Title :
The hierarchical classification of Web content by the combination of textual and visual features
Author_Institution :
Sch. of Comput. Sci. & Eng., South China Univ. of Technol., Guangzhou, China
Abstract :
This paper presents the hierarchical classification of Web content based on the combination of both textual and visual features. This combination is achieved by multiple classifier combination. A schema based on adaptive category weighting is proposed for achieving good combination, which has gained better results compared to the ordinary combination based on general voting schema.
Keywords :
Internet; feature extraction; image classification; principal component analysis; support vector machines; Web content; adaptive category weighting; hierarchical classification; multiple classifier combination; principal component analysis; support vector machines; textual features; visual features; Computer science; Data mining; Electronic mail; Feature extraction; Internet; Machine learning; Support vector machine classification; Support vector machines; Voting; Web pages;
Conference_Titel :
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN :
0-7803-8403-2
DOI :
10.1109/ICMLC.2004.1382015
