| Autor: |
Patel, Meghna, Patel, Ronak, Parikh, Satyen M. |
| Předmět: |
|
| Zdroj: |
International Journal of Advances in Soft Computing & Its Applications; Nov2023, Vol. 15 Issue 3, p278-288, 11p |
| Abstrakt: |
The fingerprint image quality is very important for a fingerprint biometric authentication system. Therefore, the performance of the extraction of the minutiae of the fingerprint strongly depends on the biometric fingerprint image. As a result, the image enhancement stage of the recognition process has a significant impact on the biometric fingerprint verification system's performance. Image enhancement is a critical stage in biometric fingerprint recognition that improves image quality by reducing noise, repairing broken ridges, and smoothing the image. In this paper compare three methods like Canny algorithm, Sobel edge detection Laplacian edge detection with proposed composite algorithm that uses a Gaussian mask to smooth the image and two sobel convolutions to detect edges. The proposed research work is implemented using .net technology and with FingerDos database. The performance of proposed work is compared using parameter like PSNR, MSE, and execution time and quality of an image prove that proposed algorithm give better performance. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
