Towards creating abstract features of complex objects - the fusion of contour points in significant contour sections for object recognition

Abstract In real world problems, where the objects are in general complex and deformed, the automatic generation of local characteristics is necessary in order to distinguish different object classes. This article presents an approach towards the automatic synthesis of significant local contour sections of closed, discrete, complex, and deformed 2D-object contours for the distinction of different classes.

[1]  Donald D. Hoffman,et al.  Salience of visual parts , 1997, Cognition.

[2]  Michael Schanz,et al.  Mustererkennung 1998, 20. DAGM-Symposium , 1998 .

[3]  Ronen Basri,et al.  Determining the similarity of deformable shapes , 1998, Vision Research.

[4]  Klaus-Dieter Kuhnert,et al.  Towards automatically learning an implicit model from 2D-images based on a local similarity analysis of contours , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[5]  Sven Loncaric,et al.  A survey of shape analysis techniques , 1998, Pattern Recognit..

[6]  Klaus-Dieter Kuhnert,et al.  Generating Automatically Local Feature Groups of Complex and Deformed Objects , 2000 .

[7]  Peisheng Gao,et al.  2-D shape blending: an intrinsic solution to the vertex path problem , 1993, SIGGRAPH.

[8]  Klaus-Dieter Kuhnert,et al.  Towards Feature Fusion - The Synthesis of Contour Sections Distinguishing Contours from Different Classes , 2000, DGCI.

[9]  Longin Jan Latecki,et al.  Shape Decomposition and Shape Similarity Measure , 1998, DAGM-Symposium.

[10]  Kaleem Siddiqi,et al.  Parts of Visual Form: Computational Aspects , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  W. Pitts,et al.  How we know universals; the perception of auditory and visual forms. , 1947, The Bulletin of mathematical biophysics.

[12]  David Sankoff,et al.  Time Warps, String Edits, and Macromolecules: The Theory and Practice of Sequence Comparison , 1983 .

[13]  Haim J. Wolfson,et al.  A new method of estimating shape similarity , 1996, Pattern Recognit. Lett..