DocumentCode :
454824
Title :
Automatic Image Annotation through Multi-Topic Text Categorization
Author :
Gao, Sheng ; Wang, De-Hong ; Lee, Chin-Hui
Author_Institution :
Inst.for Infocomm Res.
Volume :
2
fYear :
2006
fDate :
14-19 May 2006
Abstract :
We propose a new framework for automatic image annotation through multi-topic text categorization. Given a test image, it is first converted into a text document using a visual codebook learnt from a collection of training images. Latent semantic analysis is then performed on the tokenized document to extract a feature vector based on a visual lexicon with its vocabulary items defined as either a codeword or a co-occurrence of multiple codewords. The high-dimension feature vector is finally compared with a set of topic models, one for each concept to be annotated, to decide on the top concepts related to the test image. These topic classifiers are discriminatively trained from images with multiple associations, including spatial, syntactic, or semantic relationship, between images and concepts. The proposed approach was evaluated on a Corel dataset with 374 keywords, and the TRECVID 2003 dataset with ten selected concepts. When compared with state-of-the-art algorithms for automatic image annotation on the Corel test set our system obtained the best results, although we only use a simple linear classification model based on just texture and color features
Keywords :
document image processing; feature extraction; image classification; image colour analysis; image texture; Corel dataset; automatic image annotation; color features; feature vector extraction; linear classification model; multitopic text categorization; text document; texture features; visual codebook; visual lexicon; Automatic testing; Digital images; Feature extraction; Image converters; Organizing; Performance analysis; Software libraries; System testing; Text categorization; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 2006. ICASSP 2006 Proceedings. 2006 IEEE International Conference on
Conference_Location :
Toulouse
ISSN :
1520-6149
Print_ISBN :
1-4244-0469-X
Type :
conf
DOI :
10.1109/ICASSP.2006.1660358
Filename :
1660358
Link To Document :
بازگشت