Thierry Paquet

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.

A structural/statistical feature based vector for handwritten character recognition

This paper describes the application of structural features to the statistical recognition of handwritten characters. It has been demonstrated that a complete description of the characters, based on the combination of seven different families of features, can be achieved and that the same general-purpose structural/statistical feature based vector thus defined proves efficient and robust on different categories of handwritten characters such as digits, uppercase letters and graphemes.

Off-line handwritten word recognition using multi-stream hidden Markov models

In this paper, we present a multi-stream approach for off-line handwritten word recognition. The proposed approach combines low level feature streams namely, density based features extracted from 2 different sliding windows with different widths, and contour based features extracted from upper and lower contours. The multi-stream paradigm provides an interesting framework for the integration of multiple sources of information and is compared to the standard combination strategies namely fusion of representations and fusion of decisions. We investigate the extension of 2-stream approach to N streams (N=2,...,4) and analyze the improvement in the recognition performance. The computational cost of this extension is discussed. Significant experiments have been carried out on two publicly available word databases: IFN/ENIT benchmark database (Arabic script) and IRONOFF database (Latin script). The multi-stream framework improves the recognition performance in both cases. Using 2-stream approach, the best recognition performance is 79.8%, in the case of the Arabic script, on a 2100-word lexicon consisting of 946 Tunisian town/village names. In the case of the Latin script, the proposed approach achieves a recognition rate of 89.8% using a lexicon of 196 words.

Information retrieval based writer identification

This communication deals with the Writer Identificationtask. Our previous work has shown the interest of usingthe graphemes as features for describing the individualproperties of Handwriting. We propose here to exploit thesame feature set but using an information retrievalparadigm to describe and compare the handwritten queryto each sample of handwriting in the database. Using thistechnique the image processing stage is performed onlyonce and before the retrieval process can take place, thusleading to a significant saving in the computation of eachquery response, compared to our initial proposition. Themethod has been tested on two handwritten databases.The first one has been collected from 88 different writersat PSI Lab. while the second one contains 39 writers fromthe original correspondence of Emile Zola, a famousFrench novelist of the last 19th century. We also analyzethe proposed method when using concatenation ofgraphemes (bi and tri-gramme) as features.

Writer identification by writer's invariants

This communication deals with the problem of writer identification. If the assumption of writing individuality is true then graphical fragments that constitute it should be individual too. Therefore we propose a morphological grapheme based analysis to make writer identification. Template Matching is the core of the approach. The redundancy of the individual patterns in a writing, defined as the writers invariants, allows to compress the handwritten texts while maintaining good identification performance. Two series of tests are reported. The first series is designed to evaluate the relevance of our approach of identification on a basis of 88 writers by evaluating the influence of the text representation (with or without invariants) on the quality of the method. The method gives about 97,7% of correct identification when using large compressed samples of handwriting. The second series of tests is designed to evaluate the influence of the sample size of the writing to be identified on the quality of the method. It is shown that writer identification can reach a correct identification rate of 92,9% using only samples of 50 graphemes of each writing.

Defining writer's invariants to adapt the recognition task

Investigates the automatic reading of unconstrained omni-writer handwritten texts. This paper shows how to endow the reading system with adaptation faculties for each writers handwriting. The adaptation principles are of major importance for making robust decisions when neither simple lexical nor syntactic rules can be used, e.g. for a free lexicon or for full text recognition. The first part of this paper defines the concept of writers invariants. In the second part, we explain how the recognition system can be adapted to a particular handwriting by exploiting the graphical context defined by the writers invariants. This adaptation is guaranteed, thanks to the writers invariants, by activating interaction links over the whole text between the recognition procedures for word entities and those for letter entities.

Off-Line Multi-Script Writer Identification Using AR Coefficients

The problem of writer identification in a multi-script environment is attempted using a two-dimensional (2D) autoregressive (AR) modeling technique. Each writer is represented by a set of 2D AR model coefficients. A method to estimate AR model coefficients is proposed. This method is applied to an image of text written by a specific writer so that AR coefficients are obtained to characterize the writer. For a given sample, AR coefficients are computed and its L2 distance with each of the stored (writer) prototypes identifies the writer for the sample. The method has been tested on datasets of two different scripts, namely RIMES containing 382 French writers and ISI consisting of samples from 40 Bengali writers. Modeling of writing styles using different context patterns at different image resolution has been investigated. Experimental results show that the technique achieves results comparable with that of the previous approaches.

Document Image Segmentation Using a 2D Conditional Random Field Model

This work relates to the implementation of a 2D conditional random field model in the context of document image analysis. Our model makes it possible to take variability into account and to integrate contextual knowledge, while taking benefit from machine learning techniques. Experiments on handwritten drafts of Flaubert show that these models provide interesting solutions.

Recognition of handwritten sentences using a restricted lexicon

Abstract An off-line handwriting recognition system is described based on a particular model of handwritten words. This model includes a grapheme representation of words well suited for unconstrained segmentation. The tools devoted to this particular model are presented and applied for reading French bank checks.

On foreground — background separation in low quality document images

This paper deals with effective separation of foreground and background in low quality document images suffering from various types of degradations including scanning noise, aging effects, uneven background, or foreground, etc. The proposed algorithm shows an excellent adaptability to tackle with these problems of uneven illumination and local changes or nonuniformity in background and foreground colors. The approach is primarily designed for (not restricted to) processing of color documents but it works well in the gray scale domain too. Test document set considers samples (in color as well as in gray scale) of old historical documents including manuscripts of high importance. The data set used in this study consists of hundred images. These images are selected from different sources including image databases that had been scanned from working notebooks of famous writers who used to write with quill or pencil generating very low contrast between foreground and background. Evaluation of foreground extraction method has been judged by computing the accuracy of extracting handwritten lines and words from the test images. This evaluation shows that the proposed method can extract lines and words with accuracies of about 84% and 93%, respectively. Apart from this quantitative method, a qualitative evaluation is also presented to compare the proposed method with one popular technique for foreground/background separation in document images.