A new algorithm of infrared image enhancement based on rough sets and curvelet transform

Infrared image enhancement is a research focus as well as one of the difficulties in the field of information processing. Rough sets theory is a new mathematical tool to solve the issue of ambiguity and uncertainty. Curvelet transform develops from wavelet transform and has noticeable effect in denoising and signal enhancing. Based on the features of infrared image and human visual properties and combined the rough sets theory and curvelet transform, this paper has put forward a new algorithm to enhance the weak infrared image. Based on human visual properties and noise conditional properties, this algorithm first partitions an infrared image into different sub-images in accordance with two properties: pixel gradient value and noise. Then enhance the sub-images via curvelet transforming. Experiments results have shown that this new algorithm can achieve good enhancing effect and can meet the actual needs of infrared image enhancement.