Ismail Mat Amin

Morphological region-based initial contour algorithm for level set methods in image segmentation

Initial Contour (IC) is the essential step in level set image segmentation methods due to start the efficient process. However, the main issue with IC is how to generate the automatic technique in order to reduce the human interaction and moreover, suitable IC to have accurate result. In this paper a new technique which we called Morphological Region-Based Initial Contour (MRBIC), is proposed to overcome this issue. The idea is to generate the most suitable IC since the manual initialization of the level set function surface is a well-known drawback for accurate segmentation which has dependency on selection of IC and wrong selection will affect the result. We have utilized the statistical and morphological information inside and outside the contour to establish a region-based map function. This function is able to find the suitable IC on images to perform by level set methods. Experiments on synthetic and real images demonstrate the robustness of segmentation process using MRBIC method even on noisy images and with weak boundary. Furthermore, computational cost of segmentation process will be reduced using MRBIC.

Measuring fish length from digital images (FiLeDI)

In fishery research, fish length plays a great role to identify population. However, current method can be problematic as the fish should be obtained from the fishermen first. This process may lead to time consuming and cost overflowing. Therefore, a method to measure the length of a fish automatically using image processing and formula optic is greatly needed to solve these problems. In this paper, we will discuss on the details of FiLeDI framework. The FiLeDI framework is a combination between Hsius method and Serkans method. The accuracy of measuring the fish length was 99.81%.

Computer-Aided Dental Caries Detection System from X-Ray Images

The early detection of disease is one of important matter of diagnostic imaging. In this paper we developed a system to analysis the dental x-ray images and diagnosis the tooth which has abnormalities of caries. Enhancement applied to improve the quality of x-ray images and Thresholding method performed to simplify the images. Segmentation has been done by applying the integral projection technique to extract the individual tooth and therefore feature map of tooth surface generated to analysis and detection process. Nevertheless, experiments show the accurate segmentation and caries detection with proposed method which achieves high accuracy and promising result.