基于图像色彩和纹理的SOM聚类和检索方法

Clustering and retrieval using self-organized mapping networks based on image color and texture

作者根据图像的全局色彩和区域纹理信息,使用自组织映射神经网络的方法对图像内容进行聚类和检索.全局色彩在HSI空间使用区域累加的方法,避免了维数过大的问题.用区域纹理描述的方法解决了使用单一色彩带来的不准确性;自组织映射网络所特有的特征选择和无监督学习等特性,实现了对视觉相似图像的聚类.

This paper represents a method to clustering and retrieval images by Self-organizing map which using image＇s color and local texture information. Color information calculated by spatial color accumulates in the HSI color space, which avoid the high dimension problem. Additionally, using local texture descriptor decrease the inaccurate level which caused by only using color information. The ability of Self-organizing map such as characteristic selection and unsupervised learning are sufficiently used.