Off-line signature verification using classifier ensembles and flexible grid features

[摘要] ENGLISH ABSTRACT: In this study we investigate the feasibility of combining an ensemble of eight continuous base classifiers for the purpose of off-line signature verification. This work is mainly inspired by the process of cheque authentication within the banking environment. Each base classifier is constructed by utilising a specific local feature, in conjunction with aspecific writer-dependent signature modelling technique. The local features considered arepixel density, gravity centre distance, orientation and predominant slant. The modellingtechniques considered are dynamic time warping and discrete observation hidden Markov models. In this work we focus on the detection of high quality (skilled) forgeries.Feature extraction is achieved by superimposing a grid with predefined resolution onto a signature image, whereafter a single local feature is extracted from each signature sub-image corresponding to a specific grid cell. After encoding the signature image into a matrix of local features, each column within said matrix represents a feature vector (observation) within a feature set (observation sequence). In this work we propose a novel flexible grid-based feature extraction technique and show that it outperforms existing rigid grid-based techniques.The performance of each continuous classifier is depicted by a receiver operating characteristic (ROC) curve, where each point in ROC-space represents the true positive rate and false positive rate of a threshold-specific discrete classifier. The objective is therefore to develope a combined classifier for which the area-under-curve (AUC) is maximised -or for which the equal error rate (EER) is minimised.Two disjoint data sets, in conjunction with a cross-validation protocol, are used for model optimisation and model evaluation. This protocol avoids possible model overfitting,and also scrutinises the generalisation potential of each classifier. During the first optimisation stage, the grid configuration which maximises proficiency is determined for each base classifier. During the second optimisation stage, the most proficient ensemble of optimised base classifiers is determined for several classifier fusion strategies. During both optimisation stages only the optimisation data set is utilised. During evaluation, each optimal classifier ensemble is combined using a specific fusion strategy, and retrained and tested on the separate evaluation data set. We show that the performance of the optimal combined classifiers is significantly better than that of the optimal individual base classifiers.Both score-based and decision-based fusion strategies are investigated, which includes a novel extension to an existing decision-based fusion strategy. The existing strategy is based on ROC-statistics of the base classifiers and maximum likelihood estimation. We show that the proposed elitist maximum attainable ROC-based strategy outperforms the existing one.

[发布机构] Stellenbosch University