A comparative study of machine learning models for ethnicity classification

[摘要] This paper endeavours to adopt a machine learning approach to solve the problem of ethnicity recognition. Ethnicity identification is an important vision problem with its use cases being extended to various domains. Despite the multitude of complexity involved, ethnicity identification comes naturally to humans. This meta information can be leveraged to make several decisions, be it in target marketing or security. With the recent development of intelligent systems a sub module to efficiently capture ethnicity would be useful in several use cases. Several attempts to identify an ideal learning model to represent a multi-ethnic dataset have been recorded. A comparative study of classifiers such as support vector machines, logistic regression has been documented. Experimental results indicate that the logical classifier provides a much accurate classification than the support vector machine.

[发布机构] North Carolina State University, Raleigh; NC; 27695, United States^1;School of Computer Science and Engineering, VIT University, Vellore; 632014, India^2

[效力级别] 工业技术

[关键词] Comparative studies;Learning models;Logistic regressions;Machine learning approaches;Machine learning models;Meta information;Target marketing;Vision problems