Visual graph modeling for scene recognition and mobile robot localization

Trong-Ton Pham (1) , Philippe Mulhem (2) , Loïc Maisonnasse (1) , Éric Gaussier (3) , Joo-Hwee Lim (4, 5)

1 LIG - Laboratoire d'Informatique de Grenoble
2 MRIM - Modélisation et Recherche d’Information Multimédia [Grenoble]
3 AMA - Analyse de données, Modélisation et Apprentissage automatique [Grenoble]
4 Institute for Infocomm Research - I²R [Singapore]
5 IPAL - Image & Pervasive Access Lab

Image retrieval and categorization may need to consider several types of visual features and spatial information between them (e.g., different point of views of an image). This paper presents a novel approach that exploits an extension of the language modeling approach from information retrieval to the problem of graph-based image retrieval and categorization. Such versatile graph model is needed to represent the multiple points of views of images. A language model is defined on such graphs to handle a fast graph matching. We present the experiments achieved with several instances of the proposed model on two collections of images: one composed of 3,849 touristic images and another composed of 3,633 images captured by a mobile robot. Experimental results show that using visual graph model (VGM) improves the accuracies of the results of the standard language model (LM) and outperforms the Support Vector Machine (SVM) method.

Mots clés: Graph theory; Information retrieval; Language model; Scene Recognition; Robot localization

Domaines: Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]; Recherche d'information [cs.IR]

Trong-Ton Pham, Philippe Mulhem, Loïc Maisonnasse, Éric Gaussier, Joo-Hwee Lim. Visual graph modeling for scene recognition and mobile robot localization. Multimedia Tools and Applications, 2012, 60 (2), pp.419-441. ⟨10.1007/s11042-010-0598-8⟩. ⟨hal-00742059⟩