Laurent Vinet

Institut national de l'audiovisuel · Recherche

Page 131 you will find the definition of the often cited "Vinet measure" or "Vinet distance": a distance used to measure the difference between two segmentations of an image.

In the context of the Quaero program, the French Audio-visual National Institute has been especially interested in audiovisual assets management tools which make use of auto-matic analysis algorithms. We show in the following how such techniques can assist documenting and indexing applications for professional as well as amateur uses. In particular...

Cet article présente un modèle d’ingénierie des documents audiovisuels centré sur la description de contenus, ainsi que le framework FERIA, une plateforme logicielle générique qui en est une instrumentation. Il montre en quoi la norme MPEG-7 ne permet pas de répondre aux besoins de ce modèle et il décrit le langage FDL (Feria Description Language)...

Object extraction systems performances are not homogeneous over different corpora because objects can take many different aspects within such sets. An adaptation of these systems is thus required in order to maintain equal performances over every kind of object the system may be applied on. Focusing on the issue of parameters optimization, a method...

Object extraction systems performances are not homogeneous over different corpora because objects can take many different aspects within such sets. An adaptation of these systems is thus required in order to maintain equal performances over every kind of object the system may be applied on. Focusing on the issue of parameters optimization, a method...

Texts embedded in video streams convey crucial information for documentation. Many text detection and recognition systems have been designed to automatically extract such documentary data from video streams. Most of the research teams involved argue that commercial OCR do not work properly on images extracted from a video stream. They thus concieve...

INTRODUCTION 1.1. In search of the semantic content of images Content-based image retrieval (CBIR) has been a widely studied issue [1,2,3], among multimedia database management techniques. Image databases managementhave applications in various areas, such as medical databases, satellite images, photo-journalism, art, or industry, with a growing dem...

The processing of digitized color photographs is a new developing field of medical imaging with numerous potential applications in Dermatology, Cosmetology and Endoscopy. These photographs are aimed to facilitate the follow up of the patient lesions. The goal of the processing of these images is to facilitate the usual interpretation and to compute...

Page 131 you will find the definition of the often cited "Vinet measure" or "Vinet distance": a distance used to measure the difference between two segmentations of an image.

Stereo matching is the process of determining correspondences between entities in related images. Often, this is treated as two quite independent subprocesses, namely, segmentation, followed by matching. These processes are treated as naturally related, in that partial matching is fed back to the segmentation and both proceed simultaneously in a co...

The high vertical resolution of dipmeter curves makes them a potentially powerful tool in sedimentological analysis of the formations encountered in wells, providing that some core data are available. It is however tedious and time-consuming to analyze in detail 4, 6 or 8 curves over a large interval. Application of an interactive classification so...

Stereo matching is the process of determining correspondences between entities in related images. Often, this is treated as two quite independent subprocesses: segmentation, followed by matching. In this paper, we treat these processes as naturally related, in that partial matching results are fed back to the segmentation and both proceed simultane...