Texture Segmentation Method And Study On Its Application

As an important aspect of digital image process and pattern recognition, texture segmentation has always been one of the hottest and most difficult study topics. Texture segmentation involves accurately partitioning an image into sections according to the textured regions or by recognizing the borders between different textures in the image. Texture feature extraction is crucial in the texture segmentation. In this paper, we made an investigation into texture feature extraction and classification based on statistic method and its application in multi-spectral image classification. The research works of this paper have been done as follows:Firstly, in order to overcome the weakness of gray level co-occurrence matrix (GLCM), a new unsupervised texture segment algorithm, based on multi-resolution model, is presented in this thesis. It first finds the best features that are extracted from GLCM and explain the texture clearly in different resolution, and then segments on different level, at last, by combining the structure information of texture edge, extract the edge of different patterns to get a relatively accurate result of texture segmentation.Secondly, texture segmentation based on local binary pattern (LBP) texture descriptor is very time consuming. For one thing, we adjust the computing method of LBP, for another, set two merging threshold instead of only one. According to many experiments, the algorithm clearly enhances the speed of segmentation while keeps performance of LBP.Thirdly, in the multi-spectral, there are some facts that different objects have the same spectrum and the same objects have different spectrum but they are in the region having different landform so that we can deduce the effect of the fact by segmenting the image according to the texture feature that reflect the landform into blocks in advance and then classifying each pixel according to its corresponding block spectrum information. Taking Daqing ETM+ remote sensing image for example, we give the result of experiment and the evaluation of the accuracy.