Infrared image enhancement based on contourlet transform and chaotic particle swarm optimization

Abstract

The parameters for subband enhancement in the existing multi-scale image enhancement methods need to be determined according to specific images. To improve their adaptability and universality, an infrared image enhancement method based on contourlet transform and chaotic particle swarm optimization (PSO) is proposed. The low frequency subband after contourlet transform is adaptively enhanced by a method based on local mean and standard deviation, which improves the overall contrast of image. The high frequency subbands are enhanced by a general nonlinear gain function, which improve the local contrast of weak details. The chaotic particle swarm optimization is used to search the optimal parameters during the above-mentioned low and high frequency subband enhancement. Experiments with qualitative and quantitative evaluation are carried out for a large number of images, and the proposed method is compared with histogram double equalization method, second-generation wavelet transform method, stationary wavelet transform method and curvelet transform method. Experimental results show that the proposed method can enhance image details and suppress noise better, and the whole visual effect is improved significantly.