CAJ | 학술논문

图像特征提取是图像处理的一个主要环节，是图像处理技术研究和应用的一个重要领域。本文选取了新疆地方性肝包虫病中的单囊型肝包虫和正常肝脏CT图像进行研究，提取了灰度直方图、灰度共生矩阵（GLCM）、kc复杂性三种特征组成综合图像特征。首先对图像进行尺寸归一、去噪、对比度增强的预处理，并对综合特征进行统计学分析，最后应用Fisher判别分析法对特征的分类能力进行评价。实验结果表明运用综合特征对图像分类有较高的准确率，这对基于内容的新疆肝包虫病CT图像的检索的研究奠定了一定的基础。
도상특정제취시도상처리적일개주요배절，시도상처리기술연구화응용적일개중요영역。본문선취료신강지방성간포충병중적단낭형간포충화정상간장CT도상진행연구，제취료회도직방도、회도공생구진（GLCM）、kc복잡성삼충특정조성종합도상특정。수선대도상진행척촌귀일、거조、대비도증강적예처리，병대종합특정진행통계학분석，최후응용Fisher판별분석법대특정적분류능력진행평개。실험결과표명운용종합특정대도상분류유교고적준학솔，저대기우내용적신강간포충병CT도상적검색적연구전정료일정적기출。
Image feature extraction is an important part of image processing, is an important field of research and application of image processing technology. This paper selects the unicystic hepatic hydatid and healthty liver CT images of Xinjiang local liver hydatid.Histogram, GLCM, KC complex three features of CT in Xinjiang local liver hydatid were extracted and treated this three features as a comprehensive feature. The CT images are normalizing scale by uniform quantization, the noise is removed by using a median filter, the contrast is enhanced by limited adaptive histogram equalization, The features of the image are obtained by using statistical analysis,and then the classification ability of features is evaluated by Fisher discriminant analysis. Experimental results show that high accuracy for image classification is existed by using comprehensive features. This has laid certain foundation for the study of content based image retrieval of Xinjiang Local Liver Hydatid CT images.