Contribution à la détection et à la reconnaissance d'objets dans les images

Abstract : This thesis addresses the problem of object recognition in images and more precisely the problem of object localization. It have been conducted in the context of a scientific collaboration between INRIA Rhônes-Alpes and MBDA France. Therefore, a particular attention was accorded to the applicability of the proposed approaches on infrared images. The localization method proposed here relies on the sliding windows mechanism combined with a two stage cascade that, despite its simplicity, allies rapidity and precision. The first stage is a filtering stage that rejects most of the false positives using a linear classifier. The second stage prunes the detections of the first classifier using a slower yet efficient non-linear classifier. Windows are represented with HOG and Bag-of-words descriptors. The second contribution of this thesis is a method that combines object localization and image categorization. This allows, on the one hand, to take into account context information in localization, and on the other hand, to rely on geometrical structure of objects while performing image categorization. This combination leads to a significant quality improvement and obtains performance superior to the state of the art for both tasks. Finally, we consider the problem of localizing visually similar object categories and suggest to decompose the task of object localization into two steps. The first is a detection step that allows to find objects without determining their category while the second step, an identification step, predicts the objects categories. We show that this approach limits inter-class confusion, which is the main difficulty faced when localizing visually similar object classes. This thesis accords an important place to experimental validation conducted on PASCAL VOC databases as well as other databases specifically introduced for the thesis.
Document type :
Theses
Complete list of metadatas

Cited literature [88 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00623278
Contributor : Abes Star <>
Submitted on : Friday, September 30, 2011 - 11:12:37 AM
Last modification on : Wednesday, April 17, 2019 - 1:32:26 AM
Long-term archiving on : Saturday, December 31, 2011 - 2:25:27 AM

File

19220_HARZALLAH_2011_archivage...
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-00623278, version 2

Collections

Citation

Hedi Harzallah. Contribution à la détection et à la reconnaissance d'objets dans les images. Mathématiques générales [math.GM]. Université Grenoble Alpes, 2011. Français. ⟨NNT : 2011GRENM016⟩. ⟨tel-00623278v2⟩

Share

Metrics

Record views

2407

Files downloads

7137