{"title":"Enhanced face age progression and regression model using hyper-parameter tuning-large scale GAN by hybrid heuristic improvement","authors":"Tejaswini Yadav, Rajneeshkaur Sachdeo","doi":"10.1080/13682199.2023.2254134","DOIUrl":null,"url":null,"abstract":"ABSTRACTThe main challenge is to automate the model for aged or de-aged face generation. However, there are certain limitations on accuracy for age estimation and identity preservation. To achieve this, a new face age progression and regression is proposed by Hyper-parameter Tuning-Large Scale Generative Adversarial Network (HT-Large Scale GAN) with Pollination Rate-based Sunflower Dolphin Swarm Optimization (PR-SDSO). The input images are collected and fed into the object detection model, where the viola Jones algorithm is utilized. Here, the pre-processing is done by median filtering and contrast enhancement. The face age progression and regression are accomplished by novel HT-Large Scale GAN, where the hyperparameters are optimized by a new algorithm of PR-SDSO. Throughout the result analysis, the proposed model ensures that it provides the appropriate synthesized images for both the progression and regression phases and acquires less error to improve the quality of the image.KEYWORDS: Face age progression and regressionobject detection modelviola-jones algorithmmedian filtering and contrast enhancementdeep learningdolphin swarm algorithmpollination rate-based sunflower dolphin swarm optimizationhyper-parameter tuning-large scale generative adversarial networks Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsTejaswini YadavTejaswini Yadav received master degree from Pune University. She is currently research scholar in MIT-ADT University and her research area includes machine learning and artificial intelligence.Rajneeshkaur SachdeoRajneeshkaur Sachdeo received Ph.D. degree from SGBAU State University, Amravati. She is currently Dean of Engineering and Head of Computer Science and Engineering at MIT-ADT University, Pune. Her research area includes Data Security and privacy, natural language processing and linguistics, machine learning, data mining, and Wireless network. She is a member of ISTE, IACSIT and CSI.","PeriodicalId":22456,"journal":{"name":"The Imaging Science Journal","volume":"84 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The Imaging Science Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/13682199.2023.2254134","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
ABSTRACTThe main challenge is to automate the model for aged or de-aged face generation. However, there are certain limitations on accuracy for age estimation and identity preservation. To achieve this, a new face age progression and regression is proposed by Hyper-parameter Tuning-Large Scale Generative Adversarial Network (HT-Large Scale GAN) with Pollination Rate-based Sunflower Dolphin Swarm Optimization (PR-SDSO). The input images are collected and fed into the object detection model, where the viola Jones algorithm is utilized. Here, the pre-processing is done by median filtering and contrast enhancement. The face age progression and regression are accomplished by novel HT-Large Scale GAN, where the hyperparameters are optimized by a new algorithm of PR-SDSO. Throughout the result analysis, the proposed model ensures that it provides the appropriate synthesized images for both the progression and regression phases and acquires less error to improve the quality of the image.KEYWORDS: Face age progression and regressionobject detection modelviola-jones algorithmmedian filtering and contrast enhancementdeep learningdolphin swarm algorithmpollination rate-based sunflower dolphin swarm optimizationhyper-parameter tuning-large scale generative adversarial networks Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationNotes on contributorsTejaswini YadavTejaswini Yadav received master degree from Pune University. She is currently research scholar in MIT-ADT University and her research area includes machine learning and artificial intelligence.Rajneeshkaur SachdeoRajneeshkaur Sachdeo received Ph.D. degree from SGBAU State University, Amravati. She is currently Dean of Engineering and Head of Computer Science and Engineering at MIT-ADT University, Pune. Her research area includes Data Security and privacy, natural language processing and linguistics, machine learning, data mining, and Wireless network. She is a member of ISTE, IACSIT and CSI.