PROJECT TITLE :
Polyp Detection via Imbalanced Learning and Discriminative Feature Learning
Recent achievement of the learning-based classification results in the noticeable performance improvement in automatic polyp detection. Here, building large sensible datasets is very crucial for learning a reliable detector. But, it is practically difficult because of the variety of polyp sorts, expensive inspection, and labor-intensive labeling tasks. For this reason, the polyp datasets sometimes are imbalanced, i.e., the amount of non-polyp samples is much larger than that of polyp samples, and learning with those imbalanced datasets results in a detector biased toward a non-polyp category. During this paper, we have a tendency to propose a data sampling-primarily based boosting framework to find out an unbiased polyp detector from the imbalanced datasets. In our learning theme, we tend to learn multiple weak classifiers with the datasets rebalanced by up/down sampling, and generate a polyp detector by combining them. As well, for enhancing discriminability between polyps and non-polyps that have similar appearances, we propose an effective feature learning method using partial least square analysis, and use it for learning compact and discriminative features. Experimental results using challenging datasets show obvious performance improvement over different detectors. We tend to any prove effectiveness and usefulness of the proposed ways with intensive evaluation.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here