基于LBP和GLCM的肠道肿瘤图像特征提取方法

Feature Extraction Method of Intestinal Tumor Images Based on LBP and GLCM

针对肠道肿瘤图像样本有限导致肿瘤识别率低和收敛速度慢的问题,提出一种基于局部二值模式(LBP)和灰度共生矩阵(GLCM)的肠道肿瘤图像特征提取方法.首先,利用最大类间方差法自动计算图像灰度阈值,进行感兴趣区域的提取;然后,采用LBP+GLCM对肠道肿瘤部分图像进行特征提取,并利用支持向量机识别.对1500张肠道肿瘤图像进行实验的结果表明,该方法可达到94.84%的识别准确率,能有效辅助医学诊疗.

Aiming at the problems of low tumor recognition rate and slow convergence speed caused by limited samples of intestinal tumor images,we proposed a feature extraction method of intestinal tumor images based on local binary pattern(LBP)and gray level co-occurrence matrix(GLCM).Firstly,the maximum interclass variance method was used to automatically calculate the image gray threshold and extract the region of interest.Secondly,the LBP+GLCM was used to extract the features of partial intestinal tumor image,and support vector machine was used for recognition.Experimental results of 1500 intestinal tumor images show that this method can achieve 94.84%recognition accuracy and can effectively assist medical diagnosis and treatment.