Abstract
Biometric researchers have recently paid a lot of attention to recognize people by their voices. This trend can be attributed to a number of factors, including the fact that ear recognition does not suffer from some of the drawbacks of contactless biometrics, such as facial recognition; that it is the most promising face-matching candidate in the context of multi-position face recognition, and that ears can be used to identify people in surveillance videos where faces may be completely or partially obscured. In addition, the ear appears to age more slowly. Although ear detection and recognition technology has advanced to a certain point, it has only been successful in controlled indoor environments. In this study, machine vision experiments were utilized to recognize the ears of well-known musicians in Vietnam using the EarVN1.0 dataset. During the model-building process, the data set is divided into training and test sets using the ratios 70:30 and 60:40, respectively. According to experimental findings, the ResNeXt50 neural network with image enhancement approach produced good results, scoring 93% for a 70:30 ratio and 90% for a 60:40 ratio.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
