The role of features in structuring visual images.

Edges and lines carry much information about images and many models have been developed to explain how the human visual system may process them. One recent approach is the local energy model of Morrone and Burr. This model detects and locates both lines and edges simultaneously, by taking the Pythagorean sum of the output of pairs of matched filters (even- and odd-symmetric operators) to produce the all-positive local energy function. Maxima of this function signal the presence of all image features that are then classified as lines or edges (or both) and as positive or negative, depending on the strength of response of the even- and odd-symmetric operators. If the feature is an edge, it carries with it a brightness description that extends over space to the next edge. The model successfully explains many visual illusions, such as the Craik-O'Brien, Mach bands and a modified version of the Chevreul. Features can structure the visual image, often creating appearances quite contrary to the physical luminance distributions. In some examples the features dictate totally the image structure, 'capturing' all other information; in others the features are seen in transparence together with an alternate image. All cases can be predicted from the rules for combination of local energy at different scales.

[1]  B Julesz,et al.  Masking in Visual Recognition: Effects of Two-Dimensional Filtered Noise , 1973, Science.

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

[3]  David C. Burr,et al.  Added noise restores recognizability of coarse quantized images , 1983, Nature.

[4]  Mark A. Georgeson,et al.  Eye movements, afterimages and monocular rivalry , 1984, Vision Research.

[5]  R Shapley,et al.  Contrast and assimilation in the perception of brightness. , 1985, Proceedings of the National Academy of Sciences of the United States of America.

[6]  R. Watt,et al.  A theory of the primitive spatial code in human vision , 1985, Vision Research.

[7]  M C Morrone,et al.  Recognition of Positive and Negative Bandpass-Filtered Images , 1986, Perception.

[8]  George Mather,et al.  Irradiation: Implications for theories of edge localization , 1986, Vision Research.

[9]  R. F. Hess,et al.  Evidence for spatially local computations underlying discrimination of periodic patterns in fovea and periphery , 1987, Vision Research.

[10]  D. Burr.  Implications of the Craik-O'Brien illusion for brightness perception , 1987, Vision Research.

[11]  S. Grossberg,et al.  Neural dynamics of 1-D and 2-D brightness perception: A unified model of classical and recent phenomena , 1988, Perception & psychophysics.

[12]  D. Burr,et al.  Feature detection in human vision: a phase-dependent energy model , 1988, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[13]  D. Burr,et al.  The conditions under which Mach bands are visible , 1989, Vision Research.

[14]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[15]  Jitendra Malik,et al.  Detecting and localizing edges composed of steps, peaks and roofs , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[16]  F. Kingdom,et al.  A multi-channel approach to brightness coding , 1992, Vision Research.

[17]  M. C. Morrone,et al.  A Model of Human Feature Detection Based on Matched Filters , 1993 .

[18]  M. C. Morrone,et al.  Illusory brightness step in the chevreul illusion , 1994, Vision Research.