Paper Info
Title
A spatially aware generative model for image classification, topic discovery and segmentation
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.
Year
DOI
Venue
2009
10.1109/ICIP.2009.5414236
ICIP
Keywords
Field
DocType
visual word,information retrieval field,visual content,generative model,unordered visual word,years bag-of-words model,visual processing task,visual information,topic discovery,spatially aware generative model,image classification,model image,visualization,machine vision,layout,information retrieval,computational modeling,bag of words,image segmentation,semantics
Computer science,Human visual system model,Image segmentation,Artificial intelligence,Contextual image classification,Computer vision,Visual processing,Pattern recognition,Segmentation,Visualization,Machine learning,Visual Word,Generative model
Conference
ISSN
ISBN
Citations 
1522-4880 E-ISBN : 978-1-4244-5655-0
978-1-4244-5655-0
1
PageRank 
References 
Authors
0.35
7
5
Name
Order
Citations
PageRank
Iván González-Díaz1469.51
Darío García-García2244.41
Fernando Díaz-de-María320132.14
Gonzalez-Diaz, I.410.35
Diaz-de-Maria, F.510.35