การเรียนรู้ของเครื่องในการพิสูจน์ตัวตนด้วยชีวมาตร (Thai)

Within the artificial intelligence rebellion, barely any innovation has been meliorated as quickly as biometrics. Fingerprint, iris, and face are popular digital identities, routinely integrated into common devices and portable gadgets to empower a quick and secure authentication. The uniqueness and ease of use of biometrics have subrogated traditional authentication, such as password and powered up the confidence of users conducting online transactions and using mobile devices in the new normal era. The authentication systems are actuated by image processing and pattern recognition techniques. The performance of these systems are highly affected by the quality of the acquired input where noisy images, poor pathological samples, and less controlled surroundings are major challenges to overcome. An innovative and attractive alternative is the machine learning based authentication. The intelligence and efficiency of authentication process can be increased while processing time and complication processes are lessen without program adjustment. Therefore, this academic article was composed to evaluate the strengths and weaknesses of the top three aforementioned biometrics. Empirical evidences on the breakthrough of machine learning based authentication systems were presented. The benefits lie in providing solutions for those who are looking for the appropriate, cost-effective and efficient security technology for booking accommodation with a host, accessing bank account, applying for government benefits, accepting a new friend request on social media or any online interactions. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Science & Technology MSU is the property of Mahasarakham University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)