Biometric identity Authentication System Using Hand Geometry Measurements
| Autor: | Hesham Hashim Mohammed, Shatha A. Baker, Ahmed S. Nori |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | Journal of Physics: Conference Series. 1804:012144 |
| ISSN: | 1742-6596 1742-6588 |
| DOI: | 10.1088/1742-6596/1804/1/012144 |
| Popis: | In recent years hand geometric dependent biometric system has shown to be the quite acceptable biometric trait and suitable for security applications. It has been recognized as an effective means of authenticating identity in a variety of commercial applications as a result of better hardware and improved algorithms. This paper purpose a hand recognition system that extract 21 features for the right hand to identify and authorize persons. The system has two main parts, the first contain the data collection, explains the basic pre-processing required and how hand geometry characteristics like fingers length, width, coordinates of the base of the fingers, and palm width are extracted to derive the features used for discrimination, While the second part include the training and testing of three artificial neural networks to perform the recognition. After features extraction, the system uses three kinds of artificial neural networks in performing the recognition process, which are feed forward back propagation NN, Elman NN, and the cascade forward neural network NN. The proposed system shows that the Recognition Rate RR for the neural networks after testing were 95%, 92%, 88% respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|