International Journal of Pattern Recognition and Artificial Intelligence

This paper is a follow up to an article published in 1989 by R. Plamondon and G. Lorette on the state of the art in automatic signature verification and writer identification. It summarizes the activity from year 1989 to 1993 in automatic signature verification. For this purpose, we report on the different projects dealing with dynamic, static and neural network approaches. In each section, a brief description of the major investigations is given.

This paper describes possible strategies for the implementation of a feature selection algorithm particularly suited to the realisation of an efficient automatic handwritten signature verification system in which an active feature vector, optimised with respect to an individual signer, is constructed during an enrollment period. A range of configurations based on transputer arrays are considered and the possible implementational approaches evaluated. The paper demonstrates how the inherent parallelism which exists within a generic model for verification can be exploited to provide an optimised general-purpose framework for verification processing.

We are applying neural networks to the problem of handwritten signature verification. Our system is working on checks, so we can only use the static information (the image). This static information is used in three representations: geometrical parameters, outline and image. Our system is composed of several neural networks which cooperate together during the learning and decision phases. The performances in generalization, obtained with a large-scale database of 6000 signatures from real checks on random forgeries, are False Acceptance Rate (FAR)=2% and False Rejection Rate (FRR)=4%.

A system of off-line signature verification composed of a preprocessing stage and a verification stage is proposed in this paper. It is assumed that each signature is written on a surface with a background pattern and a sample of the background pattern is available. The preprocessing stage to eliminate the background pattern from a signature image consists of 5 steps: the position adjustment between a signature image and a background image, the filtering of the background pattern by local maximization, the clipping of random noises from the background pattern, the background elimination by transformation of the multilevel signature image to a binary signature image through subtraction and thresholding, and the smoothing for defects recovery and isolated noise elimination. The effect of the preprocessing operation is illustrated in figures. The verification stage following the preprocessing stage is based on the Arc Pattern Method proposed in Ref. 7. An experiment is performed to examine the performance of the proposed system. Twenty Japanese autographs, for which 20 authentic signatures, 10 genuine counter signatures and 10 forged counter signatures are provided, are used in the experiment. The experiment achieved an error rate of as low as approximately 14%.

The interpretation of handwritten signature images should be closely related to the writer’s identity. The representation and analysis of the handwritten signature is the major challenge in the field of automatic signature verification. A new concept of representation and interpretation of handwritten signature images is advocated. The segmentation process breaks up the signature into a collection of arbitrarily-shaped primitives. In the next step, a local interpretation process serves as a sophisticated template matching, permitting the labeling of all primitives from the test primitive set. This is followed by the global interpretation process, which permits the evaluation of a similarity measure between two structural graphs. Experimental results obtained from a database of 800 handwritten signature images from 20 writers show a performance with a type I error rate of ∈₁=1.50%, a type II error rate of ∈₂=1.37% and a total error rate ∈_t=1.43% in the best strategy proposed using a minimum-distance classifier and two reference signatures. A complete description of this novel automatic handwritten signature verification system is presented in this paper.

Three methods for on-line signature verification are discussed in this paper. They are based on statistical models of features that summarize different aspects of signature shape and the dynamics of signature production. Two of the methods are based on the feature statistics of genuine signatures only. Of these two methods, the simpler one using a Euclidean distance error metric was found to have superior performance when tested on a database of 919 genuine signatures and 330 forgeries. Using a procedure for selecting the individual best 10 out of 22 features, the Euclidean distance method correctly classified 99.5% of the genuine signatures, while rejecting 86% of the forgeries. The third method uses statistical properties of the forgeries as well as the genuine signatures to develop a quadratic discriminant rule for classifying signatures. On the basis of the database used in this study, this method was generally better than the simpler Euclidean distance method. At the same 99.5% acceptance of the genuine signatures, the method rejected 90% of the forgeries.

Signing is a complex and highly variable process. It results from simple bodily motions of a ballistic nature whose combined effects produce the fundamental components of the signature. Therefore, signature verification can be performed by adopting local verification strategies for the detection of personal characteristics in fundamental components.

In this paper, an on-line component-oriented signature verification system is presented. During the training phase, the set of fundamental components of each signer is derived and a suitable component-oriented knowledge-base is created by an automated technique. The verification is accomplished through a step-wise process. In the first step the structural organization of the signature is checked. In the second step each component is examined using spectral analysis. The experimental result shows the effectiveness of this approach compared with other techniques in the literature.

This paper reports on the major decisions that have to be made throughout the design phase of an automatic signature verification system. It shows how knowledge about signature control and generation, in terms of a realistic mathematical and psychophysical model, can be helpful in guiding and orienting design choices and related research activities. A system designed according to this methodology is described and the results of a robust forgery test are presented.