Texture Features Based Bag of Visual Words for a Spine MRI Images

ENTESAR, B. TALAL and KHAWLAH, H. ALI and NADRA, J. ALSAAD (2016) Texture Features Based Bag of Visual Words for a Spine MRI Images. In: Fourth International Conference on Advances in Computing, Communication and Information Technology CCIT- 2016, 17 - 18 March, 2016, Birmingham City University, Birmingham, UNITED KINGDOM.

20160414_064054.pdf - Published Version

Download (709kB) | Preview
Official URL: https://www.seekdl.org/conferences/paper/details/7...


This paper explores texture features based image descriptors that makes use of the spatial gray level of bag of visual words model to discriminately improve classification performance for spine MRI images. At first, construct feature vector by using Tamura texture features of six properties of features like: coarseness, contrast, directionality, line-likeness, regularity and roughness for spine MRI images. The second step is to generate a bag of visual word (BoW) to encode feature vector into visual words. Features of these types are used to classify seven categories of different types of spine MRI image such as: spinal cord, disc highlight ,spinal canal size, spinal alignment, in vertebral disc, nerves and abnormalities, to classify them and help the diagnose what cause the back-pain. Experiment results on spine MRI shows significant improvement of classification.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Tamura texture features, visual words, Kmeans, classification
Depositing User: Mr. John Steve
Date Deposited: 25 Mar 2019 12:13
Last Modified: 25 Mar 2019 12:13
URI: http://publications.theired.org/id/eprint/917

Actions (login required)

View Item View Item