摘要
纹理分割是图像处理与计算机视觉领域研究的重点和难点。现有的纹理分割方法大多集中于研究灰度纹理图像,该文提出了一种基于分形纹理特征和颜色信息结合的彩色纹理分割算法。该算法将复杂的彩色图像分形维数计算转化为单色图像分形维数的计算,将纹理特征和颜色信息相结合,采用区域生长法来实现分割。通过对彩色岩石裂隙图像的分割实验,结果证实该该方法行之有效。
Texture analysis is an important and difficult task in the field of image processing and computer vision. Most existing texture segmentation approaches focus on gray texture images, this paper proposes an algorithm of color texture segmentation that combine the fractal texture feature with color. The algorithm converts complicated computation of color image into the computation of homochromy image, it combines image's texture feature with color, and uses region growing to achieve the segmentation. The exper...
出处
《微计算机信息》
北大核心
2008年第4期261-262,299,共3页
Control & Automation
基金
TRUE(The Tracer Retention Understanding Ex-periments)
由瑞典SKB
欧盟联合支持
重庆市科委自然科学岩石裂隙节理图像分割(CSTC2004BB7166)
关键词
彩色纹理
分形
裂隙
图像分割
区域生长
color texture
fractal
fracture
image segmentation
region growing
