Open AccessMulti-scale image semantic recognition with hierarchical visual vocabulary
Author(s) -
Xinghao Jiang,
Tanfeng Sun,
Guanglei Fu
Publication year - 2011
Publication title -
computer science and information systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.244
H-Index - 24
eISSN - 2406-1018
pISSN - 1820-0214
DOI - 10.2298/csis100423035j
Subject(s) - computer science , vocabulary , artificial intelligence , scheme (mathematics) , feature (linguistics) , natural language processing , semantic computing , visual word , pattern recognition (psychology) , bag of words model in computer vision , semantic feature , hierarchical clustering , semantic compression , flexibility (engineering) , image (mathematics) , image retrieval , cluster analysis , semantic technology , semantic web , linguistics , mathematics , mathematical analysis , philosophy , statistics
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.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom