Title :
Signature based recognition of 2D occluded objects
Author :
Hanmandlu, M. ; Shantaram, V.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol., New Delhi, India
fDate :
30 Aug-3 Sep 1992
Abstract :
A model-based method for the recognition of 2D occluded objects is presented. Initially, to reduce the number of models to be considered for identification from the model database, two types of signatures are used. One is based on curvatures and the other on G curve. Next, exact matching is used to find the correct model. The results are illustrated for an occluded scene consisting of industrial objects. The relative performance of the proposed two types of signatures is also given
Keywords :
image processing; pattern recognition; 2D occluded objects; G curve; curvatures; model-based method; signature-based recognition; Image retrieval; Image segmentation; Layout; Length measurement; Machine vision; Object oriented databases; Q measurement; Robot vision systems; Service robots; Turning;
Conference_Titel :
Pattern Recognition, 1992. Vol.I. Conference A: Computer Vision and Applications, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2910-X
DOI :
10.1109/ICPR.1992.201632
