Share Email Print

Proceedings Paper

Learning approach for multicontent analysis of compound images
Author(s): Quentin Besnehard; Cedric Marchessoux; Tom Kimpe; Guillaume Spalla; Arnaud Joubel; François Boudet
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In the context of the European Cantata project (ITEA project, 2006-2009), within Barco, a complete Multi-Content Analysis framework was developed for detection and analysis of compound images. The framework consists of: a dataset, a Multi-Content Analysis (MCA) algorithm based on learning approaches, a Ground Truth, an evaluation module based on metrics and a presentation module. The aim of the MCA methodology presented here is to classify image content of computer screenshots into different categories such as: text; Graphical User Interface; Medical images and other complex images. The AdaBoost meta-algorithm was chosen, implemented and optimized for the classification method as it fitted the constraints (real-time and precision). A large dataset separated in training and testing subsets and their ground truth (with ViPER metadata format) was both collected and generated for the four different categories. The outcome of the MCA is a cascade of strong classifiers trained and tested on the different subsets. The obtained framework and its optimization (binary search, pre-computing of the features, pre-sorting) allow to re-train the classifiers as much as needed. The preliminary results are quite encouraging with a low false positive rate and close true positive rate in comparison with expectations. The re-injection of false negative examples from new testing subsets in the training phase resulted in better performances of the MCA.

Paper Details

Date Published: 19 January 2009
PDF: 12 pages
Proc. SPIE 7255, Multimedia Content Access: Algorithms and Systems III, 72550E (19 January 2009); doi: 10.1117/12.805789
Show Author Affiliations
Quentin Besnehard, Barco n.v. (Belgium)
Cedric Marchessoux, Barco N.V. (Belgium)
Tom Kimpe, Barco N.V. (Belgium)
Guillaume Spalla, Univ. of Poitiers (France)
Arnaud Joubel, Univ. of Poitiers (France)
François Boudet, Univ. of Poitiers (France)

Published in SPIE Proceedings Vol. 7255:
Multimedia Content Access: Algorithms and Systems III
Raimondo Schettini; Ramesh C. Jain; Simone Santini, Editor(s)

© SPIE. Terms of Use
Back to Top