15 November 2007 Image categorization based on multi-scale vocabulary
Author Affiliations +
Proceedings Volume 6788, MIPPR 2007: Pattern Recognition and Computer Vision; 67881F (2007) https://doi.org/10.1117/12.749679
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China
Nowadays, local feature based image categorization algorithm has attracted increasing attention in the computer vision community. In this paper, we present a local feature based image categorization scheme by using Multi-Scale Vocabulary. This technique works by partitioning the feature space into clusters at several different levels to form multi-scale vocabulary and generate corresponding fixed-length descriptors at different scales for each image. Then we design particular similarity measure for multi-scale descriptors and finally apply KNN and SVM to realize image categorization task. Experiments conducted on the ETH80 dataset have demonstrated the effectiveness of our approach.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xin Yang, Xin Yang, Jinhui Tang, Jinhui Tang, Xiuqing Wu, Xiuqing Wu, "Image categorization based on multi-scale vocabulary", Proc. SPIE 6788, MIPPR 2007: Pattern Recognition and Computer Vision, 67881F (15 November 2007); doi: 10.1117/12.749679; https://doi.org/10.1117/12.749679


Back to Top