3D Line Image Analysis - A Heuristic Parallel Approach with Learning and Recognition

Abstract A heuristic parallel approach for (3d) line image analysis is introduced by using the concept of coordinated graph, layered graph representation, and parallel matching techniques and it significantly reduces the time required for dealing with three-dimensional line image analysis problems. Their fundamental properties and the concept of finite representations are investigated, and an interactive and iterative recognition algorithm with learning and recognition as a part of each other is presented. Several interested examples including curved and disconnected line images are illustrated. In addition to its importance in theoretical studies, this approach can also be applied to 3d object recognition, image processing, and computer vision in industrial, military, and medical fields.

[1]  Herbert Freeman,et al.  Characteristic Views As A Basis For Three-Dimensional Object Recognition , 1982, Other Conferences.

[2]  Thomas Marill.  Recognizing Three-Dimensional Objects without the Use of Models , 1989 .

[3]  Patrick Shen-Pei Wang,et al.  A Fast and Flexible Thinning Algorithm , 1989, IEEE Trans. Computers.

[4]  D. Metzler,et al.  Mental rotation: effects of dimensionality of objects and type of task. , 1988, Journal of Experimental Psychology: Human Perception and Performance.

[5]  Patrick Shen-Pei Wang,et al.  A comment on “a fast parallel algorithm for thinning digital patterns” , 1986, CACM.

[6]  K. Sugihara.  Machine interpretation of line drawings , 1986, MIT Press series in artificial intelligence.

[7]  Ching Y. Suen,et al.  A fast parallel algorithm for thinning digital patterns , 1984, CACM.

[8]  Azriel Rosenfeld,et al.  3-D Shape Recovery Using Distributed Aspect Matching , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Charles R. Dyer,et al.  Model-based recognition in robot vision , 1986, CSUR.

[10]  Ronen Basri,et al.  Viewer-Centered Representations in Object Recognition: a Computational Approach , 1993, Handbook of Pattern Recognition and Computer Vision.

[11]  Patrick Shen-Pei Wang.  Parallel Object Representation and Recognition , 1993, Parallel Process. Lett..

[12]  Leemon Baird,et al.  Three-dimensional object recognition using gradient descent and the universal 3-D array grammar , 1992, Other Conferences.

[13]  E. K. WONG,et al.  Model matching in robot vision by subgraph isomorphism , 1992, Pattern Recognit..

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