New flexible directional filter bank by tuning Hermite transform parameters for content based medical image retrieval. Issue 11 (28th July 2020)

• Record Type: Journal Article
• Authors: Shinde, Amita; Rahulkar, Amol; Patil, Chetankumar
• Is Part Of: IET image processing. Volume 14:Issue 11(2020)
• Page Start: 2403
• Page End: 2416
• Publication Date: 2020-07-28
• Subjects: polynomials -- filtering theory -- content‐based retrieval -- visual databases -- transforms -- medical image processing -- image retrieval -- feature extraction -- biomedical MRI -- channel bank filters; new flexible directional filter bank -- content based medical image retrieval -- content‐based medical image retrieval -- imperative Hermite transform parameters -- Hermite polynomial -- flexible Hermite orthogonal basis -- retrieval performance -- 2D diamond shape filter -- McClellan transformation -- directional decomposition -- directionally decomposed images -- mean retrieval precision -- medical image databases -- magnetic resonance imaging; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0252
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : This study presents a flexible directional filter bank (DFB) by tuning Hermite transform parameters for content‐based medical image retrieval (CBMIR). Two imperative Hermite transform parameters such as the scale of Gaussian kernel and the order of Hermite polynomial are tuned to adapt the flexible Hermite orthogonal basis to improve the retrieval performance of the CBMIR system. First, the tuned 1D Hermite filter transformed into 2D diamond shape filter by McClellan transformation and made it adequate for the directional decomposition of images using DFB structure. The dominant features of these directionally decomposed images are extracted by the rotation‐invariant local neighbourhood frequency pattern. The mean retrieval precision is used as a high‐level criterion to measure retrieval performance. The proposed method is assessed on three medical image databases: two for computed tomography and one for magnetic resonance imaging and achieved 99.41, 89.07, and 88.71% mean precision, respectively, when ten images are returned by the system.