Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/333519
Title: | Texture based medical and fabric image classification by using multiscale and maximum like hood classification technique with local binary patterns |
Researcher: | Murugappan, V |
Guide(s): | Sabeenian, R S |
Keywords: | Texture Classification technique Local binary patterns |
University: | Anna University |
Completed Date: | 2020 |
Abstract: | Texture is assumed to be an integral part of various PC vision applications. A variety of strategies have been proposed for the analysis of textures and texture surfaces. Variety causes high preconditions for setting up various inspection techniques by changing the illumination and imaging conditions, such as the presence of texture. More importantly, specific applications tend to create a lot of complex texture information to prepare, and people should take care to keep the final goal taken care of. Good texture information review is exceptionally time consuming and time consuming. There is usually no reason for the convenience and essential attributes of authenticity or texture, the information that must be obtained from the image, and other prior knowledge. This is a complex job in the texture survey. In this work proposes a multi-class way to deal with learning and naming part based newlinetexture appearance models to be utilized as a part of scene texture acknowledgment employing three innovative strategies and furthermore a self-loader way to deal with learning texture appearance models for viewbased texture classification of medical and fabric image is proposed. The first approach applies the Multi-Scale Gabor Rotation-Invariant Local Binary Pattern (MGRLBP) used to analysis the texture features of a biomedical, fabric images and joined the weight aspect that is presented by the direct measure to obtain the last texture feature of an input image. By using multi-scale binary pattern (MSBP) classifier with the immediate action and Multi-Scale Gabor Rotation-Invariant Local Binary Pattern algorithm. Both quantitative and qualitative methods are applied to assess the classification results. newline newline |
Pagination: | xv,141p. |
URI: | http://hdl.handle.net/10603/333519 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 26.46 kB | Adobe PDF | View/Open |
02_certificates.pdf | 107.23 kB | Adobe PDF | View/Open | |
03_vivaproceedings.pdf | 118.34 kB | Adobe PDF | View/Open | |
04_bonafidecertificate.pdf | 124.88 kB | Adobe PDF | View/Open | |
05_abstracts.pdf | 48.56 kB | Adobe PDF | View/Open | |
06_acknowledgements.pdf | 158.29 kB | Adobe PDF | View/Open | |
07_contents.pdf | 53.73 kB | Adobe PDF | View/Open | |
08_listoftables.pdf | 45.95 kB | Adobe PDF | View/Open | |
09_listoffigures.pdf | 60.96 kB | Adobe PDF | View/Open | |
10_listofabbreviations.pdf | 46.15 kB | Adobe PDF | View/Open | |
11_chapter1.pdf | 597.68 kB | Adobe PDF | View/Open | |
12_chapter2.pdf | 148.35 kB | Adobe PDF | View/Open | |
13_chapter3.pdf | 684.36 kB | Adobe PDF | View/Open | |
14_chapter4.pdf | 303.27 kB | Adobe PDF | View/Open | |
15_chapter5.pdf | 285.11 kB | Adobe PDF | View/Open | |
16_chapter6.pdf | 256.9 kB | Adobe PDF | View/Open | |
17-chapter7.pdf | 77.4 kB | Adobe PDF | View/Open | |
18_conclusion.pdf | 77.4 kB | Adobe PDF | View/Open | |
19_references.pdf | 105.63 kB | Adobe PDF | View/Open | |
20_listofpublications.pdf | 68.62 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 125.99 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: