{"title":"Hazy to hazy free: A comprehensive survey of multi-image, single-image, and CNN-based algorithms for dehazing","authors":"Jehoiada Jackson , Kwame Obour Agyekum , kwabena Sarpong , Chiagoziem Ukwuoma , Rutherford Patamia , Zhiguang Qin","doi":"10.1016/j.cosrev.2024.100669","DOIUrl":null,"url":null,"abstract":"<div><p>The natural and artificial dispersal of climatic particles transforms images obtained in open-air conditions. Due to visibility diminishing aerosols, unfavorable climate situations such as mist, fog, and haze cause color change and reduce the contrast of the obtained image. Images seem deformed and inadequate in contrast saturation, affecting computer vision techniques considerably. Haze removal aims to decrease uncertainty inside a hazy image and enhance the visual effects for post-processing applications. However, dehazing is highly challenging due to its mathematical obscurity. This paper reviews the primary algorithms for image dehazing proposed over the past decade. The paper presents the basis for hazy image degradation, followed by a novel classification of dehazing algorithms into enhancement-based, joint-based, and Image repair methods. All techniques are evaluated, and the respective subsections are presented according to their attributes. Next, we categorize and elaborate on the various quality assessment methods using structural similarity index measure(SSIM), haze result, PSNR, and degradation score to evaluate some unique algorithms. Ultimately, some concerns about drawbacks and future research scope in haze removal methods are examined.</p></div>","PeriodicalId":48633,"journal":{"name":"Computer Science Review","volume":null,"pages":null},"PeriodicalIF":13.3000,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Science Review","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1574013724000534","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
The natural and artificial dispersal of climatic particles transforms images obtained in open-air conditions. Due to visibility diminishing aerosols, unfavorable climate situations such as mist, fog, and haze cause color change and reduce the contrast of the obtained image. Images seem deformed and inadequate in contrast saturation, affecting computer vision techniques considerably. Haze removal aims to decrease uncertainty inside a hazy image and enhance the visual effects for post-processing applications. However, dehazing is highly challenging due to its mathematical obscurity. This paper reviews the primary algorithms for image dehazing proposed over the past decade. The paper presents the basis for hazy image degradation, followed by a novel classification of dehazing algorithms into enhancement-based, joint-based, and Image repair methods. All techniques are evaluated, and the respective subsections are presented according to their attributes. Next, we categorize and elaborate on the various quality assessment methods using structural similarity index measure(SSIM), haze result, PSNR, and degradation score to evaluate some unique algorithms. Ultimately, some concerns about drawbacks and future research scope in haze removal methods are examined.
期刊介绍:
Computer Science Review, a publication dedicated to research surveys and expository overviews of open problems in computer science, targets a broad audience within the field seeking comprehensive insights into the latest developments. The journal welcomes articles from various fields as long as their content impacts the advancement of computer science. In particular, articles that review the application of well-known Computer Science methods to other areas are in scope only if these articles advance the fundamental understanding of those methods.