基于离散平稳小波变换和FCM的纹理图像分割

Texture Image Segmentation Based on Stationary Wavelet Transform and FCM

采用离散平稳小波变换对纹理图像进行分解,以各层小波系数中能量为特征相向量,采用模糊c-均值聚类(FCM)对图像分割,并对分割方法进行了改进,提出采用网格法,将图像分解成若干子图像,对图像进行粗分割,再对边缘部分的网格进行细分的两步分割法。试验结果表明该方法显著提高了分割速度和精度。

Stationary wavelet transform is used to decompose texture image for image segmentation. The texture features are extracted from the wavelet coefficient energy. Then fuzzy c-means clustering method（FCM） is used to complete the texture image segmentation. In order to progress the accurateness and efficiency of texture image segmentation, the improved segmentation method is presented. The progress is divided into two steps. The first step is coarse segmentation, then detecting the boundary of segmentation for accurate segmentation. The experiment results show that the improved method is efficient.