Early Recurrence Improves Edge Detection

A biologically motivated computational model of early recurrence is proposed for edge detection. Studies of the primate vision suggested that visual features are transmitted in the two visual pathways with different speeds (with the dorsal pathway processing faster than that of the ventral pathway) and the presences of extensive recurrent connections across the two pathways. It is thus likely that the dorsal perception facilitates the ventral perception via early recurrent mechanism. Following these neural principles, we hypothesize that early recurrence enables responses to high-spatial frequency features (fine edges) to be suppressed by low-spatial frequency features (coarse edges) in a multiplicative manner. Using real images, we quantitatively compared contours calculated by our work with another well-known biologically motivated model. To further explore early recurrence in solving machine vision problems, the representation is used to boost different popular edge algorithms. Results from both experiments lead to the conclusion that early recurrence has a positive and consistent influence on edge detection.

[1]  G. Orban,et al.  The Retinotopic Organization of the Human Middle Temporal Area MT/V5 and Its Cortical Neighbors , 2010, The Journal of Neuroscience.

[2]  Yongjie Li,et al.  Center–surround interaction with adaptive inhibition: A computational model for contour detection , 2011, NeuroImage.

[3]  John H. R. Maunsell,et al.  Hierarchical organization and functional streams in the visual cortex , 1983, Trends in Neurosciences.

[4]  C. Koch,et al.  Multiplicative computation in a visual neuron sensitive to looming , 2002, Nature.

[5]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  J. Bullier,et al.  The role of feedback connections in shaping the responses of visual cortical neurons. , 2001, Progress in brain research.

[7]  J. Bullier,et al.  Visual latencies in areas V1 and V2 of the macaque monkey , 1995, Visual Neuroscience.

[8]  N. Ranganathan,et al.  Gabor filter-based edge detection , 1992, Pattern Recognit..

[9]  Alessandro Neri,et al.  A Biologically Motivated Multiresolution Approach to Contour Detection , 2007, EURASIP J. Adv. Signal Process..

[10]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Christian Casanova,et al.  Vision : from neurons to cognition , 2001 .

[12]  Jitendra Malik,et al.  Learning Probabilistic Models for Contour Completion in Natural Images , 2008, International Journal of Computer Vision.

[13]  T. Albright.  Direction and orientation selectivity of neurons in visual area MT of the macaque. , 1984, Journal of neurophysiology.

[14]  D. J. Felleman,et al.  Distributed hierarchical processing in the primate cerebral cortex. , 1991, Cerebral cortex.

[15]  J. Bullier.  Integrated model of visual processing , 2001, Brain Research Reviews.

[16]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  N. Petkov,et al.  Motion detection, noise reduction, texture suppression, and contour enhancement by spatiotemporal Gabor filters with surround inhibition , 2007, Biological Cybernetics.

[18]  Carrie J. McAdams,et al.  Effects of Attention on Orientation-Tuning Functions of Single Neurons in Macaque Cortical Area V4 , 1999, The Journal of Neuroscience.

[19]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[20]  E Kaplan,et al.  Effects of dark adaptation on spatial and temporal properties of receptive fields in cat lateral geniculate nucleus. , 1979, The Journal of physiology.

[21]  Xiaofeng Ren,et al.  Multi-scale Improves Boundary Detection in Natural Images , 2008, ECCV.

[22]  G. Orban,et al.  Response latency of macaque area MT/V5 neurons and its relationship to stimulus parameters. , 1999, Journal of neurophysiology.

[23]  Andrew P. Witkin,et al.  Scale-space filtering: A new approach to multi-scale description , 1984, ICASSP.

[24]  Alan L. Yuille,et al.  Statistical Edge Detection: Learning and Evaluating Edge Cues , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  J. M. Hupé,et al.  Cortical feedback improves discrimination between figure and background by V1, V2 and V3 neurons , 1998, Nature.

[26]  D. G. Albrecht,et al.  Spatial frequency selectivity of cells in macaque visual cortex , 1982, Vision Research.

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

[28]  Bjørn Olstad,et al.  Edge detection in noisy data using finite mixture distribution analysis , 1994, Proceedings of 1st International Conference on Image Processing.

[29]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[30]  Leslie G. Ungerleider.  Two cortical visual systems , 1982 .