基于HOG-GLRLM特征的肠癌病理图片分类

HOG-GLRLM features for classification of colon cancer histopathological images

针对利用单一特征集对肠癌病理图像的识别率难以提高这一情况,提出了一个基于HOG-GLRLM特征肠癌病理图片分类方法。考虑到图像中丰富的纹理和边缘信息,分别利用改进型的灰度行程矩阵和梯度方向直方图提取特征。并采用最小冗余最大关联的方法对各自和合并特征集进行特征选择。实验结果表明该方法的有效性。

The recognition rate of colon cancer histopathological images using single feature set is difficult to improve. In this paper, a colon biopsy image classification system based on HOG-GLRLM features is proposed. Considering the rich texture and edge information of the histopathological image, two feature types, namely gray level run length matrix and histogram of oriented gradients based features have been proposed. Moreover, the minimum Redundancy Maximum Relevance(mRMR)feature selection method has been employed to select meaningful features from individual and hybrid feature sets. The outcome of this experiment indicates that the algorithm achieves good results in classification accuracy