基于塔形小波和特征加权的墙地砖纹理图像分割方法

Approach for Textured Image Segmentation of Tile Based on Wavelet Transformation and Feature Weight

目的基于小波变换的图像分割方法对随机纹理图像进行分割.方法通过墙地砖表面的原始纹理特征,改进原有的图像分割算法,对原始纹理图像进行高阶小波分解.结果图像整体中的背景纹理边缘被有效去除,降低了图像纹理带来的干扰,在有效提取近似信息的基础上提高了系统的实时性.结论根据墙地砖的纹理特征,采用基于塔形小波的改进分割方法,对墙地砖的原始图像进行处理,提高了边缘准确性和区域性,降低了分割错误率.

The image segmentation methods based on wavelet transformation can segment random texture image. Through the surface textured features of ceramic tiles, the traditional segmentation algorithm is improved by the higher order wavelet decomposition. As a result, background texture edge of overall image is removed effectively and the influence from image texture is reduced. Moreover, the real time capacity of system is enhanced by remaining effective approximate information. In the paper, an improved image segmentation method based on turret wavelet transformation is used to deal with original image with texture features, which can improve the accuracy of edge inspection and regionality, and reduce the error rate.