Supervised Image Segmentation for High Dynamic Range Imaging

TL;DR

This paper proposes a supervised neural network approach to segment the most visible areas in images for high dynamic range imaging, aiming to improve detail extraction from multi-exposure images.

Contribution

It introduces a neural network-based segmentation method for HDR imaging that focuses on selecting the most visible image regions, a novel approach compared to traditional exposure combination techniques.

Findings

Neural network successfully segments visible image parts.

Manual and Otsu threshold methods used for ground truth.

Segmentation improves HDR image quality.

Abstract

Regular cameras and cell phones are able to capture limited luminosity. Thus, in terms of quality, most of the produced images from such devices are not similar to the real world. They are overly dark or too bright, and the details are not perfectly visible. Various methods, which fall under the name of High Dynamic Range (HDR) Imaging, can be utilised to cope with this problem. Their objective is to produce an image with more details. However, unfortunately, most methods for generating an HDR image from Multi-Exposure images only concentrate on how to combine different exposures and do not have any focus on choosing the best details of each image. Therefore, it is strived in this research to extract the most visible areas of each image with the help of image segmentation. Two methods of producing the Ground Truth were considered, as manual threshold and Otsu threshold, and a neural network will be used to train segment these areas. Finally, it will be shown that the neural network is able to segment the visible parts of pictures acceptably.