Dark image enhancement by locally transformed histogram

Image enhancement processes an image to increase the visual information of that image. Image quality can be degraded for several reasons such as lack of operator expertise, quality of image capturing devices, etc. The process of enhancing images may produce different types of noises such as unnatural effects, over-enhancement, artifacts, etc. These drawbacks are more prominent in the dark images. Over the years, many image enhancement techniques have been proposed. However, there have been a few works specifically for dark image enhancement. Though the available methods enhance the dark images, they might not produce desired output for dark images. To overcome the above drawbacks, we propose a method for dark image enhancement. In this paper, we enhance the images by applying local transformation technique on input image histogram. We smooth the input image histogram to find out the location of peaks and valleys from the histogram. Several segments are identified using valley to valley distance. Then a transformation method is applied on each segment of image histogram. Finally, histogram specification is applied on the input image using this transformed histogram. This method improves the quality of the image with minimal unexpected artifacts. Experimental results show that our method outperforms other methods in majority cases.