Global Journal of Computer Science and Technology, D: Neural & Artificial Intelligence, Volume 22 Issue 1

Global Journal of Computer Science and Technology: D Neural & Artificial Intelligence Volume 22 Issue 1 Version 1.0 Year 2022 Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals Online ISSN: 0975-4172 & Print ISSN: 0975-4350 Strictly as per the compliance and regulations of: © 2022. Dilip Chaudhary & Venkatesh. This research/review article is distributed under the terms of the Attribution- NonCommercial-NoDerivatives 4.0 International (CC BYNCND 4.0). You must give appropriate credit to authors and reference this article if parts of the article are reproduced in any manner. Applicable licensing terms are at https://creativecommons.org/ licenses/by-nc-nd/4.0/. Deep CNN Model for Non-Screen Content and Screen Content Image Quality Assessment By Dilip Chaudhary & Venkatesh University Visvesvaraya College of Engineering Abstract- In the current world, user experience in various platforms matters a lot for different organizations. But providing a better experience can be challenging if the multimedia content on online platforms is having different kinds of distortions which impact the overall experience of the user. There can be various reasons behind distortions such as compression or minimal lighting condition while taking photos. In this work, a deep CNN-based Non-Screen Content and Screen Content NR-IQA framework is proposed which solves this issue in a more effective way. The framework is known as DNSSCIQ. Two different architectures are proposed based upon the input image type whether the input is a screen content or non-screen content image. This work attempts to solve this by evaluating the quality of such images. Index Terms: deep learning, convolutional neural network (CNN), screen content image (SCI), image quality assessment (IQA), no-reference IQA (NR-IQA). GJCST-D Classification: F.1.1 DeepCNNModelforNonScreenContentandScreenContentImageQualityAssessment