Image Contrast Enhancement using Block based CNN Learner

EasyChair Preprint 3644

Abstract

Image enhancement is one of the difficult problems of image processing. The purpose of image enhancement is to process an image so that the result is more suitable for a particular application than the original image. Digital image enhancement techniques offer various ways to improve the visual quality of images. The appropriate selection of these techniques is very important. Producing the natural scene with good contrast, vivid color and rich details is an essential goal of digital photography. The acquired images, however, are often low contrast because of poor lighting conditions and the limited dynamic range of imaging device. Contrast enhancement is thus an important step to improve the quality of recorded images and make the image details more visible. In this paper, a block-based methodology is proposed for contrast enhancement of low contrast indoor and outdoor images with reference images. The low contrast images are adjusted with CNN Adaptive Bilateral Enhancer with reference image blocks.

Keyphrases: Convolution Neural Network, Digital Image Processing, Quality Measure., bilateral filter, image enhancement

@booklet{EasyChair:3644,
  author    = {Pooja Patel and Arpana Bhandari},
  title     = {Image Contrast Enhancement using Block based CNN Learner},
  howpublished = {EasyChair Preprint 3644},
  year      = {EasyChair, 2020}}