This paper presents the used of histogram of oriented gradient (HOG) for facial expression recognition using support vector machine (SVM). In this work, the facial expression images are firstly preprocessed by face detection and cropped images. Then, HOG method is adopted as feature extraction on facial image. The ability of HOG to preserve the local information and orientation density distribution in facial images suitable as shape descriptor for facial expression. It divides the image into cell or patch that has magnitude and orientations. The extracted HOG was then concatenated into histogram bin to form one feature vector before feed into SVM classifier. Both JAFFE and KDEF datasets were employed to evaluate the performance of proposed method. Based on results, the average recognition rates of JAFFE and KDEF datasets are 76.19% and 80.95% respectively. The results show that the performance of expression surprise has outperformed compared to others expression while expression fear contributes the lowest recognition rate. Thus, utilization of HOG features with SVM classifier have shown the promising results in recognizing facial expression.

Electroencephalograph (EEG) is an electrical field that generated by our brain incessantly. The EEG signal released by the brain is different when a people is performing different activities in their daily life. And such EEG signals consist complicated information that can be interpreted. The aims of this study is to analyse the specific EEG channels of a user when they are performing a typing task with laptop. Meanwhile, this research also aimed to verify the performance of the different sub frequency band which is alpha and beta to recognize the specified tasks. The frequency sampling was set at 1024 Hz and the impedance was kept below 5k ohm of each channels. The Truscan EEG (Deymed, Diagnostic, Czech Republic) device consists of 19 channels and only selected channels which is F3 and F4 is filtered through butterworth bandpass filter (1Hz-80Hz) in the pre-processing stage. Power Spectra Density was calculated by using Welch and Burg Method to extract the features from filtered data. K-Nearest Neighbour (KNN) classifier and Linear Discriminant Analysis (LDA) were used in classification. It is found that the combination of channel F3 and F4 for Alpha frequency using Welch method gives the highest accuracy which is 98.45%.

Helminthiasis disease is one of the most serious health problems in the world and frequently occurs in children, especially in unhygienic conditions. The manual diagnosis method is time consuming and challenging, especially when there are a large number of samples. An automated system is acknowledged as a quick and easy technique to assess helminth sample images by offering direct visibility on the computer monitor without the requirement for examination under a microscope. Thus, this paper aims to compare the human intestinal parasite ova segmentation performance between machine learning segmentation and deep learning segmentation. Four types of helminth ova are tested, which are Ascaris Lumbricoides Ova (ALO), Enterobious Vermicularis Ova (EVO), Hookworm Ova (HWO), and Trichuris Trichiura Ova (TTO). In this paper, fuzzy c-Mean (FCM) segmentation technique is used in machine learning segmentation, while convolutional neural network (CNN) segmentation technique is used for deep learning. The performance of segmentation algorithms based on FCM and CNN segmentation techniques is investigated and compared to select the best segmentation procedure for helminth ova detection. The results reveal that the accuracy obtained for each helminth species is in the range of 97% to 100% for both techniques. However, IoU analysis showed that CNN based on ResNet technique performed better than FCM for ALO, EVO, and TTO with values of 75.80%, 55.48%, and 77.06%, respectively. Therefore, segmentation through deep learning is more suitable for segmenting the human intestinal parasite ova.

Phase-shifting fringe projection methods have been developed for three-dimensional scanning (Zuo et al., 2018). However, the 3-Dimensional (3D) scanning of objects with a high dynamic reflectivity range based on structured light is a challenging task to achieve (Feng et al., 2018). The incorrect intensities captured will cause phase and measurement errors. Thus, this paper proposes a method that improves the current High Dynamic Range (HDR) (Jiang et al., 2016)) method to increase the dynamic range. The camera and projector have 3 channels, red, green, and blue, which can absorb and project these lights independently. This paper proposes a method that makes use of this by controlling the intensity of each projected for the camera. Each image can be split into 3 channels and provide 3 images which contain different intensities, then it will be used to compute the 3D information. In general, this is done by controlling the projection of red, green and blue (RGB) channel and apply the Jiang’s algorithm (Jiang et al., 2016). The results are compared and analysed with current HDR (Jiang’s method) and the regular three-step phase-shifting methods. From the experimental results, it has shown that our proposed method outperforms the current HDR and the regular three-step phase-shifting methods. Specifically, the proposed method manages to increase the dynamic range of the reflective property of objects. Additionally, our proposed method has also significantly reduced the times of 3D object measurements.

Diabetic Retinopathy remains one of the most feared diabetes complications that could lead to blindness. Image processing techniques have been widely used all around the world for early detection of diabetic retinopathy. However, most techniques used do not focus on the low visual quality problems in the fundus image. Low visual quality of fundus image may lead to difficulty in evaluation by ophthalmologist before reading it out to the patients. Hence, Automated Screening for Diabetic Retinopathy was created to focus on image enhancement of the fundus image. In this study, two main algorithms for image processing have been used which are green channel conversion and top-hat filters. Green channel in fundus image is selected due to better contrast of the features and background compared to the red and blue channel. While Top-hat filter used to details out small features in the fundus image. The evaluation result of the techniques is compared by using Mean-Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR) and Entropy calculations to measure quality of the enhanced fundus images. Results of image enhancement techniques implemented has proved that quality of the fundus image is improved.