Arsmah Ibrahim

An Automatic Generation of G^1 Curve Fitting of Arabic Characters

An Arabic font is difficult to fit as it is cursive in character, having varying curves and cusps. Here, the Arabic character is represented as an outline font fitted with G1 rational Bezier cubic curves. As a method in reverse engineering, the Arabic character is created by way of digitizing an image that already exists and then fitting G1 curves automatically to the outline of the digitized image. The outline font representation is done in several phases - contour extraction of font image, corner points detection and lastly contour segment fitting. Image is considered as binary and boundary is obtained accordingly. Eigenvalues of covariance matrix and the concept of region of support are employed to search for the corners of the Arabic characters which are of varying degrees of smoothness. G 1 rational Bezier cubics, iteratively determined, are used in the last step. The weights are adjusted automatically to get curves that are as close as need be to the digitized data points. This technique can be extended to visualizing outlines of other contour-based images automatically

The geometrical feature of weld defect in assessing digital radiographic image

Digital Radiography is a filmless radiographic image that has been introduced to replace conventional film. It is one of the nondestructive techniques (NDT) that is used to indicate the internal condition of the sample being inspected. It is also an efficient technique in defect detection. Weld defect is any flaws that compromise the usefulness of finished weld specimen. The segmentation of weld defect in radiographic image is an important task which can be used for defect feature analysis by extracting its boundary. This study was performed to extract the weld defect and evaluate its geometrical feature. The boundary of defect is extracted by converting the image into binary form. The defect boundary is detected by recognizing the black pixel of eight neighborhoods of 3×3 filtering. The coordinates of the boundary pixel are stored and used to calculate the information of defect features. The information can be used by interpreter to interpret a defect.

Comparison of Balloon Snake and GVF Snake in Segmenting Masses from Breast Ultrasound Images

The active contour or Snake is a computational model that can trace boundaries of images. It is formulated based on controlled continuous splines and adopts energy minimization conception. This paper presents the application of Snakes for the segmentation of masses on breast ultrasound images. The boundaries of the masses identified may be used in locating potential cancerous cases for further analysis. Initially, Balloon Snake and Gradient Vector Flow (GVF) Snake are applied in segmenting the masses in the breast ultrasound phantom images. Comparison on the masses areas segmented by the Balloon Snake and the GVF Snake is done against the actual masses area. The better method with smaller values of average percentage area difference is chosen to be applied in segmenting masses on real breast ultrasound images. The performance is measured in terms of average percentage area difference traced by the chosen method against the area traced by expert radiologist. It is found that from eighty breast ultrasound phantom images (40 cyst and 40 solid masses) tested, the values of average percentage area difference for cyst and solid masses in the Balloon Snake are 3.07% and 9.17% respectively while GVF Snake are 13.43% and 48.37% respectively. Therefore Balloon Snake is chosen to segment real breast ultrasound images. Fifty images are tested. Segmentation on the images shows that the average percentage area difference of Balloon Snake is 4.29% which mean 95.71% accurate.

High performance visualization of human tumor detection using WTMM on Parallel Computing System

In the effort to reduce the number of cancer survivor, various technique have been conducted. The major problem is the cancer cannot be detected in the early stage. Majority patients have been diagnosed the cancer at the final level. If the problem can be solved, death because of the cancer can be reduced. Therefore, edge detection of tumor can help radiologist to diagnose the disease at an early stage. This paper focused on the implementation of parallel algorithm for the human tumor edge detection. The objectives of this study is to detect the edge of breast and brain tumor in Mammogram and MRI medical imaging respectively. Edge of the tumors is detected by using Wavelet Transform Modulus Maxima on Parallel Computing System that is used as a platform to compute the parallel algorithm for the edge detection of the tumors. Performance of parallel computer in terms of time processing, speedup and efficiency is reported.

Segmentation and characterization of masses in breast ultrasound images using active contour

The active contour or Snake is a computer generated curve, used to trace boundaries of images. This paper presents the application of Snake for the segmentation of masses on breast ultrasound images and the characterization of the segmented masses as malignant or benign. Initially, the Balloon Snake is chosen to segment the masses. Comparison on the masses areas segmented by the Balloon Snake is done against the areas traced by radiologist. Experimental result shows that from fifty masses tested, the Balloon Snake successfully segment the masses with accuracy of 95.71%. Then, a mass is characterized as benign or malignant using a proposed method namely the semi-automated characterization (SAC) method. The method is based on the segmented masses produced by the Balloon Snake. The criterion of angular margin is considered in characterizing the masses as malignant or benign by the SAC method. The characterization reading of a mass by the SAC method is compared with thirty sets of characterization readings of a mass by different radiologists. The comparison is made in terms of sensitivity and specificity values. Based on the values, the receiver operating characteristics (ROC) curve is plotted for each set of comparison. From the thirty sets of comparisons, it is found that the area under curve of all the thirty ROC curves are greater than 0.7. The value implies that the SAC method gives high accuracy in characterizing benign from malignant mass. Since the method is based on the segmented masses by the Balloon Snake, the value also implies that the accuracy of Balloon Snake in segmenting the images is high (95.71%).

Composite contour generation for Beta-spline surface reconstruction

Branching is a process of connecting two adjacent contours called base and branch contours where the numbers of sub contours for each of both contours are different. All points between the contours have to be correctly paired to avoid a twisting surface. In contours connection, continuity is an issue to ensure the surface fit to the required smoothness. Therefore, two main steps to be focused in surface reconstructions are branching technique and surface continuity. This study used composite contour generation as the branching technique which generates an intermediate contour as combination of modified base and branch contours. Although the inserted new contour will disturb the position of original contours, the continuity can be preserved if the fitted surface is Beta-spline. Beta-spline is built with G2 continuity condition, and the changes of the data points position will not affect the continuity. Hence, surface fitting using Beta-spline will simplify the reconstruction process. The result shows sever...

Performance of noise removal methods with image quality parameter on μ-focused digital radiographic image

This study deals with noise removal methods on radiographic image which acquired using μ-focused digital radiography machine. The purposes of the study are to enhance the quality of radiographic image using noise removal methods and analyze the image quality using error measurement metrics. Median, gaussian, average and circular averaging filters are the noise removal methods applied on original radiographic image to produce processed image. Then, the processed image are measured in terms of Signal to Noise Ratio (SNR), Maximum Absolute Error (MAXABS), Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR) and Root Mean Square Error (RMSE). Besides that, the image quality is also measured using Modulation Transfer Function (MTF). Results show that gaussian filter gives the best enhancement of image quality based on error metrics and MTF. The development of image enhancement and quality measurement methods implementation are done using MATLAB R2009a.

Efficiency of Enhanced Distance Active Contour (EDAC) for Microcalcifications Segmentation

In this paper the boundaries of microcalcifications in mammogram are segmented images by using the Distance Active Contour (DAC) method. However, the DAC requires longer computational time to finish the segmentation process. Thus, the Enhanced Distance Active Contour (EDAC) is proposed to overcome the problems. The efficiency is measured in terms of time lapse and number of iterations. Results obtained show that the EDAC has successfully reduced the processing time as well as the number of iterations. In addition to that, the boundaries of microcalcifications have been successfully segmented by the EDAC. It is also found that the efficiency of EDAC is better than the DAC.

A Pilot Study In Image Enhancement In Computed Radiography Mammogram Images Using Histogram Stretching Method

Efforts on the development of Computer Aided Diagnosis (CADG) system have been extensive. However, locally made CADG systems suitable for Malaysian patients are still unavailable. Many present CADG systems are developed based on Caucasian data. These systems may not be suitable for Malaysian data because the breast tissues of Malaysian women may differ from the Caucasians. This project initiates a study to develop a CADG system suitable for local data. This paper reports the image enhancement stage of 42 computed radiography mammogram images collected from the National Cancer Society of Malaysia. The method of histogram stretching is used to enhance these images which are then evaluated by radiologists based on the BIRADS standardization.

Automatic G1 Surface Reconstruction from Serial Cross-Sectional Images

Biomedical imaging facilities today like MRI, PET, CT scan and confocal microscopy produce sequentially parallel cross sectional images. Recon-structing trustworthy 3D explicit models which enable better understanding of the topology and shape of structure is crucial in facilitating diagnosis, improves surgical planning and aid in biological research. Our technique produce a surface from G1cross sectional contour curves of images. Surface accuracy is controlled by a tolerance measure. Features can be isolated and identified for corresspondence. First the boundaries of the region of interest are extracted and corner points detected. G1rational Bezier cubics, iteratively determined, are fitted piecewise between these corners and approximating the boundary. as close as need be. Adjacent contour curves are blended together to form the surface. Technique is fully automatic.