Offline Handwritten Signature Verification and Recognition Based on Deep Transfer Learning

Foroozandeh, Atefeh; Hemmat, A. Askari; Rabbani, Hossein

doi:10.1109/mvip49855.2020.9187481

Cited by 20 publications

(17 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A confusion matrix provides a value for comparing the image classification result to the model performance. EER (Equal Error Rate) measures network accuracy by balancing the False Acceptance Rate (FAR) and False Rejection Rate (FRR) [19], [43]. A confusion matrix is a matrix that provides a comparison value for the classification result within the context of the model's prediction performance.…”

Section: Model Evaluationmentioning

confidence: 99%

CNN with Batch Normalization Adjustment for Offline Hand-written Signature Genuine Verification

Fatihia

Fariza

Karlita

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Signature genuine verifications of offline hand-written signatures are critical for preventing forgery and fraud. With the growth of protecting personal identity and preventing fraud, the demand for an automatic system for signature verification is high. The signature verification system is then studied by many researchers using various methods, especially deep learning-based methods. Hence, deep learning has a problem. Deep learning requires much training time for the data to obtain the best model accuracy result. Therefore, this paper proposed a CNN Batch Normalization, the CNN architectural adaptation model with a normalization batch number added, to obtain a CNN model optimization with high accuracy and less training time for offline hand-written signature verification. We compare CNN with our proposed model in the experiments. The research method in this study is data collection, pre-processing, and testing using our private signature dataset (collected by capturing signature images using a smartphone), which becomes the difficulties of our study because of the different lighting, media, and pen used to sign. Experiment results show that our model ranks first, with a training accuracy of 88.89%, an accuracy validation of 75.93%, and a testing accuracy of 84.84%—also, the result of 2638.63 s for the training time consumed with CPU usage. The model evaluation results show that our model has a smaller EER value; 2.583, with FAR = 0.333 and FRR = 4.833. Although the results of our proposed model are better than basic CNN, it is still low and overfitted. It has to be enhanced by better pre-processing steps using another augmentation method required to improve dataset quality.

show abstract

Section: Model Evaluationmentioning

confidence: 99%

CNN with Batch Normalization Adjustment for Offline Hand-written Signature Genuine Verification

Fatihia

Fariza

Karlita

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…Networks -Atefeh Foroozandeh, Ataollah Askari Hemmat, Hossein Rabbani Atefeh Foroozandeh, et al (2020) proposed an offline signature verification and recognition system based on Deep Transfer Learning using CNN (Convolutional Neural Network). GPDS Synthetic Signature, MCYT-75, UTSig, and FUM datasets were used for the implementation.…”

Section: Offline Handwritten Signature Verification and Recognition B...mentioning

confidence: 99%

Comparison of Signature Forgery Detection Architectures

Teja¹

2022

IJRASET

View full text Add to dashboard Cite

In today's society, we use signatures for many important documents like passports, driving licenses, bank cheques, etc. But signatures can be forged in multiple ways, which can create a number of problems, such as identity theft, hacking, fake identification, etc. To reduce these problems, our project is about developing a system for detecting whether a signature is forged or real from a dataset of signatures. For our project, we are developing an offline signature verification system. This system is based on CNN (Convolutional Neural Network) and SNN (Siamese Neural Network). In this project, we will be comparing both CNN’s and SNN's to find which produces a better result. We are implementing the project using a custom CNN, a CNN with VGG16 architecture, a custom SNN and a SNN using the SigNet architecture.

show abstract

“…Pretrained Deep Learning is a series of neural networks used to classify the object. Pretrained Deep Learning is also called Transfer Learning and can save time since researchers do not need to train the models from scratch like traditional Convolutional Neural networks (CNN) [13]. CNN consists of neural networks with untrained weights and bias, which makes CNN take longer time to do the identification process [14].…”

Section: Feature Extractionmentioning

confidence: 99%

Offline Signature Identification Using Deep Learning and Euclidean Distance

Nugraha

Nurhadiyatna²,

Arsa

2021

LKJITI

View full text Add to dashboard Cite

Hand signature is one of human characteristic that human have since birth, which can be used as identity recognition. A high accuracy signature recognition is needed to identify the right owner of signature. This study present signature identification using a combination method between Deep Learning and Euclidean Distance. 3 different signature datasets are used in this study which consist of SigComp2009, SigComp2011, and private dataset. Signature images preprocessed using binary image conversion, Region of Interest, and thinning. Several testing scenarios is applied to measure proposed method robustness, such as usage of various Pretrained Deep Learning, dataset augmentation, and dataset split ratio modifier. The best accuracy achieved is 99.44% with high precision rate.

show abstract

Offline Handwritten Signature Verification and Recognition Based on Deep Transfer Learning

Cited by 20 publications

References 23 publications

CNN with Batch Normalization Adjustment for Offline Hand-written Signature Genuine Verification

CNN with Batch Normalization Adjustment for Offline Hand-written Signature Genuine Verification

Comparison of Signature Forgery Detection Architectures

Offline Signature Identification Using Deep Learning and Euclidean Distance

Contact Info

Product

Resources

About