2021/01/26 by Nikolaos Athanasios Anagnostopoulos, Anagnostopoulos, Nikolaos Athanasios
Computer Science · #68T10 #Biometric Identification and Security #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #FOS: Electrical engineering #I.5 #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2101.10540
openalex publication_date 2021/01/26 · openalex created_date 2024/04/11 · openalex updated_date 2026/07/28
Ear recognition can be described as a revived scientific field. Ear biometrics were long believed to not be accurate enough and held a secondary place in scientific research, being seen as only complementary to other types of biometrics, due to difficulties in measuring correctly the ear characteristics and the potential occlusion of the ear by hair, clothes and ear jewellery. However, recent research has reinstated them as a vivid research field, after having addressed these problems and proven that ear biometrics can provide really accurate identification and verification results. Several 2D and 3D imaging techniques, as well as acoustical techniques using sound emission and reflection, have been developed and studied for ear recognition, while there have also been significant advances towards a fully automated recognition of the ear. Furthermore, ear biometrics have been proven to be mostly non-invasive, adequately permanent and accurate, and hard to spoof and counterfeit. Moreover, different ear recognition techniques have proven to be as effective as face recognition ones, thus providing the opportunity for ear recognition to be used in identification and verification applications. Finally, even though some issues still remain open and require further research, the scientific field of ear biometrics has proven to be not only viable, but really thriving.