Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Computing | en_US |
| dc.contributor.advisor | Zhang, Lei (COMP) | - |
| dc.creator | Tsui, Wai Yiu | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/9406 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Probabilistic collaborative representation for hyperspectral image classification | en_US |
| dcterms.abstract | Hyperspectral Image Classification can classify distinct material constituents in hyperspectral data collected by remote sensor [1]. Sparse representation classifier (SRC) and collaborative representation classifier (CRC) are broadly adopted in image classification field. Zhang et al. [2] argued that l2-norm of collaborative representation instead of the l1- norm involved in sparse representation gives a good performance in image classification, whilst probabilistic collaborative representation classifier (ProCRC) explains the good performance of CRC involving l2-norm by exploiting the knowledge of the type of variation that being critical in expressing similarity [3]. This study would first aim at evaluating the performance of ProCRC on hyperspectral image classification. Concerning the curse of dimensionality [4] in hyperspectral image classification, kernel-based classification methods are widely adopted in hyperspectral image classification for mapping the image data to a higher dimensionality for better classification performance. This study would also propose a novel Kernel Probabilistic Collaborative Representation Classifier (KProCRC) for hyperspectral image classification. Experiments with four publicly available real hyperspectral image data sets would demonstrate that the ProCRC can outperform SRC and CRC in terms of classification accuracies, whilst the KProCRC can outperform CRC and ProCRC in terms of classification accuracies. | en_US |
| dcterms.extent | xiii, 122 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2018 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.LCSH | Remote sensing | en_US |
| dcterms.LCSH | Multispectral imaging | en_US |
| dcterms.LCSH | Image processing -- Digital techniques | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 991022109836603411.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 1.57 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/9406