Diagnosis Support System for Mucous Membrane Diseases in Oral Cavity

Authors:
Keiichi Horio;Shuhei Matsumoto;Taishi Ohtani;Manabu Habu;Kazuhiro Tominaga;Takeshi Yamakawa
Affiliations:
Grad. Sch. of Life Science and Systems Engineering, Kyushu Inst. of Tech., Japan 808-0196;Grad. Sch. of Life Science and Systems Engineering, Kyushu Inst. of Tech., Japan 808-0196;Dept. of Oral and Maxillofacial Surgery, Kyushu Dental College, Japan 803-8580;Dept. of Oral and Maxillofacial Surgery, Kyushu Dental College, Japan 803-8580;Dept. of Oral and Maxillofacial Surgery, Kyushu Dental College, Japan 803-8580;Grad. Sch. of Life Science and Systems Engineering, Kyushu Inst. of Tech., Japan 808-0196
Venue:
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Year:
2009

Citing 4
Cited 0

A survey of thresholding techniques

Computer Vision, Graphics, and Image Processing
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, a diagnosis support system for mucous membrane diseases in oral cavity, in which a shape of vitiligo is judged as lacy or not-lacy from an intraoral image, is proposed. Intraoral images are not unstandardized, and lighting conditions or angles are variant. To extract vitiligo area from such images, we employ dynamic threshold method. SIFT and bag of keypoints are used in feature extraction, and classification is achieved by SVM. From the simulation, in which the shape of vitiligo is classified to lacy or not-lacy classes, the effectiveness of the proposed system was verified.