Handwritten Signature Verification Using Transfer Learning and Data Augmentation

Gupta, Yash; Ankit, .; Kulkarni, Sanchit; Jain, Pooja

doi:10.1007/978-981-16-7136-4_19

Cited by 5 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The task of preprocessing is to remove invalid information that is not discriminative during the identification process and to reduce the intra-class variability between images of genuine and fake signatures [15]. In practical applications, in the offline handwritten signature system, the signer signs on paper, and then all signature data is scanned into a static image, so the signature image may have changes in the background, pen thickness, scale, rotation, etc., To improve the validity of the model, the signature image model needs to be cropped and resized.…”

Section: Preprocessingmentioning

confidence: 99%

Multilingual Offline Signature Verification Based on Improved Inverse Discriminator Network

et al. 2022

View full text Add to dashboard Cite

To further improve the accuracy of multilingual off-line handwritten signature verification, this paper studies the off-line handwritten signature verification of monolingual and multilingual mixture and proposes an improved verification network (IDN), which adopts user-independent (WI) handwritten signature verification, to determine the true signature or false signature. The IDN model contains four neural network streams with shared weights, of which two receiving the original signature images are the discriminative streams, and the other two streams are the reverse stream of the gray inversion image. The enhanced spatial attention models connect the discriminative streams and reverse flow to realize message propagation. The IDN model uses the channel attention mechanism (SE) and the improved spatial attention module (ESA) to propose the effective feature information of signature verification. Since there is no suitable multilingual signature data set, this paper collects two language data sets (Chinese and Uyghur), including 100,000 signatures of 200 people. Our method is tested on the self-built data set and the public data sets of Bengali (BHsig-B) and Hindi (BHsig-H). The method proposed in this paper has the highest discrimination rate of FRR of 10.5%, FAR of 2.06%, and ACC of 96.33% for the mixture of two languages.

show abstract

Section: Preprocessingmentioning

confidence: 99%

Multilingual Offline Signature Verification Based on Improved Inverse Discriminator Network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Hafemann et al used deep Convolutional Neural Networks for feature learning for offline handwritten signature authentication [9]; Yapici et al used Deep Learning methods for data augmentation [10]; Tsourounis et al al-so used deep feature learning method for offline handwritten signature authentication [11]. In terms of transfer learning, Souza et al proposed a signature authentication method based on the combination of transfer learning and feature selection [12]; Tuncer et al also use transfer learning to generate deep features and perform feature selection through iterative minimum redundancy maximum correlation method before signature authentication [13]; Gupta et al combined transfer learning and data augmentation methods for offline handwritten signature authentication [14]. These methods have achieved the best authentication effect at that time.…”

Section: Introductionmentioning

confidence: 99%

Offline handwritten signature authentication based on perceptual hash and DFT

Chen

Qian

Liu

et al. 2023

Third International Conference on Artificial Intelligence and Computer Engineering (ICAICE 2022)

View full text Add to dashboard Cite

In order to solve the problem of sparse and missing example in the off-line handwritten signature authentication scenario, a handwritten signature authentication tree algorithm was proposed. The algorithm improves the perceptual hash algorithm based on the discrete Fourier transform, which is used to gather the subject information in the signature image, compress and generate the perceptual digest; then the cosine distance is used to calculate the distance between the perceptual digest vectors. According to the cosine distance matrix, an authentication tree composed by multiple nodes is constructed and the distance threshold is determined to authenticate the unknown data. The authentication result can be used for the self-renewal of the authentication tree. The experimental results show that the handwritten signature authentication tree algorithm has high accuracy and strong robustness. The false rejection rate and false acceptance rate on small datasets are significantly lower than the traditional machine learning algorithm, and its self-renewal mechanism can also cope with the style changes of signature handwriting very well.

show abstract