Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electronic and Information Engineering | en_US |
| dc.creator | Lin, Jing | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/4597 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Living plants recognition from leaf features | en_US |
| dcterms.abstract | This thesis presents leaf image feature extraction and retrieval. Two main contributions are reported in the thesis. They include: (1) specific features of leaf shape and texture; and (2) a botany ontology based similarity measure of leaf images. In the first investigation, we propose four descriptors to characterize a leaf in terms of shape, size, as well as texture. The first two features are shape features which describe the lobation and margin calculated base on the CCD curve. A leaf can be labeled as either a lobed leaf or an unlobed leaf by calculating the local minimums of the normalized CCD curve. Leaves have two local minimum CCD curve are unlobed; others are lobed. The second shape feature called teeth indicates the margin of a leaf is either entire or toothed. Besides the above two shape features, a feature called comparative area is proposed. By computing the ratio of the leaf area and the black bar area, plants with large size leaves and those of small size leaves can be easily differentiated. For the texture, a region-based Grey Level Co-occurrence Matrix is proposed to get rid of the influence from the background when computing the contrast and homogeneity of a leaf image. In the second investigation, we propose a botany ontology based two-stage search algorithm* used in leaf images similarity measure. In the first stage, a query image is categorized to a certain class based on the botany ontology; in the second stage, only the images in the same class are searched using the Euclidean distance. By using this method, the precision of the retrieval results can be improved. | en_US |
| dcterms.extent | x, 98 leaves : ill. ; 30 cm. | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2009 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations. | en_US |
| dcterms.LCSH | Image processing -- Digital techniques. | en_US |
| dcterms.LCSH | Plants -- Imaging. | en_US |
| dcterms.LCSH | Leaves -- Imaging. | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b23030604.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 14.62 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/200/4597