Rafal Doroz

Dynamic signature recognition based on velocity changes of some features

Dynamic signature analysis allows us to register individuals and their hidden human behaviour. This paper presents a stroke-based approach to dynamic analysis of signature. Individual features can be identified by finding the discrete signature points like x,y-coordinates, pressure, time and pen velocity. Between signatures, the correlation measure is determined. The dynamic features are extracted from authentic and forged signatures. Experimental results show that measurement of dynamic features (velocity changes) contains important information and offers a high level of accuracy for signature verification in comparison with the results without such measurements, which will be explained in the following parts of the paper.

The k-NN classifier and self-adaptive Hotelling data reduction technique in handwritten signatures recognition

The paper proposes a novel signature verification concept. This new approach uses appropriate similarity coefficients to evaluate the associations between the signature features. This association, called the new composed feature, enables the calculation of a new form of similarity between objects. The most important advantage of the proposed solution is case-by-case matching of similarity coefficients to a signature features, which can be utilized to assess whether a given signature is genuine or forged. The procedure, as described, has been repeated for each person presented in a signatures database. In the verification stage, a two-class classifier recognizes genuine and forged signatures. In this paper, a broad range of classifiers are evaluated. These classifiers all operate on features observed and computed during the data preparation stage. The set of signature composed features of a given person can be reduced what decrease verification error. Such a phenomenon does not occur for the raw features. The approach proposed was tested in a practical environment, with handwritten signatures used as the objects to be compared. The high level of signature recognition obtained confirms that the proposed methodology is efficient and that it can be adapted to accommodate as yet unknown features. The approach proposed can be incorporated into biometric systems.

A new signature similarity measure

The paper presents a new signature similarity measure and new efficient method of recognizing handwritten signatures. Each signature is represented as a set of features such as coordinates of signature points, pen pressure, and speed of writing. Proposed approach consists in dividing signature into windows and calculating similarity values between individual windows. The influence of the size of windows and their location in a signature has been analysed. Additionally, the influence of individual features on the signature similarity value has been examined.

Method of signature recognition with the use of the mean differences

The paper presents a new method of recognizing handwritten signatures, based on the mean differences, which has been modified appropriately. The modification proposed by the authors consists in dividing signatures into windows and calculating similarity values between individual windows. Each signature is represented as a set of features with specific values. Coordinates of signature points, pen pressure, and speed of writing have been accepted as signature features. The influence of the size of windows and their position in a signature have been analysed within the study. Additionally, the influence of individual features on the signature similarity value has been examined.

The New Method of Signature Recognition Based on Least Squares Contour Alignment

The paper presents a new method of signature recognition based on least squares contour alignment. During the study six features of signatures were examined, such as: X, Y , P, V x, V y, V p. On the basis of the analyzed features of each signature two-dimensional graphs were created. Values of successive elements of any features of a signature, were taken as coordinates of points on the chart. Then, the chart created in such a way was treated as a contour and compared each other. In the study, usefulness of individual features was also evaluated.

A Method of Lip Print Recognition Based on Sections Comparison

This paper presents a method for recognition lip print images. The presented method is based on the analysis and comparison of the features extracted from lip print images. These features are the sections that represent the lines located on the lips. Sections were extracted using the Hough transform and an algorithm for searching for the sections lying on straight lines. The coefficient of similarity of average differences was used as the measure of the similarity between the sections. This coefficient was modified to take account of section features such as: the length, the angle of inclination in relation to the X axis, and the location of the midpoint of the section. The effect of the length of the analysed sections on the results of the classification was also determined during the studies.

On-Line Signature Recognition Based on an Analysis of Dynamic Feature

The paper presents a new method of signature recognition. The method consists in the division of a set containing all the points of a signature into subsets. Signature points are assigned to a given subset on the basis of an analysis of dynamic feature values registered in these points. The similarity of signatures is evaluated by determining the similarity between corresponding subsets in the signatures being compared. In the study, usefulness of individual features was also evaluated.

Handwritten Signature Recognition with Adaptive Selection of Behavioral Features

The presented work focuses on the method of handwritten signature recognition, which takes into consideration a lack of repetition of the signature features. Up till now signature recognition methods based only on signature features selection. Proposed approach allows to determine both the most useful features and methods which these features should be analyzed. In the developed method different features and similarity measures can be freely selected. Additionally, selected features and similarity measures can be different for every person.

Self-adaptive Biometric Classifier Working on the Reduced Dataset

The paper presents a method of object recognition by means of a reduced data set. These data are specially prepared. The proposed method was also compared with two other well-known data reduction techniques, Principal Component Analysis (PCA) and Singular Value Decomposition (SVD). Objects can mostly be described through many features but these features can have different discriminant powers. The Hotellings statistical method, allows determining the best discriminatory features and similarity measures which can be simultaneously selected.

Using a Probabilistic Neural Network for lip-based biometric verification

In classical recognition techniques only raw features of objects are employed. Our approach allows use the composed features so called Sim coefficients and landmarks which determine the area where biometric features should be searched. Biometric composed features are associated with appropriate similarity coefficients. Such approach brings significant advantages recognition level of objects is higher compared to method based on the raw data. In this paper, a novel and effective lip-based biometric recognition approach with the Probabilistic Neural Network (PNN) is proposed. Lip based recognition has been less developed than the recognition of other human physical attributes such as the fingerprint, voice patterns, blood vessel patterns, or the face. For this reason, achieved results on this field are still improved and new recognition techniques are searched. Results achieved by PNN were improved by the Particle Swarm Optimization (PSO) technique.In the first step, lip area is restricted to a Region Of Interest (ROI) and in the second step, features extracted from ROI are specifically modeled by dedicated image processing algorithms. Extracted lip features are then an input data of neural network. All experiments were confirmed in the ten-fold cross validation fashion on three diverse datasets, Multi-PIE Face Dataset, PUT database and our own faces dataset. Obtained in researches result show that proposed approach achieves an average classification accuracy of 86.95%, 87.14%, and 87.26%, on these three datasets, respectively. Announced results were verified in the comparative studies and confirm the efficacy of the proposed lip based biometrics learned by PSO technique. We proposed a novel biometric system based on lip geometrical features measurements.Each lip feature is paired with a similarity measure and form a composed feature.The set of the most discriminative lip composed features is determined.Probabilistic Neural Network classifier is used for lip verification. Display Omitted