Rémy Mullot

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.

Three decision levels strategy for Arabic and Latin texts differentiation in printed and handwritten natures

Arabic and Latin script identification in printed and handwritten nature present several difficulties because the Arabic (printed or handwritten) and the handwritten Latin scripts are cursive scripts of nature. To avoid all possible confusions which can be generated, we propose in this paper a strategy which is based on three decision levels where each level will have its own features vector and will consist in identifying only one script among the scripts to identify.

Language and Script Identification Based on Steerable Pyramid Features

Arabic and Latin language and script identification in machine printed and handwritten types present several difficulties because the Arabic (machine printed or handwritten) and the handwritten Latin scripts are cursive scripts of nature. To avoid all possible confusions which can be generated, we propose in this paper an accurate and suitable designed system for language and script identification at word level which is based on steerable pyramid transform. The features extracted from pyramid sub bands serve to classify the scripts on only one script among the scripts to identify. The encouraging and promising results obtained are presented in this research paper.

Text/graphic labelling of ancient printed documents

This paper presents a text/graphic labelling for ancient printed documents. Our approach is based on the extraction and the quantification of the various orientations that are present in ancient printed document images. The documents are initially cut into normalized square windows in which we analyze significant orientations with a directional rose. Each kind of information (textual or graphical) is typically identified and marked by its orientation distribution. This choice of characterization allows us to separate textual regions from graphics by minimizing the a priori knowledge. The evaluation of our proposition lies on a page classification using layout extraction criteria. The system has been tested over several ancient printed books of the Renaissance.

Texture feature evaluation for segmentation of historical document images

Texture feature analysis has undergone tremendous growth in recent years. It plays an important role for the analysis of many kinds of images. More recently, the use of texture analysis techniques for historical document image segmentation has become a logical and relevant choice in the conditions of significant document image degradation and in the context of lacking information on the document structure such as the document model and the typographical parameters. However, previous work in the use of texture analysis for segmentation of digitized historical document images has been limited to separately test one of the well-known texture-based approaches such as autocorrelation function, Grey Level Co-occurrence Matrix (GLCM), Gabor filters, gradient, wavelets, etc. In this paper we raise the question of which texture-based method could be better suited for discriminating on the one hand graphical regions from textual ones and on the other hand for separating textual regions with different sizes and fonts. The objective of this paper is to compare some of the well-known texture-based approaches: autocorrelation function, GLCM, and Gabor filters, used in a segmentation of digitized historical document images. Texture features are briefly described and quantitative results are obtained on simplified historical document images. The achieved results are very encouraging.

Arabic and Latin Script Identification in Printed and Handwritten Types Based on Steerable Pyramid Features

Arabic and Latin script identification in printed and handwritten nature present several difficulties because the Arabic (printed or handwritten) and the handwritten Latin scripts are cursive scripts of nature. To avoid all possible confusions which can be generated, we propose in this paper an accurate and suitable designed system for script identification at word level which is based on steerable pyramid transform. The features extracted from pyramid sub bands serve to classify the scripts on only one script among the scripts to identify. The encouraging and promising results obtained are presented in this research paper.

Multilevel Approach and Distributed Consistency for Technical Map Interpretation

We describe the architecture of a system capable of fully automatic interpretation of images of Frenchcadastral(city map) documents. Our approach is based onmultilevel perceptionswithin hierarchical descriptions of the maps and is guided bya priorimodels of this particular style of maps. Essentially, we attempt to extract and then reconcile several potentially inconsistent “points of view” of the image. To resolve the many types of semantic inconsistency that we encounter, we organize the computation in feedback cycles between high- and low-level processing. Examples of reliable interpretation of complex and noisy images are discussed.

Unsupervised word spotting using a graph representation based on invariants

We are currently working on the concept of an interactive word retrieval system for ancient document collection navigation, based on query composition for non-expert users. We have introduced a new notion: invariants, which are writing pieces automatically extracted from the old document collection. The invariants can be used in query making process in where the user selects and composes appropriate invariants to make the query. The invariants can be also used as descriptor to characterize word images. We introduced our unsupervised method for extracting invariants in our earlier paper. In this paper, we present a new structural word spotting system using a graph representation based on invariants as a descriptor. Through experiments, we conclude that our proposed system can adapt to different types of homogenous alphabetic languages documents (regardless of language/script, antiquity, handwritten or printed).

Complex documents images segmentation based on steerable pyramid features

Page segmentation and classification is very important in document layout analysis system before it is presented to an OCR system or for any other subsequent processing steps. In this paper, we propose an accurate and suitably designed system for complex documents segmentation. This system is based on steerable pyramid transform. The features extracted from pyramid sub-bands serve to locate and classify regions into text (either machine-printed or handwritten) and non-text (images, graphics, drawings or paintings) in some noise-infected, deformed, multilingual, multi-script document images. These documents contain tabular structures, logos, stamps, handwritten script blocks, photographs, etc. The encouraging and promising results obtained on 1,000 official complex document images data set are presented in this research paper. We compared our results with those from existing state-of-the-art methods. This comparison shows that the proposed method performs consistently well on large sets of complex document images.

Semi-synthetic Document Image Generation Using Texture Mapping on Scanned 3D Document Shapes

This article presents a method for generating semi-synthetic images of old documents where the pages might be torn (not flat). By using only 2D deformation models, most existing methods give non-realistic synthetic document images. Thus, we propose to use 3D approach for reproducing geometric distortions in real documents. First, a new proposed texture coordinate generation technique extracts texture coordinates of each vertex in the document shape (mesh) resulting from 3D scanning of a real degraded document. Then, any 2D document image can be overlayed on the mesh by using an existing texture image mapping method. As a result, many complex real geometric distortions can be integrated in generated synthetic images. These images then can be used for enriching training sets or for performance evaluation. The degradation method here is jointly used with the character degradation model we proposed in [1] to generate the 6000 semi-synthetic degraded images of the music score removal staff line competition of ICDAR 2013.