Julien Lerouge

• MSc in Computer Science
• Analyst at QuickSign

Developing smart ways of interacting with scanners is one of the emerging needs identified by numerous digitization professionals. To achieve better interaction with scanners, the research community in historical document image analysis is particularly interested in providing reliable tools for computer-aided indexing and retrieval of historical do...

In this paper, a new binary linear programming formulation for computing the exact Graph Edit Distance (GED) between two graphs is proposed. A fundamental strength of the formulations lies in their genericity since the GED can be computed between directed or undirected fully attributed graphs. Moreover, a continuous relaxation of the domain constra...

This paper presents a binary linear program which computes the exact graph edit distance between two richly attributed graphs (i.e. with attributes on both vertices and edges). Without solving graph edit distance for large graphs, the proposed program enables to process richer and larger graphs than existing approaches based on mathematical program...

Cet article s'intéresse à un des éléments importants dans l'analyse de graphiques sur les images de documents anciens que sont les lettrines. Nous proposons dans ce travail des méthodes génériques pour la reconnaissance et la classification de lettrines. Tout d'abord, une méthode ascendante de segmentation à base de descripteurs de bas niveau est p...

This article presents a binary linear program for the Minimum Cost Subgraph Matching (MCSM) problem. MCSM is an extension of the subgraph isomorphism problem where the matching tolerates substitutions of attributes and modifications of the graph structure. The objective function proposed in the formulation can take into account rich attributes (e.g...

In this paper, we propose a deep neural network (DNN) architecture called Input Output Deep Architecture (IODA) for solving the problem of image labeling. IODA directly links a whole image to a whole label map, assigning a label to each pixel using a single neural network forward step. Instead of designing a handcrafted a priori model on labels (su...

The work conducted in this article presents a structural signature based on texture for the characterization and categorization of digitized historical book pages. The proposed signature does not assume a priori knowledge regarding page layout and content, and hence, it is applicable to a large variety of ancient books. By integrating varying low-l...

This article tackles some important issues relating to the analysis of a particular case of complex ancient graphic images, called " lettrines " , " drop caps " or " ornamental letters ". Our contribution focuses on proposing generic solutions for lettrine recognition and classification. Firstly, we propose a bottom-up segmentation method, based on...

The substitution-tolerant subgraph isomorphism is a particular error-tolerant subgraph matching that allows label substitutions for both vertices and edges. Such a matching is often required in pattern recognition applications since graphs extracted from images are generally labeled with features vectors computed from raw data which are naturally s...

PIVAJ is a platform for archived digitized newspaper emphasizing articles: extracting them from digitized documents by automated page layout analysis, OCRing them, indexing their text transcription to allow users to search for content. Crowdsourcing is used to improve the quality of the indexing, by correcting the transcription and by tagging artic...