Improved Bag of Feature for Automatic Polyp Detection in Wireless Capsule Endoscopy Images

Wireless capsule endoscopy (WCE) needs computerized method to reduce the review time for its large image data. In this paper, we propose an improved bag of feature (BoF) method to assist classification of polyps in WCE images. Instead of utilizing a single scale-invariant feature transform (SIFT) feature in the traditional BoF method, we extract different textural features from the neighborhoods of the key points and integrate them together as synthetic descriptors to carry out classification tasks. Specifically, we study influence of the number of visual words, the patch size and different classification methods in terms of classification performance. Comprehensive experimental results reveal that the best classification performance is obtained with the integrated feature strategy using the SIFT and the complete local binary pattern (CLBP) feature, the visual words with a length of 120, the patch size of 8*8, and the support vector machine (SVM). The achieved classification accuracy reaches 93.2%, confirming that the proposed scheme is promising for classification of polyps in WCE images. Note to Practitioners-WCE is a new technology to review the digestive tract diseases especially for the small intestine. But the large amount of video data produced in each examination is a major problem for its further application, motivating the design of a computer-aided detection system for different diseases in WCE images. We present an automatic polyp WCE image detection scheme with bag of features and textural features. Results from comprehensive comparison experiments suggest that the proposed computer-aided polyp detection system achieve better classification accuracy. This work also can support other related disease detection applications.