This page has only limited features, please log in for full access.
Proliferative Diabetic Retinopathy (PDR) is a severe retinal disease that threatens diabetic patients. It is characterized by neovascularization in the retina and the optic disk. PDR clinical features contain highly intense retinal neovascularization and fibrous spreads, leading to visual distortion if not controlled. Different image processing techniques have been proposed to detect and diagnose neovascularization from fundus images. Recently, deep learning methods are getting popular in neovascularization detection due to artificial intelligence advancement in biomedical image processing. This paper presents a semantic segmentation convolutional neural network architecture for neovascularization detection. First, image pre-processing steps were applied to enhance the fundus images. Then, the images were divided into small patches, forming a training set, a validation set, and a testing set. A semantic segmentation convolutional neural network was designed and trained to detect the neovascularization regions on the images. Finally, the network was tested using the testing set for performance evaluation. The proposed model is entirely automated in detecting and localizing neovascularization lesions, which is not possible with previously published methods. Evaluation results showed that the model could achieve accuracy, sensitivity, specificity, precision, Jaccard similarity, and Dice similarity of 0.9948, 0.8772, 0.9976, 0.8696, 0.7643, and 0.8466, respectively. We demonstrated that this model could outperform other convolutional neural network models in neovascularization detection.
Michael Tang; Soo Teoh; Haidi Ibrahim; Zunaina Embong. Neovascularization Detection and Localization in Fundus Images Using Deep Learning. Sensors 2021, 21, 5327 .
AMA StyleMichael Tang, Soo Teoh, Haidi Ibrahim, Zunaina Embong. Neovascularization Detection and Localization in Fundus Images Using Deep Learning. Sensors. 2021; 21 (16):5327.
Chicago/Turabian StyleMichael Tang; Soo Teoh; Haidi Ibrahim; Zunaina Embong. 2021. "Neovascularization Detection and Localization in Fundus Images Using Deep Learning." Sensors 21, no. 16: 5327.
Face detection by electronic systems has been leveraged by private and government establishments to enhance the effectiveness of a wide range of applications in our day to day activities, security, and businesses. Most face detection algorithms that can reduce the problems posed by constrained and unconstrained environmental conditions such as unbalanced illumination, weather condition, distance from the camera, and background variations, are highly computationally intensive. Therefore, they are primarily unemployable in real-time applications. This paper developed face detectors by utilizing selected Haar-like and local binary pattern features, based on their number of uses at each stage of training using MATLAB’s trainCascadeObjectDetector function. We used 2577 positive face samples and 37,206 negative samples to train Haar-like and LBP face detectors for a range of False Alarm Rate (FAR) values (i.e., 0.01, 0.05, and 0.1). However, the study shows that the Haar cascade face detector at a low stage (i.e., at six stages) for 0.1 FAR value is the most efficient when tested on a set of classroom images dataset with 100% True Positive Rate (TPR) face detection accuracy. Though, deep learning ResNet101 and ResNet50 outperformed the average performance of Haar cascade by 9.09% and 0.76% based on TPR, respectively. The simplicity and relatively low computational time used by our approach (i.e., 1.09 s) gives it an edge over deep learning (139.5 s), in online classroom applications. The TPR of the proposed algorithm is 92.71% when tested on images in the synthetic Labeled Faces in the Wild (LFW) dataset and 98.55% for images in MUCT face dataset “a”, resulting in a little improvement in average TPR over the conventional face identification system.
Sirajdin Adeshina; Haidi Ibrahim; Soo Teoh; Seng Hoo. Custom Face Classification Model for Classroom Using Haar-Like and LBP Features with Their Performance Comparisons. Electronics 2021, 10, 102 .
AMA StyleSirajdin Adeshina, Haidi Ibrahim, Soo Teoh, Seng Hoo. Custom Face Classification Model for Classroom Using Haar-Like and LBP Features with Their Performance Comparisons. Electronics. 2021; 10 (2):102.
Chicago/Turabian StyleSirajdin Adeshina; Haidi Ibrahim; Soo Teoh; Seng Hoo. 2021. "Custom Face Classification Model for Classroom Using Haar-Like and LBP Features with Their Performance Comparisons." Electronics 10, no. 2: 102.
A multi-camera system combines features from different cameras to exploit a scene of an event to increase the output image quality. The combination of two or more cameras requires prior settings in terms of calibration and architecture. Therefore, this paper surveys the available literature in terms of multi-camera systems’ physical arrangements, calibrations, algorithms, and their advantages and disadvantages. We also survey the recent developments and advancements in four areas of multi-camera system applications, which are surveillance, sports, education, and mobile phones. In the surveillance system, the combination of multiple heterogeneous cameras and the discovery of Pan-Tilt-Zoom (PTZ) and smart cameras have brought tremendous achievements in the area of multi-camera control and coordination. Different approaches have been proposed to facilitate effective collaboration and monitoring among the camera network. Furthermore, the application of multi-cameras in sports has made the games more interesting in the aspect of analyses and transparency. The application of the multi-camera system in education has taken education beyond the four walls of the class. The method of teaching, student attendance enrollment, determination of students’ attention, teacher and student assessment can now be determined with ease, and all forms of proxy and manipulation in education can be reduced by using a multi-camera system. Besides, the number of cameras featuring on smartphones is gaining noticeable recognition. However, most of these cameras serve different purposes, from zooming, telephoto, and wider Field of View (FOV). Therefore, future smartphones should be expecting more cameras or the development would be in a different direction.
Adeshina Sirajdin Olagoke; Haidi Ibrahim; Soo Siang Teoh. Literature Survey on Multi-Camera System and Its Application. IEEE Access 2020, 8, 172892 -172922.
AMA StyleAdeshina Sirajdin Olagoke, Haidi Ibrahim, Soo Siang Teoh. Literature Survey on Multi-Camera System and Its Application. IEEE Access. 2020; 8 (99):172892-172922.
Chicago/Turabian StyleAdeshina Sirajdin Olagoke; Haidi Ibrahim; Soo Siang Teoh. 2020. "Literature Survey on Multi-Camera System and Its Application." IEEE Access 8, no. 99: 172892-172922.
Abnormal rises in temperature of electrical equipment could be a sign of electric fault. By measuring the temperature of the equipment, it is possible to detect the early sign of electrical failure. Therefore, preventive maintenance based on thermal inspection is important to ensure the safety operation of the electrical system. Thermal inspection is normally done by using a handheld thermal camera. However, professional thermal camera is expensive and not suitable to be installed at a fixed location for continuous temperature monitoring. In this paper, a low-cost embedded system is proposed for measuring the temperature of electrical equipment based on thermal imaging. The system can be permanently installed to continuously monitor the thermal condition of an electrical installation. The proposed system consists of a Raspberry Pi 3 controller board connected to a MLX90640 32x24 pixels thermal sensor and a Pi NoIR camera. The temperatures measured by the thermal array sensor are converted into a heat map to form a thermal image. The thermal image is then overlaid on the visual image and displayed on the LCD screen. The system can be programmed to generate warning signal when the measured temperature is above a certain threshold value. Experiments carried out on the developed system showed that it is able to locate the hotspot regions of an electrical installation.
Min Qi Ng; Soo Siang Teoh. Development of a Low-cost Thermal Camera for Electrical Condition Monitoring. Universal Journal of Electrical and Electronic Engineering 2019, 6, 94 -99.
AMA StyleMin Qi Ng, Soo Siang Teoh. Development of a Low-cost Thermal Camera for Electrical Condition Monitoring. Universal Journal of Electrical and Electronic Engineering. 2019; 6 (5A):94-99.
Chicago/Turabian StyleMin Qi Ng; Soo Siang Teoh. 2019. "Development of a Low-cost Thermal Camera for Electrical Condition Monitoring." Universal Journal of Electrical and Electronic Engineering 6, no. 5A: 94-99.
Infrared thermography is a non-contact and non-destructive technique for electrical equipment monitoring and fault diagnostics. It has been widely used since it can inspect the condition of electrical equipment and detect possible faults without needing to disconnect the equipment from its normal operation. Fault diagnosis is performed through the analysis of thermal images captured by a thermal camera. Manual analysis of thermogram for diagnosing the status of equipment needs to be carried out by a trained personal and this may take a lot of time. It may also prone to human error in the diagnosis. To overcome this, there are several researches focus on the development of methods for automatic electrical fault diagnostics. Most of the methods combine image processing and computational intelligence techniques in the diagnosis. Due to the large variability of equipment and diverse fault conditions, the diagnosis task could be very challenging. There are different techniques being proposed in the literature. This paper presents a survey on the current techniques for automatic electrical fault diagnostics based on infrared thermography.
Shin Yee Lee; Soo Siang Teoh. A Survey on Infrared Thermography Based Automatic Electrical Fault Diagnosis Techniques. 10th International Conference on Robotics, Vision, Signal Processing and Power Applications 2019, 537 -542.
AMA StyleShin Yee Lee, Soo Siang Teoh. A Survey on Infrared Thermography Based Automatic Electrical Fault Diagnosis Techniques. 10th International Conference on Robotics, Vision, Signal Processing and Power Applications. 2019; ():537-542.
Chicago/Turabian StyleShin Yee Lee; Soo Siang Teoh. 2019. "A Survey on Infrared Thermography Based Automatic Electrical Fault Diagnosis Techniques." 10th International Conference on Robotics, Vision, Signal Processing and Power Applications , no. : 537-542.
The ability to detect pedestrian is an important feature in autonomous driving vehicle and advanced driver assistance system (ADAS). The detection can be very challenging due to the complex scene and bad visibility on the road. In addition, it is difficult to achieve high accuracy and good speed performance at the same time due to more processing power is required to increase the accuracy. To address this constraint, we propose a framework to detect pedestrian through fusion of image gradient and magnitude properties and the process is speed up with integral image implementation. Both image gradient and magnitude properties were extracted using Histogram of Oriented Gradient (HOG) and Histogram of Magnitude (HOM) features. From the experiment results, we showed that the combination of HOG and HOM features can achieve 99.0% accuracy compared to HOG (98.6%) or HOM (95.5%) features when they are used independently.
Kok Wei Chee; Soo Siang Teoh. Pedestrian Detection in Visual Images Using Combination of HOG and HOM Features. International Conference on Communication, Computing and Electronics Systems 2019, 591 -597.
AMA StyleKok Wei Chee, Soo Siang Teoh. Pedestrian Detection in Visual Images Using Combination of HOG and HOM Features. International Conference on Communication, Computing and Electronics Systems. 2019; ():591-597.
Chicago/Turabian StyleKok Wei Chee; Soo Siang Teoh. 2019. "Pedestrian Detection in Visual Images Using Combination of HOG and HOM Features." International Conference on Communication, Computing and Electronics Systems , no. : 591-597.
Ambulance location is one of the critical factors that determine the efficiency of emergency medical services delivery. Maximal Covering Location Problem is one of the widely used ambulance location models. However, its coverage function is considered unrealistic because of its ability to abruptly change from fully covered to uncovered. On the contrary, Gradual Cover Location Problem coverage is considered more realistic compared to Maximal Cover Location Problem because the coverage decreases over distance. This paper examines the delivery of Emergency Medical Services under the models of Maximal Covering Location Problem and Gradual Cover Location Problem. The results show that the latter model is superior, especially when the Maximal Covering Location Problem has been deemed fully covered.
Mohd Hafiz Azizan; Ting Loong Go; W.A. Lutfi W.M. Hatta; Cheng Siong Lim; Soo Siang Teoh. Comparison of Emergency Medical Services Delivery Performance using Maximal Covering Location and Gradual Cover Location Problems. International Journal of Electrical and Computer Engineering (IJECE) 2017, 7, 2791 .
AMA StyleMohd Hafiz Azizan, Ting Loong Go, W.A. Lutfi W.M. Hatta, Cheng Siong Lim, Soo Siang Teoh. Comparison of Emergency Medical Services Delivery Performance using Maximal Covering Location and Gradual Cover Location Problems. International Journal of Electrical and Computer Engineering (IJECE). 2017; 7 (5):2791.
Chicago/Turabian StyleMohd Hafiz Azizan; Ting Loong Go; W.A. Lutfi W.M. Hatta; Cheng Siong Lim; Soo Siang Teoh. 2017. "Comparison of Emergency Medical Services Delivery Performance using Maximal Covering Location and Gradual Cover Location Problems." International Journal of Electrical and Computer Engineering (IJECE) 7, no. 5: 2791.
Poaching for massive traditional medicine demands is the single greatest threat of extinction that looms over most wildlife especially the endangered tiger. One way to curb the poaching activity is to have tighter monitoring of the protected area by using camera traps. In this research, an embedded system with human detection features for anti-poaching application is proposed. The system uses a 4 × 4 pixels' thermal sensor to detect any heat presence before an infrared camera is activated to capture video images. The images will be processed with a human detection algorithm based on frame differencing and orientation features. The detected human will then be verified using a Support Vector Machine (SVM) classifier. Once a human is identified, the image and the location of the human can then be sent through a long range data connection to a ranger office to alert the authorities. The system was implemented on a Raspberry Pi 2 board. Experiments have been conducted to evaluate the functionality of the system in non-urban environment during day and night times. The results showed that it can successfully detect human in an average of less than 2s even during night time with complete darkness.
Ting Feng Tan; Soo Siang Teoh; Jun Ee Fow; Kin Sam Yen. Embedded human detection system based on thermal and infrared sensors for anti-poaching application. 2016 IEEE Conference on Systems, Process and Control (ICSPC) 2016, 37 -42.
AMA StyleTing Feng Tan, Soo Siang Teoh, Jun Ee Fow, Kin Sam Yen. Embedded human detection system based on thermal and infrared sensors for anti-poaching application. 2016 IEEE Conference on Systems, Process and Control (ICSPC). 2016; ():37-42.
Chicago/Turabian StyleTing Feng Tan; Soo Siang Teoh; Jun Ee Fow; Kin Sam Yen. 2016. "Embedded human detection system based on thermal and infrared sensors for anti-poaching application." 2016 IEEE Conference on Systems, Process and Control (ICSPC) , no. : 37-42.
Histogram of Oriented Gradient (HOG) feature which was originally proposed by Dalal and Triggs is widely used in vision-based human detection. However, HOG feature extraction method produced a large feature pool which is computationally intensive and very time consuming, causing it not so suitable for real time application. This paper proposed a method to reduce the HOG feature extraction time without affecting too much on its detection performance. The proposed method performs feature extraction using selective number of histogram bins. Higher number of histogram bins which can extract more detailed orientation information is applied on the regions of image that may contain human figure. The rest of the regions in the image are extracted using lower number of histogram bins. This will reduce the feature size without compromising too much on the performance. To further reduce the feature size, Principal Component Analysis (PCA) is used to rank the features and select only the representative features. A linear SVM classifier is used to evaluate the performance of the proposed method. Experiment was conducted using the INRIA human dataset. The test results showed that the proposed method is able to reduce the feature extraction time by 2.6 times compared to the original HOG and 7 times compared to the LBP method while providing comparable detection performance.
Chi Qin Lai; Soo Siang Teoh. Efficiency Improvement in the Extraction of Histogram Oriented Gradient Feature for Human Detection Using Selective Histogram Bins and PCA. Lecture Notes in Electrical Engineering 2016, 267 -275.
AMA StyleChi Qin Lai, Soo Siang Teoh. Efficiency Improvement in the Extraction of Histogram Oriented Gradient Feature for Human Detection Using Selective Histogram Bins and PCA. Lecture Notes in Electrical Engineering. 2016; ():267-275.
Chicago/Turabian StyleChi Qin Lai; Soo Siang Teoh. 2016. "Efficiency Improvement in the Extraction of Histogram Oriented Gradient Feature for Human Detection Using Selective Histogram Bins and PCA." Lecture Notes in Electrical Engineering , no. : 267-275.
Histogram of Oriented Gradient (HOG) is a popular image feature for human detection. It presents high detection accuracy and therefore has been widely used in vision-based surveillance and pedestrian detection systems. However, the main drawback of this feature is that it has a large feature size. The extraction algorithm is also computationally intensive and requires long processing time. In this paper, a time-efficient HOG-based feature extraction method is proposed. The method uses selective number of histogram bins to perform feature extraction on different regions in the image. Higher number of histogram bin which can capture more detailed information is performed on the regions of the image which may belong to part of a human figure, while lower number of histogram bin is used on the rest of the image. To further reduce the feature size, Principal Component Analysis (PCA) is used to rank the features and remove some unimportant features. The performance of the proposed method was evaluated using INRIA human dataset on a linear Support Vector Machine (SVM) classifier. The results showed the processing speed of the proposed method is 2.6 times faster than the original HOG and 7 times faster than the LBP method while providing comparable detection performance
C. Q. Lai; S. S. Teoh. An Efficient Method of HOG Feature Extraction Using Selective Histogram Bin and PCA Feature Reduction. Advances in Electrical and Computer Engineering 2016, 16, 101 -108.
AMA StyleC. Q. Lai, S. S. Teoh. An Efficient Method of HOG Feature Extraction Using Selective Histogram Bin and PCA Feature Reduction. Advances in Electrical and Computer Engineering. 2016; 16 (4):101-108.
Chicago/Turabian StyleC. Q. Lai; S. S. Teoh. 2016. "An Efficient Method of HOG Feature Extraction Using Selective Histogram Bin and PCA Feature Reduction." Advances in Electrical and Computer Engineering 16, no. 4: 101-108.
This paper investigates the performance of image features for vehicle classification. We focused on two important image features which have been widely used for vehicle detection. These features are the Histogram of Oriented Gradient (HOG) and the Gabor features. Although there are several literature proposed these features for vehicle classification, it is very hard to make a fair comparison from their published results since they were tested using different data sets and performance matrices. This paper compares the performance of these two features under the same experimental setups. The efficiency of the features in combination with three popular classifiers, namely Support Vector Machines (SVM), Multilayer Perceptron Neural Network (MLP) and Mahalanobis distance classifiers were systematically investigated. The experiment results show that the combination of HOG feature with SVM classifier produced the best result. The processing time required for HOG feature's extraction and classification is also considerably shorter compared to Gabor feature.
Soo Siang Teoh; Thomas Braunl. Performance evaluation of HOG and Gabor features for vision-based vehicle detection. 2015 IEEE International Conference on Control System, Computing and Engineering (ICCSCE) 2015, 66 -71.
AMA StyleSoo Siang Teoh, Thomas Braunl. Performance evaluation of HOG and Gabor features for vision-based vehicle detection. 2015 IEEE International Conference on Control System, Computing and Engineering (ICCSCE). 2015; ():66-71.
Chicago/Turabian StyleSoo Siang Teoh; Thomas Braunl. 2015. "Performance evaluation of HOG and Gabor features for vision-based vehicle detection." 2015 IEEE International Conference on Control System, Computing and Engineering (ICCSCE) , no. : 66-71.
This paper describes a method to classify vehicle type using computer vision technology. In this study, Visual Background Extractor (ViBe) was used to extract the vehicles from the captured videos. The features of the detected vehicles were extracted using Histogram of Oriented Gradient (HOG). Multi-class Support Vector Machine (SVM) was used to recognise four classes of images: motorcycle, car, lorry and background (without vehicles). The results show that the proposed classifier was able to achieve an average accuracy of 92.3 %.
Lee Teng Ng; Shahrel Azmin Suandi; Soo Siang Teoh. Vehicle Classification Using Visual Background Extractor and Multi-class Support Vector Machines. Lecture Notes in Electrical Engineering 2014, 221 -227.
AMA StyleLee Teng Ng, Shahrel Azmin Suandi, Soo Siang Teoh. Vehicle Classification Using Visual Background Extractor and Multi-class Support Vector Machines. Lecture Notes in Electrical Engineering. 2014; ():221-227.
Chicago/Turabian StyleLee Teng Ng; Shahrel Azmin Suandi; Soo Siang Teoh. 2014. "Vehicle Classification Using Visual Background Extractor and Multi-class Support Vector Machines." Lecture Notes in Electrical Engineering , no. : 221-227.
In this paper, we describe the development of a symmetry-based vehicle detection system. The system uses a single forward looking camera to capture the road scene. Vehicles are detected based on their edges and symmetrical characteristics. A method to extract the symmetric regions in the image using a multi-sized window and clustering technique is introduced. We hypothesize the vehicle’s locations in the image from the detected symmetric regions and the regions are then further processed to enhance their symmetrical edges. A bounding box of a vehicle is detected from the projection maps of the enhanced vertical and horizontal edges. The hypothesized vehicles are then verified using a two-class classifier, which consists of an edge oriented histogram (EOH) feature extractor and a support vector machine (SVM). Once a vehicle is verified, a tracking process based on a Kalman filter and a reliability point system is used to track the movement of the vehicle in consecutive video frames. The system was successfully implemented and tested on a standard PC. Experimental results on live video feed and pre-recorded video sequences for various road scenes showed that the system is able to detect multiple vehicles in real time.
Soo Siang Teoh; Thomas Braunl. Symmetry-based monocular vehicle detection system. Machine Vision and Applications 2011, 23, 831 -842.
AMA StyleSoo Siang Teoh, Thomas Braunl. Symmetry-based monocular vehicle detection system. Machine Vision and Applications. 2011; 23 (5):831-842.
Chicago/Turabian StyleSoo Siang Teoh; Thomas Braunl. 2011. "Symmetry-based monocular vehicle detection system." Machine Vision and Applications 23, no. 5: 831-842.