Multi-level colored directional motif histograms for content-based image retrieval

Abstract

Color features and local geometrical structures are the two basic image features which are sufficient to convey the image semantics. Both of these features show diverse nature on the different regions of a natural image. Traditional local motif patterns are standard tools to emphasize these local visual image features. These motif-based schemes consider either structural orientations or limited directional patterns which are not sufficient to realize the detailed local geometrical properties of an image. To address these issues, we have proposed a new multi-level colored directional motif histogram (MLCDMH) for devising a content-based image retrieval scheme. The proposed scheme extracts local structural features at three different levels. Initially, MLCDMH scheme extracts directional structural patterns from a $$3 \times 3$$ pixel grids of an image. This reflects the $$9^9$$ different structural arrangements using 28 directional patterns. Next, we have used a weighted neighboring similarity (WNS) scheme to exploit the uniqueness of each motif pixel in its local surrounding. The WNS scheme will compute the importance of each directional motif pattern in its $$3 \times 3$$ local neighborhood. In the last level, we have fused all directional motif images into a single directional difference matrix which reflects the local structural and directional motif features in detail and also reduces the computation overhead. The MLCDMH considers all possible permutations and rotations of the motif patterns to generate rotational invariant structural features. The image retrieval performance of this proposed scheme has been evaluated using different Corel/natural, object, texture and heterogeneous image datasets. The results of the retrieval experiments have shown satisfactory improvement over other motif- and non-motif-based CBIR approaches.