Using Residual Networks and Cosine Distance-Based K-NN Algorithm to Recognize On-Line Signatures

Abstract

As a result of the urgent need to immediately identify individuals through the Internet, especially given the Coronavirus (COVID-19) pandemic at present, the recognition of online handwritten signatures has quickly evolved to become an urgent and necessary matter. However, signature identification remains challenging in the pattern recognition field due to intra-class variability and inter-class similarity. Intra-class variability is a characteristic of human behavioural activities, particularly in handwriting where no two handwritten signatures of any person can exactly coincide. The inter-class similarity is also a characteristic of human movement-based activities such as handwritten signatures particularly when the number of writers is large. In this research, an optimized transfer-learning-based architecture is proposed as a highly accurate identification technique for online-signatures using ResNet18 as a feature extraction deeplearning module. The X-Y time-series signals of the signatures were initially converted into images and used in retraining the ResNet18 model to achieve relatively high accuracy. The retrained ResNet18 model was then used to extract features that possess high discriminative distances among different classes of handwritten signatures. The model's deep layers were searched to determine the best layer that provided the most discriminative features when using a 1-nearest neighbour learning algorithm based on the cosine distance. By using an ensemble of five models trained on rotated versions of the original signatures and using only three training samples from each writer, the classification accuracy achieved 100% when applied on the genuine signatures of public datasets such as SVC 2004 TASK1 and TASK2, and a new proprietary dataset composed of 120 genuine users. When the abovementioned technique was tested on the aggregated version of the aforementioned datasets, the resultant accuracy was still above 99%. Moreover, the robustness of the technique was proven by testing the generated models trained with one dataset with the other two datasets resulting in accuracy above 99% for all combinations.

Interpol questioned documents review 2019–2022

“…Another article about online signature verification addressed the challenges of this task in the pattern recognition field [ 141 ]. The main challenge to overcome for this task was the variability of handwriting both within an individual (intra-class variability) and as compared to other individuals (inter-class variability).…”

A Hybrid Price Auction-Based Secure Routing Protocol Using Advanced Speed and Cosine Similarity-Based Clustering against Sinkhole Attack in VANETs

“…By considering the maximum cosine similarity under the constrained communication distance, we can control the cluster member to make more stable cluster members in the viewpoint of mobility. Then, the cosine distance of the node used to find the distance between two nodes can be calculated by [ 40 ] If selects the , the node can be as the best cluster head. Node sends the joint-cluster (JC) packet to the .…”

Optimum “Eye Location” Problem for Spectral Clustering With Cosine Distance

“…Anjum et.al., used the CS in [68] for the multiple sequence alignment method, which is a wellestablished approach for sequence analysis and comparison. The CD is used in the recognition of online handwritten signatures in [69] where comparisons with state-of-the-art techniques were presented. It was empirically proven in [69] that the CD is the most accurate discriminating distance when comparing features for handwritten signatures classification.…”