Pit pattern classification using extended Local Binary Patterns

In this work we present a method for automated classification of endoscopic images according to the pit pattern classification scheme. Images taken during colonoscopy are transformed using a modified version of the local binary patterns operator (LBP). Then, two-dimensional histograms based on the LBP data from different color channels are created. Finally, the classification is carried out by employing the nearest-neighbors (1-NN) classifier in conjunction with the Bhattacharyya distance metric. The experimental results show that the extended LBP operator delivers superior results and an automated classification of endoscopic images based on the pit pattern classification scheme is feasible.