研究者情報 | 神奈川大学

チョウ　ゼンシュン Zhang Shanjun 張　善俊所属神奈川大学情報学部計算機科学科神奈川大学大学院理学研究科理学専攻（情報科学領域）職種教授
言語種別	英語
発行・発表の年月	2020/11
形態種別	学術雑誌
査読	査読あり
標題	Single Image Defogging Algorithm Based on Conditional Generative Adversarial Network
執筆形態	共著
掲載誌名	Hindawi: Mathematical Problems in Engineering
掲載区分	国外
出版社・発行元	Hindawi
巻・号・頁	2020(11),pp.1-8
著者・共著者	Rui-Qiang Ma, Xing-Run Shen, and Shan-Jun Zhang
概要	We use generative adversarial network (GAN) for training and embed target map (TM) in the anti-network generator, only the part of bright area layer of image, in local attention model image training and testing in deep learning, and the effective processing of the wrong removal part is achieved, thus better restoring the defog image. Then, the DCP method obtains a good defog visual effect, and the evaluation index peak signal-to-noise ratio (PSNR) is used to make a judgment; the simulation result is consistent with the visual effect. We proved the DbGAN is a practical import of target map in the GAN.
DOI	https://doi.org/10.1155/2020/7938060