DOI: 10.2298/CSIS100423035J

Multi-Scale Image Semantic Recognition with Hierarchical Visual Vocabulary

Xinghao Jiang1,2, Tanfeng Sun1,2 and GuangLei Fu1

  1. School of Information Security Engineering, Shanghai Jiao Tong University
    Shanghai, 200240, China
    {xhjiang, tfsun}@sjtu.edu.cn
  2. Key Lab. of Shanghai Information Security Management and Technology Research
    Shanghai, 200240, China

Abstract

Local features have been proved to be effective in image/video semantic analysis. The BOVW (bag of visual words) scheme can cluster local features to form the visual vocabulary which includes an amount of words, where each word is the center of one clustering feature. The vocabulary is used to recognize the image semantic. In this paper, a new scheme to construct semantic-binding hierarchical visual vocabulary is proposed. Some attributes and relationship of the semantic nodes in the model are discussed. The hierarchical semantic model is used to organize the multi-scale semantic into a level-by-level structure. Experiments are performed based on the LabelMe dataset, the performance of our scheme is evaluated and compared with the traditional BOVW scheme, experimental results demonstrate the efficiency and flexibility of our scheme.

Key words

local feature, bag of visual words, image semantic analysis, visual vocabulary

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS100423035J

Publication information

Volume 8, Issue 3 (June 2011)
Year of Publication: 2011
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Jiang, X., Sun, T., Fu, G.: Multi-Scale Image Semantic Recognition with Hierarchical Visual Vocabulary. Computer Science and Information Systems, Vol. 8, No. 3, 931-951. (2011), https://doi.org/10.2298/CSIS100423035J