| Autor: |
Ahamed, S. Riyaz, Geetha, B. T. |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2023, Vol. 2822 Issue 1, p1-8, 8p |
| Abstrakt: |
This work proposed work is to evaluate the performance of a novel feature point extraction method in predicting a signature image to get a clear form of image by comparing it with a digital configured replication method. Comparison was based on their accuracy and skewness values. Gpower software used to determine the sample size with pretest power is 0.8. A total number of 100 samples of old signature images which are collected from various classes and labels. The accuracy and skewness values were generated to estimate the effectiveness of the novel feature point extraction method and digital programmed replication method. These samples are split into training dataset (60%) and test dataset (40%) datasets. Novel Feature point extraction method achieved the accuracy 96.1%, compared to 85.3% of the digital configured replication method of accuracy and skewness. The 2-tailed significance value is established as 0.0001 (p<0.05). In this investigation, it was discovered that the innovative feature point extraction approach greatly outperformed the digital configured replication method when it came to correctness and skewness in the verification of the signature. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
