Informative visual words construction to improve bag of words image representation. Issue 5 (1st May 2014)

• Record Type: Journal Article
• Authors: Farhangi, Mohammad Mehdi; Soryani, Mohsen; Fathy, Mahmood
• Is Part Of: IET image processing. Volume 8:Issue 5(2014)
• Page Start: 310
• Page End: 318
• Publication Date: 2014-05-01
• Subjects: computer vision -- image classification -- image representation; informative visual words construction -- computer vision -- image representation -- adjacency information -- binary tree structure -- image classification; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2013.0449
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Bag of visual words model has recently attracted much attention from computer vision society because of its notable success in analysing images and exploring their content. This study improves this model by utilising the adjacency information between words. To explore this information, a binary tree structure is constructed from the visual words in order to model the is – a relationships in the vocabulary. Informative nodes of this tree are extracted by using the χ 2 criterion and are used to capture the adjacency information of visual words. This approach is a simple and computationally effective way for modelling the spatial relations of visual words, which improves the image classification performance. The authors evaluated our method for visual classification of three known datasets: 15 natural scenes, Caltech‐101 and Graz‐01.