PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A SPATIALLY AWARE GENERATIVE MODEL FOR IMAGE CLASSIFICATION, TOPIC DISCOVERY AND SEGMENTATION
Iván Gonzalez-Diaz, Darío García-García and Fernando Díaz-de-María
In: International Conference on Image Processing (ICIP), 7-10 Nov 2009, Cairo.

Abstract

For the last few years bag-of-words models have been succesfully applied to the information retrieval field. However their application to visual content suffers from an important shortcoming: they model images as sets of unordered visual words rather than consider their spatial and geometric layout. Visual information is highly organized along the dimensions of an image and algorithms should make use of this to enhance the performance of several visual processing tasks. In this paper, a generative model is proposed that fuses both the local information obtained from visual words and the global geometric layout given by a previous segmentation of the image. Furthermore, the model considers inter-region influences so topics can spread along the image and, thus, generate final segmentations in which regions represent semantic concepts. The proposed model is succesfully tested on three different tasks.

PDF - Archive staff only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:6062
Deposited By:Darío García-García
Deposited On:08 March 2010