Image Retrieval by Effetive Description of Macro- and Micro-Content of Images

被引：0

作者：

Kuo, Chang-Ming ^{[1
]}

Hung, Mao-Hsiung ^{[2
]}

Yang, Nai-Chung ^{[1
]}

Kuo, Chung-Ming ^{[1
]}

Hsieh, Chaur-Heh ^{[3
]}

机构：

[1] I Shou Univ, Dept Informat Engn, Kaohsiung, Taiwan

[2] Fujian Univ Technol, Coll Informat Sci & Engn, Fuzhou, Peoples R China

[3] Ming Chuan Univ, Dept Comp & Commun Engn, Taoyuan, Taiwan

来源：

2015 THIRD INTERNATIONAL CONFERENCE ON ROBOT, VISION AND SIGNAL PROCESSING (RVSP) | 2015年

关键词：

Visual words; Image retrieval; Macro-based; Micro-based; CATEGORIZATION;

D O I：

10.1109/RVSP.2015.23

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The visual words are a collection of local features of images, and generally used to represent image content. Considering the homogeneity of visual words, we design a visual vocabulary which contains macro-based and micro-based corresponding to feature points and key blocks visual words, respectively. We also apply the proposed visual vocabulary and description scheme to construct an image retrieving system. The performance evaluation of the method indicates that the proposed visual vocabulary achieves promising results.

引用

页码：59 / 62

页数：4

共 7 条

[1] Bag of spatio-visual words for context inference in scene classification [J].