Computer vision feature recognition method based on Improved Wavelet arithmetic

DOI

10.2991/amcce-15.2015.312How to use a DOI?

Keywords

feature extraction; wavelet moment invariants; binary wavelet

Abstract

in the process of studying on computer vision feature recognition method, with the current algorithm for feature recognition, the amount of calculation is large, and noise is strong, recognition rate is low. For this, a computer vision feature recognition method based on Improved Wavelet arithmetic is put forward. Firstly, spline binary wavelet decomposition is fused in the method to extract edge feature from collected images, and then wavelet moment invariants of the processed image is calculated and acted as the characteristic quantity of computer vision, so as to complete the accurate identification of the characteristics of computer vision. Characteristic quantity extracted through this method can not only solve the problem of uneven illumination, illumination variation and noise interference, also translation, rotation and zoom. Simulation results show that accuracy of computer vision feature recognition based on improved wavelet algorithm is great, and effect is ideal.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lili Liu
PY  - 2015/04
DA  - 2015/04
TI  - Computer vision feature recognition method based on Improved Wavelet arithmetic
BT  - Proceedings of the 2015 International Conference on Automation, Mechanical Control and Computational Engineering
PB  - Atlantis Press
SN  - 1951-6851
UR  - https://doi.org/10.2991/amcce-15.2015.312
DO  - 10.2991/amcce-15.2015.312
ID  - Liu2015/04
ER  -