Logo

Detection and Classification of Bleeding Using Statistical Color Features for Wireless Capsule Endoscopy Images

Suman, Shipra and Hussin, Fawnizu Azmadi and Nicolas, Walter and Malik, Aamir Saeed and Hooi, Shaiw and Goh, Khean Lee (2016) Detection and Classification of Bleeding Using Statistical Color Features for Wireless Capsule Endoscopy Images. In: International Conference on Signal and Information Processing (IConSIP-2016), 6-8 Oct 2016, Hyderabad, India. (In Press)

[img] PDF - Accepted Version
Restricted to Registered users only

301Kb

Abstract

Wireless capsule endoscopy (WCE) is an immense discovery for Gastrointestinal Tract (GIT) diagnosis and it can visualize complete area in GIT. However, A severe problem associated with this new technology is that there are huge amount of images to be inspected by clinician through naked eyes which causes visual fatigue often and it leads to false detection. Therefore an automatic platform is much needed to find significant disease detection more accurately. This approach focuses on various color features which are also quite important and concerned criteria for clinicians. Here we propose five color features in HSV color space to differentiate between bleeding and non-bleeding frames. Support vector machine (SVM) is used as classifier to validate the performance of the proposed method and authorize the frames status. The result outcome shows that proposed method for feature and classification is quite effective and achieve high performance classifier.

Item Type:Conference or Workshop Item (Paper)
Academic Subject One:Academic Department - Electrical And Electronics - Pervasisve Systems - Digital Electronics - Programmable Devices
Departments / MOR / COE:Centre of Excellence > Center for Intelligent Signal and Imaging Research
ID Code:11953
Deposited By: Dr Fawnizu Azmadi Hussin
Deposited On:07 Oct 2016 01:42
Last Modified:19 Jan 2017 08:20

Repository Staff Only: item control page

Document Downloads

More statistics for this item...