Multichannel Distributed Local Pattern for Content Based Indexing and Retrieval
This work addresses the problem of improving image retrieval accuracy for researchers and practitioners in computer vision, though it appears incremental as it builds on existing local pattern methods.
The authors proposed a novel color feature descriptor called Multichannel Distributed Local Pattern (MDLP) for content-based image retrieval, which combines local binary and mesh patterns to robustly extract texture arrangements across color channels, achieving substantial improvements in retrieval performance on benchmark datasets like Corel-5000, Corel-10000, and MIT-Color Vistex.
A novel color feature descriptor, Multichannel Distributed Local Pattern (MDLP) is proposed in this manuscript. The MDLP combines the salient features of both local binary and local mesh patterns in the neighborhood. The multi-distance information computed by the MDLP aids in robust extraction of the texture arrangement. Further, MDLP features are extracted for each color channel of an image. The retrieval performance of the MDLP is evaluated on the three benchmark datasets for CBIR, namely Corel-5000, Corel-10000 and MIT-Color Vistex respectively. The proposed technique attains substantial improvement as compared to other state-of- the-art feature descriptors in terms of various evaluation parameters such as ARP and ARR on the respective databases.