Semi‐supervised learning dehazing algorithm based on the OSV model. Issue 3 (24th November 2022)

• Record Type: Journal Article
• Authors: Zhu, Lijun; Wei, Weibo; Pan, Zhenkuan; Ji, Lianshun; Song, Jintao; Li, Jinhan
• Is Part Of: IET image processing. Volume 17:Issue 3(2023)
• Page Start: 872
• Page End: 885
• Publication Date: 2022-11-24
• Subjects: generative adversarial network -- semi‐supervised learning -- single image dehazing -- the OSV model; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/ipr2.12679
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract: Despite the great progress that has been made in the task of single image dehazing, the results of the existing models in restoring image edge and texture information are still challenging. Besides, most dehazing models are trained on synthetic data, resulting in poor generalization ability to real‐world images. To address the aforementioned problems, a semi‐supervised learning dehazing method based on the decomposition model of Osher, Solé, and Vese(The OSV model) is presented. Specifically, the OSV model is first applied to decompose the hazy image into the structure layer and texture layer, save the texture layer and dehaze for the structure layer to restore images with sharper texture and edge. Furthermore, the network adopts a semi‐supervised learning algorithm based on generative adversarial networks (GAN) to generalize better to real‐world images, which includes two branches: supervised learning and unsupervised learning. Extensive experiments indicate that the proposed method preserves the texture and edge information of images more accurately while dehazing better, and performs favourably against the advanced dehazing algorithms on both synthetic outdoor datasets and real‐world hazy images. Abstract : We propose a semi‐supervised learning dehazing method based on the OSV model, which novelly combines the decomposition model by the variational method with deep convolutional neural networks (CNNs) for dehazing. Adopting the decomposition model can restore images with clearer texture and edge details and semi‐supervised learning can improve the generalization ability of our algorithm.