Journal of the Korean Institute of Telematics and Electronics B (전자공학회논문지B)
- Volume 31B Issue 12
- /
- Pages.124-131
- /
- 1994
- /
- 1016-135X(pISSN)
Stereopsis with cellular neural networks
국소적인 연결을 갖는 신경회로망을 이용한 스테레오 정합
Abstract
In this paper, we propose a new approach of solving the stereopsis problem with a discrete-time cellular neural network(DTCNN) where each node has connections only with its local neithbors. Because the matching process of stereo correspondence depends on its geometrically local characteristics, the DTCNN is suitable for the stereo correspondence. Moreover, it can be easily implemented in VLSI. Therefore, we employed a two-layer DTCNN with dual templates, which are determined with the back propagation learning rule. Based on evaluation of the proposed approach for several random-dot stereograms, its performance is better than that of the Marr-Poggio algorithm.
Keywords