A neural matching algorithm for 3-D reconstruction from stereo pairs of linear images
Pattern Recognition Letters - Special issue on neural networks for computer vision applications
An Experimental Comparison of Stereo Algorithms
ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
Image segmentation using evolutionary computation
IEEE Transactions on Evolutionary Computation
Hi-index | 0.01 |
This paper presents a new cooperative algorithm based on the integration of stereo matching and segmentation. Stereo correspondence is recovered from two stereo images with the help of a segmentation result. Using a genetic algorithm (GA)-based image segmentation, we can refine the depth map more effectively. Experimental results are presented to illustrate the performances of the proposed method.