Jean-Yves Ramel

User classification for keystroke dynamics authentication

In this paper, we propose a method to realize a classification of keystroke dynamics users before performing user authentication. The objective is to set automatically the individual parameters of the classification method for each class of users. Features are extracted from each user learning set, and then a clustering algorithm divides the user set in clusters. A set of parameters is estimated for each cluster. Authentication is then realized in a two steps process. First the users are associated to a cluster and second, the parameters of this cluster are used during the authentication step. This two steps process provides better results than system using global settings.

Detection, extraction and representation of tables

We are concerned with the extraction of tables from exchange format representations of very diverse composite documents. We put forward a flexible representation scheme for complex tables, based on a clear distinction between the physical layout of a table and its logical structure. Relying on this scheme, we develop a new method for the detection and the extraction of tables by an analysis of the graphic lines. To deal with tables that lack all or most of the graphic marks, one must focus on the regularities of the text elements alone. We propose such a method, based on a multi-level analysis of the layout of text components on a page. A general graph representation of the relative positions of blocks of text is exploited.

Document image characterization using a multiresolution analysis of the texture: application to old documents

In this article, we propose a method of characterization of images of old documents based on a texture approach. This characterization is carried out with the help of a multi-resolution study of the textures contained in the images of the document. Thus, by extracting five features linked to the frequencies and to the orientations in the different areas of a page, it is possible to extract and compare elements of high semantic level without expressing any hypothesis about the physical or logical structure of the analyzed documents. Experimentation based on segmentation, data analysis and document image retrieval tools demonstrate the performance of our propositions and the advances that they represent in terms of characterization of content of a deeply heterogeneous corpus.

User-driven page layout analysis of historical printed books

In this paper, based on the study of the specificity of historical printed books, we first explain the main error sources in classical methods used for page layout analysis. We show that each method (bottom-up and top-down) provides different types of useful information that should not be ignored, if we want to obtain both a generic method and good segmentation results. Next, we propose to use a hybrid segmentation algorithm that builds two maps: a shape map that focuses on connected components and a background map, which provides information about white areas corresponding to block separations in the page. Using this first segmentation, a classification of the extracted blocks can be achieved according to scenarios produced by the user. These scenarios are defined very simply during an interactive stage. The user is able to make processing sequences adapted to the different kinds of images he is likely to meet and according to the user needs. The proposed “user-driven approach” is capable of doing segmentation and labelling of the required user high level concepts efficiently and has achieved above 93% accurate results over different data sets tested. User feedbacks and experimental results demonstrate the effectiveness and usability of our framework mainly because the extraction rules can be defined without difficulty and parameters are not sensitive to page layout variation.

Fusion of methods for keystroke dynamic authentication

In this article, we present three methods for the keystroke dynamic authentication problem. We use in the first method, the average and the standard deviation, in the second the rhythm of striking and in the third, a comparison of the times order. After having presented these methods, we propose to realize a fusion of them. The results obtained indicate good performance of each method alone, as well as a significant improvement of performance with fusion, from 3.43% of EER for the best method alone down-to 1.8% with fusion.

Fuzzy multilevel graph embedding

Structural pattern recognition approaches offer the most expressive, convenient, powerful but computational expensive representations of underlying relational information. To benefit from mature, less expensive and efficient state-of-the-art machine learning models of statistical pattern recognition they must be mapped to a low-dimensional vector space. Our method of explicit graph embedding bridges the gap between structural and statistical pattern recognition. We extract the topological, structural and attribute information from a graph and encode numeric details by fuzzy histograms and symbolic details by crisp histograms. The histograms are concatenated to achieve a simple and straightforward embedding of graph into a low-dimensional numeric feature vector. Experimentation on standard public graph datasets shows that our method outperforms the state-of-the-art methods of graph embedding for richly attributed graphs. Highlights? We propose an explicit graph embedding method. ? We perform multilevel analysis of graph to extract global, topological/structural and attribute information. ? We use homogeneity of subgraphs in graph for extracting topological/structural details. ? We encode numeric information by fuzzy histograms and symbolic information by crisp histograms. ? Our method outperforms graph embedding methods for richly attributed graphs.

AGORA: the interactive document image analysis tool of the BVH project

In this paper, we describe how meta-data of indexation can be extracted from historical document images using an interactive process with a software called AGORA. The algorithms involved in AGORA use two maps to segment noisy images: a shape map that focuses on connected components and a background map that provides information on white areas corresponding to block separations in the page. Using a first segmentation result obtained by using these two maps, meta-data can be extracted according to scenarios produced by the users. These scenarios are defined very simply during an interactive stage. The user is able to make processing sequences adapted to the different kinds of images he is likely to meet and according to the desired meta-data. Finally, we describe different experimentations that have been done during the BVH project to test the usability and the performances of AGORA software

Comparison between 2D and 3D Local Binary Pattern Methods for Characterisation of Three-Dimensional Textures

Our purpose is to extend the Local Binary Pattern method to three dimensions and compare it with the two-dimensional model for three-dimensional texture analysis. To compare these two methods, we made classification experiments using three databases of three-dimensional texture images having different properties. The first database is a set of three-dimensional images without any distorsion or transformation, the second contains additional gaussian noise. The last one contains similar textures as the first one but with random rotations according x, y and z axis. For each of these databases, the three-dimensional Local Binary Pattern method outperforms the two-dimensional approach which has more difficulties to provide correct classifications.

Spotting Symbols in Line Drawing Images Using Graph Representations

Many methods of graphics recognition have been developed throughout the years for the recognition of pre-segmented graphics symbols but very few techniques achieved the objective of symbol spotting and recognition together in a generic case. To go one step forward through this objective, this paper presents an original solution for symbol spotting using a graph represen-tation of graphical documents. The proposed strategy has two main step. In the first step, a graph based representation of a document image is generated that includes selection of description primitives (nodes of the graph) and organisation of these features (edges). In the second step the graph is used to spot interesting parts of the image that potentially correspond to symbols. The sub-graphs associated to selected zones are then submitted to a graph matching algorithm in order to take the final decision and to recognize the class of the symbol. The experimental results obtained on different types of documents demonstrates that the system can handle different types of images without any modification.

Selection of points for on-line signature comparison

Authentication based on handwritten signature is the most accepted authentication system based on biometry because it is easy to use and because the use of signature is part of our habits. In the field of authentication by on-line signature, we present a method to reduce the amount of data to be stored for pattern comparison and that needs few processing. Many systems described in literature keep the whole signatures points even if it is not recommended, even advised against it, in order to avoid forgers to obtain a signatures pattern. The proposed method for data reduction was evaluated with respect to a method of curve comparison very often used for authentication by on-line handwritten signature: dynamic time warping (DTW). After we have presented several reduction methods of signature data, we show the results obtained with each one. In order to evaluate their efficiency, the results were compared to those obtained with the whole coarse data points of the signature.