Automatic Tongue Diagnosis Using a Smart Phone

Abstract

An automatic tongue diagnosis framework is proposed to analyzing tongue images taken by smart phones. Different from conventional tongue diagnosis systems, our input tongue images are usually in low resolution and taken under unknown lighting conditions. Consequently, existing tongue diagnosis methods cannot be directly applied to give accurate results. We propose a lighting condition estimation method based on the SVM classifier to predict the color correction matrix according to color difference of images taken with and without flashlight. We also modify the state of the art work of fur and fissure detection and successfully
improve the detection accuracy by taking hue information into consideration and adding a de-noising step.

Citation

Min-Chun Hu, Guang-Yu Zheng, and Kun-chan Lan "Automatic Tongue Diagnosis Using a Smart Phone"  2014 IEEE International Conference on Systems, Man, and Cybernetics, Available online: 5 June 2014.

Bitex

@ARTICLE{lan2014: ,
AUTHOR = {Kun-Chan Lan, Guang-Yu Zheng, Min-Chun Hu},
TITLE = {Automatic Tongue Diagnosis Using a Smart Phone},
BOOKTITLE = { 2014 IEEE International Conference on Systems, Man, and Cybernetics},
MONTH = {June},
YEAR = {2014}
}

Download

pdf Full Text (PDF Format)