Réjean Plamondon

Online and off-line handwriting recognition: a comprehensive survey

Handwriting has continued to persist as a means of communication and recording information in day-to-day life even with the introduction of new technologies. Given its ubiquity in human transactions, machine recognition of handwriting has practical significance, as in reading handwritten notes in a PDA, in postal addresses on envelopes, in amounts in bank checks, in handwritten fields in forms, etc. This overview describes the nature of handwritten language, how it is transduced into electronic data, and the basic concepts behind written language recognition algorithms. Both the online case (which pertains to the availability of trajectory data during writing) and the off-line case (which pertains to scanned images) are considered. Algorithms for preprocessing, character and word recognition, and performance with practical systems are indicated. Other fields of application, like signature verification, writer authentification, handwriting learning tools are also considered.

Automatic signature verification and writer identification — the state of the art

Abstract This paper presents a survey of the literature on automatic signature verification and writer identification by computer, and an overview of achievements in static and dynamic approaches to solving these problems, with a special focus on preprocessing techniques, feature extraction methods, comparison processes and performance evaluation. In addition, for each type of approache special attention is given to requirement analysis, human factors, practical application environments, and appropriate definitions and terminology. Throughout the paper, new research directions are suggested.

AUTOMATIC SIGNATURE VERIFICATION: THE STATE OF THE ART—1989–1993

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.

UNIPEN project of on-line data exchange and recognizer benchmarks

We report the status of the UNIPEN project of data exchange and recognizer benchmarks started two years ago at the initiative of the International Association of Pattern Recognition (Technical Committee 11). The purpose of the project is to propose and implement solutions to the growing need of handwriting samples for online handwriting recognizers used by pen-based computers. Researchers from several companies and universities have agreed on a data format, a platform of data exchange and a protocol for recognizer benchmarks. The online handwriting data of concern may include handprint and cursive from various alphabets (including Latin and Chinese), signatures and pen gestures. These data will be compiled and distributed by the Linguistic Data Consortium. The benchmarks will be arbitrated the US National Institute of Standards and Technologies. We give a brief introduction to the UNIPEN format. We explain the protocol of data exchange and benchmarks.

A comparative analysis of regional correlation, dynamic time warping, and skeletal tree matching for signature verification

A report is presented on a comparative study of three different signal matching algorithms in the context of signature verification: regional correlation, dynamic time warping, and skeletal tree matching. The algorithm performances are compared in a single experimental protocol over the same database. Algorithm performance is analyzed in terms of verification error rates, execution time, and number and sensitivity of algorithm parameters. Three different script types (normal signatures, handwritten passwords, and initials) and three different signal representation spaces (position, velocity, and acceleration) are considered. Verification errors show that no algorithm consistently outperforms the others in all circumstances. >

An evaluation of motor models of handwriting

A general method is presented for describing and analyzing biomedical handwriting models. Using Laplaces transform theory, a model can be represented in what is called the neural firing-rate domain. Consistent terminology is proposed to facilitate model evaluation and comparison. An overview of previously published models suggests that they could be described using this method, with second- and third-order linear model representation. Fourteen simplified theoretical models are simulated in an experiment designed to study the parameter domain in which handwriting is controlled by the nervous system in order to gain insight into which type of model provides the best reconstruction of natural handwriting. Results show that velocity-controlled models produce the best outputs, with no significant difference between second- and third-order systems. In handwriting, fine motor behavior is thus velocity-controlled. These findings agree with other recent automatic signature verification results and are of interest for a number of applications, from pattern recognition to handwriting education. >

A kinematic theory of rapid human movements

This paper proposes a kinematic theory that can be used to study and analyze rapid human movements. It describes a synergy in terms of the agonist and antagonist neuromuscular systems involved in the production of these movements. It is shown that these systems have a log-normal impulse response that results from the limiting behavior of a large number of interdependent neuromuscular networks, as predicted by the central limit theorem. The delta log-normal law that follows from this model is very general and can reproduce almost perfectly the complete velocity patterns of an end-effector. The theory accounts for the invariance and rescalability of these patterns, as well as for the various observations that have been reported concerning the change in maximum and mean velocities, time to maximum velocity, etc., under different experimental conditions. Movement time, load effects, and control strategies are discussed in a companion paper.

Segmenting handwritten signatures at their perceptually important points

A new algorithm for segmenting continuous handwritten signatures sampled by a digitizer is described. The segmentation points are found using a two-step procedure. The principal step is to construct a function that weights the perceptual importance of every signature point according to its specific neighboring points. The second step points out the various local maxima of this function that correspond to where the signature should be segmented. The method is well illustrated and tested on a number of signatures that require different kinds of segmentation decisions. >

Training hidden Markov models with multiple observations-a combinatorial method

Hidden Markov models (HMM) are stochastic models capable of statistical learning and classification. They have been applied in speech recognition and handwriting recognition because of their great adaptability and versatility in handling sequential signals. On the other hand, as these models have a complex structure and also because the involved data sets usually contain uncertainty, it is difficult to analyze the multiple observation training problem without certain assumptions. For many years researchers have used the training equations of Levinson (1983) in speech and handwriting applications, simply assuming that all observations are independent of each other. This paper presents a formal treatment of HMM multiple observation training without imposing the above assumption. In this treatment, the multiple observation probability is expressed as a combination of individual observation probabilities without losing generality. This combinatorial method gives one more freedom in making different dependence-independence assumptions. By generalizing Baums auxiliary function into this framework and building up an associated objective function using the Lagrange multiplier method, it is proven that the derived training equations guarantee the maximization of the objective function. Furthermore, we show that Levinsons training equations can be easily derived as a special case in this treatment.

The generation of handwriting with delta-lognormal synergies

Abstract. This paper presents a handwriting generation model that takes advantage of the asymptotic impulse response of neuromuscular networks to produce and control complex two-dimensional synergistic movements. A parametric definition of a ballistic stroke in the context of the kinematic theory of rapid human movements is given. Two types of parameters are used: command and system parameters. The first group provides a representation of the action plan while the second takes into account the temporal properties of the neuromuscular systems executing that plan. Handwriting is described as the time superimposition of basic discontinuous strokes that results in a continuous summation of delta-lognormal velocity vectors. The model leads to trajectory reconstruction, both in the spatial and in the kinematic domain. According to this new paradigm, the angular velocity does not have to be controlled independently and continuously; it naturally emerges from the vectorial summation process. Several psychophysical phenomena related to two-dimensional movements are explained and analyzed in the context of the model: the speed/accuracy trade-offs, spatial scaling, the isochrony principle, the two-thirds power law, effector independence, etc. The overall approach also shows how basic handwriting characteristics (dimension, slant, baseline, shape, etc.) are affected and controlled using an action plan made up of virtual targets fed into a neuromuscular synergy that is governed by a delta-lognormal law.