DocumentCode :
3588385
Title :
Performance analysis of skin classifiers in RGB and YCbCr color space
Author :
Qureshi, Anam ; Marvi, Murk ; Unar, Mukhtiar Ali ; Umrani, Fahim Aziz
Author_Institution :
Inst. of Inf. & Commun. Technol. (IICT), Mehran Univ. of Eng. & Technol., Pakistan
fYear :
2014
Firstpage :
223
Lastpage :
228
Abstract :
Skin detection serves as a preliminary step for number of applications like face detection, gesture recognition, internet pornographic image filtering, and surveillance system. Number of artificial neural network (ANN) based skin detection algorithms have been presented in literature which are mostly based on back propagation (BP) ANNs. This paper attempts to analyze the performance of skin classifiers using AdaBoost learning algorithm in both RGB and YCbCr color space. Three RGB based classifiers (i.e., red, green, and blue) and one YCbCr based classifier is designed in order to analyze the performance of algorithm for each case. Set of weak heuristic rules are designed for the classifiers to reduce the false positive rate (FPR) without significantly affecting the correct detection rate (CDR). The results reveal that the best performance is achieved by RGB based classifiers with heuristic rules in terms of both accuracy and processing time. Without heuristic rules the best results have been provided by Y-classifier. The classifiers are trained and tested using SFA database. The classifiers are also tested by using images of FERET and CVL database.
Keywords :
image classification; image colour analysis; learning (artificial intelligence); skin; AdaBoost learning algorithm; CVL database; FERET database; RGB based classifier; RGB color space; SFA database; YCbCr based classifier; YCbCr color space; correct detection rate; false positive rate; skin classifiers; weak heuristic rules; Algorithm design and analysis; Artificial neural networks; Classification algorithms; Databases; Image color analysis; Skin; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multi-Topic Conference (INMIC), 2014 IEEE 17th International
Print_ISBN :
978-1-4799-5754-5
Type :
conf
DOI :
10.1109/INMIC.2014.7097341
Filename :
7097341
Link To Document :
بازگشت