@inproceedings{scholars8833,
           title = {Detection and classification of bleeding using statistical color features for wireless capsule endoscopy images},
         journal = {2016 International Conference on Signal and Information Processing, IConSIP 2016},
       publisher = {Institute of Electrical and Electronics Engineers Inc.},
             doi = {10.1109/ICONSIP.2016.7857440},
            year = {2017},
            note = {cited By 8; Conference of 2016 International Conference on Signal and Information Processing, IConSIP 2016 ; Conference Date: 6 October 2016 Through 8 October 2016; Conference Code:126490},
             url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85016123838&doi=10.1109\%2fICONSIP.2016.7857440&partnerID=40&md5=b0b97d9464e5b183ae7c9d21f1b79972},
        keywords = {Classifiers; Color; Diagnosis; Endoscopy; Feature extraction; Image classification; Support vector machines; Vector spaces, Color features; Color space; Disease detection; False detections; Gastrointestinal tract; HSV color spaces; Wireless capsule endoscopy; Wireless capsule endoscopy image, Classification (of information)},
        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. {\^A}{\copyright} 2016 IEEE.},
          author = {Suman, S. and Hussin, F. A. B. and Walter, N. and Malik, A. S. and Ho, S. H. and Goh, K. L.},
            isbn = {9781509015221}
}