计算机与数字工程2019，Vol.47Issue(6)：1497-1501,5.DOI:10.3969/j.issn.1672-9722.2019.06.043
乳腺肿瘤图像的融合纹理特征提取方法
Extraction of Fusion Feature from Breast Cancer Images
摘要
Abstract
In order to accurately identify breast tumor image features,an improved textural feature extraction algorithm based on improved gray level co-occurrence matrix(GLCM)and Tamura is proposed. First,the images are preprocessed by eliminating im?age noise and enhancing image contrast. Then,the traditional gray level co-occurrence matrix is improved,and redundant informa?tion is reduced,improving the recognition rate of the image and the running speed of the program. Finally,The symbiotic matrix is combined with Tamura to obtain the image texture features,and the extracted features are identified. The experimental results show that the recognition rate of fusion features can reach 96.67% with 14.6s average calculation rate,which has high recognition accura?cy and omputational efficiency.关键词
纹理特征/灰度共生矩阵/Tamura纹理/图像分类Key words
textural feature/gray level co-occurrence matrix/Tamura texture/image classification分类
信息技术与安全科学引用本文复制引用
汪友明,张菡玫..乳腺肿瘤图像的融合纹理特征提取方法[J].计算机与数字工程,2019,47(6):1497-1501,5.基金项目
"十三五"国防预研项目"高性能图形支撑技术"(编号:31511070401)资助. （编号:31511070401）
