scispace - formally typeset
Search or ask a question
Topic

Signature recognition

About: Signature recognition is a research topic. Over the lifetime, 2138 publications have been published within this topic receiving 37605 citations.


Papers
More filters
Journal Article
TL;DR: Touch screen based user input is learned by the dynamic signature recognition system and the dynamic parameters of signature are recorded using slope based method and stored in SQL database.
Abstract: Abstract— For centuries, Signature have been accepted socially as a mean of identity verification. The core concept of dynamic signature system is behavioural (how it is signed) and not visual (image of the signature).In this paper, Touch screen based user input is learned by the system. The dynamic parameters of signature are recorded using slope based method and are stored in SQL database. Recognition is done by comparing and calculating percentage match. In dynamic signature recognition forgery is detected even if the forger manages to get the authentic signature. Keywords—Dynamic signature recognition, Biometrics, Touch screen, authentication, verification, AVR, slope based, databases.
Journal Article
TL;DR: A method of recognition of hand written signatures with the use of Hidden Markov Mo dels (HMM) and the results are competitive in relation to other methods known from the literature.
Abstract: This paper presents a method of recognition of hand written signatures with the use of Hidden Markov Mo dels (HMM). The method in question consists in describin g each signature with a sequence of symbols. Sequen ces of symbols were generated on the basis of an analysis of local extremes determined on diagrams of dynamic features of signatures. For this purpose, the method proposed b y G.K. Gupta and R.C. Joyce has been modified. The det rmined sequences were then used as input data for the HMM method. The studies were conducted with the use of the SVC2004 database. The results are competitive in relation t o other methods known from the literature.
Book ChapterDOI
10 Sep 2021
TL;DR: Wang et al. as mentioned in this paper proposed a multi-lingual hybrid handwritten signature recognition method based on deep residuals attention network, which achieved the highest recognition accuracy of 99.44% for multilingual handwritten signature database.
Abstract: The writing styles of Uyghur, Kazak, Kirgiz and other ethnic minorities in Xinjiang are very similar, so it is extremely difficult to extract the effective features of handwritten signatures of different languages by hand. To solve this problem, a multi-lingual hybrid handwritten signature recognition method based on deep residuals attention network was proposed. Firstly, an offline handwritten signature database in Chinese, Uyghur, Kazak and Kirgiz was established, with a total of 8,000 signed images. Then, the signature image is pre-processed by grayscale, median filtering, binarization, blank edge removal, thinning and size normalization. Finally, transfer learning method is used to input the signature image into the deep residual network, and the high-dimensional features are extracted automatically by the fusion channel attention for classification. The experimental results show that the highest recognition accuracy of this method is 99.44% for multi-lingual hybrid handwritten signature database, which has a high application value.
01 Nov 2002
TL;DR: An algorithm with three new features: Incorporation of pen-velocity trajectories, a new distance measure between two signatures, and a new efficient algorithm for computing the distance measure is proposed.
Abstract: Authentication of individuals is rapidly becoming an important issue. The authors have previously proposed a pen-input on-line signature verification algorithm incorporating pen-position, pen-pressure and pen-inclination trajectories. This paper proposes an algorithm with three new features: (i) Incorporation of pen-velocity trajectories, (ii) A new distance measure between two signatures, and (iii) A new efficient algorithm for computing the distance measure. Preliminary experimental result looks encouraging.
01 Jan 2015
TL;DR: This research presents a method for offline signature recognition that consists of three main steps: image preprocessing, feature extraction and classification and achieves 95% for recognition of 196 similar signatures.
Abstract: 53 ISSN: 2278 – 7798 All Rights Reserved © 2015 IJSETR Abstract—Among all biological techniques for identifying persons, handwritten signature has an important role because signature of each person is provided easily and processedquickly. Having a high performance recognition system is very essential. Persian signatures are different from other kind of signatures because people usually do not write their name or a text part and they draw a shape so the processing of signatures is more difficult. In [1] we used three classifiers for identifying 360 signatures from 20 signers with a ratio of 95.625%. But theproposed system suffers froma high number of signatures and especially similar ones. In this research, we present a method for offline signature recognition. The proposed system consists of three main steps: image preprocessing, feature extraction and classification.The database includes 700 Persiansignatures from 50 individuals. We use some features to make exact detection of signatures with high similarity and we achieve 95% for recognition of 196 similar signatures. The total detectionratiofor 700 signatures is 84%.

Network Information
Related Topics (5)
Feature extraction
111.8K papers, 2.1M citations
89% related
Image segmentation
79.6K papers, 1.8M citations
85% related
Feature (computer vision)
128.2K papers, 1.7M citations
85% related
Convolutional neural network
74.7K papers, 2M citations
83% related
Deep learning
79.8K papers, 2.1M citations
83% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202310
202219
202122
202028
201925
201832