A comparative study of machine learning models for ethnicity classification

14th International Conference on Science, Engineering and Technology

自然科学;工业技术

Trivedi, Advait^1 ; Geraldine Bessie Amali, D.^2

North Carolina State University, Raleigh

NC

27695, United States^1

School of Computer Science and Engineering, VIT University, Vellore

632014, India^2

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

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/263/4/042091/pdf
DOI  :  10.1088/1757-899X/263/4/042091

来源: IOP

【 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.