Writer Verification Research Articles

Texture-based descriptors for writer identification and verification

In this work, we discuss the use of texture descriptors to perform writer verification and identification. We use a classification scheme based on dissimilarity representation, which has been successfully applied to verification problems. Besides assessing two texture descriptors (local binary patterns and local phase quantization), we also address important issues related to the dissimilarity representation, such as the impact of the number of references used for verification and identification, how the framework performs on the problem of writer identification, and how the dissimilarity-based approach compares to other feature-based strategies. In order to meet these objectives, we carry out experiments on two different datasets, the Brazilian forensic letters database and the IAM database. Through a series of comprehensive experiments, we show that both LBP- and LPQ-based classifiers are able to surpass previous results reported in the literature for the verification problem by about 5 percentage points. For the identification problem, the proposed approach using LPQ features is able to achieve accuracies of 96.7% and 99.2% on the BFL and IAM and databases respectively.

Text-independent and Character-dependent Online Writer Verification

Text-independent and Character-dependent Online Writer Verification

State of the art in off-line writer identification of handwritten text and survey of writer identification of Arabic text

In this paper we present the state of the art in writer identification and verification of handwritten text. In addition, a special and extensive survey of writer identification and verification of Arabic handwritten text is also included. Different feature extraction techniques are addressed showing the different research groups’ efforts as well as individual efforts. The different classification approaches, e.g. minimum distance classifiers and statistical classifiers, used for identification by writer and verification by different groups and individuals are presented. Identification results of surveyed publications are investigated and tabulated for ease of reference. Examples of writer identification and verification of others languages are addressed. An extensive survey of databases used in writer identification and verification for Latin and Arabic text is presented. Conclusions relevant to writer identification of Arabic text are discussed and future directions stated. Key words: Writer identification, writer verification, handwritten database, feature extraction, handwriting analysis, distance measures, literature survey.

AN OFF-LINE TEXT-INDEPENDENT PERSIAN WRITER IDENTIFICATION METHOD

The behavioral-biometrics methods of writer identification and verification have been considered as a research topic for many years. However, many writer identification and verification methods have been designed based on English handwriting properties, but because of many differences between English and Persian handwriting and the challenges facing Persian handwriting analysis, designing such methods has many interests in Persian yet. In this paper, we have presented a fully text-independent and texture based method for identifying writers of Persian handwritten documents. As a result of special properties of Persian handwriting, a modified version of Gabor filter that is called Extended Gabor (XGabor) filter has been used to extract the features. An MLP (Multi Layer Perceptron (Node)) neural network and a K-NN classifier have been employed to classify the extracted features. In the evaluation phase, an exhaustive database of Persian handwritten documents was prepared and the method applied on. The experimental results showed that the accuracy of proposed method is about 97% and it is competitive with others. We believe that the proposed method may be extended to identify writers in other languages by adjusting some parameters.

Writer verification using texture-based features

In this work, we propose a writer verification system that takes into account texture-based features and dissimilarity representation. Textures of the handwritings are created based on the inherent properties of the writer. Independent of the writing style, the proposed method reduces the spaces between lines, words, and characters, producing a texture that keeps the main features thus avoiding the complexity of segmentation. We also address an important issue of verification system, i.e., the number of writers used for training. Our experiments show that the number of writers do not have an important impact on the overall error rate, but it has an important role in reducing the false acceptance of the verification system. We show that the false acceptance decreases as the number of writers increases. Finally, the ROC curves produced by different classifiers trained with different texture descriptors are combined using the maximum likelihood analysis, producing a ROC combined classifier. A set of experiments on a database composed of 315 writers show the efficiency of the texture-based features and the ROC combination scheme. Experimental results report an overall error rate of about 4%. This performance compares to the state of the art. Besides, the combination scheme is able to considerably reduce the false-positive rates while maintaining the same true-positive rates.

A statistical handwriting model for style-preserving and variable character synthesis

Synthesizing handwritten-style characters is an interesting issue in today’s handwriting analysis field. The purpose of this study is to artificially generate training data, foster a deep understanding of human handwriting, and promote the use of the handwritten-style computer fonts, in which the individuality or variety of the synthesized characters is considered important. Research considering such two properties together, however, is very rare. In this paper, a handwriting model is proposed to synthesize various handwritten characters while preserving the writer’s individuality from a limited number of training data, using a statistical approach. The proposed model is verified in single- and multiple-stroke characters, such as Arabic numbers, small English letters, and Japanese Kanji letters. Synthesized characters are evaluated in three ways. First, they are analyzed visually using the selected samples, and the relationship between the training and synthesized characters is explained. Second, the personalities and varieties of all the data are evaluated using a conventional writer verification method. Third, a questionnaire is developed and administered to evaluate the subjective responses of the users regarding the personal styles of the synthesized characters. The results prove that the proposed model stably synthesizes personalized characters by being invariant to the number of training data, whereas the variety increases gradually as the data increase.

Towards robust writer verification by correcting unnatural slant

Slant is a salient feature of Western handwriting and it is considered to be an important writer-specific feature. In disguised handwriting however, slant is often modified. It was tested whether slant is indeed an important factor and it was tested whether the distorting effect of deliberate slant change can be countered by a simple shear transform. This was done in two off-line writer verification experiments in image processing conditions of slant elimination and slant correction. The experiments were performed using three features based on statistical pattern recognition, including the state-of-the-art features Fraglets and Hinge. A new public dataset was created and used, containing natural and slanted handwriting by 47 writers. A striking result is that the average natural slant value is much less important for biometric systems than is usually assumed: eliminating slant yields just a 1–5% performance loss. A second result is that the effects of deliberate slant change cannot be fully countered by a simple shear transform: it raises performance on the distorted handwriting from 53–68% to 64–90%, but this is still lower than normal operation on natural handwriting: 97–100%.

EXPERIMENTAL ANALYSIS OF INDIVIDUALITY OF JAPANESE HANDWRITING

A handwriting examination to determine the writer (writer verification and writer identification) is based upon the hypothesis that each person has characteristic handwriting that is distinct from the handwriting of other individuals. This hypothesis has been accepted empirically through many case studies. However, this hypothesis must be established with scientific and quantitative rigor in order to increase its admissibility as forensic evidence. This paper describes the results of a quantitative investigation into individuality of Japanese handwriting. The authors investigated the individuality (consistency and discriminability) of normal Japanese handwriting using variation entropy and writer verification algorithms. We also compared these results with the analysis results of Japanese signatures that we investigated previously. The authors discuss the differences of individuality between normal handwriting and signatures. Individuality of normal handwriting becomes noticeable as the number of strokes increases, and varies with the complexity of the character class. Although individuality of both normal handwriting and signatures also depends on the writer, this is more noticeable for signatures. It is important that these facts are considered in actual forensic analysis of Japanese handwriting.

筆跡鑑定の知見に基づく特性値を用いたオンライン筆者照合

This paper investigates writer verification using feature parameters based on the knowledge of document examiners, which are automatically extracted from handwritten kanji characters on a digitizing tablet. Criteria of feature selection using the evaluation measure that is obtained by modifying the measure of decidability, d-prime, is established and the criteria are applied to the evaluation measures that are calculated from learning samples. Then two classifiers based on the frequency distribution of deviations of the selected features are proposed and its design method using learning samples is showed. The effectiveness of the proposed method is evaluated by verification experiments with the database including skilled forgeries. The experimental results show that the proposed methods are effective in writer verification.

A writer identification and verification system using HMM based recognizers

A writer identification and verification system using HMM based recognizers

A segmentation-free biometric writer verification method based on continuous dynamic programming

By introducing the continuous dynamic programming (CDP) algorithm developed by Oka [Oka, R., 1998. Spotting method for classification of real world data. The Comput. J. 41 (8), 559–565], we have developed a new segmentation-free, text-independent biometric writer verification method improving the average correct acceptance rate and the average correct rejection rate of forgeries to a practically useful level of about 95% and 100%, respectively, outperforming the only other biometric text-independent writer verification method of Yamazaki and Komatsu [Yamazaki, Y., Komatsu, N., 1999. Extraction of personal features from stroke shape, writing pressure and pen inclination in ordinary characters. In: Proc. 5th Internat. Conf. on Document Analysis and Recognition (ICDAR1999), pp. 426–429] based on a P-type Fourier descriptor-based learning vector quantisation scheme. To implement a text-independent, DP-based biometric writer verification, our spotting-enabling CDP algorithm has not only successfully traced and tracked an optimal microscopic dynamic features of real-time writing processes of either scanned characters or images of relevant individuals but also has implemented extension to a more secure text-independent writer verification method by exploiting the built-in spotting function of the CDP method, which is capable of ignoring inputs outside the task domain. This is so because a text-independent sample can be selected from any of many possible candidates located at an arbitrary location within the specified long reference sample. We have demonstrated the applicability of the method not only to Japanese text but also to English text that tends to assess the language independence of the method.

Handwritten Document Analysis for Automatic Writer Recognition

In this paper, we show that both the writer identification and the writer verification tasks can be carried out using local features such as graphemes extracted from the segmentation of cursive handwriting. We thus enlarge the scope of the possible use of these two tasks which have been, up to now, mainly evaluated on script handwritings. A textual based Information Retrieval model is used for the writer identification stage. This allows the use of a particular feature space based on feature frequencies. Image queries are handwritten documents projected in this feature space. The approach achieves 95% correct identification on the PSI_DataBase and 86% on the IAM_DataBase. Then writer hypothesis retrieved are analysed during a verification phase. We call upon a mutual information criterion to verify that two documents may have been produced by the same writer or not. Hypothesis testing is used for this purpose. The proposed method is first scaled on the PSI_DataBase then evaluated on the IAM_DataBase. On both databases, similar performance of nearly 96% correct verification is reported, thus making the approach general and very promising for large scale applications in the domain of handwritten document querying and writer verification.

A writer identification and verification system

In this paper, we show that both the writer identification and the writer verification tasks can be carried out using local features such as graphemes extracted from the segmentation of cursive handwriting. We thus enlarge the scope of the possible use of these two tasks which have been, up to now, mainly evaluated on script handwritings. A textual based Information Retrieval model is used for the writer identification stage. This allows the use of a particular feature space based on feature frequencies. Image queries are handwritten documents projected in this feature space. The approach achieves 95% correct identification on the PSI_ DataBase and 86% on the IAM_ DataBase. Then writer hypothesis retrieved are analysed during a verification phase. We call upon a mutual information criterion to verify that two documents may have been produced by the same writer or not. Hypothesis testing is used for this purpose. The proposed method is first scaled on the PSI_ DataBase then evaluated on the IAM_ DataBase. On both databases, similar performance of nearly 96% correct verification is reported, thus making the approach general and very promising for large scale applications in the domain of handwritten document querying and writer verification.

Text-indicated Writer Verification

Text-indicated Writer Verification

自己想起型ニューラルネットワークによる筆者識別と照倉

自己想起型ニューラルネットワークによる筆者識別と照倉

Fusion of correlated decisions for writer verification

A fusion approach is proposed for improving the efficiency of writer verification systems. A short handwritten sentence is employed for this purpose. Each word of the sentence is used to tackle an individual verification problem. Then, the word-level (local) decisions are fused in order to obtain a more reliable global decision by means of the Neyman–Pearson approach. The correlation of the local decisions is extensively studied and incorporated in the fusion procedure by means of the Bahadur–Lazarsfeld expansion series. A database containing 4800 sentences is employed to validate the performance of the method. The improvement in verification performance is due to both the fusion procedure applied and the full discretion of the writer to choose his own secret word.

ストロークの方向性に着目したテキスト独立型筆者照合

ストロークの方向性に着目したテキスト独立型筆者照合

Fusion of correlated decisions for writer verification

Abstract A fusion approach is proposed for improving the efficiency of writer verification systems. A short handwritten sentence is employed for this purpose. Each word of the sentence is used to tackle an individual verification problem. Then, the word-level (local) decisions are fused in order to obtain a more reliable global decision by means of the Neyman–Pearson approach. The correlation of the local decisions is extensively studied and incorporated in the fusion procedure by means of the Bahadur–Lazarsfeld expansion series. A database containing 4800 sentences is employed to validate the performance of the method. The improvement in verification performance is due to both the fusion procedure applied and the full discretion of the writer to choose his own secret word.

Off-line writer verification utilizing multiple neural networks

A writer verification system based on multiple neural network classifiers is described, aimed to be easily extendable. Each writer reg- isters with the system by writing a set of discrete Chinese characters. One neural network is constructed for each enrolled character class on a per-person or a per-subgroup basis. The decisions from individual net- work classifiers are combined by voting. The method has been verified to work reliably on our testing database: a verification rate above 96% is achieved on short-term data. © 1997 Society of Photo-Optical Instrumentation En- gineers. (S0091-3286(97)01211-7)

Off-line writer verification using ordinary characters as the object

A system of writer recognition using ordinary characters as the verification object is proposed. In the system, some optional constants, the trimming number of a modified Mahalanobis' distance, the threshold coefficient and the number of characters in the text, are determined. The leave-one-out method is proposed for determining the optional constants. The feasibility of the proposed system was examined with an experiment using a database composed of Japanese writing. The effectiveness of two types of features (the direction feature and the are feature) was also compared. Error rates as low as 0.5% were achieved in the proposed system using the direction feature.