Recognition of images represented by a final set of points
We describe a new approach to the problem of visual pattern recognition. This approach is based on figure encoding. The encoding used is invariant under affine transformations of discrete sets of points (discrete figures).
KeywordsCharacteristic Image Point Triple Image Point Projection Direction Rigid Transformation
Unable to display preview. Download preview PDF.
- 1.V. N. Kozlov, “Image coding and recognition and some problems of stereovision,” Pattern Recogn. Image Anal., 7, No. 4, 448–466 (1997).Google Scholar
- 2.V. N. Kozlov, “On recognition of affine different discrete visual patterns,” Intellekt. Sist., 3, Nos. 3-4, 95–122 (1998).Google Scholar
- 3.V. N. Kozlov, “On visual patterns, mathematical approaches to visual pattern definition, and pattern recognition,” Zh. Vychisl. Mat. Mat. Fiz., 39, No. 11, 1929–1946 (1999).Google Scholar
- 4.V. N. Kozlov, Elements of Mathematical Theory of Visual Perception [in Russian], Izd. Centra Prikl. Issled. Mekh.-Mat. Fak. MGU, Moscow (2001).Google Scholar