Face and hand gesture recognition algorithm based on wavelet transforms and principal component analysis

2012 ◽  
Author(s):  
T. T. T. Bui ◽  
N. H. Phan ◽  
V. G. Spitsyn
Keyword(s):  
Principal Component Analysis ◽  
Gesture Recognition ◽  
Wavelet Transforms ◽  
Principal Component ◽  
Component Analysis ◽  
Recognition Algorithm ◽  
Hand Gesture Recognition ◽  
Hand Gesture

Fusion of Image Contour Moments and Fourier Descriptors for the Hand Gesture Recognition

2012 ◽  
Vol 433-440 ◽  
pp. 5188-5192
Author(s):  
Hai Long Lei ◽  
Sheng Yang
Keyword(s):  
Gesture Recognition ◽  
Recognition Rate ◽  
Recognition Algorithm ◽  
Hand Gesture Recognition ◽  
Hand Gesture ◽  
Fourier Descriptor ◽  
Bp Network ◽  
Moment Invariant ◽  
Hand Shape ◽  
Image Contour

Hand is a highly variable organ and hand features are easily affected by environmental factors. Considering the characteristics of hand gesture, a novel hand gesture recognition algorithm based on hybrid moments is presented. First, According to the color cue, the hand shape is available to extract from the complicated background, then the contour moment invariant and Fourier Descriptor are extracted and fused into a hybrid feature, finally the hybrid feature are put into the BP network to identity. The experimental results show that the method has better robustness and higher recognition rate.

Hand Gesture Recognition Algorithm: A Real-Time Human-Body-Based Approach

2013 ◽  
Vol 303-306 ◽  
pp. 1338-1343
Author(s):  
Xin Xiong Li ◽  
Yi Xiong ◽  
Zhi Yong Pang ◽  
Di Hu Chen
Keyword(s):  
Real Time ◽  
Gesture Recognition ◽  
Human Body ◽  
Skin Color ◽  
Average Rate ◽  
Vital Role ◽  
Recognition Algorithm ◽  
Hand Gesture Recognition ◽  
High Tech ◽  
Hand Gesture

Despite the appearance of high-tech human computer interface (HCI) devices, pattern recognition and gesture recognition with single camera are still playing vital role in research. A real-time human-body based algorithm for hand gesture recognition is proposed in this paper. The basis of our approach is a combination of moving object segmentation process and skin color detector based on human body structure to obtain the moving hands from input images, which is able to deal with the problem of complex background and random noises, and a rotate correction process for better finger detection. With ten fingers detected, more than 1000 gestures can be recognized before concerning motion paths. This paper includes experimental results of five gestures, which can be extended to other conditions. Experiments show that the algorithm can achieve a 99 percent recognition average rate and is suitable for real-time applications.

Sign in / Sign up

Export Citation Format

Share Document