Siti Nurul Aqmariah Mohd Kanafiah
Thumbnail Image
Preferred name
Siti Nurul Aqmariah Mohd Kanafiah
Official Name
Siti Nurul Aqmariah, Mohd Kanafiah
Alternative Name
Kanafiah, S. N.Aqmariah
Kanafiah, S. N.A.M.
Kanafiah, Siti Nurul Aqmariah Mohd
Aqmariah Kanafiah, S. N.
Kanafiah, S. N. A. M
Main Affiliation
Scopus Author ID
55987982900
Researcher ID
HTR-1815-2023

Research Output

Filters

2
1
2
2
Reset filters

Settings
Now showing 1 - 2 of 2
Thumbnail Image
Publication

Features Extraction to Differentiate of Spinal Curvature Types using Hue Moment Algorithm

2020-03-10 , Salleh M.A.M. , Siti Nurul Aqmariah Mohd Kanafiah , Jusman Y. , Yusof M.I.

Nowadays, diagnosing the spinal problems is very important to medical field. The objective of this research is to develop feature extraction technique to obtain the features, which automatically differentiate images of normal and abnormal (scoliosis) spinal curvatures. The process to extract features of spinal image start with image acquisition, image processing (i.e. enhancement, filtering, and segmentation). For image processing method, the most important part in this phase is the segmentation using manual threshold method. After the segmentation, hue moment for size and parameter are used to extract features that should be considered based on probabilistic to classify the spine images. The final experimental result shows that the developed features extraction technique can differentiate between normal and scoliosis spine images.

View
Thumbnail Image
Publication

Analysis of Features Extraction Performance to Differentiate of Dental Caries Types Using Gray Level Co-occurrence Matrix Algorithm

2020-08-01 , Jusman Y. , Tamarena R.I. , Puspita S. , Saleh E. , Siti Nurul Aqmariah Mohd Kanafiah

This study analyzes the features extraction performance of dental caries image using Gray Level Cooccurrence Matrix (GLCM) algorithm for contrasted two types of caries is based on the theory of GV Black, namely: Dental caries Class 3 and Class 4. The study aims to determine the pixel value and quantization value of the GLCM used for an automated classification system of dental caries types. The analysis is conducted by using variations of pixel distances and quantization value to perform features on the image in values such as contrast, correlation, energy, and homogeneity. Then these values are used as input to the classification stage Knearest neighbor (KNN). Result performed on four data sets containing 60 images of each set is an accuracy value. The highest performance obtained is 80% of accuracy in 100 and 200 of pixel distances and 16 and 32 of quantization value. The pixel distances and quantization values are recommended to be used for an automated classification system of dental caries types based on X-ray images.

View