Certain Improvements in Hybrid Feature Extraction Methods for Medical Image Classification

Author:

Abstract: Content Based Image Retrieval is a technique which uses visual contents for searching images from large scale image databases Information extracted from images such as color, texture and shape are known as feature vectors. Using multiple feature vectors to describe an image during retrieval process increases the accuracy when compared to the retrieval using single feature vector. The objective of this paper is to analyze the performance of coif let wavelet and Moment Invariant (MI) feature extraction methods and to evaluate the classification accuracy using Support Vector Machines (SVM) with Radial Basis Function kernel (RBF). Experiments were conducted on CT scan images of head, lung and stomach and the performance is investigated.

WSEAS Transactions on Computer Research, ISSN / E-ISSN: 1991-8755 / 2415-1521, Volume 5, 2017, Art. #10

PDF
XML
Cite
×
Citation Tools
WSEAS AMA
N. T. Renukadevi, "Certain Improvements in Hybrid Feature Extraction Methods for Medical Image Classification," WSEAS Transactions on Computer Research, vol. 5, pp. 85-91, 2017, DOI:
N. T. Renukadevi. Certain Improvements in Hybrid Feature Extraction Methods for Medical Image Classification. WSEAS Transactions on Computer Research. 2017;5:85-91.
Copy to Clipboard
Citation copied to Clipboard

Certification

---