An optimal IMF selection based on fast BEEMD with Dlac analysis for detection of Polyp and Ulcer in WCE images

The main contribution of this paper is the presentation of a novel tool for WCE image analysis and classification by exploiting color-texture features. The proposed scheme has based on the ingenious combination of optimal selection of image components (IMFs) of BEEMD and DLac, applied on the green/red component of WCE images in order to identify ulcerations and polyp affected images from WCE images. Optimal IMF's of BEEMD was exploited to reveal the intrinsic components (IMFs) of the images in order to achieve data driven, Coefficient of standard Deviation and efficient SVM classifier to boost the distinctness between polyp and ulcer regions. However, DLac analysis facilitates to extract efficient texture characteristics. The proposed approach has evaluated on selected WCE images, captured from patients, depicting ulcer and polyp tissue. The optimum image components (IMFs) that contain the majority of texture information include IMFs 5- 8which produce 100% accuracy for ulcer images. Individual IMFs score up to 80 % classification accuracy, while their higher exploitation as a group enhances the detection rate up to 93.34% for ulcer and 90% for polyp tissue.