DocumentCode :
3336416
Title :
Skin detection: A random forest approach
Author :
Khan, Rehanullah ; Hanbury, Allan ; Stoettinger, Julian
Author_Institution :
Tech. Univ. Wien, Vienna, Austria
fYear :
2010
fDate :
26-29 Sept. 2010
Firstpage :
4613
Lastpage :
4616
Abstract :
Skin detection is used in applications ranging from face detection, tracking body parts and hand gesture analysis, to retrieval and blocking objectionable content. For robust skin segmentation and detection, we investigate color classification based on random forest. A random forest is a statistical framework with a very high generalization accuracy and quick training times. The random forest approach is used with the IHLS color space for raw pixel based skin detection. We evaluate random forest based skin detection and compare it to Bayesian network, Multilayer Perceptron, SVM, AdaBoost, Naive Bayes and RBF network. Results on a database of 8991 images with manually annotated pixel-level ground truth show that with the IHLS color space, the random forest approach outperforms other approaches. We also show the effect of increasing the number of trees grown for random forest. With fewer trees we get faster training times and with 10 trees we get the highest F-score.
Keywords :
face recognition; image colour analysis; image segmentation; statistical analysis; Bayesian network; color classification; face detection; hand gesture analysis; random forest approach; robust skin segmentation; skin detection; statistical framework; Accuracy; Bayesian methods; Image color analysis; Radial basis function networks; Skin; Support vector machines; Training;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location :
Hong Kong
ISSN :
1522-4880
Print_ISBN :
978-1-4244-7992-4
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2010.5651638
Filename :
5651638
Link To Document :
بازگشت