Saufiah Abdul Rahim, Dr.
http://dspace.unimap.edu.my:80/xmlui/handle/123456789/32993
This page provides access to scholarly publications by UniMAP Faculty members and researchers.2024-03-29T05:26:08ZSoftware solution for Testing Image Processing Algorithm on Conveyor-Based Vision Systems
http://dspace.unimap.edu.my:80/xmlui/handle/123456789/69035
Software solution for Testing Image Processing Algorithm on Conveyor-Based Vision Systems
Azman, Muhamad Yusof; Ali Yeon, Md Shakaff; Saufiah, Abdul Rahim
Vision systems have been used in many applications that intends to reduce the need for human operators. This is especially true for tasks that are simple but repetitive in nature, which is largely applicable to most manufacturing and agriculture’s post-harvest processes. Many such processes utilize conveyor-based systems where the objects being processed are placed
on a conveyor belt that runs through multiple processing stations. Implementing a vision system to capture images of an object that is moving usually requires setting up an imaging device to a working conveyor system. Getting a working conveyor system to be ready can take some time and consequently delay development work on the vision system itself, especially those
involving image processing algorithms. This paper proposes a software solution that can be used to expedite initial work on such systems. The solution is written in C and is therefore easily ported to any development machine. A basic image processing library has also been developed so that it does not depend on any development library or suite, which is usually huge
in size. Thus, the solution can easily be compiled and run on embedded development boards like Raspberry Pi - for a more portable solution.
Link to publisher's homepage at https://iopscience.iop.org/
2019-01-01T00:00:00ZDetection of Pulmonary Nodule using Shape-Based Feature Descriptor and Neural Network
http://dspace.unimap.edu.my:80/xmlui/handle/123456789/69014
Detection of Pulmonary Nodule using Shape-Based Feature Descriptor and Neural Network
Nurfarhana Hazwani, Jusoh; Haniza, Yazid; Shafriza Nisha, Basah; Saufiah, Abdul Rahim
This research aims to detect the pulmonary nodule presented in lung Computed Tomography (CT) scan images. Generally, a Computer-Aided Diagnostic (CAD) system was designed and developed to aid the radiologists in medical imaging department to reduce the time and to obtain faster and better results for lung nodules diagnosis of a patient. Four major stages
involve in this paper which are pre-processing, segmentation, features extraction and classification. The images that were utilized were acquired from LIDC-IDRI database that available publicly for CT scan lung images. Initially, the median filter was employed in preprocessing to filter and remove the noises, unwanted distortions and artifacts presented in the
images during scanning process. For the second stage, the implementation of Otsu thresholding
(thresholding-based method) and watershed algorithm (region-based method) were used to
segment the nodules (Region of Interest (ROI)). Manual cropping method was implemented to
segment the nodule for further process. The main contribution of this paper is the extraction of
the features based on shape descriptor. 10 features were extracted from the segmented nodules.
Finally, all extracted features from the segmented nodules were classified into nodule candidates
and non-nodule candidates using Back Propagation Neural Network (BPNN). Based on the
experiment, it can be observed that the proposed approach works well with CT scan images and
segmented the interested nodules with the accuracy of 94%. This semi-automated approach is
fast compared with the conventional approach used by the radiologists in current time being.
Link to publisher's homepage at https://iopscience.iop.org/
2019-01-01T00:00:00ZDevelopment of EEG-based epileptic detection using artificial neural network
http://dspace.unimap.edu.my:80/xmlui/handle/123456789/21437
Development of EEG-based epileptic detection using artificial neural network
Azian Azamimi, Abdullah; Saufiah, Abdul Rahim; Adira, Ibrahim
Epilepsy is one of the most common neurological disorders causing from repeating brain seizures that are the result of the temporal and sudden electrical disturbance of the brain. Electroencephalogram (EEG) signal plays an important role in the diagnosis of epilepsy. This project proposed to develop
a system that can detect epilepsy based on EEG signal using artificial neural network. Discrete Wavelet Transform (DWT) and Fast Fourier Transform (FFT) were applied as feature extraction methods. These features then set as input to the feedforward neural network with backpropagation training
algorithm to get the classification accuracy. The accuracy of DWT with 10000 epochs is 97% while accuracy of FFT method gives 53.889% accuracy. The combination of DWT and FFT
extracted features give the highest accuracy, which is 98.889%. The classification accuracy depends on the number of epoch and the features from the feature extraction. Increased number of epoch gives long response time to train the network.
Link to publisher's homepage at http://ieeexplore.ieee.org/
2012-02-27T00:00:00Z