Adaptive Salient Block Based Image Retrieval in Multi-Feature Space

In this paper, an approach to tackle the object based image retrieval problem is proposed. The core technique is designed to adaptively and efficiently locate the salient block of objects of interest in each image. The salient blocks are then used as cues for representing the whole images when semantic-based searching is performed. Relevance Feedback is seamlessly integrated in the retrieval process. In each iteration, the user is requested to select images relevant to the query concept. Salient blocks of the selected images are used as training examples. To guarantee the accuracy of salient block matching, the similarities of block regions are calculated within an optimised concept-specific multi-feature space. In the multi-feature space, it is expected that the visual patterns of objects of interest can be effectively discriminated from irrelevant regions. This multi-feature space metric is learned from a group of representative salient blocks using a multi-objective optimisation approach. An empirical assessment of the proposed technique was conducted. Selected results show good performance of the proposed approach.