关键词: 小波域, 多尺度MRF, 特征场, 标记场, 小波金字塔

Abstract: Textile printing pattern image segmentation is a very important process in textile printing and dyeing process, in order to improve the accuracy, this paper adopts MRMRF algorithm realized texture segmentation. At first a preceding process is taken in this algorithm. Then , the image is decomposed by wavelet pyramids. In the algorithm, the segmentation on each scale can make full use of information on all scales. the relationship among each wavelet coefficient can reflect the feature of each pixel location, and the interaction of neighborhoods can reflect the regional of image segmentation. Both of these two fields constraint each other by product of joint probability, and act on the segmentation process together. The image segmentation procedure is sequentially executed from the coarsest resolution scale to the finest resolution scale, and segmentation result of the coarser scale is directly projected on the nearest finer resolution scale as its initial segmentation. The segmentation result on the finest resolution is used as the final result of the algorithm.

Key words: wavelet domain, multiscale Markov random field, feature field, label field, wavelet , pyramid