Recognition of isolated elements picture using backpropagation neural network / Melati Sabtu
This project is developed to train the computer programs to recognize objects in the pictures. The purpose of the project is basically to extract and identify each object elements in an image picture. The reviews about the project had been done through the study about image recognition and back-prop...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2005
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/9397/ |
| _version_ | 1848802940605693952 |
|---|---|
| author | Sabtu, Melati |
| author_facet | Sabtu, Melati |
| author_sort | Sabtu, Melati |
| building | UiTM Institutional Repository |
| collection | Online Access |
| description | This project is developed to train the computer programs to recognize objects in the pictures. The purpose of the project is basically to extract and identify each object elements in an image picture. The reviews about the project had been done through the study about image recognition and back-propagation neural network. Several methods that related to this project also been derived through discussion about the image extraction, image preprocessing and some techniques about image segmentation. Gaining information from some resources such as articles and journals contribute various information and knowledge in process of investigation and discussion in order to make this project work smoothly. The project used Back-propagation Neural Network for the algorithm to classified images. Images that capture using digital camera will perform through the algorithm to classified images. The methodology used in the development of this project is basically based on the eight major steps. There are problem assessment, data acquisition, cropping, pre-processing, design, training, testing and documentation. There are three main programs work together. The programs are back-propagation neural network program, training and performance program and recognition program. The momentum rate, learning rate, the number of nodes and layers are the important factors that affect the neural network performance. For overall, the back-propagation algorithm has been proved as a method that can be used for recognition areas. |
| first_indexed | 2025-11-14T21:31:20Z |
| format | Thesis |
| id | uitm-9397 |
| institution | Universiti Teknologi MARA |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T21:31:20Z |
| publishDate | 2005 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | uitm-93972017-01-25T08:05:19Z https://ir.uitm.edu.my/id/eprint/9397/ Recognition of isolated elements picture using backpropagation neural network / Melati Sabtu Sabtu, Melati Neural networks (Computer science) Pattern recognition systems This project is developed to train the computer programs to recognize objects in the pictures. The purpose of the project is basically to extract and identify each object elements in an image picture. The reviews about the project had been done through the study about image recognition and back-propagation neural network. Several methods that related to this project also been derived through discussion about the image extraction, image preprocessing and some techniques about image segmentation. Gaining information from some resources such as articles and journals contribute various information and knowledge in process of investigation and discussion in order to make this project work smoothly. The project used Back-propagation Neural Network for the algorithm to classified images. Images that capture using digital camera will perform through the algorithm to classified images. The methodology used in the development of this project is basically based on the eight major steps. There are problem assessment, data acquisition, cropping, pre-processing, design, training, testing and documentation. There are three main programs work together. The programs are back-propagation neural network program, training and performance program and recognition program. The momentum rate, learning rate, the number of nodes and layers are the important factors that affect the neural network performance. For overall, the back-propagation algorithm has been proved as a method that can be used for recognition areas. 2005 Thesis NonPeerReviewed text en https://ir.uitm.edu.my/id/eprint/9397/1/TD_MELATI%20SABTU%20CS%2005_5%201.pdf Sabtu, Melati (2005) Recognition of isolated elements picture using backpropagation neural network / Melati Sabtu. (2005) Degree thesis, thesis, Universiti Teknologi MARA. |
| spellingShingle | Neural networks (Computer science) Pattern recognition systems Sabtu, Melati Recognition of isolated elements picture using backpropagation neural network / Melati Sabtu |
| title | Recognition of isolated elements picture using backpropagation neural network / Melati Sabtu |
| title_full | Recognition of isolated elements picture using backpropagation neural network / Melati Sabtu |
| title_fullStr | Recognition of isolated elements picture using backpropagation neural network / Melati Sabtu |
| title_full_unstemmed | Recognition of isolated elements picture using backpropagation neural network / Melati Sabtu |
| title_short | Recognition of isolated elements picture using backpropagation neural network / Melati Sabtu |
| title_sort | recognition of isolated elements picture using backpropagation neural network / melati sabtu |
| topic | Neural networks (Computer science) Pattern recognition systems |
| url | https://ir.uitm.edu.my/id/eprint/9397/ |