Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476538Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Assoc. Prof. Dr. Siti Norul Huda Sheikh Abdullah | |
| dc.contributor.author | Firas Mahmood Khaleel. (P61034) | |
| dc.date.accessioned | 2023-10-06T09:20:36Z | - |
| dc.date.available | 2023-10-06T09:20:36Z | - |
| dc.date.issued | 2014-06-22 | |
| dc.identifier.other | ukmvital:118712 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476538 | - |
| dc.description | Object localization is one of the most important stages in license plate recognition application. Object localization searches and locates the region of interest of license plate automatically and eases the subsequent recognition phase where each character of the license plate can be identified accurately. Speeded Up Robust Features (SURF), which is a sibling with faster mode algorithm of Scale Invariant Feature Transform (SIFT), has used widely in image processing for searching invariant object similarity within images. However, SURF descriptor alone is still insufficient and inefficient to locate the license plate because the features between two images cannot be compared based on their locations only, since the positions and number of features may locate in different part of each image. Therefore, this thesis proposes a combination approach based on SURF method to improve license plate localization process. Taking the advantage of K-means clustering algorithm, SURF feature descriptors are clustered by using K-means clusters centroid to form a novel way of localizing the license plate’s region in an image. Finally, Laplacian filter and Multi-Layer Perceptron Back Propagation Neural Network are also applied for feature extraction and classification phases respectively. The proposed work has been tested on Malaysian license plate datasets as off-line and on-line modes, where the offline mode denoted by stand-still image test captured in out-door environment, while the online mode denoted by the closed circuit television and webcam tests. Finally, the obtained results showed that the proposed method can achieve up to 90.69%, 90.32% and 98% of accuracy rates for the license plate localization in standstill image, video and webcam tests subsequently. The license plate recognition results also demonstrate the proposed method is more promising than the standard SURF.,Tesis ini tiada Perakuan Tesis Sarjana / Doktor Falsafah" | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
| dc.rights | UKM | |
| dc.subject | Application software-Development. | |
| dc.subject | Mobile computing | |
| dc.title | License plate recognition based on speeded up robust features and k-means clustering | |
| dc.type | theses | |
| dc.format.pages | 118 | |
| dc.identifier.callno | QA76.76.A65.K484 2014 3 | |
| dc.identifier.barcode | 002601 (2014) | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_118712+SOURCE1+SOURCE1.0.PDF Restricted Access | 1.15 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.