Image contrast enhancement by contourlet transform and PCNN

We put forward a contourlet transform and PCNN based image enhancement algorithm in this paper. This method overcomes the traditional wavelet transform´s deficiencies in sparse representing inseparable semantic details of images, such as multidirectional edges. Firstly the images are decomposed into multi-directional and multi-scale contour segments by the contourlet transform, the directions of the line-shaped discontinuity in the images are detected. Secondly, a new physiological enhancement function based on the pulse coupled neural networks (PCNN) is proposed to enhance the coefficients by contourlet transform. At last, we reconstruct the enhanced coefficients and obtain the enhanced results of the original images, in order to verify the effectiveness of this method, we compare it to conventional contrast enhancement methods, such as the histogram equalization. The results show that our contrast enhancement method is better than other in enhancing the directional line-shaped objects.