Content-aware dark image enhancement using fast fourier transform

Image contrast enhancement is a typical problem in image processing and computer visualization. This problem increases for images taken under poor lighting conditions. So different enhancement technique is necessary to improve such images that are captured in extreme lighting conditions, such as very bright or dark environments. The enhancement task, however, is complicated by require of any general unifying theory of image enhancement. In this paper a content-aware algorithm is described that enhances dark images, sharpens edges and conserves the smoothness of flat regions. In this method the RGB colour image is firstly transformed to hue-saturation-value (HSV) colour space, then the algorithm is applied to enhance the image intensity (i.e. V component). To enhance the intensity value fast fourier transform is used on fixed size of cells (8×8) and then enhanced intensity values are normalized to overcome out of range problem.