APSO based Gabor wavelet feature extraction method

A Gabor wavelet based method is used for tracking a target such as plane and vehicle. Optimizing Gabor wavelet´s parameters of translation, orientation, and scale to make it approximates a local image contour region. The method of Sobel edge detection is used to get the initial position and orientation value of optimization in order to reduce iterative times. Applying improved optimizing technique, APSO (adapting particle swarm optimization) algorithm is adopted to automatic target recognizing system. Comparing with the LM and PSO algorithm, the good impact is gained when it is applied to target recognition. It can ensure reliable convergence of the target, and it can also improve convergent speed. Tested in low contrast image, the feasibility and effectiveness of the algorithm are demonstrated by VC++ simulation platform in experiments.