Title: Random forest-based active learning for content-based image retrieval

Authors: Nilesh Bhosle; Manesh Kokare

Addresses: Department of Electronics and Telecommunication Engineering, D.Y. Patil College of Engineering, Ambi, Pune-410506, India ' Department of Electronics and Telecommunication Engineering, S.G.G.S. Institute of Engineering and Technology, Vishnupuri, Nanded-431606, India

Abstract: The classification-based relevance feedback approach suffers from the problem of imbalanced training dataset, which causes instability and degradation in the retrieval results. In order to tackle with this problem, a novel active learning approach based on random forest classifier and feature reweighting technique is proposed in this paper. Initially, a random forest classifier is used to learn the user's retrieval intention. Then, in active learning the most informative classified samples are selected for manual labelling and added in training dataset, for retraining the classifier. Also, a feature reweighting technique based on Hebbian learning is embedded in the retrieval loop to find the weights of most perceptive features used for image representation. These techniques are combined together to form a hypothesised solution for the image retrieval problem. The experimental evaluation of the proposed system is carried out on two different databases and shows a noteworthy enhancement in retrieval results.

Keywords: content-based image retrieval; CBIR; relevance feedback; random forest learning; active learning; semantic gap; feature reweighting; information retrieval.

DOI: 10.1504/IJIIDS.2020.108223

International Journal of Intelligent Information and Database Systems, 2020 Vol.13 No.1, pp.72 - 88

Accepted: 13 Nov 2019
Published online: 06 Jul 2020 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article