Human Recognition based on Multi-instance Ear Scheme

Abstract

Ear biometrics is one of the primary biometrics that is definitely standing out. Ear recognition enjoys special benefits and can make distinguishing proof safer and dependable along with other biometrics (for example fingerprints and face). Particularly as a supplement to face recognition schemes that experience issues in genuine circumstances. This is because of the extraordinary variety of a planar representation of a confusing object that is varied in shapes, illumination, and profile shape. This study is an endeavor to conquer these restrictions, by proposing scale-invariant feature transform (SIFT) calculation to extract feature vector descriptors from both left and right ears which is to be melded as one descriptor utilized for verification purposes. Likewise, another plan is proposed for the recognition stage, based on a genetic algorithm-backpropagation neural network as an accurate recognition approach. This approach will be tried by utilizing images from the Indian Institute of Technology Delhi's creation (IITD). The suggested system exhibits a 99.7% accuracy recognition rate.