Signature recognition

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

Off-Line Handwritten Signature Recognition Based on Discrete Curvelet Transform

Abstract: In order to improve the offline handwritten signature recognition effect, an offline handwritten signature recognition method based on discrete curvelet transform is proposed. First, the necessary pre-processing of offline handwritten signatures is carried out, including grayscale, binarization, smooth denoising, etc. The pre-processed signature image is subjected to curvelet transform to obtain real-numbered curve coefficients in the cell matrix, and a total of 82-dimensional energy features are extracted, and multi-scale block local binary mode (MBLBP) is combined on the cell matrix of discrete curvelet transform to form a new signature feature, use the SVM classifier for training and classification. Experiments on two databases, Uyghur and Kirgiz, the highest accuracy was 97.95% and 97.42% respectively. The experimental results show that the proposed method has better accuracy in offline handwritten signature recognition.

Real-Time Signature Recognition Using Neural Network

Abstract: The human signature is an important biometric feature that is used to identify human identity. It is essential in preventing falsification of documents in numerous financial, legal, and other commercial settings. The computerized system enters many aspects of our life, security is one of them, continues developing in computer vision and artificial network leads researcher to develop computerized signature recognition. This paper proposed a real-time algorithm for signature recognition. It is based on client and server operation.in which, client agent captures a signature and sends it to the server through the network. The server receives data and performs processing on it. Processing algorithm is based on weightless neural network. It is chosen for its simplicity and few numbers of sample required for training. The algorithm is tested and evaluated and show the ability to process 4.7 images per second.

Non-Western Script Based Off-Line Handwritten Signature Technology: A Survey

Abstract: Recognition and verification systems plays very critical role in the area of information security as they are very essential to user certification. In resent years, off-line signature recognition and verification receiving renewed interest and only one of several techniques used to verify the identities of individuals, also that one of the biometric techniques. Signatures offer a secure means for confirmation and authorization in legal documents. Thus, nowadays the signature identification and verification becomes an indispensable part for including embedded signatures of automating the rapid processing of documents. Researchers have been proposed various approaches for handwritten signature recognition and verification in the past years. This paper presents a survey for non-western handwritten signature based offline signature verification and identification. In this area, the accuracy rates obtained so far from the available systems is not sufficiently high, and more researches on off-line signature verification as well as off-line signature identification are required.

Method, device and system for protecting biometric feature data

Abstract: A method, a device and a system for protecting a biometric feature template are provided, which belong to the recognition field, wherein the method includes: encrypting a user biometric feature data by using a key, and generating the encrypted biometric feature data; binding the data of the user biometric characteristic with the key, and generating a biometric key corresponding to the encrypted biometric feature data. The present invention encrypts the biometric feature data by using a conventional key, binds the data of the user biometric characteristic with the conventional key, and generates the biometric key corresponding to the encrypted biometric feature data; thereby the security and the reliability of the biometric feature data protection could be improved, meanwhile, the security and the reliability of the biometric certification could be improved as well.

Online slant signature algorithm analysis

Abstract: A vector rule-based approach and analysis to on-line slant signature recognition algorithm is presented. Extracting features in signature is an intense area due to complex human behavior, which is developed through repetition. Features such as direction, slant, baseline, pressure, speed and numbers of pen ups and downs are some of the dynamic information signature that can be extracted from an online method. This paper presents the variables involve in designing the algorithm for extracting the slant feature. Signature Extraction Features System (SEFS) is used to extract the slant features in signature automatically for analysis purposes. The system uses both local and global slant characteristics in extracting the feature. Local slant is the longest slant among the detected slant while the global slant represents the highest quantity of classified slant whether the slant are leftward, upright or rightward. Development and analysis are reported on a database comprises of 20 signatures from 20 subjects. The system is compared to human expert evaluation. The results demonstrate a competitive performance with 85% accuracy.