Full metadata record
|dc.contributor||Department of Electronic Engineering||en_US|
|dc.publisher||Hong Kong Polytechnic University||-|
|dc.rights||All rights reserved||en_US|
|dc.title||Recognition of degraded character images||en_US|
|dcterms.abstract||Gray-level character images extracted from a natural scene are usually ambiguous because they are probably degraded by noise, inadequate resolution of sensor and blurring effect of lens system. Automatic recognition of these character images is therefore non-trivial. Two robust and reliable character recognition algorithms are proposed in this dissertation specially for recognizing this type of images. The proposed recognition systems base on mathematical morphology image processing algorithms. The first system performs grey-scale morphological operations to extract strokes from the character image. The features extracted are organised as a feature vector. This vector is then classified based on a weighted distance measure between the vector and the reference vectors. The second system applies the concept of fuzziness to characterise strokes and their spatial relations. Fuzzy attributed graphs (FAGs) are then used to represent the structural information of characters. These FAGs are compared with reference FAGs to accomplish the classification of character images. In the testing phase of the systems, 51 images of license plate are used. The total number of character images on these plates are 303. A character block segmentation algorithm is proposed to isolate these character images from the images of license plate. The algorithm makes use of the c-means clustering method to adaptively threshold the grey-scale image. In this test, both character recognition systems proposed can achieve 99.7% recognition rate.||en_US|
|dcterms.extent||71,  leaves : ill. ; 30 cm||en_US|
|dcterms.LCSH||Optical character recognition devices||en_US|
|dcterms.LCSH||Optical data processing||en_US|
|dcterms.LCSH||Hong Kong Polytechnic University -- Dissertations||en_US|
Files in This Item:
|b14418836.pdf||For All Users (off-campus access for PolyU Staff & Students only)||2.37 MB||Adobe PDF||View/Open|
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: