Low light and over exposed Image Enhancement using Weight Matrix Technique
Premanand Pralhad Ghadekar, Rohit Kale, Nikhil Agrawal, Atharva Pophale, Saurabh Rudrawar · International Journal of Computer Applications · 2020
Due to the low exposure, the low light pictures aren't so conductive to human observation and computer vision algorithm.Though many image improvement techniques are planned to unravel this drawback, existing ways ultimately introduce under and over improvement of contrast.This paper recommends an image contrast algorithm to produce a certain improvement of contrast.Specifically, the weight matrix for image fusion using illumination estimation techniques is designed.Then algorithm tend to introduce camera response model to synthesize multi-exposure pictures.Next, algorithm tend to find the most effective exposure ratio so the artificial image is well-exposed within the regions wherever the first image under-exposed.Finally, the input image and the artificial image are fused according to the weight matrix to get the improvement result.Experiments show that this methodology gets results with less contrast and lightness distortion compared to that of many state-of-the-art methods.The proposed algorithm also preserves the information content by reducing the overexposure and gives the best results in terms of processing time.