An efficient and robust approach for biomedical image retrieval using Zernike moments. (January 2018)

• Record Type: Journal Article
• Authors: Kumar, Yogesh; Aggarwal, Ashutosh; Tiwari, Shailendra; Singh, Karamjeet
• Is Part Of: Biomedical signal processing and control. Volume 39(2018)
• Page Start: 459
• Page End: 473
• Publication Date: 2018-01
• Subjects: Medical imaging -- Image retrieval -- Zernike moments -- Noise invariance; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2017.08.018
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The basic objective is to explore ZMs for biomedical image retrieval of CT and MR images. Experiments performed on both noisy and noise-free CT and MR images. Retrieval performance of the proposed method is far better than the existing as well as recently published approaches. Average improvement of 10–14% in case of noise free images by the proposed approach over the existing approaches. Average improvement of 15–17% in case of noisy images by the proposed approach over the existing approaches. Abstract: Success of any image retrieval system depends heavily on the feature extraction capability of its feature descriptor. In this paper, we present a biomedical image retrieval system which uses Zernike moments (ZMs) for extracting features from CT and MRI medical images. ZMs belong to the class of orthogonal rotation invariant moments (ORIMs) and possess very useful characteristics such as superior information representation capability with minimum redundancy, insensitivity to image noise etc. Existence of these properties as well as the ability of lower order ZMs to discriminate between different image shapes and textures motivated us to explore ZMs for biomedical retrieval application. To prove the effectiveness of our system, experiments have been carried out on both noise-free and noisy versions of two different medical databases i.e. Emphysema-CT database for CT image retrieval and OASIS-MRI database for MRI image retrieval. The proposed ZMs-based approach has been compared with the existing and recently published approaches based on local binary pattern (LBP), local ternary patterns (LTP), local diagonal extrema pattern (LDEP), etc., in terms of various evaluation measures like ARR, ARP, F _ score, and mAP . The results after being investigated have shown a significant improvement (10–14% and 15–17% in case of noise-free and noisy images, respectively) in comparison to the state-of-the-art techniques on the respective databases.