Signature recognition

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

Handwritten signature verification using neural network & ecludean approach

Abstract: This is review paper which is based on signature verification which is recognized and verified off-line. The approach for signature verification which will be using is based on artificial neural network which discriminates between (i) original signature and (ii) forgery signature. This approach uses the technique of signature procurement, signature pre-processing, feature point extraction and neural network training and finally verifies the authenticity of the signature. The main objective of this proposed approach is to reduce two critical parameters i.e False Rejection Rate (FRR) and False Acceptance Rate (FAR) . It means that the output is expressed in terms of FRR and FAR and subsequently comparison has been made with existing techniques. This technique will give more productive result than existing techniques.

Multi-dimensional signature system

Abstract: In a multi-dimensional signature system, the matching of signatures is determined by acquisition of multi-dimensional time series of a signature and feature values attached thereto and by comparison of the acquired multi-dimensional time series and the feature values with a reference multi-dimensional time series and reference feature values. The multi-dimensional signature system includes an inputting means for inputting a multi-dimensional time series of a signature and feature values by capturing an image of a pointing device in three-dimensional space and by analyzing the captured image to recognize the multi-dimensional time series of the signature and the feature values based on the displacement of the pointing device and ON/OFF status of illuminators arranged on a front side of the pointing device. By attaching the feature values to the multi-dimensional time series of the signature, the signature recognition rate of the multi-dimensional signature system can be improved.

Offline Handwritten Signature Recognition using Convolutional Neural Network Approach

Abstract: Handwritten signature is one of the essential biometric parameters widely used for document validation and verification. Other methods such as fingerprints, iris/retina scanning, face, and voice recognition, although more accurate, need special equipment. The purpose of the research is to demonstrate an appropriate and reliable technology organizations may use to recognize signatures automatically. Convolutional neural networks are trained on preprocessed signature images. The code was developed using MATLAB, and results indicate our method to provide promising results and have contributed by extending the technique to be reliable. The CNN is tested with 4 different datasets with N number of individuals and M number of signatures for each individual and contains signatures that differ from each other in many aspects like the type of signature, its readability, etc. We used our CNN to train and test on all the datasets to observe the performance and make interesting observations of our implementation. The network performed reasonably well on all datasets, which is presented in the results section.

Feature Selection in a Low Cost Signature Recognition System Based on Normalized Signatures and Fractional Distances

Abstract: In a previous work a new proposal for an efficient on-line signature recognition system with very low computational load and storage requirements was presented. This proposal is based on the use of size normalized signatures, which allows for similarity estimation, usually based on DTW or HMMs, to be performed by an easy distance calcultaion between vectors, which is computed using fractional distance. Here, a method to select representative features from the normalized signatures is presented. Only the most stable features in the training set are used for distance estimation. This supposes a larger reduction in system requirements, while the system performance is increased. The verification task has been carried out. The results achieved are about 30% and 20% better with skilled and random forgeries, respectively, than those achieved with a DTW-based system, with storage requirements between 15 and 142 times lesser and a processing speed between 274 and 926 times greater. The security of the system is also enhanced as only the representative features need to be stored, it being impossible to recover the original signature from these.

Biosignal recognition for patients identification

Abstract: A biometric security system has becoming an important application in client identification and verification system. A conventional biometric system is normally based on unimodal biometric that depends on either behavioral or physiological information for authentication purposes. The behavioral biometric depends on human body biometric signal (such as speech) and biosignal biometric (such as electrocardiogram and phonocardiogram or heart sound). The speech signal is commonly used in a recognition system in biometric, while the electrocardiogram and the heart sound have been used to identify a person's diseases, uniquely related to its cluster. However, the conventional biometric system is liable to spoof attack, which affect the performance of the system. In this paper, a multimodal biometric security system is developed, which is based on biometric signal of electrocardiogram and heart sound. The biosignal data involved in the biometric system initially segmented, with each segment Mel Frequency Cepstral Coeffiecients method is exploited for extracting the features. The Hidden Markov Model is used to model the client and to classify the unknown input with respect to the modal. The recognition system involved training and testing session that is known as Client Identification. In this project, twenty clients are tested with the developed system. The best overall performance for 20 clients at 44 kHz was 93.92% for electrocardiogram train at 70% of the training data however the worst overall performance was also electrocardiogram at an increment of data client of 63 clients at 79.91% for 30% training data. It can be concluded that the difference multimodal biometric has a substantial effect on performance of the biometric system and with the increment of data, even with higher sampling rate, the performance still decreased slightly as predicted.