Recognition of partially occluded objects based on segmentation by median filtering of extended direction code
- 21 Downloads
The image contour is segmented into lines, arcs and smooth curves by median filtering of extended direction code. Based on this segmentation, a set of new local invariant features are proposed to recognize partially occluded objects, which is more reasonable compared with conventional corner features. The matching results of some typical examples shows that these features are robust, effective in recognition.
Key wordspattern recognition Freeman's code extended code median filtering corner
Unable to display preview. Download preview PDF.
- 1.Wang Y P, Zhao H Z, Cai Q. Recognition of 3D objects with order normalized invariant moments.J Wuhan Univ Natur Sci Ed, 1996,42(5):639–646 (in Chinese)Google Scholar
- 3.Yuan J, Liao Y, Hu Z Yet al. A matching method of occluded images using feature templet.J Wuhan Univ Natur Sci Ed, 1997,5(43):655–660 (in Chinese)Google Scholar
- 5.Han MinHong, Jang Dongsig. The use of maximum curvature points for the recognition of partially occluded objects.Pattern Recognition, 1988,23:21–33Google Scholar