{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/understanding-how-image-quality-affects-deep","title":"Understanding How Image Quality Affects Deep Neural Networks","arxiv_id":"1604.04004","date":"2016-04-14","proceeding":null,"authors":["Samuel Dodge","Lina Karam"],"abstract":"Image quality is an important practical challenge that is often overlooked in\nthe design of machine vision systems. Commonly, machine vision systems are\ntrained and tested on high quality image datasets, yet in practical\napplications the input images can not be assumed to be of high quality.\nRecently, deep neural networks have obtained state-of-the-art performance on\nmany machine vision tasks. In this paper we provide an evaluation of 4\nstate-of-the-art deep neural network models for image classification under\nquality distortions. We consider five types of quality distortions: blur,\nnoise, contrast, JPEG, and JPEG2000 compression. We show that the existing\nnetworks are susceptible to these quality distortions, particularly to blur and\nnoise. These results enable future work in developing deep neural networks that\nare more invariant to quality distortions.","url_abs":"http://arxiv.org/abs/1604.04004v2","url_pdf":"http://arxiv.org/pdf/1604.04004v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"understanding-how-image-quality-affects-deep","repo_url":"https://github.com/PurvaChiniya/Effects-of-image-quality-on-deep-nueral-network-paper-code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"understanding-how-image-quality-affects-deep","repo_url":"https://github.com/ibabbar/Traffic-Sign-Classifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"understanding-how-image-quality-affects-deep","repo_url":"https://github.com/kadirnar/combat-drone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"understanding-how-image-quality-affects-deep","repo_url":"https://github.com/premthomas/keras-image-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.04004","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}