Retrieval of images with objects of specific size, location and spatial configuration

被引：1

作者：

Pourian, Niloufar ^{[1
]}

Manjunath, B. S. ^{[1
]}

机构：

[1] Univ Calif Santa Barbara, Dept Elect & Comp Engn, Santa Barbara, CA 93106 USA

来源：

2015 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV) | 2015年

关键词：

D O I：

10.1109/WACV.2015.133

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

An approach to image retrieval using spatial configurations is presented. The goal is to search the database for images that contain similar objects (image-patches) with a given configuration, size and position. The proposed approach consists of creating localized representations robust to segmentation variations, and a sub-graph matching method to compare the query with the database items. Localized object representations are created using a community detection method that groups visually similar segments. Extensive experimental results on three challenging datasets are provided to demonstrate the feasibility of the approach.

引用

页码：960 / 967

页数：8