Citation

Lim, Sin Liang and Tan, Hui Hui (2022) Malaysian Vanity License Plate Recognition Using Convolutional Neural Network. FYP Poster Contest 2022. (Submitted)

Image (FYP Poster) 11_1161104336 TAN HUI HUI_SLLim_FYP2 Poster.png - Presentation Restricted to Repository staff only Download (1MB)

Abstract

Convolutional Neural Network (CNN) is used to train a Malaysian vanity license plate recognition model to recognize vanity license plate available in Malaysia. The type of transfer learning method applied in this project to train the model is finetuning. A modified pretrained ResNet18 network architecture is used to train the Malaysian vanity license plate recognition model. Some hyperparameters such as batch size, learning rate, step size, gamma and momentum are set before training. The optimizer used in this project is SGD (Stochastic Gradient Descent). The available Malaysian vanity license plates images provided by Tapway company consist of 3 types, which are MALAYSIA, PUTRAJAYA and NORMAL LP (known as Normal License plate). All the images are randomly split into 70%, 20%, and 10% for training set, validation set and testing set. After that, the images are cropped, normalized and transformed into tensors for training. The training is carried out for 70 epochs. Both models trained from original and modified pretrained ResNet18 network architectures are compared and discussed. The accuracy for both models of Malaysian vanity license plate recognition models is 92%. Both training models using original ResNet18 and modified ResNet18 network architecture approach can be used to train the Malaysian vanity license plate recognition model and obtain similar results.

Item Type:	Other
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75-76.95 Calculating machines T Technology > TA Engineering (General). Civil engineering (General)
Divisions:	Faculty of Engineering (FOE)
Depositing User:	Dr. Sin Liang Lim
Date Deposited:	25 Oct 2022 02:50
Last Modified:	25 Oct 2022 05:28
URII:	http://shdl.mmu.edu.my/id/eprint/10568

Downloads

Edit (login required)