|Title:||Object recognition using multi-resolution wavelet transform|
|Subject:||Optical pattern recognition|
Image processing -- Digital techniques
Hong Kong Polytechnic University -- Dissertations
Department of Electronic and Information Engineering
|Pages:||64 leaves : ill. ; 30 cm|
|Abstract:||In this project, a software system written in C for recognition of planar objects or nearly planar objects in a three-dimensional space obtained by a camera under arbitrary orientation is implemented. The pre-processing steps of segmentation of an image and the parameterization of a contour are assumed to be performed by commonly available packages. Features, which are invariant to affine transformation, are extracted from the contours with the multi-resolution approach by using wavelet. Hence a set of feature points in different resolution levels is obtained. A dissimilarity function is then used in matching objects to their models in the database. This function is calculated only from the extreme points of each level of the features points instead of using all the points. The complete system is then tested by a set of aeroplanes viewed from different angles and experimental results show that the recognition rate is 94 % in most favorite case and over 50 % in average. Discussion on the recognition features is done with comparison on plots of the feature data domain. Besides, case studies on resolution level mismatch is also provided.|
|Rights:||All rights reserved|
Files in This Item:
|b15383647.pdf||For All Users (off-campus access for PolyU Staff & Students only)||2.38 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: