Title :
Spotted tongue recognition via cascade filtering
Author :
Xiaoqiang Li ; Caixia Sha ; Huang Zhang ; Zhicheng Fu
Author_Institution :
Sch. of Comput. Eng. & Sci., Shanghai Univ., Shanghai, China
Abstract :
This paper introduces a method for spotted tongue recognition via cascade filtering. The original image is preprocessed and filtered through four characteristics of spot, respectively in position, color, gray and shape. Then, every spotted region is marked with circle using above filter and is used to judge whether a tongue is spotted according to the number of detected spot regions. Experimental results in datasets collected by tongue acquisition system demonstrated that this method has a good performance in identifying both spotted tongue and non-spotted tongue.
Keywords :
biomedical optical imaging; cascade systems; filtering theory; image recognition; medical image processing; cascade filtering; nonspotted tongue; original image; spot characteristics; spot color; spot gray; spot position; spot shape; spotted region; spotted tongue recognition; tongue acquisition system; Convolution; Educational institutions; Image color analysis; Medical diagnostic imaging; Shape; Tongue; filtering; pattern recognition; spotted tongue;
Conference_Titel :
Biomedical Engineering and Informatics (BMEI), 2013 6th International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-4799-2760-9
DOI :
10.1109/BMEI.2013.6746927