Leveraging active learning for relevance feedback using an information theoretic diversity measure
CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval
| Hi-index | 0.00 |
The relevance feedback approach is one of widely used image retrieval technique. The main role of relevance feedback is to make the links between human's high level concept andcomputer's low level feature. Even though, there are several relevance feedback algorithms, some algorithms use ad-hoc heuristics or assume that feature vectors are independent regardless of their correlation. In this paper, we propose a new relevance feedback algorithm using Probabilistic Neural Networks (PNN) supporting multi-class learning. In our approach, there is no need to assume that feature vectors are independent and it permits system to insert additional classes for detail classification. In addition, it does not take long computation time for training, because it has only four layers. In PNN classification process, we keep user's entire past feedback actions as history in order to improve performance for future iterations. By history, our approach can capture the user's subjective intension more precisely and prevent retrieval performance from fluctuating or degrading in the next iteration. To validate the effectiveness of our feedback approach, we incorporate the proposed algorithm to our region-based image retrieval tool, FRIP (Finding Region In the Pictures). The efficacy of our method is validated using a set of 3000 images from Corel-photo CD.