A Computational Model Of Texture Segmentation

An algorithm for finding texture boundaries in images is developed on the basis of a computational model of human texture perception. The model consists of three stages: (1) the image is convolved with a bank of even-symmetric linear filters followed by half-wave rectification to give a set of responses; (2) inhibition, localized in space, within and among the neural response profiles results in the suppression of weak responses when there are strong responses at the same or nearby locations; and (3) texture boundaries are detected using peaks in the gradients of the inhibited response profiles. The model is precisely specified, equally applicable to grey-scale and binary textures, and is motivated by detailed comparison with psychophysics and physiology. It makes predictions about the degree of discriminability of different texture pairs which match very well with experimental measurements of discriminability in human observers. From a machine-vision point of view, the scheme is a high-quality texture-edge detector which works equally on images of artificial and natural scenes. The algorithm makes the use of simple local and parallel operations, which makes it potentially real-time.<<ETX>>

[1]  J. Robson,et al.  Application of fourier analysis to the visibility of gratings , 1968, The Journal of physiology.

[2]  D. Tolhurst Adaptation to square‐wave gratings: inhibition between spatial frequency channels in the human visual system , 1972, The Journal of physiology.

[3]  K. Tanaka,et al.  Organization of cat visual cortex as investigated by cross-correlation technique. , 1981, Journal of neurophysiology.

[4]  D. G. Albrecht,et al.  Striate cortex of monkey and cat: contrast response function. , 1982, Journal of neurophysiology.

[5]  J. Beck Organization and representation in perception , 1982 .

[6]  BELA JULESZ,et al.  Rapid discrimination of visual patterns , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[7]  Azriel Rosenfeld,et al.  Human and Machine Vision , 1983 .

[8]  K. D. De Valois,et al.  Spatial‐frequency‐specific inhibition in cat striate cortex cells. , 1983, The Journal of physiology.

[9]  J. Canny Finding Edges and Lines in Images , 1983 .

[10]  A. Rosenfeld,et al.  A Theory of Textural Segmentation , 1983 .

[11]  D. Field,et al.  Phase reversal discrimination , 1984, Vision Research.

[12]  Ingo Rentschler,et al.  Loss of spatial phase relationships in extrafoveal vision , 1985, Nature.

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

[14]  H. Nothdurft Sensitivity for structure gradient in texture discrimination tasks , 1985, Vision Research.

[15]  T. Caelli Three processing characteristics of visual texture segmentation. , 1985, Spatial vision.

[16]  Luc Van Gool,et al.  Texture analysis Anno 1983 , 1985, Comput. Vis. Graph. Image Process..

[17]  B.J.A. Krose,et al.  A description of visual structure: Relations with human information processing mechanisms , 1986 .

[18]  J. Enns,et al.  Seeing textons in context , 1986, Perception & psychophysics.

[19]  R. Browse,et al.  Micropattern properties and presentation conditions influencing visual texture discrimination , 1987, Perception & psychophysics.

[20]  H. Voorhees Finding Texture Boundaries in Images , 1987 .

[21]  A. Mackay "Textures" , 1987 .

[22]  M. Banks,et al.  Sensitivity loss in odd-symmetric mechanisms and phase anomalies in peripheral vision , 1987, Nature.

[23]  J Rovamo,et al.  Texture discrimination at different eccentricities. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[24]  Jacob Beck,et al.  Spatial frequency channels and perceptual grouping in texture segregation , 1987, Comput. Vis. Graph. Image Process..

[25]  H. Jasper,et al.  Neurotransmitters and cortical function : from molecules to mind , 1988 .

[26]  Jitendra Malik,et al.  On image texture , 1988 .

[27]  Terry Caelli,et al.  On the discrimination of compound Gabor signals and textures , 1988, Vision Research.

[28]  E. Adelson,et al.  Early vision and texture perception , 1988, Nature.

[29]  Tomaso Poggio,et al.  Computing texture boundaries from images , 1988, Nature.

[30]  Rangasami L. Kashyap,et al.  Texture Boundary Detection Based on the Long Correlation Model , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Jitendra Malik,et al.  A computational model of texture perception , 1989 .

[32]  D. Burr,et al.  Evidence for edge and bar detectors in human vision , 1989, Vision Research.

[33]  RussLL L. Ds Vnlos,et al.  SPATIAL FREQUENCY SELECTIVITY OF CELLS IN MACAQUE VISUAL CORTEX , 2022 .

[34]  M.,et al.  Statistical and Structural Approaches to Texture , 2022 .