基于反身性、反对称性和及物性的性别启发面部年龄识别

遥感信息 Pub Date : 2019-12-20 DOI:10.1109/ICMRSISIIT46373.2020.9405924

Ebenezer Nii Ayi Hammond, Kwadwo Kusi

{"title":"基于反身性、反对称性和及物性的性别启发面部年龄识别","authors":"Ebenezer Nii Ayi Hammond, Kwadwo Kusi","doi":"10.1109/ICMRSISIIT46373.2020.9405924","DOIUrl":null,"url":null,"abstract":"We propose an age recognition method that compares a pair of image instances from the same gender for the three conditions of reflexivity, antisymmetry, and transitivity corresponding to older, similar, and younger than respectively. The approach uses a small number of reference set to address performance issues due to the lack of datasets for age recognition. Experimental results demonstrate that the use of a few optimally selected class references for the comparison resulted in a dramatic improvement on the baseline. Thus, with a Mean Absolute Error (MAE) of 4.07 and Cumulative score (CS) of 93.87% on the adience dataset, our proposal shows superiority among other gender-inspired age recognition proposals.","PeriodicalId":64877,"journal":{"name":"遥感信息","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Gender-inspired Facial Age Recognition based on Reflexivity, Antisymmetry and Transitivity\",\"authors\":\"Ebenezer Nii Ayi Hammond, Kwadwo Kusi\",\"doi\":\"10.1109/ICMRSISIIT46373.2020.9405924\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose an age recognition method that compares a pair of image instances from the same gender for the three conditions of reflexivity, antisymmetry, and transitivity corresponding to older, similar, and younger than respectively. The approach uses a small number of reference set to address performance issues due to the lack of datasets for age recognition. Experimental results demonstrate that the use of a few optimally selected class references for the comparison resulted in a dramatic improvement on the baseline. Thus, with a Mean Absolute Error (MAE) of 4.07 and Cumulative score (CS) of 93.87% on the adience dataset, our proposal shows superiority among other gender-inspired age recognition proposals.\",\"PeriodicalId\":64877,\"journal\":{\"name\":\"遥感信息\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-12-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"遥感信息\",\"FirstCategoryId\":\"1087\",\"ListUrlMain\":\"https://doi.org/10.1109/ICMRSISIIT46373.2020.9405924\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"遥感信息","FirstCategoryId":"1087","ListUrlMain":"https://doi.org/10.1109/ICMRSISIIT46373.2020.9405924","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

我们提出了一种年龄识别方法，该方法对来自同一性别的一对图像实例进行了反身性、反对称性和及物性三个条件的比较，分别对应于年长、相似和年轻。该方法使用少量的参考集来解决由于缺乏年龄识别数据集而导致的性能问题。实验结果表明，使用几个最佳选择的类参考进行比较导致了基线上的显着改善。因此，我们的建议在观众数据集上的平均绝对误差(MAE)为4.07，累积分数(CS)为93.87%，在其他基于性别的年龄识别建议中表现出优势。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Gender-inspired Facial Age Recognition based on Reflexivity, Antisymmetry and Transitivity

We propose an age recognition method that compares a pair of image instances from the same gender for the three conditions of reflexivity, antisymmetry, and transitivity corresponding to older, similar, and younger than respectively. The approach uses a small number of reference set to address performance issues due to the lack of datasets for age recognition. Experimental results demonstrate that the use of a few optimally selected class references for the comparison resulted in a dramatic improvement on the baseline. Thus, with a Mean Absolute Error (MAE) of 4.07 and Cumulative score (CS) of 93.87% on the adience dataset, our proposal shows superiority among other gender-inspired age recognition proposals.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

遥感信息

自引率

0.00%

发文量

3984

期刊介绍： Remote Sensing Information is a bimonthly academic journal supervised by the Ministry of Natural Resources of the People's Republic of China and sponsored by China Academy of Surveying and Mapping Science. Since its inception in 1986, it has been one of the authoritative journals in the field of remote sensing in China.In 2014, it was recognised as one of the first batch of national academic journals, and was awarded the honours of Core Journals of China Science Citation Database, Chinese Core Journals, and Core Journals of Science and Technology of China. The journal won the Excellence Award (First Prize) of the National Excellent Surveying, Mapping and Geographic Information Journal Award in 2011 and 2017 respectively. Remote Sensing Information is dedicated to reporting the cutting-edge theoretical and applied results of remote sensing science and technology, promoting academic exchanges at home and abroad, and promoting the application of remote sensing science and technology and industrial development. The journal adheres to the principles of openness, fairness and professionalism, abides by the anonymous review system of peer experts, and has good social credibility. The main columns include Review, Theoretical Research, Innovative Applications, Special Reports, International News, Famous Experts' Forum, Geographic National Condition Monitoring, etc., covering various fields such as surveying and mapping, forestry, agriculture, geology, meteorology, ocean, environment, national defence and so on. Remote Sensing Information aims to provide a high-level academic exchange platform for experts and scholars in the field of remote sensing at home and abroad, to enhance academic influence, and to play a role in promoting and supporting the protection of natural resources, green technology innovation, and the construction of ecological civilisation.