Paper Info
Title
Image retrieval based on saliency for urban image contents
Abstract
With the increase of image datasets size and of descriptors complexity in Content-Based Image Retrieval (CBIR) and Computer Vision, it is essential to find a way to limit the amount of manipulated data, while keeping its quality. Instead of treating the entire image, the selection of regions which hold the essence of information is a relevant option to reach this goal. As the visual saliency aims at highlighting the areas of the image which are the most important for a given task, in this paper we propose to exploit visual saliency maps to prune the most salient image features. A novel visual saliency approach based on the local distribution analysis of the edges orientation, particularly dedicated to structured contents, such as street view images of urban environments, is proposed. It is evaluated for CBIR according to three criteria: quality of retrieval, volume of manipulated features and computation time. The proposal can be exploited into various applications involving large sets of local visual features; here it is experimented within two applications: cross-domain image retrieval and image-based vehicle localisation.
Year
DOI
Venue
2017
10.1109/IPTA.2017.8310131
2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA)
Keywords
Field
DocType
CBIR,visual saliency,local descriptors,edge orientation
Computer vision,Histogram,Pattern recognition,Visualization,Computer science,Feature (computer vision),Salience (neuroscience),Image retrieval,Image segmentation,Artificial intelligence,Computation,Salient
Conference
ISSN
ISBN
Citations 
2154-512X
978-1-5386-1843-1
0
PageRank 
References 
Authors
0.34
29
2
Name
Order
Citations
PageRank
Kamel Guissous100.34
Valérie Gouet-brunet2699.90