Flávio Bortolozzi

Automatic recognition of handwritten numerical strings: a recognition and verification strategy

A modular system to recognize handwritten numerical strings is proposed. It uses a segmentation-based recognition approach and a recognition and verification strategy. The approach combines the outputs from different levels such as segmentation, recognition, and postprocessing in a probabilistic model. A new verification scheme which contains two verifiers to deal with the problems of oversegmentation and undersegmentation is presented. A new feature set is also introduced to feed the oversegmentation verifier. A postprocessor based on a deterministic automaton is used and the global decision module makes an accept/reject decision. Finally, experimental results on two databases are presented: numerical amounts on Brazilian bank checks and NIST SD19. The latter aims at validating the concept of modular system and showing the robustness of the system using a well-known database.

Off-line signature verification using HMM for random, simple and skilled forgeries

The problem of signature verification is in theory a pattern recognition task used to discriminate two classes, original and forgery signatures. Even after many efforts in order to develop new verification techniques for static signature verification, the influence of the forgery types has not been extensively studied. This paper reports the contribution to signature verification considering different forgery types in an HMM framework. The experiments have shown that the error rates of the simple and random forgery signatures are very closed. This reflects the real applications in which the simple forgeries represent the principal fraudulent case. In addition, the experiments show promising results in skilled forgery verification by using simple static and pseudodynamic features.

A comparison of SVM and HMM classifiers in the off-line signature verification

The SVM is a new classification technique in the field of statistical learning theory which has been applied with success in pattern recognition applications like face and speaker recognition, while the HMM has been found to be a powerful statistical technique which is applied to handwriting recognition and signature verification. This paper reports on a comparison of the two classifiers in off-line signature verification. For this purpose, an appropriate learning and testing protocol was created to observe the capability of the classifiers to absorb intrapersonal variability and highlight interpersonal similarity using random, simple and simulated forgeries.

A METHODOLOGY FOR FEATURE SELECTION USING MULTIOBJECTIVE GENETIC ALGORITHMS FOR HANDWRITTEN DIGIT STRING RECOGNITION

In this paper a methodology for feature selection for the handwritten digit string recognition is proposed. Its novelty lies in the use of a multiobjective genetic algorithm where sensitivity analysis and neural network are employed to allow the use of a representative database to evaluate fitness and the use of a validation database to identify the subsets of selected features that provide a good generalization. Some advantages of this approach include the ability to accommodate multiple criteria such as number of features and accuracy of the classifier, as well as the capacity to deal with huge databases in order to adequately represent the pattern recognition problem. Comprehensive experiments on the NIST SD19 demonstrate the feasibility of the proposed methodology.

Unsupervised feature selection using multi-objective genetic algorithms for handwritten word recognition

In this paper a methodology for feature selection in unsupervisedlearning is proposed. It makes use of a multi-objectivegenetic algorithm where the minimization of thenumber of features and a validity index that measures thequality of clusters have been used to guide the search towardsthe more discriminant features and the best numberof clusters. The proposed strategy is evaluated usingtwo synthetic data sets and then it is applied to handwrittenmonth word recognition. Comprehensive experimentsdemonstrate the feasibility and efficiency of the proposedmethodology.

Feature selection using multi-objective genetic algorithms for handwritten digit recognition

Discusses the use of genetic algorithms for feature selection for handwriting recognition. Its novelty lies in the use of multi-objective genetic algorithms where sensitivity analysis and neural networks are employed to allow the use of a representative database to evaluate fitness and the use of a validation database to identify the subsets of selected features that provide a good generalization. Comprehensive experiments on the NIST database confirm the effectiveness of the proposed strategy.

An off-line signature verification method based on the questioned document expert's approach and a neural network classifier

In an off-line signature verification method based on personal models, an important issue is the number of genuine samples required to train the writers model. In a real application, we are usually quite limited in the number of samples we can use for training [Cha, S., 2001, Baltzakis, H. et al., 2001, Yingyong, Q. et al., 1994]. Classifiers like the neural network [Baltzakis, H. et al., 2001], the hidden Markov model [Justino, E.J.R. et al., 2001] and the support vector machine [Justino, E.J.R. et al., 2003] need a substantial number of samples to produce a robust model in the training phase. This paper reports on a global method based on only two classes of models, the genuine signature and the forgery. The main objective of this method is to reduce the number of signature samples required by each writer in the training phase. For this purpose, a set of graphometric features and a neural network (NN) classifier are used.

The interpersonal and intrapersonal variability influences on off-line signature verification using HMM

Off-line signature verification rests on the hypothesis that each writer has similarity among signature samples, with small distortion and scale variability. This kind of distortion represents intrapersonal variability. This paper reports interpersonal and intrapersonal variability influences in a software approach based on a hidden Markov model (HMM) classifier. The experiments have shown error rate variability considering different forgery types, random, simple and skilled. The mathematical approach and resulting software also report considerations in a real application problem.

Multi-objective genetic algorithms to create ensemble of classifiers

Feature selection for ensembles has shown to be an effective strategy for ensemble creation due to its ability of producing good subsets of features, which make the classifiers of the ensemble disagree on difficult cases. In this paper we present an ensemble feature selection approach based on a hierarchical multi-objective genetic algorithm. The algorithm operates in two levels. Firstly, it performs feature selection in order to generate a set of classifiers and then it chooses the best team of classifiers. In order to show its robustness, the method is evaluated in two different contexts: supervised and unsupervised feature selection. In the former, we have considered the problem of handwritten digit recognition while in the latter, we took into account the problem of handwritten month word recognition. Experiments and comparisons with classical methods, such as Bagging and Boosting, demonstrated that the proposed methodology brings compelling improvements when classifiers have to work with very low error rates.

Feature subset selection using genetic algorithms for handwritten digit recognition

Two approaches using genetic algorithms for feature subset selection are compared. The first approach considers a simple genetic algorithm (SGA) while the second one takes into account an iterative genetic algorithm (IGA) which is claimed to converge faster than SGA. Initially, we present an overview of the system to be optimized and the methodology applied in the experiments as well. Next, we discuss the advantages and drawbacks of each approach based on experiments carried out on NIST SD19. Finally, we conclude that the IGA converges faster than the SGA, however, the SGA seems more suitable for our problem.