Space variant image processing

This paper describes a graph-based approach to image processing, intended for use with images obtained from sensors having space variant sampling grids. The connectivity graph (CG) is presented as a fundamental framework for posing image operations in any kind of space variant sensor. Partially motivated by the observation that human vision is strongly space variant, a number of research groups have been experimenting with space variant sensors. Such systems cover wide solid angles yet maintain high acuity in their central regions. Implementation of space variant systems pose at least two outstanding problems. First, such a system must be active, in order to utilize its high acuity region; second, there are significant image processing problems introduced by the non-uniform pixel size, shape and connectivity. Familiar image processing operations such as connected components, convolution, template matching, and even image translation, take on new and different forms when defined on space variant images. The present paper provides a general method for space variant image processing, based on a connectivity graph which represents the neighbor-relations in an arbitrarily structured sensor. We illustrate this approach with the following applications: (1) Connected components is reduced to its graph theoretic counterpart. We illustrate this on a logmap sensor, which possesses a difficult topology due to the branch cut associated with the complex logarithm function. (2) We show how to write local image operators in the connectivity graph that are independent of the sensor geometry. (3) We relate the connectivity graph to pyramids over irregular tessalations, and implement a local binarization operator in a 2-level pyramid. (4) Finally, we expand the connectivity graph into a structure we call a transformation graph, which represents the effects of geometric transformations in space variant image sensors. Using the transformation graph, we define an efficient algorithm for matching in the logmap images and solve the template matching problem for space variant images. Because of the very small number of pixels typical of logarithmic structured space variant arrays, the connectivity graph approach to image processing is suitable for real-time implementation, and provides a generic solution to a wide range of image processing applications with space variant sensors.

[1]  D. Casasent,et al.  Position, rotation, and scale invariant optical correlation. , 1976, Applied optics.

[2]  Narsingh Deo,et al.  Graph Theory with Applications to Engineering and Computer Science , 1975, Networks.

[3]  Benjamin B. Bederson,et al.  A miniaturized space-variant active vision system: Cortex-I , 1995, Machine Vision and Applications.

[4]  Benjamin B. Bederson,et al.  Voice-bandwidth visual communication through logmaps: the Telecortex , 1992, [1992] Proceedings IEEE Workshop on Applications of Computer Vision.

[5]  R. Nevatia,et al.  Detecting moving objects from a moving platform , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[6]  N.R. Malik,et al.  Graph theory with applications to engineering and computer science , 1975, Proceedings of the IEEE.

[7]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[8]  Eric L. Schwartz,et al.  Connectivity Graphs for Space-variant Active Vision , 1993 .

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

[10]  E. L. Schwartz,et al.  Spatial mapping in the primate sensory projection: Analytic structure and relevance to perception , 1977, Biological Cybernetics.

[11]  Alan Rojer.  Space-variant computer vision with a complex-logarithmic sensor geometry , 1990 .

[12]  Eric L. Schwartz,et al.  Design considerations for a space-variant visual sensor with complex-logarithmic geometry , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[13]  Michael J. Swain,et al.  Promising directions in active vision , 1993, International Journal of Computer Vision.

[14]  Benjamin B. Bederson,et al.  A miniaturized active vision system , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. IV. Conference D: Architectures for Vision and Pattern Recognition,.

[15]  Giulio Sandini,et al.  Active vision based on space-variant sensing , 1991 .

[16]  Marc Levoy,et al.  Gaze-directed volume rendering , 1990, I3D '90.

[17]  Carl F. R. Weiman,et al.  3-D Sensing With Polar Exponential Sensor Arrays , 1988, Defense, Security, and Sensing.

[18]  Benjamin B. Bederson,et al.  Calibration of the spherical pointing motor , 1992, Other Conferences.

[19]  Giulio Sandini,et al.  Retinalike space variant CCD sensor , 1990, Other Conferences.

[20]  Akio Shio.  An automatic thresholding algorithm based on an illumination-independent contrast measure , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[21]  Benjamin B. Bederson,et al.  Two miniature pan-tilt devices , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[22]  Carl F. R. Weiman.  Polar Exponential Sensor Arrays Unify Iconic and Hough Space Representation , 1990, Other Conferences.

[23]  Benjamin B. Bederson,et al.  A miniature pan-tilt actuator: the spherical pointing motor , 2011, IEEE Trans. Robotics Autom..

[24]  Tomaso Poggio,et al.  Visual information: Do computers need attention? , 1986, Nature.

[25]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Giulio Sandini,et al.  A Foveated Retina-Like Sensor Using CCD Technology , 1989, Analog VLSI Implementation of Neural Systems.

[27]  Azriel Rosenfeld,et al.  Hierarchical Image Analysis Using Irregular Tessellations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Rafael M. Inigo,et al.  Motion-vision architectures , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[29]  Richard A. Messner,et al.  An image processing architecture for real time generation of scale and rotation invariant patterns , 1985, Comput. Vis. Graph. Image Process..

[30]  V. Tagliasco,et al.  A model of the early stages of the human visual system: Functional and topological transformations performed in the peripheral visual field , 1982, Biological Cybernetics.

[31]  Carl F. R. Weiman,et al.  Exponential Sensor Array Geometry And Simulation , 1988, Defense, Security, and Sensing.

[32]  Ping-Wen Ong,et al.  Space-variant optical character recognition , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[33]  Yukio Kobayashi,et al.  A TV Camera System Which Extracts Feature Points For Non-Contact Eye Movement Detection , 1990, Other Conferences.

[34]  Allen M. Waxman,et al.  A neural system for behavioral conditioning of mobile robots , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[35]  Carl F. R. Weiman,et al.  Logarithmic spiral grids for image-processing and display , 1979 .

[36]  Hanan Samet,et al.  Region representation: quadtrees from boundary codes , 1980, CACM.

[37]  Tutis Vilis,et al.  The superior colliculus and spatiotemporal translation in the saccadic system , 1990, Neural Networks.

[38]  Eric L. Schwartz,et al.  Applications of computer graphics and image processing to 2D and 3D modeling of the functional architecture of visual cortex , 1988, IEEE Computer Graphics and Applications.

[39]  Azriel Rosenfeld,et al.  Hierarchical Image Analysis Using Irregular Tessellations , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[40]  Charles M Hains,et al.  Image-processing system , 1993 .

[41]  Azriel Rosenfeld,et al.  Connectivity in Digital Pictures , 1970, JACM.