DocumentCode :
3223198
Title :
Hand gesture recognition based on improved histograms of oriented gradients
Author :
Lan Tiantian ; Shen Jinyuan ; Liu Runjie ; Guo Yingying
Author_Institution :
Sch. of Inf. Eng., Zhengzhou Univ., Zhengzhou, China
fYear :
2015
fDate :
23-25 May 2015
Firstpage :
4211
Lastpage :
4215
Abstract :
To reduce the influence of edge information in background, an improved feature extraction method for hand gestures in which the histograms of oriented gradients is combined with the skin similarity is proposed. Weight computed on the skin similarity is introduced into the gradient of each image pixel. This new gradients can enhance the hand features. Histograms of oriented gradients with different size of cells are employed to classify the hand gestures because different sizes of cells depict different local features. The experiment results indicate that the size of the cell affects the recognition rate greatly and the combination of histograms of oriented gradients with two appropriate different cells can represent the hand gesture features well. Images with different time, illumination and background collected by real environment and images in Marcel database are recognized by the improved method and the results show that the proposed method can improve the hand gesture recognition.
Keywords :
edge detection; feature extraction; gesture recognition; image classification; image colour analysis; skin; Marcel database; edge information; feature extraction; hand gesture features; hand gesture recognition; hand gestures classification; histograms of oriented gradients; illumination; image pixel; local features; recognition rate; skin similarity; Colored noise; Feature extraction; Gesture recognition; Histograms; Image color analysis; Image recognition; Skin; Cascade classifier; Hand gesture location; Hand gesture recognition; Histograms of oriented gradients; Skin similarity;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control and Decision Conference (CCDC), 2015 27th Chinese
Conference_Location :
Qingdao
Print_ISBN :
978-1-4799-7016-2
Type :
conf
DOI :
10.1109/CCDC.2015.7162670
Filename :
7162670
Link To Document :
بازگشت