A Kernel-Modified SVM Based Computer-Aided Diagnosis System in Initial Caries

Author

Kuang, Wei ; Ye, Weiping

Author_Institution

Coll. of Inf. Sci. & Technol., Beijing Normal Univ., Beijing

Volume

3

fYear

2008

fDate

20-22 Dec. 2008

Firstpage

207

Lastpage

211

Abstract

Clinical initial caries appear as no obvious difference to normal ones in X-ray images. Researchers attempt to set up computer-aided system to facilitate clinical initial caries diagnosis. This paper mainly made two efforts, image enhancement using watershed and modification of SVM kernel function. Experiments show that the testing accuracy of the kernel-modified SVM caries detection is improved compared to the former research, and the image enhancement helps dentists to find caries easier.

Keywords

dentistry; diagnostic radiography; image enhancement; image segmentation; medical image processing; support vector machines; SVM kernel; X-ray image; clinical initial caries diagnosis; computer-aided diagnosis system; image enhancement; watershed method; Artificial neural networks; Computer aided diagnosis; Dentistry; Educational institutions; Histograms; Image enhancement; Image segmentation; Kernel; Support vector machines; Teeth; Caries detection; Kernel Modification; SVM; Watershed;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information Technology Application, 2008. IITA '08. Second International Symposium on

Conference_Location

Shanghai

Print_ISBN

978-0-7695-3497-8

Type

conf

DOI

10.1109/IITA.2008.206

Filename

4739988