Offline Signature Verification Using Multi Classifiers: A Deep Feature Extraction Framework

Recently, there has been a lot of interest in offline signature verification utilising handwritten signature images. Despite the large number of studies on the topic, the performance of the methods used to verify signatures is insufficient. Additionally, there are a variety of issues that are frequently associated with signature verification systems during the phase of feature extraction, which researchers find to be extremely challenging to solve. This study proposes an enhanced model that can extract signature features and verify signatures. The signature features are extracted ‎from the image using Features from Accelerated Segment Test (FAST) and ‎Histogram Orientation Gradient (HOG), where (FAST) is used for selecting the ‎strength points in signature image, and then (HOG) is used to extract features ‎from the selected strength points. For our experiment, the databases UTSig and CEDAR were utilised. This study's fundamental improvement is in its ability to detect offline signature images, verify them, and determine the forged signature based on selected features points from the system database. We utilised three classifiers to assess the efficiency of the proposed method: ‎ Support Vector Machine, Long Short-Term Memory, and K-Nearest Neighbor. ‎Our results ensure the effectiveness of our proposed model in verifying offline signature and detecting forged signature with different types of datasets. The testing results showed that our proposed model performs fairly well regarding of performance and predictive capacity and had an accuracy of (91.6%, 92.4%, and 91.7%) with the UTSig dataset and (92.7%, 92.1%, and 91.7%) with the CEDAR dataset. When compared to several state-of-the-art techniques, our results are promising and have the potential to increase the reliability of signature verification.