,et al.  The Fusiform Face Area: A Module in Human Extrastriate Cortex Specialized for Face Perception , 1997, The Journal of Neuroscience.

[47]  K. Rayner.  Eye movements in reading and information processing: 20 years of research. , 1998, Psychological bulletin.

[48]  F. C. Volkmann.  Human visual suppression , 1986, Vision Research.

[49]  J. Stern.  Theoretical and applied aspects of eye movement research A. G. Gale and F. Johnson, (Elsevier Science Publishers B.V., Amsterdam, 1984) pp. xiii + 565, Dfl. 185 , 1985, Biological Psychology.

[50]  Giulio Sandini,et al.  A Foveated Retina-Like Sensor Using CCD Technology , 1989, Analog VLSI Implementation of Neural Systems.

[51]  R. Carpenter,et al.  Movements of the Eyes , 1978 .

[52]  Andrew Liu.  Chapter 20 – What the Driver's Eye Tells the Car's Brain , 1998 .

[53]  M. Goodale,et al.  The visual brain in action , 1995 .

[54]  H. Ellis.  Recognizing faces. , 1975, British journal of psychology.

[55]  Ronald A. Howard,et al.  Dynamic Programming and Markov Processes , 1960 .

[56]  M. Tarr,et al.  Levels of categorization in visual recognition studied using functional magnetic resonance imaging , 1997, Current Biology.

[57]  N. J. Cohen,et al.  Eye-movement-based memory effect: a reprocessing effect in face perception. , 1999, Journal of experimental psychology. Learning, memory, and cognition.

[58]  Mohammed Ismail,et al.  Analog VLSI Implementation of Neural Systems , 2011, The Kluwer International Series in Engineering and Computer Science.

[59]  Sridhar Mahadevan,et al.  Automatic Programming of Behavior-Based Robots Using Reinforcement Learning , 1991, Artif. Intell..

[60]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[61]  Francisco J. Vico,et al.  Residual Q-Learning Applied to Visual Attention , 1996, ICML.

[62]  G. Winocur,et al.  What Is Special about Face Recognition? Nineteen Experiments on a Person with Visual Object Agnosia and Dyslexia but Normal Face Recognition , 1997, Journal of Cognitive Neuroscience.

[63]  T. Allison,et al.  Face-Specific Processing in the Human Fusiform Gyrus , 1997, Journal of Cognitive Neuroscience.