Université de Fribourg

Reconnaissance de documents assistée : architecture logicielle et intégration de savoir-faire

Bapst, Frédéric ; Ingold, Rolf (Dir.)

Thèse de doctorat : Université de Fribourg, 1998 ; no 1228.

This thesis addresses the question of document recognition with an assisted perspective advocating an adequate combination between human and machine capabilities. Our contributions tackle various aspects of the underlying software architecture. Both a study of existing systems and a projection on some future applications of document recognition illustrate the need of cooperative environments....

Université de Fribourg

A framework for interactive document recognition

Hitz, Oliver ; Ingold, Rolf (Dir.)

Thèse de doctorat : Université de Fribourg, 2005 ; Nr. 1488.

Document recognition is a research domain that doesn’t lose its relevance even in a world where documents are increasingly often available in an electronic form. Whereas some years ago, the goal of document recognition was to convert documents from paper into an electronic form, the problem is shifted more and more from pure recognition towards document understanding. This requires much more...

Université de Fribourg

Phonographic record sound extration by image processing

Stotzer, Sylvain ; Ingold, Rolf (Dir.)

Thèse de doctorat : Université de Fribourg, 2006 ; no. 1534.

The phonographic record was the only way to store sounds until the introduction of magnetic tape in the early 1950s. Therefore there are huge collections of phonographic records, for example in radio stations and national sound archives. Such archives include pressed discs, which were produced in mass by record companies for commercial distribution, as well as direct cut discs obtained by the...

Université de Fribourg

A study on multimodal document alignment : bridging the gap between textual documents and spoken language

Mekhaldi, Dalila ; Ingold, Rolf (Dir.)

Thèse de doctorat : Université de Fribourg, 2006.

This thesis proposes a multimodal alignment framework that bridges the gap between static documents and spoken language. This alignment aims mainly at linking static documents with temporal data, in order to exploit the multi-level structure of documents for indexing multimedia recordings of events. This novel multimodal alignment method, largely described in this thesis, is applied on two...

Université de Fribourg

A visual signature-based identification method of low-resolution document images and its exploitation to automate indexing of multimodal recordings

Behera, Ardhendu ; Ingold, Rolf (Dir.)

Thèse de doctorat : Université de Fribourg, 2006 ; no. 1529.

This thesis investigates methods for building an efficient application system for the document-based automatic indexing and retrieval (DocMIR) of multimedia data captured from multimodal environments such as meetings, conferences, etc. Both empirical image processing, video segmentation methods and document analysis approaches are studied to bridge the gap between temporal data and static...

Université de Fribourg

Eine statistische Methode zur Erkennung von Dokumentstrukturen

Brugger, Rolf ; Ingold, Rolf (Dir.)

Thèse de doctorat : Université de Fribourg : 1999 ; Nr. 1251.

This PhD thesis is on the topic of document recognition. It particularly discusses the aspects of learning document models and the recognition of the logical structure of documents. In order to achieve high reliability and user friendliness, we describe an interactive system which can easily be adapted to new document classes. In an initial learning session the system is able to generate a...

Université de Fribourg

2(CREM) : une méthode de reconnaissance structurelle de documents complexes basée sur des patterns bidimensionnels

Robadey, Lyse ; Ingold, Rolf (Dir.) ; Bapst, Frédéric (Codir.)

Thèse de doctorat : Université de Fribourg : 2001 ; No 1364.

This thesis addresses the question of printed document recognition. We studied existing systems, first in a general context, by making the distinction between physical and logical structure recognition systems. Then, we focused on methods specific for complex layout documents and on methods having a learning aptitude. Since there do not seem to exist learning systems which are able to recognise...

Université de Fribourg

Une approche uniforme pour la reconnaissance de la structure physique de documents composites fondée sur l'analyse des espaces

Azokly, Antoine Sourou ; Ingold, Rolf (Dir.) ; Stamon, Georges (Codir.)

Thèse de doctorat : Université de Fribourg : 1995 ; 1105.

We present in this thesis a uniform approach to recognize the physical structure of printed documents that may contain various kinds of blocks: we call such documents composite documents. After an introduction to the subject of this thesis, we present first the state of the art in the field of document recognition. In this part, we present models and standards used to represent document...

Université de Fribourg

Content-based image retrieval using hand-drawn sketches and local features : a study on visual dissimilarity

Banfi, Folco ; Ingold, Rolf (Dir.)

Thèse de doctorat : Université de Fribourg : 2000 ; no 1312.

This thesis addresses the question of content-based image retrieval (CBIR) in heterogeneous databases. In an analysis of the existing CBIR tools that was done at the beginning of this work, we have shown that there was room for improvement in three key areas: query form, image and query representation, and computation of similarity. This analysis led us to studying the usability of a method for...