Pengecaman Plat Kereta Menggunakan Rangkaian Neural Dan Pemprosesan Imej

ABDULLAH, KILAUSURIA (2000) Pengecaman Plat Kereta Menggunakan Rangkaian Neural Dan Pemprosesan Imej. Other thesis, Universiti Teknologi Malaysia.

[img]
Preview
PDF
kilausuria_abdullah.PDF

Download (3296Kb) | Preview

Abstract

This research is carried out to implement a number plate recognition solution in Malaysia based on neural network and image processing. The main task for this implementation can be divided into three categories; the location of the number plate from the image taken, character segmentation process and character recognition process. Even then, this project will not include the process of the location of the number plates from the image. This project focus on the recognition of the number plates which include character segmentation process, image enhancement process, feature extraction process and character recognition process. In the character segmentation process. Top Down Block Segmentation and Run Length Smoothing Algorithm are to be used. Where as image enhancement proces as Two Pass Thinning Algorithm is to be used and Geometric Moments Invariant method is used for feature extraction process. For the recognition process will be using Feed Forward Multi Layer Perceptron and Back Propagation Algorithm.

Item Type: Thesis (Other)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Computer Science and Information System > Software Engineering
Depositing User: Unnamed user with email knizam@utm.my
Date Deposited: 04 Jul 2013 07:09
Last Modified: 04 Jul 2013 07:09
URI: http://ir.fsksm.utm.my/id/eprint/1367

Actions (login required)

View Item View Item