scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Learning features for offline handwritten signature verification using deep convolutional neural networks

TL;DR: A novel formulation of the problem that includes knowledge of skilled forgeries from a subset of users in the feature learning process, that aims to capture visual cues that distinguish genuine signatures and forgeries regardless of the user is proposed.
About: This article is published in Pattern Recognition.The article was published on 2017-10-01 and is currently open access. It has received 252 citations till now. The article focuses on the topics: Feature learning & Deep learning.
Citations
More filters
Journal ArticleDOI
TL;DR: A systematic review of the last 10 years of the literature on handwritten signatures with respect to the new scenario is reported, focusing on the most promising domains of research and trying to elicit possible future research directions in this subject.
Abstract: Handwritten signatures are biometric traits at the center of debate in the scientific community. Over the last 40 years, the interest in signature studies has grown steadily, having as its main reference the application of automatic signature verification, as previously published reviews in 1989, 2000, and 2008 bear witness. Ever since, and over the last 10 years, the application of handwritten signature technology has strongly evolved and much research has focused on the possibility of applying systems based on handwritten signature analysis and processing to a multitude of new fields. After several years of haphazard growth of this research area, it is time to assess its current developments for their applicability in order to draw a structured way forward. This perspective reports a systematic review of the last 10 years of the literature on handwritten signatures with respect to the new scenario, focusing on the most promising domains of research and trying to elicit possible future research directions in this subject.

184 citations


Cites background from "Learning features for offline handw..."

  • ...However, deep learning [4, 11, 46, 109, 110, 139, 145, 220, 247, 275] seems to be one of the hot topics in ASV....

    [...]

  • ...Such work was extended in [110] by a novel formulation of the problem that includes applying a knowledge of skilled forgeries during the feature learning process....

    [...]

  • ...- Statistical models Neural Networks (NNs) [144] and Deep Learning (Recurrent Neural Networks (RNNs) [4, 146, 247],*, Convolutional Neural Networks (CNNs) [268],* [11, 46, 109, 110, 139],** Deep Neural Networks (DNN) [220],** Deep Multitask Metric Learning (DMML) [240],** DCGANs [275]**), Hidden Markov Models (HMMs) [15, 72, 157, 251],* [48, 74],** Support Vector Machine (SVM) [103],* [54, 56, 76, 104, 198, 274],** Random Forest [203],* ....

    [...]

Proceedings ArticleDOI
01 Nov 2017
TL;DR: How the problem has been handled in the past few decades is presented, the recent advancements in the field are analyzed, and the potential directions for future research are analyzed.
Abstract: The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. The objective of signature verification systems is to discriminate if a given signature is genuine (produced by the claimed individual), or a forgery (produced by an impostor). This has demonstrated to be a challenging task, in particular in the offline (static) scenario, that uses images of scanned signatures, where the dynamic information about the signing process is not available. Many advancements have been proposed in the literature in the last 5–10 years, most notably the application of Deep Learning methods to learn feature representations from signature images. In this paper, we present how the problem has been handled in the past few decades, analyze the recent advancements in the field, and the potential directions for future research.

135 citations


Cites background or methods from "Learning features for offline handw..."

  • ...6 WD [28] Feature learning (SVM) 12 - 4....

    [...]

  • ...94 WD [28] Feature learning (SVM) 12 3....

    [...]

  • ...Recent studies approach the problem from a representation learning perspective [27], [28], [50], [68]: instead of designing feature extractors for the task, these methods rely on learning feature representations directly from signature images....

    [...]

  • ...work [28], the authors also proposed a multi-task framework, where the CNN is trained with both genuine signatures and skilled forgeries, optimizing to jointly discriminate between users, and discriminate between genuine signatures and forgeries....

    [...]

  • ...Other authors use a fixed frame size (width and height), and center the signature in this frame [49], [28]....

    [...]

Proceedings ArticleDOI
TL;DR: In this article, the authors present how the signature verification problem has been handled in the past few decades, analyze the recent advancements in the field, and the potential directions for future research.
Abstract: The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. The objective of signature verification systems is to discriminate if a given signature is genuine (produced by the claimed individual), or a forgery (produced by an impostor). This has demonstrated to be a challenging task, in particular in the offline (static) scenario, that uses images of scanned signatures, where the dynamic information about the signing process is not available. Many advancements have been proposed in the literature in the last 5-10 years, most notably the application of Deep Learning methods to learn feature representations from signature images. In this paper, we present how the problem has been handled in the past few decades, analyze the recent advancements in the field, and the potential directions for future research.

132 citations

Posted Content
TL;DR: This work provides a comprehensive survey of more than 120 promising works on biometric recognition (including face, fingerprint, iris, palmprint, ear, voice, signature, and gait recognition), which deploy deep learning models, and show their strengths and potentials in different applications.
Abstract: Deep learning-based models have been very successful in achieving state-of-the-art results in many of the computer vision, speech recognition, and natural language processing tasks in the last few years. These models seem a natural fit for handling the ever-increasing scale of biometric recognition problems, from cellphone authentication to airport security systems. Deep learning-based models have increasingly been leveraged to improve the accuracy of different biometric recognition systems in recent years. In this work, we provide a comprehensive survey of more than 120 promising works on biometric recognition (including face, fingerprint, iris, palmprint, ear, voice, signature, and gait recognition), which deploy deep learning models, and show their strengths and potentials in different applications. For each biometric, we first introduce the available datasets that are widely used in the literature and their characteristics. We will then talk about several promising deep learning works developed for that biometric, and show their performance on popular public benchmarks. We will also discuss some of the main challenges while using these models for biometric recognition, and possible future directions to which research in this area is headed.

88 citations

Journal ArticleDOI
TL;DR: In this paper, a fixed-sized representation from variable-sized signatures was learned by modifying the network architecture, using spatial pyramid pooling, which achieved state-of-the-art performance on handwritten signature verification.
Abstract: Methods for learning feature representations for offline handwritten signature verification have been successfully proposed in recent literature, using deep convolutional neural networks to learn representations from signature pixels. Such methods reported large performance improvements compared to handcrafted feature extractors. However, they also introduced an important constraint: the inputs to the neural networks must have a fixed size, while signatures vary significantly in size between different users. In this paper, we propose addressing this issue by learning a fixed-sized representation from variable-sized signatures by modifying the network architecture, using spatial pyramid pooling. We also investigate the impact of the resolution of the images used for training and the impact of adapting (fine-tuning) the representations to new operating conditions (different acquisition protocols, such as writing instruments and scan resolution). On the GPDS dataset, we achieve results comparable with the state of the art, while removing the constraint of having a maximum size for the signatures to be processed. We also show that using higher resolutions (300 or 600 dpi) can improve performance when skilled forgeries from a subset of users are available for feature learning, but lower resolutions (around 100dpi) can be used if only genuine signatures are used. Lastly, we show that fine-tuning can improve performance when the operating conditions change.

62 citations

References
More filters
Proceedings Article
03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

73,978 citations

Proceedings Article
04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

55,235 citations


"Learning features for offline handw..." refers methods in this paper

  • ...gued in [37], these pre-trained models offer a strong baseline for Computer Vision tasks. We used two pre-trained models3, namely Caffenet (Caffe reference network, based on AlexNet [25]), and VGG-19 [38]. 3https://github.com/BVLC/caffe/wiki/Model-Zoo 18 We used these networks to extract the feature representations ˚(X) for signatures, and followed the same protocol for training Writing-Dependent clas...

    [...]

Proceedings Article
01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

49,914 citations

Journal ArticleDOI
28 May 2015-Nature
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Abstract: Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

46,982 citations


"Learning features for offline handw..." refers methods in this paper

  • ... images. Methods based on learning multiple levels of representation have shown to be very effective to process natural data, especially in computer vision and natural language processing [21], [22], [23]. The intuition is to use such methods to learn multiple intermediate representations of the input, in layers, in order to better represent a given problem. In a classification task, the higher layers ...

    [...]

  • ...ut that are important for classification, while disregarding irrelevant variations [23]. In particular, Convolutional Neural Networks (CNNs) [24] have been used to achieve state-of-the-art performance [23] in many computer vision tasks [25], [26]. These models use local connections and shared weights, taking advantage of the spatial correlations of pixels in images by learning and using the same filters...

    [...]

Proceedings ArticleDOI
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

40,257 citations