Stereo matching is always the crucial problem of the computer vision. The less-textured area stereo matching problem can be solved by region-based stereo matching algorithm, in which the key steps are dividing and matching of less-textured area. According to the characters of less-textured area, a novel approach is provided for less-textured area dividing. It describes the texture with Laws′ masks and gets the less-textured area by histogram-based segmentation. It can get the best result for various scene images by comparing various combinations of Laws′ masks. Experimental results on the international standard image data show that our algorithm has better recognition rate of less-textured area and better robustness of choosing the dividing threshold than the previous method which describes the texture with gray level co-occurrence matrix and gets the less-textured area by region growing-based segmentation. This new algorithm is helpful to increase the accuracy and usability of region-based stereo matching algorithm.