A cancelable ear recognition system via optimized deep feature fusion
Zeinab F. Elsharkawy, Eman M. Omran, Ayman A. Eisa, A. A. Saleh, Nabil A. Ismail, Fathi E. Abd El-Samie · 2026
Read A cancelable ear recognition system via optimized deep feature fusion by Zeinab F. Elsharkawy, Eman M. Omran, Ayman A. Eisa, A. A. Saleh, Nabil A. Ismail, Fathi E. Abd El-Samie (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13264620.txt.
Description
Zeinab F Elsharkawy and co-authors present a 2026 paper on using the human ear to identify people. Ears keep a stable, personal shape, but photos vary with angle, light, and size, which hurts matching. Their system joins two deep learning tools and then protects the stored template so it can be cancelled if leaked.
One tool reads broad features and the other reads fine detail, and their outputs are merged. A search method then keeps only the most telling features. A filter step turns those features into a template that cannot be reversed into the raw ear data. On five public ear data sets, accuracy ranged from about 93 to nearly 100 percent. The authors say the system beat prior methods.
Catalog record
| CREATOR | Zeinab F. Elsharkawy, Eman M. Omran, Ayman A. Eisa, A. A. Saleh, Nabil A. Ismail, Fathi E. Abd El-Samie |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 89583 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |