Support vector machines versus multi-layer perceptrons for efficient off-line signature recognition

On-line handwriting recognition systems are usually better than their off-line counterparts thanks to the accessibility of dynamic information such as stroke order, velocity, acceleration, and pressure. Whilst the exact value of velocity as well as acceleration or pressure is unlikely to be recoverable, the temporal order of the strokes or the pen trajectory is shown to be more promising for recovery. The published experimental results suggest that the recovered pen trajectory information actually improves the off-line recognition accuracy. This paper presents an overview and discussion of pen trajectory recovery methods developed to date.

/pdf/techniques-for-static-handwriting-trajectory-recovery-a-4t0al45bdg.pdf

Techniques for static handwriting trajectory recovery: a survey

Off-line signature verification methods have to tackle with a number of high resolution images, therefore it is vital to use efficient image processing algorithms. This paper proposes a heuristic stroke extraction algorithm to create a compact representation of the signature whilst minimizing the loss of semantic information and the computational needs. Some issues of the algorithm are highlighted and - as far as possible - also eliminated. Finally an experimental validation of the algorithm is presented and evaluated. This algorithm could be used to refine existing signature verification methods, and also to create new ones.

http://www.wseas.us/e-library/conferences/2007venice/papers/600-424.pdf

Time-efficient stroke extraction method for handwritten signatures

This paper describes a combined behavioral techniques based on speech and signature biometrics modalities. Fusion of multiple biometric modalities for human verification performance improvement has received considerable attention. Multi-biometric systems, which consolidate information from multiple biometric sources, are gaining popularity because they are able to overcome limitations such as non-universality, noisy sensor data, large intra-user variations and susceptibility to spoof attacks that are commonly encountered in mono modal biometric systems. Soft decision level fusion based Gaussian mixture models (GMM), in which the (EM) and (GEM) algorithms for estimating the parameters of the mixture model and the number of mixture components have been compared. The test performance of the fusion, EER=0.0 % for "EM" and EER=0.02 % for "GEM", show that the combined behavioral information scheme is more robust and have a discriminating power, which can be explored for identity authentication.

Soft Decision Level Fusion Approach to a Combined Behavioral Speech-Signature Biometrics Verification

Signature recognition is an important requirement of automatic document verification system. Many approaches for signature recognition are found in literature. A novel approach for offline signature recognition system is presented in this paper, which is based on powerful global and local wavelet features (Energy features). The proposed system functions in three stages. Pre-processing stage, which consists of four steps: gray scale conversion, binarization, thinning and fitting boundary box in order to make signatures ready for feature extraction, Feature extraction stage, where totally 59 global and local wavelet based energy features are extracted which are used to distinguish the different signatures. Finally in classification stage, a simple Euclidean distance measure is used as decision tool. The average recognition accuracy obtained using this model ranges from 90% to 100% with the training set of 10 persons to 30 persons.

Euclidean Distance Based Offline Signature Recognition System Using Global and Local Wavelet Features

This paper proposes a simple adaptive off-line signature recognition method based on the feature analysis of extracted significant strokes for a given signature. Our system correctly decides on the majority of tested patterns, which include both simple and skilled forgeries. The presence of possible doubtful signatures (those ones on which is difficult to decide) is also considered. Experimental results have shown a good trade-off between response time and reasonable accuracy of recognition results.

/pdf/simplified-stroke-based-approach-for-off-line-signature-4zrd18xgeo.pdf

A. Pérez-Hernández

Papers

Simplified Stroke-based Approach for Off-line Signature Recognition