Please use this identifier to cite or link to this item:
https://dspace.univ-ouargla.dz/jspui/handle/123456789/40045| Title: | FKP Recognition and Classification |
| Authors: | Azzaoui, Nadjet Berziga, Safa Naam, Racha Elhelli, Hamza |
| Keywords: | Finger Knuckle Print (FKP) Deep Learning, Feature Extraction CNN ANN |
| Issue Date: | 2025 |
| Publisher: | UNIVERSITY OF KASDI MERBAH OUARGLA |
| Citation: | FACULTY OF NEW TECHNOLOGIES OF INFORMATION AND COMMUNICATION |
| Abstract: | In order to identify a person based on their physiological and behavioural traits, biometrics are crucial. When interacting with others who might be familiar or unreliable, this provides us with certainty. Because biometrics have unique and independent properties, they are also entirely reliant on individual dependability. Technologies for identification or recognition are being developed to investigate novel, cutting-edge approaches. The growing sophistication of coun- terfeit technology and certain security issues are to blame for this. For accurate identification and recognition, specific bodily parts—such as the iris, fingerprint, etc.—are utilised. Even with this advancement, many systems continue to have issues, such as sluggish processing Finger- print knuckles (FKP) have emerged as a biometric method for identifying individuals due to their stability and uniqueness. This master’s thesis presents a comprehensive and in-depth study of fingerprint knuckles, their uses, and the use of deep features for authentication using CNN and ANN models,Excellent results were achieved. |
| Description: | Industrial |
| URI: | https://dspace.univ-ouargla.dz/jspui/handle/123456789/40045 |
| Appears in Collections: | Département d'informatique et technologie de l'information - Master |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| BERZIGA-NAAM-ELHELLI.pdf | Industrial | 8,08 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.