Loading...
Thumbnail Image
Item

Improving Bag-of-Words model with spatial information

Abstract
Bag-of-Words (BOW) models have recently become popular for the task of object recognition, owing to their good performance and simplicity. Much work has been proposed over the years to improve the BOW model, where the Spatial Pyramid Matching technique is the most notable. In this work, we propose three novel techniques to capture more re_ned spatial information between image features than that provided by the Spatial Pyramids. Our techniques demonstrate a performance gain over the Spatial Pyramid representation of the BOW model.
Type
Conference Contribution
Type of thesis
Series
Citation
Zhang, E. & Mayo, M. (2010) Improving Bag-of-Words model with spatial information. Paper presented at the 25th International Conference of Image and Vision Computing New Zealand, Queenstown, 8 & 9 November 2010.
Date
2010
Publisher
IEEE
Degree
Supervisors
Rights
© 2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.