Stereo Matching Optimization by Means of Texture Analysis

The extraction of disparity data by means of stereo matching has well known issues in regions of low texture. This paper proposes a method which employs texture classification metrics in order to make predictions on the quality of the stereo matching output. Such predictions can then be used to alter the way the disparity data is used in further processing, or to even cancel processing of a pixel when the predicted quality is too low. Three metrics (based on laws, entropy and energy) are evaluated to this purpose on two stereo matching algorithms.