ANTIC: antithetic isomeric cluster patterns for medical image retrieval and change detection. Issue 1 (10th January 2019)

• Record Type: Journal Article
• Authors: Mandal, Murari; Chaudhary, Mallika; Vipparthi, Santosh Kumar; Murala, Subrahmanyam; Gonde, Anil Balaji; Nagar, Shyam Krishna
• Is Part Of: IET computer vision. Volume 13:Issue 1(2019)
• Page Start: 31
• Page End: 43
• Publication Date: 2019-01-10
• Subjects: feature extraction -- image retrieval -- image motion analysis -- Gaussian processes -- object detection -- medical image processing -- video signal processing -- image resolution -- image sequences -- image filtering; antithetic isomeric cluster pattern -- change detection -- feature descriptor -- antithetic isomerism -- antithetical orientations -- multiresolution ANTIC -- feature dimensionality -- rotation invariant features -- biomedical image retrieval applications -- retinopathy image retrieval applications -- intra-ANTIC -- inter-ANTIC -- spatiotemporal feature extraction -- isomeric property -- successive pixel intensity differences -- corner point information -- multiresolution Gaussian filter -- feature dimensionality reduction -- motion change detection -- video sequences; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2018.5206
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : In this study, new feature descriptors are designed for medical image retrieval and change detection applications, respectively. Inspired by isomerism, the authors propose a novel feature descriptor named antithetic isomeric cluster pattern (ANTIC). The ANTIC is defined by the two properties: cluster patterns and antithetic isomerism (ANTI). The cluster pattern corresponds to successive pixel intensity differences at antithetical orientations. Furthermore, the ANTI is characterised by two aspects: first, the clusters are oppositely oriented (antithetical) to each other and second, both adhere to a defined isomeric property. The ANTIC identifies the lines and corner point information in the local neighbourhood across various directions. To attain enhanced robustness, they further proposed multiresolution ANTIC by integrating the multiresolution Gaussian filter. Moreover, to reduce the feature dimensionality, they extended their work to rotation invariant features. The proposed method outperforms other widely used feature descriptors in biomedical and retinopathy image retrieval applications. In addition, they extracted spatiotemporal features by designing intra‐ANTIC and inter‐ANTIC to detect motion changes in video sequences. They validated the effectiveness of these features by conducting experiments on CDNet 2014 dataset. The proposed descriptor achieves better performance in various challenging conditions for change detection as compared to other state‐of‐the‐art techniques.