Wood species recognition using CNN / Mohammad Othman Norhaiza

This study aims to develop an automated wood species recognition model using Convolutional Neural Networks (CNNs) based on macroscopic wood images. CNNs, known for their effectiveness in image recognition, leverage transfer learning to address limited training data challenges. The study pursues thre...

Full description

Saved in:

Bibliographic Details
Main Author:	Norhaiza, Mohammad Othman
Format:	Thesis
Language:	English
Published:	2024
Subjects:	Neural networks (Computer science)
Online Access:	https://ir.uitm.edu.my/id/eprint/96518/1/96518.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uitm-ir.96518
record_format	uketd_dc
spelling	my-uitm-ir.965182024-06-06T06:38:04Z Wood species recognition using CNN / Mohammad Othman Norhaiza 2024 Norhaiza, Mohammad Othman Neural networks (Computer science) This study aims to develop an automated wood species recognition model using Convolutional Neural Networks (CNNs) based on macroscopic wood images. CNNs, known for their effectiveness in image recognition, leverage transfer learning to address limited training data challenges. The study pursues three objectives: feature extraction using CNNs, developing a wood species recognition system, and evaluating CNN model accuracy. Accurate wood identification is crucial for quality control, combating illegal logging, and regulatory compliance. Computer vision, particularly CNNs, offer automated solutions, surpassing labour-intensive traditional methods. The proposed CNN model utilises RGB images for feature extraction and transfer learning for efficient training on limited datasets. Evaluation compares two CNN models, Xception and VGG-16, with Xception demonstrating superior accuracy, precision, and F1-score. The research addresses wood species identification challenges, enhancing industry efficiency. Limitations include dataset size, environmental variability during image capture, and hardware constraints. Future work suggests dataset expansion, consideration of environmental factors, exploration of advanced techniques, and hardware infrastructure upgrades for scalability. Continuous refinement of wood species recognition systems is essential to meet evolving industry demands. 2024 Thesis https://ir.uitm.edu.my/id/eprint/96518/ https://ir.uitm.edu.my/id/eprint/96518/1/96518.pdf text en public degree Universiti Teknologi MARA, Terengganu College of Computing, Informatics and Media Ab Jabal, Mohamad Faizal
institution	Universiti Teknologi MARA
collection	UiTM Institutional Repository
language	English
advisor	Ab Jabal, Mohamad Faizal
topic	Neural networks (Computer science)
spellingShingle	Neural networks (Computer science) Norhaiza, Mohammad Othman Wood species recognition using CNN / Mohammad Othman Norhaiza
description	This study aims to develop an automated wood species recognition model using Convolutional Neural Networks (CNNs) based on macroscopic wood images. CNNs, known for their effectiveness in image recognition, leverage transfer learning to address limited training data challenges. The study pursues three objectives: feature extraction using CNNs, developing a wood species recognition system, and evaluating CNN model accuracy. Accurate wood identification is crucial for quality control, combating illegal logging, and regulatory compliance. Computer vision, particularly CNNs, offer automated solutions, surpassing labour-intensive traditional methods. The proposed CNN model utilises RGB images for feature extraction and transfer learning for efficient training on limited datasets. Evaluation compares two CNN models, Xception and VGG-16, with Xception demonstrating superior accuracy, precision, and F1-score. The research addresses wood species identification challenges, enhancing industry efficiency. Limitations include dataset size, environmental variability during image capture, and hardware constraints. Future work suggests dataset expansion, consideration of environmental factors, exploration of advanced techniques, and hardware infrastructure upgrades for scalability. Continuous refinement of wood species recognition systems is essential to meet evolving industry demands.
format	Thesis
qualification_level	Bachelor degree
author	Norhaiza, Mohammad Othman
author_facet	Norhaiza, Mohammad Othman
author_sort	Norhaiza, Mohammad Othman
title	Wood species recognition using CNN / Mohammad Othman Norhaiza
title_short	Wood species recognition using CNN / Mohammad Othman Norhaiza
title_full	Wood species recognition using CNN / Mohammad Othman Norhaiza
title_fullStr	Wood species recognition using CNN / Mohammad Othman Norhaiza
title_full_unstemmed	Wood species recognition using CNN / Mohammad Othman Norhaiza
title_sort	wood species recognition using cnn / mohammad othman norhaiza
granting_institution	Universiti Teknologi MARA, Terengganu
granting_department	College of Computing, Informatics and Media
publishDate	2024
url	https://ir.uitm.edu.my/id/eprint/96518/1/96518.pdf
_version_	1804889991774470144

Wood species recognition using CNN / Mohammad Othman Norhaiza

Similar Items