A Two Level Model-Based Approach of Object Recognition for Robotics Application

The model-based object-recognition system is one of the most promising approach for robot vision applications. The block diagram of a typical model-based recognition system is shown in Figure 1. The key issue of the model-based approach is matching the unknown image with a set of predefined models of objects. The capability of recognizing objects accurately depends upon the adequacy of the model, the description of the image, and the matching algorithm used.

[1]  Theodosios Pavlidis,et al.  Algorithms for Shape Analysis of Contours and Waveforms , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Theodosios Pavlidis.  Comment on "A Declustering Criterion for Feature Extraction in Pattern Recognition , 1979 .

[3]  Ramakant Nevatia,et al.  Matching Images Using Linear Features , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  F. Badi'i,et al.  Functional approximation of planar curves via adaptive segmentation , 1982 .

[5]  Theodosios Pavlidis.  The Use of a Syntactic Shape Analyzer for Contour Matching , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  King-Sun Fu,et al.  Syntactic Pattern Recognition And Applications , 1968 .

[7]  B. Peikari,et al.  A two level model-based approach for object recognition , 1988 .

[8]  Bir Bhanu,et al.  Recognition of occluded objects: A cluster structure paradigm , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.