Understanding image structure from a new multi-scale representation of higher order derivative filters

We are proposing a biologically inspired multi-scale derivative filter in which the higher order derivatives are expressed as a linear combination of a smoothing function at various scales. One of the functions in the summation has been approximated to a Dirac-delta function to finally yield the new filter. This modification has some support from the point of view of authentic edge detection as well as from neurophysiological and psychophysical experiments at the retinal level. Besides, it improves the quality of the filter in a number of ways. The proposed filter can be optimized at any desired scale. Hence it is very effective in extracting the features from a noisy picture. The filter is rotationally symmetric. Zero-crossing map of any picture filtered with the proposed model gives a half-toning effect to the retrieved image and hence preserves the intensity information in the image even in the edge map.

[1]  S. Sarkar,et al.  Extended surround based neuromorphically implementable model of human visual system , 2005, Proceedings of 2005 International Conference on Intelligent Sensing and Information Processing, 2005..

[2]  D Marr,et al.  Bandpass channels, zero-crossings, and early visual information processing. , 1979, Journal of the Optical Society of America.

[3]  J. Koenderink,et al.  Representation of local geometry in the visual system , 1987, Biological Cybernetics.

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

[5]  Sandip Sarkar,et al.  Image Enhancement by High-Order Gaussian Derivative Filters Simulating Non-classical Receptive Fields in the Human Visual System , 2005, PReMI.

[6]  Sandip Sarkar,et al.  A possible mechanism of zero-crossing detection using the concept of the extended classical receptive field of retinal ganglion cells , 2005, Biological Cybernetics.

[7]  B. Logan.  Information in the zero crossings of bandpass signals , 1977, The Bell System Technical Journal.

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

[9]  Jack Koplowitz,et al.  Edge location error for local maximum and zero-crossing edge detectors , 1992 .

[10]  R. W. Rodieck,et al.  Analysis of receptive fields of cat retinal ganglion cells. , 1965, Journal of neurophysiology.

[11]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[12]  R. Young.  GAUSSIAN DERIVATIVE THEORY OF SPATIAL VISION: ANALYSIS OF CORTICAL CELL RECEPTIVE FIELD LINE-WEIGHTING PROFILES. , 1985 .

[13]  C. Enroth-Cugell,et al.  Suppression of cat retinal ganglion cell responses by moving patterns. , 1980, The Journal of physiology.

[14]  Tony Lindeberg,et al.  Linear scale-space and related multi-scale representations , 1994 .

[15]  Steven W. Zucker,et al.  Logical/Linear Operators for Image Curves , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  J. Krüger,et al.  The shift-effect enhances X- and suppresses Y-type response characteristics of cat retinal ganglion cells , 1980, Brain Research.

[17]  J. Mcilwain.  Some evidence concerning the physiological basis of the periphery effect in the cat's retina , 2004, Experimental Brain Research.

[18]  H Ikeda,et al.  Functional organization of the periphery effect in retinal ganglion cells. , 1972, Vision research.

[19]  Kim L. Boyer,et al.  On Optimal Infinite Impulse Response Edge Detection Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  T. Shou,et al.  Orientation bias of the extraclassical receptive field of the relay cells in the cat's dorsal lateral geniculate nucleus , 2004, Neuroscience.

[21]  J. Koenderink,et al.  Receptive field families , 1990, Biological Cybernetics.

[22]  J. Koenderink.  The structure of images , 2004, Biological Cybernetics.

[23]  C. Enroth-Cugell,et al.  The contrast sensitivity of retinal ganglion cells of the cat , 1966, The Journal of physiology.

[24]  Refractor.  Vision , 2000, The Lancet.

[25]  R. Shapley,et al.  Area (mt) Spatial Summation, End Inhibition and Side Inhibition in the Middle Temporal Visual Adaptation Complex Cells Increase Their Phase Sensitivity at Low Contrasts and following Dependence of Response Properties on Sparse Connectivity in a Spiking Neuron Model Of , 2022 .

[26]  Isaac Weiss.  High-Order Differentiation Filters that Work , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  J. Koenderink,et al.  The Shape of Smooth Objects and the Way Contours End , 1982, Perception.

[28]  C. Enroth-Cugell,et al.  Effects of Remote Stimulation on the Mean Firing Rate of Cat Retinal Ganglion Cells , 2001, The Journal of Neuroscience.

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

[30]  R. Jampel.  Mach Bands, Quantitative Studies on Neural Networks in the Retina. , 1966 .

[31]  R A Young,et al.  The Gaussian derivative model for spatial vision: I. Retinal mechanisms. , 1988, Spatial vision.

[32]  Alan L. Yuille,et al.  Scaling Theorems for Zero Crossings , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Jack Koplowitz,et al.  On the Edge Location Error for Local Maximum and Zero-Crossing Edge Detectors , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Sandip Sarkar,et al.  A New Mechanism of "Fuzzy" Edge Detection by Multi-scale Gaussian Filters in the light of Human Visual System , 2005, IICAI.

[35]  Songde Ma,et al.  Derivative computation by multiscale filters , 1998, Image Vis. Comput..

[36]  Sandip Sarkar,et al.  A possible explanation of the low-level brightness–contrast illusions in the light of an extended classical receptive field model of retinal ganglion cells , 2006, Biological Cybernetics.

[37]  D. Marr,et al.  Smallest channel in early human vision. , 1980, Journal of the Optical Society of America.

[38]  Mitra Basu,et al.  Image enhancement using a human visual system model , 1997, Pattern Recognit..