Parameter Networks: Towards a Theory of Low-Level Vision

One of the most fundamental problems in vision is segmentation; the way in which parts of an image are perceived as a meaningful whole. Recent work has shown how to calculate images of physical parameters from raw intensity data. Such images are known as intrinsic images, and examples are images of velocity (optical flow), surface orientation, occluding contour, and disparity. While intrinsic images are not segmented, they are distinctly easier to segment than the original intensity image. Segments can be detected by a general Hough transform technique. Networks of feature parameters are appended to the intrinsic image organization. Then the intrinsic image points are mapped into these networks. This mapping will be many-to-one onto parameter values that represent segments. This basic method is extended into a general representation and control technique with the addition of three main ideas: abstraction levels; sequential search; and tight counting These ideas are a nucleus of a connectionist theory of low 'eve and m'ermediate-level vision. This theory explains segmentation in terms of massively parallel cooperative computation among intrinsic images and a set of parameter spaces at different levels of abstraction.

[1]  D. Jameson,et al.  An opponent-process theory of color vision. , 1957, Psychological review.

[2]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[3]  Jack Sklansky,et al.  Finding circles by an array of accumulators , 1975, Commun. ACM.

[4]  Azriel Rosenfeld,et al.  Scene Labeling by Relaxation Operations , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.

[6]  D. Brandt,et al.  Multi-level adaptive solutions to boundary-value problems math comptr , 1977 .

[7]  Geoffrey E. Hinton.  Relaxation and its role in vision , 1977 .

[8]  Keith Price,et al.  Picture Segmentation Using a Recursive Region Splitting Method , 1998 .

[9]  H. Barrow,et al.  RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES , 1978 .

[10]  Allen R. Hanson,et al.  Computer Vision Systems , 1978 .

[11]  K. Ikeuchi.  Numerical Shape from Shading and Occluding Contours in a Single View , 1979 .

[12]  B K Horn,et al.  Calculating the reflectance map. , 1979, Applied optics.

[13]  Shimon Ullman,et al.  Relaxation and constrained optimization by local processes , 1979 .

[14]  John M. Prager,et al.  Extracting and Labeling Boundary Segments in Natural Scenes , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  William B. Thompson,et al.  TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2009 .

[16]  Takeo Kanade,et al.  Mapping Image Properties into Shape Constraints: Skewed Symmetry and Affine-Tramsfornable Patterns, and the Shape-from-Texture Paradigm , 1980, AAAI.

[17]  Takeo Kanade,et al.  A Theory of Origami World , 1979, Artif. Intell..

[18]  Ernesto Bribiesca,et al.  How to describe pure form and how to measure differences in shapes using shape numbers , 1980, Pattern Recognit..

[19]  Martin A. Fischler,et al.  An iconic transform for sketch completion and shape abstraction , 1980 .

[20]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[21]  On Shapes , 1981, IJCAI.

[22]  Jerome A. Feldman,et al.  Computing with Connections , 1981 .

[23]  Takeo Kanade,et al.  Recovery of the Three-Dimensional Shape of an Object from a Single View , 1981, Artif. Intell..

[24]  Anna R. Bruss.  The Image Irradiance Equation: Its Solution and Application , 1981 .

[25]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[26]  Daniel Sabbah,et al.  Design Of A Highly Parallel Visual Recognition System , 1981, IJCAI.

[27]  Kenneth R. Sloan,et al.  Dynamically Quantized Pyramids , 1981, IJCAI.

[28]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[29]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Takeo Kanade,et al.  Mapping Image Properties into Shape Constraints: Skewed Symmetry, Affine-Transformable Patterns, and the Shape-from-Texture Paradigm , 1983 .