26 October 2013 Design of a hand-shape acquisition and recognition system based on DSP
Author Affiliations +
Proceedings Volume 8921, MIPPR 2013: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 89211D (2013) https://doi.org/10.1117/12.2031374
Event: Eighth International Symposium on Multispectral Image Processing and Pattern Recognition, 2013, Wuhan, China
Abstract
In this paper, we design a hand-shape image acquisition and processing system based on DSP for solving the problem of hand-shape recognition. Acquisition configuration was designed, and the key parts (encoder, decoder, memory chip etc.) are selected. And a new method for hand-shape recognition based on wavelet moment is presented to overcome some shortage in present method for hand shape recognition. Firstly, image processing including binary processing and segment of hand silhouette are used, and then translation and scale normalization algorithms is implemented on the palms and fingers image. After that the wavelet moment characteristics of image are extracted. At last, support vector is achieved by training 100 images data in images database, 10 testing images were selected randomly to verify validity and feasibility of algorithms. Experimental results indicate that the 10 testing images are all classified correctly. The new method of extracting hand shape wavelet moment as characteristic matrix is easy to realize with characteristic of high utility and accuracy, and solve the problem of translation, rotation and scaling during the image acquisition process without positioning aids.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wenwen Li, Fu Liu, Lei Gao, "Design of a hand-shape acquisition and recognition system based on DSP", Proc. SPIE 8921, MIPPR 2013: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 89211D (26 October 2013); doi: 10.1117/12.2031374; https://doi.org/10.1117/12.2031374
PROCEEDINGS
5 PAGES


SHARE
Back to Top