Syamsiah Mashohor

Review of brain MRI image segmentation methods

Brain image segmentation is one of the most important parts of clinical diagnostic tools. Brain images mostly contain noise, inhomogeneity and sometimes deviation. Therefore, accurate segmentation of brain images is a very difficult task. However, the process of accurate segmentation of these images is very important and crucial for a correct diagnosis by clinical tools. We presented a review of the methods used in brain segmentation. The review covers imaging modalities, magnetic resonance imaging and methods for noise reduction, inhomogeneity correction and segmentation. We conclude with a discussion on the trend of future research in brain segmentation.

A highly interpretable fuzzy rule base using ordinal structure for obstacle avoidance of mobile robot

Conventional fuzzy logic controller is applicable when there are only two fuzzy inputs with usually one output. Complexity increases when there are more than one inputs and outputs making the system unrealizable. The ordinal structure model of fuzzy reasoning has an advantage of managing high-dimensional problem with multiple input and output variables ensuring the interpretability of the rule set. This is achieved by giving an associated weight to each rule in the defuzzification process. In this work, a methodology to design an ordinal fuzzy logic controller with application for obstacle avoidance of Khepera mobile robot is presented. The implementation will show that ordinal structure fuzzy is easier to design with highly interpretable rules compared to conventional fuzzy controller. In order to achieve high accuracy, a specially tailored Genetic Algorithm (GA) approach for reinforcement learning has been proposed to optimize the ordinal structure fuzzy controller. Simulation results demonstrated improved obstacle avoidance performance in comparison with conventional fuzzy controllers. Comparison of direct and incremental GA for optimization of the controller is also presented.

Survey on liver CT image segmentation methods

The segmentation of liver using computed tomography (CT) data has gained a lot of importance in the medical image processing field. In this paper, we present a survey on liver segmentation methods and techniques using CT images, recent methods presented in the literature to obtain liver segmentation are viewed. Generally, liver segmentation methods are divided into two main classes, semi-automatic and fully automatic methods, under each of these two categories, several methods, approaches, related issues and problems will be defined and explained. The evaluation measurements and scoring for the liver segmentation are shown, followed by the comparative study for liver segmentation methods, pros and cons of methods will be accentuated carefully. In this paper, we concluded that automatic liver segmentation using CT images is still an open problem since various weaknesses and drawbacks of the proposed methods can still be addressed.

Vertical-Edge-Based Car-License-Plate Detection Method

This paper proposes a fast method for car-license-plate detection (CLPD) and presents three main contributions. The first contribution is that we propose a fast vertical edge detection algorithm (VEDA) based on the contrast between the grayscale values, which enhances the speed of the CLPD method. After binarizing the input image using adaptive thresholding (AT), an unwanted-line elimination algorithm (ULEA) is proposed to enhance the image, and then, the VEDA is applied. The second contribution is that our proposed CLPD method processes very-low-resolution images taken by a web camera. After the vertical edges have been detected by the VEDA, the desired plate details based on color information are highlighted. Then, the candidate region based on statistical and logical operations will be extracted. Finally, an LP is detected. The third contribution is that we compare the VEDA to the Sobel operator in terms of accuracy, algorithm complexity, and processing time. The results show accurate edge detection performance and faster processing than Sobel by five to nine times. In terms of complexity, a big-O-notation module is used and the following result is obtained: The VEDA has less complexity by K2 times, whereas K2 represents the mask size of Sobel. Results show that the computation time of the CLPD method is 47.7 ms, which meets the real-time requirements.

New multi-scale medical image segmentation based on fuzzy c-mean (FCM)

Image segmentation is a key process in computer vision and image process applications. Accurate segmentation of medical images is very essential in medical applications but it is very difficult job due to noise and in homogeneity that are usual of medical images. In this paper a new method, based on FCM, is proposed to make FCM more robust against noise. Multi-scale images are obtained by smoothing input image in different scales. FCM is applied to multi-scale images from high scale to low scale. First FCM is applied to image with highest scale. Then in each scale, cluster centers of previous scale are used to initialization membership for current scale. Moreover, in FCM, neighborhood attraction is used to more decrease effect of noise in clustering. Experimental result shows effectiveness of new method.

A review of computer assisted detection/diagnosis (CAD) in breast thermography for breast cancer detection

Breast cancer is the leading type of cancer diagnosed in women. For years human limitations in interpreting the thermograms possessed a considerable challenge, but with the introduction of computer assisted detection/diagnosis (CAD), this problem has been addressed. This review paper compares different approaches based on neural networks and fuzzy systems which have been implemented in different CAD designs. The greatest improvement in CAD systems was achieved with a combination of fuzzy logic and artificial neural networks in the form of FALCON-AART complementary learning fuzzy neural network (CLFNN). With a CAD design based on FALCON-AART, it was possible to achieve an overall accuracy of near 90%. This confirms that CAD systems are indeed a valuable addition to the efforts for the diagnosis of breast cancer. Lower cost and high performance of new infrared systems combined with accurate CAD designs can promote the use of thermography in many breast cancer centres worldwide.

Evaluation of Genetic Algorithm based solar tracking system for Photovoltaic panels

The maximum power supplied by a photovoltaic (PV) panels system change over time. It depends on environmental factors such as the solar irradiation and the temperature of these panels. The average solar energy harvested by the conventional solar panels during the course of the day, is not always maximized. This is due to the static placement of the panel which limits their area of exposure to the sun. In practice, there are three possible approaches for maximizing the solar power extraction in medium and large scale PV systems are sun tracking, maximum power point (MPP) tracking or combination of both. In this paper, a genetic algorithm (GA) has been proposed utilizing sun tracking approaches to maximize the performance of PV panels. Literature suggested that the PV panels could produce maximum power if the panels have angle of inclination zero degree to the sun position. This work evaluate the best combination of GA parameters to optimize a solar tracking system for PV panels in terms of azimuth angle and tilt angle. Simulation results demonstrated the ability of the proposed GA system to search for optimal panel positions in term of consistency and convergence properties. It also has proved the ability of the GA-solar to adapt to different environmental conditions and successfully track sun positions in finding the maximum power by precisely orienting the PV panels.

3D facial expression recognition using maximum relevance minimum redundancy geometrical features

In recent years, facial expression recognition (FER) has become an attractive research area, which besides the fundamental challenges, it poses, finds application in areas, such as human-computer interaction, clinical psychology, lie detection, pain assessment, and neurology. Generally the approaches to FER consist of three main steps: face detection, feature extraction and expression recognition. The recognition accuracy of FER hinges immensely on the relevance of the selected features in representing the target expressions. In this article, we present a person and gender independent 3D facial expression recognition method, using maximum relevance minimum redundancy geometrical features. The aim is to detect a compact set of features that sufficiently represents the most discriminative features between the target classes. Multi-class one-against-one SVM classifier was employed to recognize the seven facial expressions; neutral, happy, sad, angry, fear, disgust, and surprise. The average recognition accuracy of 92.2% was recorded. Furthermore, inter database homogeneity was investigated between two independent databases the BU-3DFE and UPM-3DFE the results showed a strong homogeneity between the two databases.

Medical Image Segmentation Using Fuzzy C-Mean (FCM), Learning Vector Quantization (LVQ) and User Interaction

Accurate segmentation of medical images is very essential in medical applications. We proposed a new method, based on combination of Learning Vector Quantization (LVQ), FCM and user interaction to make segmentation more robust against inequality of content with semantic, low contrast, in homogeneity and noise. In the postulated method, noise is decreased using Stationary wavelet Transform (SWT); input image is clustered using FCM to the n clusters where n is the number of target classes, afterwards, user selects some of the clusters to be partitioned again; each user selected cluster is clustered to two sub clusters using FCM. This process continues until user to be satisfied. Then, user selects clusters for each target class; user selected clusters are used to train LVQ. After training LVQ, image pixels are clustered by LVQ. Segmentation of simulated and real images is demonstrated to show effectiveness of new method.

A new vertical edge detection algorithm and its application

Edge detection is a very important process for many image processing applications, especially in Car License Plate Detection and Recognition Systems(CLPDRS). The need to distinguish the desired details is a very important pre-process in order to give good results in short time processing. We proposed a new and fast vertical edge detection algorithm (VEDA) which is based on the contrast between the gray scale values. Once, input gray image was binarized by using adaptive threshold, unwanted lines elimination algorithm (ULEA) was proposed and applied. After that, a VEDA was applied for experimental images. Then, implementation on the application is performed and discussed in order to confirm that VEDA is robust for highlighting license plate details easily. The results revealed accurate edge detection performance and demonstrated the great efficiency of using VEDA in order to highlight license plate details. Finally, VEDA showed that it is faster than Sobel operator by about 7-9 times.