The Pyramid as a Structure for Efficient Computation

Many basic image operations may be performed efficiently within pyramid structures. Pyramid algorithms can generate sets of low-and band-pass filtered images at a fraction of the cost of the FFT. Local image properties such as texture statistics can be estimated with equal efficiency within Gaussianlike windows of many sizes. Pyramids support fast “coarse-fine” search strategies. Pyramids also provide a neural-like image representation which is robust, compact and appropriate for a variety of higher level tasks including motion analysis. Through “linking,” pyramids may be used to isolate and represent image segments of arbitrary size and shape. Here the pyramid will be viewed primarily as a computational tool. However, interesting similarities will be noted between pyramid processing and processing within the human visual system.

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

[2]  A. Rosenfeld,et al.  Edge and Curve Detection for Visual Scene Analysis , 1971, IEEE Transactions on Computers.

[3]  C. Tyler.  Stereoscopic Vision: Cortical Limitations and a Disparity Scaling Effect , 1973, Science.

[4]  Theodosios Pavlidis,et al.  A hierarchical data structure for picture processing , 1975 .

[5]  C. Tyler.  Spatial organization of binocular disparity sensitivity , 1975, Vision Research.

[6]  J. Limb,et al.  Estimating the Velocity of Moving Images in Television Signals , 1975 .

[7]  J. Lappin,et al.  The detection of coherence in moving random-dot patterns , 1976, Vision Research.

[8]  E. Hall,et al.  Hierarchical search for image matching , 1976, 1976 IEEE Conference on Decision and Control including the 15th Symposium on Adaptive Processes.

[9]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[10]  C. Tyler,et al.  Visual echoes: The perception of repetition in quasi-random patterns , 1977, Vision Research.

[11]  Claude L. Fennema,et al.  Velocity determination in scenes containing several moving objects , 1979 .

[12]  Patrick C. Chen,et al.  Image segmentation as an estimation problem , 1979, 1979 18th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes.

[13]  B. Julesz,et al.  A disparity gradient limit for binocular fusion. , 1980, Science.

[14]  P. J. Burt,et al.  Fast Filter Transforms for Image Processing , 1981 .

[15]  P. Burt,et al.  Time, distance, and feature trade-offs in visual apparent motion. , 1981 .

[16]  P. Burt.  Fast filter transform for image processing , 1981 .

[17]  Azriel Rosenfeld,et al.  Segmentation and Estimation of Image Region Properties through Cooperative Hierarchial Computation , 1981, IEEE Transactions on Systems, Man, and Cybernetics.

[18]  A. Rosenfeld,et al.  Image Segmentation by Texture Using Pyramid Node Linking. , 1981 .

[19]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[20]  C H Anderson,et al.  Spatially inhomogeneous scaled transforms for vision and pattern recognition. , 1981, Optics letters.

[21]  Paul S. Schenker,et al.  New sensor geometries for image processing: Computer vision in the polar exponential grid , 1981, ICASSP.

[22]  Peter J. Burt,et al.  Fast algorithms for estimating local image properties , 1982, Comput. Graph. Image Process..

[23]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..