Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/342533
Title: | Novel content based medical image retrieval scheme with GWO optimized SVM for high retrieval rates |
Researcher: | Benyl Renita, D |
Guide(s): | Seldev Christopher, C |
Keywords: | Medical image retrieval Computer tomography GWO-SVM |
University: | Anna University |
Completed Date: | 2020 |
Abstract: | Content Based Medical Image Retrieval (CBMIR) systems mainly support for retrieving the useful information from a huge set of medical images.CBMIR procedures are useful in zones like Biomedicine, Education, Military, Web Image organization and SearchingMany researches proposed various methodologies in the field of medical Image Retrieval. Now-a-days the CBMIR is fetching a source of precise and fast retrieval.To enhance the execution of CBIR, a considerable amount of strategies have been created. These techniques are helpful in classifying an image. Content-based image retrieval (CBIR) is a technique of searching the images based on the content of the image. CBIR is a promising technology to enrich the core functionality of picture archiving and communication systems (PACS) in medicine. CBIR in medical domain has a potential for making a strong impact in diagnostics, research and education. In this thesis, content based medical image retrieval systems based on new techniques have been proposed. In the conventional CBIR systems, the content of the image is represented by features such as color, shape and texture of the image. Various shape feature extraction methods are studied and a new shape feature extraction method is proposed. A medical image retrieval system based on the new shape feature descriptor is developed and experimental results show that the proposed CBIR system s retrieval performance is high, when compared with other CBIR systems based on the existing shape descriptors. Various texture feature extraction methods are studied and a new texture descriptor isproposed. A medical image retrieval system based on this new texture descriptor is developed. The experimental results show that this new framework outperforms the other existing texture descriptor in medical CBIR systems. This research aims to investigate an effective CBIR framework for combining the primary image features. A multiple classifier framework for content based image retrieval in medical domain has been proposed and implemented |
Pagination: | xvii,165 p. |
URI: | http://hdl.handle.net/10603/342533 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 66.16 kB | Adobe PDF | View/Open |
02_certificates.pdf | 232.55 kB | Adobe PDF | View/Open | |
03_vivaproceedings.pdf | 376.57 kB | Adobe PDF | View/Open | |
04_bonafidecertificate.pdf | 4.12 MB | Adobe PDF | View/Open | |
05_abstracts.pdf | 1.9 MB | Adobe PDF | View/Open | |
06_acknowledgements.pdf | 4.21 MB | Adobe PDF | View/Open | |
07_contents.pdf | 1.9 MB | Adobe PDF | View/Open | |
08_listoftables.pdf | 1.9 MB | Adobe PDF | View/Open | |
09_listoffigures.pdf | 1.9 MB | Adobe PDF | View/Open | |
10_listofabbreviations.pdf | 1.9 MB | Adobe PDF | View/Open | |
11_chapter1.pdf | 1.91 MB | Adobe PDF | View/Open | |
12_chapter2.pdf | 1.91 MB | Adobe PDF | View/Open | |
13_chapter3.pdf | 1.9 MB | Adobe PDF | View/Open | |
14_chapter4.pdf | 1.91 MB | Adobe PDF | View/Open | |
15_chapter5.pdf | 1.91 MB | Adobe PDF | View/Open | |
16_chapter6.pdf | 1.9 MB | Adobe PDF | View/Open | |
17_conclusion.pdf | 1.9 MB | Adobe PDF | View/Open | |
18_references.pdf | 1.9 MB | Adobe PDF | View/Open | |
19_listofpublications.pdf | 46.68 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 87.28 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: