A Novel Global and Local Saliency Coding Method for Polyp Recognition in WCE Videos

Wireless Capsule Endoscopy (WCE) allows physicians to examine the entire digestive system without any surgical operation. Although it provides a noninvasive imaging approach to access the gastrointestinal (GI) tract, the biggest drawback of this technology is the large numbers of images need to be diagnosed. In this paper, a global and local saliency coding (GLSAC) method is proposed to detect polyps from WCE images. We first extract the Scale Invariant Feature Transform (SIFT) features from image patches and apply K-means method on these features to obtain visual words. Since saliency is a fundamental characteristic of feature coding, a novel coding strategy: the global and local saliency coding (GLSAC) is proposed. The calculation of the global saliency coding and local saliency coding is obtained by the exponential function of feature differences to the nearest visual code and all visual words. Specifically, the local saliency strategy considers coding bases based on the distribution of the distances between the features and visual words adaptively. Furthermore, we present a concentric circle-based spatial-rotation-invariant pooling strategy to obtain final image features from the patch features. Experiment results achieve promising 91.13% accuracy and 92.51% sensitivity, validating the effectiveness of the proposed method. Moreover, the comparison results show that our strategy outperforms the state-of-the-art methods on the polyp recognition task.