The 11th Iranian and the first International Conference on Machine Vision and Image Processing

High Dynamic Range Image Reconstruction Using Multi-Exposure Wavelet HDRCNN

Alireza Omrani, Mohammad Reza Soheili, Manoochehr Kelarestaghi
The 11th Iranian and the first International Conference on Machine Vision and Image Processing (MVIP 2020)

Abstract

Despite the advances in technology in the world of mobile and photography, the images taken from such devices do not resemble the scene in terms of brightness or details that users see in the scene cannot be seen in the images. Standard devices capture images with limit dynamic range, hence these images will have high-exposure and low-exposure areas. To tackle this problem, High Dynamic Range (HDR) imaging algorithms are used in which these algorithms pay more attention to the detail reconstruction however in this research, a method will be proposed that in addition to the reconstruction of the details, also it will be focused on image generation time. For this purpose, merging images and image Wavelet coefficients are used to reconstruct more details and make data reduction, respectively. Eventually, the proposed algorithm will be evaluated using PSNR and SSIM evaluation metrics which the results will be shown that the proposed method has appropriate results.

Keywords: Wavelet Transform, Deep Learning, Convolutional Neural Network, High Dynamic Range Imaging, Exposure Fusion



© 2017-2021 ISMVIP All Rights Reserved