Automatic gastroscopy video quality assessment

Automatic endoscope video analysis is an essential function for medical robot and computer-aided diagnosis system. However, the performance of these video analysis algorithms are often degraded by low quality endoscope images under the uncontrolled environment, where some of them are difficult even for human ourselves for analysis, such as over-saturated by reflection, too dark or obscure. In this paper, we formulate the problem of gastroscopy video quality evaluation as a supervised framework and detect non-informative frames from gastroscopy video sequence. In order to achieve this goal, HSV histograms, pyramid of histograms of orientation gradients and uniform Local Binary Pattern are extracted to represent frames. And then the Random Forests classifier is used to classify non-informative frames. Experimental results in our new gastroscopy video dataset with about 110000 frames demonstrate that the accuracy of our method is about 95% with the false positive rate lower than 1.3%.