Thierry Brouard

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.

Secure Biometric Authentication with Improved Accuracy

We propose a new hybrid protocol for cryptographically secure biometric authentication. The main advantages of the proposed protocol over previous solutions can be summarised as follows: (1) potential for much better accuracy using different types of biometric signals, including behavioural ones; and (2) improved user privacy, since user identities are not transmitted at any point in the protocol execution. The new protocol takes advantage of state-of-the-art identification classifiers, which provide not only better accuracy, but also the possibility to perform authentication without knowing who the user claims to be. Cryptographic security is based on the Paillier public key encryption scheme.

Graphic Symbol Recognition Using Graph Based Signature and Bayesian Network Classifier

We present a new approach for recognition of complex graphic symbols in technical documents. Graphic symbol recognition is a well known challenge in the field of document image analysis and is at heart of most graphic recognition systems. Our method uses structural approach for symbol representation and statistical classifier for symbol recognition. In our system we represent symbols by their graph based signatures: a graphic symbol is vectorized and is converted to an attributed relational graph, which is used for computing a feature vector for the symbol. This signature corresponds to geometry and topology of the symbol. We learn a Bayesian network to encode joint probability distribution of symbol signatures and use it in a supervised learning scenario for graphic symbol recognition. We have evaluated our method on synthetically deformed and degraded images of pre-segmented 2D architectural and electronic symbols from GREC databases and have obtained encouraging recognition rates.

Optimizing Hidden Markov Models with a Genetic Algorithm

In this paper is presented the application of genetic algorithms (GAs) to the learning of hidden Markov models (HMMs). The Baum-Welch algorithm (BW), which optimizes the coefficients of a HMM, is improved by the use of a GA. The GA is able to find rapidly a good initial model compared to random generation, and this initial model is optimized further with BW. A representation and adapted genetic operators have been introduced in order to evolve matrix of probabilities. Several tests on artificial data show the interest in using a GA with BW.

Two evolutionary methods for learning Bayesian network structures

This paper describes two approaches based on evolutionary algorithms for determining Bayesian networks structures from a database of cases. One major difficulty when tackling the problem of structure learning with evolutionary strategies is to avoid the premature convergence of the population to a local optimum. In this paper, we propose two methods in order to overcome this obstacle. The first method is a hybridization of a genetic algorithm with a tabu search principle whilst the second method consists in the application of a dynamic mutation rate. For both methods, a repair operator based on the mutual information between the variables was defined to ensure the closeness of the genetic operators. Finally, we evaluate the influence of our methods over the search for known networks

A new way to use hidden Markov models for object tracking in video sequences

In this paper, we are dealing with color object tracking. We propose to use hidden Markov models in a different way as classical approaches. Indeed, we use these mathematical tools to model the object in the spatial domain rather than in the temporal domain. Besides in order to manage multidimensional (color) data, multidimensional hidden Markov models are involved. Object learning step is performed using the GHOSP algorithm whereas object tracking step is done by approximate object position prediction and then precise object position localisation. This last step can be seen as an object recognition problem and will be solved using a method based on the forward algorithm.

A fusion methodology based on Dempster-Shafer evidence theory for two biometric applications

Different features carry more or less rich and varied pieces of information to characterize a pattern. The fusion of these different sources of information can provide an opportunity to develop more efficient biometric system compared when using a feature vector. Thus a new automatic fusion methodology using different sources of information (different feature sets) is presented here. Dempster-Shafer evidence theory is employed for this purpose. For performance evaluation significantly large data sets of the biometric sources signature and hand shape are used. The results on combining different feature vectors compared to a single vector with our approach prove the importance of a fusion process

A Content Spotting System for Line Drawing Graphic Document Images

We present a content spotting system for line drawing graphic document images. The proposed system is sufficiently domain independent and takes the keyword based information retrieval for graphic documents, one step forward, to Query By Example (QBE) and focused retrieval. During offline learning mode: we vectorize the documents in the repository, represent them by attributed relational graphs, extract regions of interest (ROIs) from them, convert each ROI to a fuzzy structural signature, cluster similar signatures to form ROI classes and build an index for the repository. During online querying mode: a Bayesian network classifier recognizes the ROIs in the query image and the corresponding documents are fetched by looking up in the repository index. Experimental results are presented for synthetic images of architectural and electronic documents.

Personal Identification and Verification by Hand Recognition

A new methodology for the person identification and verification using hand features is presented. The features are extracted from gray level hand images, which are scanned by an ordinary commercial scanner. Contrary to other bimodal biometric systems, the palmprint and hand geometry features are acquired from the same image. On their individual performances, these features are grouped into four different feature vectors. A k-NN classifier based on majority vote rule and distance-weighted rule is employed to establish four classifiers. Dempster-Shafer evidence theory is then used to combine these classifiers in case of identification. Besides, for verification step a simple majority rule was found robust for our system. Dempster-Shafer theory has proved to be much more efficient than fusion by others methods like majority vote rule and Borda count method

Subgraph Spotting through Explicit Graph Embedding: An Application to Content Spotting in Graphic Document Images

We present a method for spotting a subgraph in a graph repository. Subgraph spotting is a very interesting research problem for various application domains where the use of a relational data structure is mandatory. Our proposed method accomplishes subgraph spotting through graph embedding. We achieve automatic indexation of a graph repository during off-line learning phase, where we (i) break the graphs into 2-node sub graphs (a.k.a. cliques of order 2), which are primitive building-blocks of a graph, (ii) embed the 2-node sub graphs into feature vectors by employing our recently proposed explicit graph embedding technique, (iii) cluster the feature vectors in classes by employing a classic agglomerative clustering technique, (iv) build an index for the graph repository and (v) learn a Bayesian network classifier. The subgraph spotting is achieved during the on-line querying phase, where we (i) break the query graph into 2-node sub graphs, (ii) embed them into feature vectors, (iii) employ the Bayesian network classifier for classifying the query 2-node sub graphs and (iv) retrieve the respective graphs by looking-up in the index of the graph repository. The graphs containing all query 2-node sub graphs form the set of result graphs for the query. Finally, we employ the adjacency matrix of each result graph along with a score function, for spotting the query graph in it. The proposed subgraph spotting method is equally applicable to a wide range of domains, offering ease of query by example (QBE) and granularity of focused retrieval. Experimental results are presented for graphs generated from two repositories of electronic and architectural document images.