Edmore Chikohora, B. M. Esiefarienrhe, T. Chikohora
{"title":"Analysis and Performance Evaluation of Parameterization Algorithms in Remote Sensing Image Processing","authors":"Edmore Chikohora, B. M. Esiefarienrhe, T. Chikohora","doi":"10.1109/OI.2018.8535671","DOIUrl":null,"url":null,"abstract":"The study reviews currently used Feature Extraction Techniques (FET) and analyze their parameterization strategies as discussed by different authors, thereby setting the ground to do a performance evaluation of the GenApp, a novel adaptive algorithm for parameterization of FET that was introduced in our previous publication. We performed efficiency analysis, worst-case analysis and fitness value tests to the feature extraction algorithms to evaluate their strengths in a comparative manner. The results obtained from the experiments reflect a marginally higher complexity value on the execution of the GenApp, a reduced number of generations in finding an optimum parameter value and a relatively constant fitness value which gives us confidence in the algorithm's potential to improve parameterization and output images from FET.","PeriodicalId":331140,"journal":{"name":"2018 Open Innovations Conference (OI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 Open Innovations Conference (OI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/OI.2018.8535671","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
The study reviews currently used Feature Extraction Techniques (FET) and analyze their parameterization strategies as discussed by different authors, thereby setting the ground to do a performance evaluation of the GenApp, a novel adaptive algorithm for parameterization of FET that was introduced in our previous publication. We performed efficiency analysis, worst-case analysis and fitness value tests to the feature extraction algorithms to evaluate their strengths in a comparative manner. The results obtained from the experiments reflect a marginally higher complexity value on the execution of the GenApp, a reduced number of generations in finding an optimum parameter value and a relatively constant fitness value which gives us confidence in the algorithm's potential to improve parameterization and output images from FET.