ISSN : 2319-7323

INTERNATIONAL JOURNAL OF COMPUTER SCIENCE ENGINEERING

ABSTRACT

Title	:	A Recognition Method of Medical Image Based on Feature Optimization
Authors	:	Pengpeng Jiao, Yizheng Guo, Huiming Xia, Xia Lu
Keywords	:	Medical Image Recognition; Feature Extraction; Local Linear Embedding; Support Vector Machine
Issue Date	:	Sep-Oct 2020
Abstract	:	Taking liver CT image as the research object, in order to improve the recognition rate of normal and abnormal images, a recognition method of medical image based on feature optimization is proposed in this paper. The basic idea is that: for the collected CT images, firstly, the color feature, texture feature and shape feature of each image are extracted and used to establish sample database; then the features are normalized between 0 and 1; next, the LLE (Locally Linear Embedding) method is used to reduce the dimension of feature data; finally, the SVM (Support Vector Machine) classifier is used to classify and recognize the test images. The experimental results show that the recognition rate is 86.5%. On the one hand, the recognition rate of multi-features with dimension reduction fusion is higher than that of single feature, at the same time, the LLE dimension reduction method shows strong robustness in manifold learning algorithm.
Page(s)	:	365-369
ISSN	:	2319-7323
Source	:	Vol. 9, No. 5