Content

CONTRAST ENHANCEMENT OF FLAT EEG IMAGES VIA INTUITIONISTIC FUZZY APPROACH
Z. Suzelawati

CLOTH SIMULATION USING AN ENHANCED CATMULL-CLARK SUBDIVISION SCHEME AND COLLISION DETECTION IN A VIRTUAL ENVIRONMENT
*Tulasii Sivaraja, Abdullah Bade

VISUALISING POINT SOURCE POLLUTANT CONCENTRATION LEVEL DISPERSION USING THE GAUSSIAN MODEL
Choo Khing Onn1, *Zaturrawiah Ali Omar1, Justin Sentian2

PLATE NUMBER RECOGNITION SYSTEMS BASED ON A CONTOURS AND CHARACTER RECOGNITION APPROACH
Chua Jing Yi1, Rechard Lee2, Prof. Madya Dr. Abdullah Bade3

UTILISING FUZZY INTERPOLATION BEZIER CURVES FOR ALPHABET VERIFICATION
Rozaimi Zakaria1*, Soon Yun Yee2

Download FULL Journal HERE (From Google Drive)

Z. Suzelawati
Mathematics with Computer Graphics Program, Faculty of Science and Natural Resources,
Universiti Malaysia Sabah, Jalan UMS, 88400, Kota Kinabalu, Sabah
Corresponding author: suzela@ums.edu.my

ABSTRACT. Image enhancement is an initial step in medical imaging before further processing. It is a process to improve the quality of an image which is affected by the presence of noise. Various approaches such as classical and fuzzy methods are used in the area of image processing to obtain the desired output. However, in this paper, an advanced fuzzy approach for contrast enhancement is used. The method is known as intuitionistic fuzzy set (IFS) and it is implemented on flat EEG (fEEG) input images during epileptic seizures. The output images are displayed with different values of parameter   lambda, . Unsmooth output images occurred as increased.

KEYWORDS. Flat EEG, intuitionistic fuzzy set, hesitation degree, contrast enhancements, medical image processing

Download Full Paper Here (From Google Drive)

*Tulasii Sivaraja, Abdullah Bade
Faculty of Science and Natural Resources, Universiti Malaysia Sabah,
Jalan UMS, 88400, Kota Kinabalu, Sabah
*Corresponding author: tulasii.sivaraja@gmail.com

ABSTRACT. Subdivision surface techniques smoothen the surface of any 3D object by splitting the polygons into smaller sub-polygons. However, most methods of subdivision encounter the same problem when dealing with extraordinary points. This project aims is to implement an enhanced Catmull-Clark subdivision scheme and simulated cloth that can detect and identify the collision ofan object against the simulated cloth in a virtual environment. The original Catmull-Clark subdivision scheme was enhanced by manipulating the weights present in the original scheme while adhering to a few rules. The cloth used a mass-spring model to be initialised, and the enhanced subdivision scheme was integrated into this model. Then, the collision detection was performed based on the bounding volume approach, and an appropriate collision response was used to simulate the behaviour of the cloth in real life. Experiments and tests were conducted to evaluate the smoothness ofthe enhanced subdivision scheme and the computation time. The enhanced subdivision scheme was only able to create an acceptably smooth surface until the second iteration ofthe subdivision. On the third iteration, noticeable sharp points were present, which indicated that the enhanced subdivision scheme did not improve the original scheme. Additionally, the execution time for the enhanced subdivision scheme
was insignificantly longer compared to the original scheme for all the levels ofsubdivision. The frame rate test showed that the cloth simulation ran at the average rate of43.572 fps, which was within the acceptable range. In conclusion, this research focuses on creating a cloth simulation that implemented an enhanced Catmull-Clark subdivision scheme and collision detection. However, the proposed enhancement for this scheme can be improved to account for the subdivision at individual cases of extraordinary points.
KEYWORDS. Catmull-Clark subdivision surface; collision detection; cloth simulation; extraordinary points; weights

Download Full Paper Here (From Google Drive)

Choo Khing Onn1, *Zaturrawiah Ali Omar1, Justin Sentian2
1Mathematics with Computer Graphics Programme, Faculty of Science and Natural Resources,
Universiti Malaysia Sabah, Jalan UMS, 88400 Kota Kinabalu Sabah
2Environmental Science Programme, Faculty of Science and Natural Resources, Universiti Malaysia
Sabah, Jalan UMS, 88400 Kota Kinabalu Sabah
*Corresponding author: zatur@ums.edu.my

ABSTRACT. In this study, we examined the usage of the Gaussian air dispersion model to visualise point source pollutant concentration levels and implemented it in MASPLUME, a newly developed computer software which functioned as an estimation tool application for measuring the concentration level (at ground zero) of a selected pollutant dispersed from a single point source. The identified pollutants were carbon monoxide, nitrogen dioxide, and sulphur dioxide. MASPLUME was able to show a twodimensional static air pollution dispersion and concentration level, as well as graphical data for different scenario analysis. Although MASPLUME is in its initial development stage as a comprehensive software, it would still be sufficient as a current teaching and learning aid.

KEYWORDS. Visualisation; Gaussian Model, Air Pollution, Concentration Dispersion, Point Source

Download Full Paper Here (From Google Drive)

Chua Jing Yi1, Rechard Lee2, Prof. Madya Dr. Abdullah Bade3
Faculty of Science and Natural Resources, University Malaysia Sabah,
Kota Kinabalu, Sabah, Malaysia.
*Corresponding author : 1jingyi5991@gmail.com, 2rechard@ums.edu.my, 3abade08@yahoo.com

ABSTRACT. License plate recognition system (LPR) plays an important role in intelligent traffic control system. However, most of the existing LPR are complex and hard to implement. The aim of this project is to improve the LPR techniques in terms of speed and accuracy by applying the Connected Component Analysis (CCA) and K-Nearest Neighbour algorithm (KNN). The LPR is divided into three stages which are image pre-processing, character segmentation, and character recognition. First, the input plate image will undergo some image property functions such as omission of noise to enhance the quality of the image. The CCA is applied to segment the characters by drawing rectangle boxes on each character, based on contours to extract the characters into smaller images. These images are then used as query images in character recognition stage. The images are fed to a pre-defined KNN classifier to determine the features of each image and to identify them. Five experiments were carried out to validate the proposed system. Ten Malaysia single row plate images and two foreign plate images were used as the input images on these tests. The findings show that the proposed system has an 80.0% success rate in segmentation, 92.21% accuracy rate in recognition, the optimal K value is 1, and the input image must be in a single row and comprises of a black background and white characters namely letters and digits. In conclusion, a prototype for plate number recognition has been developed with a high success rate in segmentation and a high accuracy in character recognition. Suggested future studies include a focus on segmenting double row license plates and recognizing similar characters.

KEYWORDS. License Plate Recognition, Malaysia license plate surface, Connected Component Analysis, character recognition, K-Nearest neighbour

Download Full Paper Here (From Google Drive)

Rozaimi Zakaria1*, Soon Yun Yee2
1 ,2Faculty Science and Natural Resources,
Universiti Malaysia Sabah, 88400 Kota Kinabalu, Sabah, MALAYSIA.
Corresponding author’s email: rozaimi@ums.edu.my (Tel: 088-320000 ext: 5628, Fax: 088-320223)

ABSTRACT. In this paper, alphabet verification is conducted using fuzzy interpolation Bezier curves. Uncertain data can be defined by using the fuzzy number concept. Firstly, Fuzzification in the form of triangular fuzzy numbers is discussed. Then, the defuzzification process is implemented to produce crisp fuzzy data points. An error is obtained by comparing the defuzzified model of alphabet verification with the crisp model. The small error value obtained indicates that the fuzzy interpolation Bezier curve model is acceptable and can be used in modeling alphabet verification.

KEYWORD. Fuzzy interpolation Bezier curve, alphabet verification, uncertainty data, alpha–cut triangular fuzzy number, defuzzification process

REFERENCES

• Wahab, A.F. 2008. Pemodelan Geometri Menggunakan Teori Set Kabur, Universiti Sains Malaysia.
• Karim, N. A. A., Wahab, A. F., Gobithaasan, R. U., & Zakaria, R. 2013. Model of Fuzzy B-Spline Interpolation For Fuzzy Data. Far East Journal of Mathematical Sciences (FJMS) 72 (2):269- 280.
• Roslan, N. & Yahya, Z. R. 2015. Pembinaan Semula Fon dengan Bezier Kubik Menggunakan Evolusi Pembezaan. Sains Malaysiana 44 (8):1203-1208.
• Wahab, A. F., and Zakaria, R. 2015. Fuzzy Tuning B-spline Curve. AIP Proceedings:1-7.
• Zadeh, L. 1965. Fuzzy Sets. Information and Control 8:338-353.
• Zakaria, R. 2010. Pemodelan Interpolasi Splin Bezier Kabur, Jabatan Matematik, Universiti Malaysia Terengganu.
• Zakaria, R. and Wahab, A. F. 2012. Fuzzy B-spline Modeling of Uncertainty Data. Applied Mathematical Sciences 6 (140):6971-6991.
• Zakaria, R. 2014. Pemodelan Titik Data Kabur Teritlak. Sains Malaysiana 43 (5):799-805.
• Zakaria, R., Wahab, A. F., & Gobithaasan, R. U. 2014. Fuzzy B-Spline Surface Modeling. Journal of Applied Mathematics 2014:8 pages.
• Zakaria, R., Wahab, A. F., & Gobithaasan, R. U. 2016. The Series of Fuzzified Fuzzy Bezier Curve. Jurnal Teknologi 78 (2-2).

Download Full Paper Here (Right-Click and Save As)