Cortical object segregation and categorization by multi-scale line and edge coding

In this paper we present an improved scheme for line and edge detection in cortical area V1, based on responses of simple and complex cells, truly multi-scale with no free parameters. We illustrate the multi-scale representation for visual reconstruction, and show how object segregation can be achieved with coarse-to-finescale groupings. A two-level object categorization scenario is tested in which pre-categorization is based on coarse scales only, and final categorization on coarse plus fine scales. Processing schemes are discussed in the framework of a complete cortical architecture.

[1]  Sudeep Sarkar,et al.  Robust Visual Method for Assessing the Relative Performance of Edge-Detection Algorithms , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  J. M. Hans du Buf,et al.  Ramp edges, Mach bands, and the functional significance of the simple cell assembly , 1994, Biological Cybernetics.

[3]  C. Koch,et al.  Computational modelling of visual attention , 2001, Nature Reviews Neuroscience.

[4]  L. Zhaoping,et al.  V1 mechanisms and some figure–ground and border effects , 2003, Journal of Physiology-Paris.

[5]  Antonio Torralba,et al.  Top-down control of visual attention in object detection , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[6]  P Girard,et al.  Feedback connections act on the early part of the responses in monkey visual cortex. , 2001, Journal of neurophysiology.

[7]  David J. Fleet,et al.  Phase-based disparity measurement , 1991, CVGIP Image Underst..

[8]  Christoph Rasche.  The Making of a Neuromorphic Visual System , 2004 .

[9]  D. Berson,et al.  Strange vision: ganglion cells as circadian photoreceptors , 2003 .

[10]  J. M. Hans du Buf,et al.  Simultaneous Detection of Lines and Edges Using Compound Gabor Filters , 2000, Int. J. Pattern Recognit. Artif. Intell..

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

[12]  Zhaoping Li.  V1 mechanisms and some figure-ground and border effects. , 2003, Journal of physiology, Paris.

[13]  J. M. Hans du Buf,et al.  Responses of simple cells: events, interferences, and ambiguities , 1993, Biological Cybernetics.

[14]  João M. F. Rodrigues,et al.  Multi-scale Keypoints in V1 and Face Detection , 2005, BVAI.

[15]  Olaf Kübler,et al.  Simulation of neural contour mechanisms: from simple to end-stopped cells , 1992, Vision Research.

[16]  D. Hubel.  Eye, brain, and vision , 1988 .

[17]  Norbert Krüger,et al.  Object Recognition with Banana Wavelets , 1997, ESANN.

[18]  Nicolai Petkov,et al.  Contour detection based on nonclassical receptive field inhibition , 2003, IEEE Trans. Image Process..

[19]  Fabrizio Smeraldi,et al.  Retinal vision applied to facial features detection and face authentication , 2002, Pattern Recognit. Lett..

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

[21]  Steven W. Zucker,et al.  Local Scale Control for Edge Detection and Blur Estimation , 1996, ECCV.

[22]  João M. F. Rodrigues,et al.  Multi-scale Cortical Keypoint Representation for Attention and Object Detection , 2005, IbPRIA.

[23]  Ronald A. Rensink.  The Dynamic Representation of Scenes , 2000 .

[24]  João M. F. Rodrigues,et al.  Visual Cortex Frontend: Integrating Lines, Edges, Keypoints, and Disparity , 2004, ICIAR.

[25]  L. Pessoa,et al.  Mach Bands: How Many Models are Possible? Recent Experimental Findings and Modeling Attempts , 1996, Vision Research.

[26]  João M. F. Rodrigues,et al.  A vision fronted with a new disparity model , 2004 .

[27]  Bernt Schiele,et al.  Analyzing appearance and contour based methods for object categorization , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[28]  Stefan Fischer,et al.  Modeling brightness perception and syntactical image coding , 1995 .

[29]  Tomaso A. Poggio,et al.  CBF: A New Framework for Object Categorization in Cortex , 2000, Biologically Motivated Computer Vision.

[30]  M. Bar.  Visual objects in context , 2004, Nature Reviews Neuroscience.