This paper presents a new method of occluded object matching for machine vision applications. The current methods for occluded object matching lack robustness and require high computational effort. In this paper, a new Hybrid Hopfield Neural Network (HHN) algorithm, which combines the advantages of both a Continuous Hopfield Network (CHN) and a Discrete Hopfield Network (DHN), will be described and applied for partially occluded object recognition in a multi-context scenery. The HHN proposed as a new approach provides great fault tolerance and robustness and requires less computation time. Also, advantages of HHN such as reliability and speed will be discussed.
Bibliographical noteFunding Information:
Acknowledgements--This research has been supported by FAA under Grant No. 93-G-012, ARO under Grant No. DAAL03-90-0913, NASA-CORE under Grant No. NAGW-2924, and ARPA under Grant No. N00600-93-K-2051.
All Science Journal Classification (ASJC) codes
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence