Showing papers on "Signature recognition published in 1993"

A complexity measure of handwritten curves: modeling of dynamic signature forgery

Abstract: It is generally accepted that highly unstable and easily imitated signatures are among the main causes of deterioration in handwritten signature verification system performance. The authors attempt to estimate, quantitatively and a priori from the coordinates sampled during its execution, the difficulty that could be experienced by a typical imitator in reproducing both visually and dynamically a signature. A functional model of what a typical imitator must do to copy dynamically any signature is derived. A specific difficulty coefficient is then numerically estimated for a given signature. Experimentation geared specifically to signature imitation demonstrates the effectiveness of the model. The ranking of the tested signatures given by the difficulty coefficient is compared to three different sources: the opinions of the imitators themselves, the ones of an expert document examiner, and the ranking given by a specific pattern recognition algorithm. An example of application is also given. >

Sophisticated topology of hidden Markov models for cursive script recognition

Abstract: The paper describes an adaptation of hidden Markov models (HMM) to automatic recognition of unrestricted handwritten words. Many interesting details of a 50,000 vocabulary recognition system for US city names are described. This system includes feature extraction, classification, estimation of model parameters, and word recognition. The feature extraction module transforms a binary image to a sequence of feature vectors. The classification module consists of a transformation based on linear discriminant analysis and Gaussian soft-decision vector quantizers which transform feature vectors into sets of symbols and associated likelihoods. Symbols and likelihoods form the input to both HMM training and recognition. HMM training performed in several successive steps requires only a small amount of gestalt labeled data on the level of characters for initialization. HMM recognition based on the Viterbi algorithm runs on subsets of the whole vocabulary. >

On speaker-independent, speaker-dependent, and speaker-adaptive speech recognition

Abstract: The DARPA Resource Management task is used as a domain for investigating the performance of speaker-independent, speaker-dependent, and speaker-adaptive speech recognition. The error rate of the speaker-independent recognition system, SPHINX, was reduced substantially by incorporating between-word triphone models additional dynamic features, and sex-dependent, semicontinuous hidden Markov models. The error rate for speaker-independent recognition was 4.3%. On speaker-dependent data, the error rate was further reduced to 2.6-1.4% with 600-2400 training sentences for each speaker. Using speaker-independent models, the authors studied speaker-adaptive recognition. Both codebooks and output distributions were considered for adaptation. It was found that speaker-adaptive systems outperform both speaker-independent and speaker-dependent systems, suggesting that the most effective system is one that begins with speaker-independent training and continues to adapt to users. >

Strategies for handwritten words recognition using hidden Markov models

Abstract: Several approaches for the application of hidden Markov models to the recognition of handwritten words are described. All approaches share the same description of words through strings of symbols. They differ with respect to the size of the vocabulary which has to be recognized. The authors distinguish between two cases: where the vocabulary is small and constant, and where the vocabulary is limited but dynamic in the sense that it is a varying subset of an open one. The authors also describe an application of hidden Markov models to the representation of contextual knowledge and propose some strategies to reject unreliable word interpretations, in particular when the word corresponding to the image is not guaranteed to belong to the lexicon. >

A 1-D, sequence decomposition based, autoregressive hidden Markov model for dynamic signature identification and verification

Abstract: A new model for use in writer identification and verification is presented. The signature, represented by a one-dimensional (1-D) spatial stochastic sequence, is decomposed into pseudo-stationary segments; a characterization which allows descriptions of abrupt and gradual changes in the contours. An autoregressive hidden Markov model is employed to describe the evolution of such changes. An experimental study is presented which demonstrates the model's effectiveness. >

Connectionist architectural learning for high performance character and speech recognition

Abstract: The authors applied an automatic structure optimization (ASO) algorithm to the optimization of multistate time-delay neural networks (MSTDNNs), an extension of the TDNN. These networks allow the recognition of sequences of ordered events that have to be observed jointly. For example, in many speech recognition systems the recognition of words is decomposed into the recognition of sequences of phonemes or phonemelike units. In handwritten character recognition the recognition of characters can be decomposed into the joined recognition of characteristic strokes, etc. The combination of the proposed ASO algorithm with the MSTDNN was applied successfully to speech recognition and handwritten character recognition tasks with varying amounts of training data. >

Evaluation of character recognition systems

Abstract: Eleven different Census Optical Character Recognition Systems systems are evaluated using correlations between the answers of different systems, comparing the decrease in error rate as a function of confidence of recognition, and comparing the writer dependence of recognition. This comparison shows that methods that use different algorithms for feature extraction and recognition perform with very high levels of correlation. >

A study on feature extraction using a fuzzy net for off-line signature recognition

Abstract: This paper presents a method of off-line signature recognition using feature strokes and a fuzzy net. Each stroke has features of signatures, and the fuzzy net proposed by the authors can extract personal characteristics from the strokes. An experiment is done to show the feasibility of the new method.

Visual keyword recognition using hidden Markov models

Abstract: An algorithm for robust machine recognition of keywords embedded in a poorly printed document is presented. For each keyword, two statistical models, named hidden Markov models (HMMs), are created for representing the actual keyword and all the other extraneous words, respectively. Dynamic programming is then used for matching an unknown input word with the two models and making a maximum likelihood decision. Both the 1D and pseudo-2D HMM approaches are proposed and tested. The 2D models are shown to be general enough in characterizing printed words efficiently. These pseudo-2D HMMs facilitate an elastic matching property in both the horizontal and vertical directions, which makes the recognizer not only independent of size and slant but also tolerant of highly deformed and noisy words. The system is evaluated on a synthetically created database. Recognition accuracy of 99% is achieved when words in testing and training sets are in the same font size, and 96% is achieved when they are in different sizes. In the latter case, the 1D HMM achieves only a 70% accuracy rate. >

Optimal design of reference models using simulated annealing combined with an improved LVQ3

Abstract: For the recognition of large-set handwritten characters, classification methods based on pattern matching have been commonly used, and good reference models play a very important role in achieving high performance in these methods. Learning vector quantization (LVQ) has been studied intensively to generate good reference models in speech recognition since 1986. However, the design of reference models based on LVQ has several drawbacks for the recognition of large-set handwritten characters. To cope with these, the authors propose a method for the optimal design of reference models using simulated annealing combined with an improved LVQ3 for the recognition of large-set handwritten characters. Experimental results reveal that the proposed method is superior to the conventional method based on averaging and other LVQ-based methods. >

2-stage character recognition by detection and correction of erroneously-identified characters

Abstract: The authors propose a two-stage text recognition system with high recognition rate. In the first stage, characters recognized as different recognition results by two matching modules are rejected, since they are recognized incorrectly by at least one of the two matching modules. The rejected characters are then processed by a Markov language model in the second stage. Since most of the input characters are recognized in the first stage, the computation cost of the language model is low and the recognition rate of the language model is excellent. By using this erroneously-identified text recognition approach, a system with high character recognition accuracy can be achieved. Our text recognition system can be extended to a multiple-stage recognition system to further improve the recognition accuracy. In each stage, various matching modules can be used. The recognized result of an input character will be accepted only when all matching modules produce the same result. Rejected characters will be fed into the next stage for further processing. >

Real time signature recognition: A method for personal identification

Abstract: A methodology for the identification of individuals is presented. Using the geometrical, dynamic, and graphological characteristics of a set of signatures, the proposed algorithm generates a reference vector. In the validation phase the vector of the signature under evaluation is compared, in real time, with the reference vector for acceptance or rejection. >

A system for bankchecks processing

Abstract: A complete system for automatic processing of bankchecks is presented. It consists of several modules, some of them work in parallel, others follow a serial scheme. They are devoted to machine-printed numeral recognition, layout processing, handwritten digit amount recognition, handwritten worded amount recognition, amount validation, and signature verification. Integrated approaches and crosscheck strategies are used to meet the severe constraints required by the application. >

A hybrid system for handprinted word recognition

Abstract: The authors describe an alternative approach to handprinted word recognition using a hybrid of procedural and connectionist techniques. They utilize two connectionist components, which are to concurrently make recognition and segmentation hypotheses, and to perform refined recognition of segmented characters. Both networks are governed by a procedural controller which incorporates systematic domain knowledge and procedural algorithms to guide recognition. A recognition method is presented whereby an image is processed over time by a spatiotemporal connectionist network. The scheme offers several attractive features including shift-invariance and retention of local spatial relationships along the dimensions being temporalized, a reduction in the number of free parameters, and the ability to process arbitrarily long images. Recognition results on a set of real-world isolated zip code digits are comparable to the best reported to date with a 96.0% recognition rate. A pilot implementation of the complete system, and results on overlapping and touching pairs of zip code digits are reported. >

Dynamic Character Recognition Using Hidden Markov Models

Abstract: Hidden Markov Model theory is an extension of the Markov Model process. It has found uses in such areas as speech recognition, target tracking and word recognition. One area which has received little in the way of research interest, is the use of Hidden Markov Models in character recognition. In this paper the application of Hidden Markov Model theory to dynamic character recognition is investigated. The basic Hidden Markov Model theory is reviewed, and so are the algorithms associated with it. A quick overview of the dynamic character recognition process is considered. Then three types of describing characters are considered, position, inclination angle of small vectors and stroke directional encoding using a Freeman code. A system using each of these descriptions, using Hidden Markov Models in the comparison stage, is described. It is recognised that experiments using the different encoding systems have to be carried out to check the validity of this chosen method.

Hidden Markov model with noise-adaptive codebook for noisy speech recognition

Abstract: At present, many researchers turn their attention to automatic speech recognition in noisy environments. The main reason is that speech recognizers trained in quiet conditions but operated in a noisy environment usually have poor performance. We use discrete the hidden Markov model with noise-adaptive codebook for noisy speech recognition. The goal is to improve the recognition accuracy of recognizer in a noisy environment. When testing with noise-contaminated utterances at an SNR of 20 dB, the system has a recognition accuracy of 35%, by using the noise-adaptive codebook, the system has an accuracy of up to 90%. >

Fuzzy arithmetic based power harmonics signature recognition

Abstract: The aim of this paper is to analyse the fundamental differences between patterns of power harmonics generated by various common loads in a distribution system. A method to identify the harmonics distribution patterns of each type of load by fuzzy sets is described. Furthermore, power harmonics signature recognition by solving a set of fuzzy linear equations is presented. Such analysis leads to the definition of a fuzzy arithmetic based parameter that can truly reveal the degree of seriousness of harmonic pollution at any utilisation point of electric power.

Rotating machines fault identification using back-propagation artificial neural network

Abstract: The authors describe a newly developed technique and system for real-time monitoring and identification of machine condition The machine health identification process is mainly based on recognition and comparison of the real-time captured vibrational signature to its standard signature The features extraction of the vibrational signature uses the technique of higher order spectra analysis These signature features will then input to an artificial neural network (ANN) for recognition and identification The output of the neural network was trained to generate a healthy index that indicates the machine health condition A DSP56001 based digital signal processor is employed to implement the signal processing algorithms together with the artificial neural networks for real-time operation The authors briefly describe the methodology, system and vibrational signature recognition Very encouraging and successful results have been obtained and are presented and discussed >

Analysis on the efficiency of pattern recognition layers using information measures

Abstract: This paper describes a method for measuring the efficiency of a sequence of each layer in layered pattern recognition. Considering pattern recognition as nonlinear transforms of input patterns, we claim that the efficient layers reduce variations within the classes while maintaining separability among the classes. In order to quantify these values, we define two measures, named as inter-class separability and intra-class variation, based on entropy. We propose a method to analyze the efficiency of pattern recognition layers using these measures. Applying this method to a handwritten digit recognition system, we can successfully identify inefficient layers.