Vital signs such as pulse rate and breathing rate are currently measured using contact probes. But, non-contact methods for measuring vital signs are desirable both in hospital settings (e.g. in NICU) and for ubiquitous in-situ health tracking (e.g. on mobile phone and computers with webcams). Recently, camera-based non-contact vital sign monitoring have been shown to be feasible. However, camera-based vital sign monitoring is challenging for people with darker skin tone, under low lighting conditions, and/or during movement of an individual in front of the camera. In this paper, we propose distancePPG, a new camera-based vital sign estimation algorithm which addresses these challenges. DistancePPG proposes a new method of combining skin-color change signals from different tracked regions of the face using a weighted average, where the weights depend on the blood perfusion and incident light intensity in the region, to improve the signal-to-noise ratio (SNR) of camera-based estimate. One of our key contributions is a new automatic method for determining the weights based only on the video recording of the subject. The gains in SNR of camera-based PPG estimated using distancePPG translate into reduction of the error in vital sign estimation, and thus expand the scope of camera-based vital sign monitoring to potentially challenging scenarios. Further, a dataset will be released, comprising of synchronized video recordings of face and pulse oximeter based ground truth recordings from the earlobe for people with different skin tones, under different lighting conditions and for various motion scenarios.

DistancePPG: Robust non-contact vital signs monitoring using a camera

A review of state-of-the-art techniques for abnormal human activity recognition

A review of disability EEG based wheelchair control system: Coherent taxonomy, open challenges and recommendations.

Recent advancement in genomics technologies has opened a new realm for early detection of diseases that shows potential to overcome the drawbacks of manual detection technologies. In this work, we have presented efficient contour aware segmentation approach based based on fully conventional network whereas for classification we have used extreme machine learning based on CNN features extracted from each segmented cell. We have evaluated system performance based on segmentation and classification on publicly available dataset. Experiment was conducted on 64000 blood cells and dataset is divided into 80% for training and 20% for testing. Segmentation results are compared with the manual segmentation and found that proposed approach provided with 98.12% and 98.16% for RBC and WBC respectively whereas classification accuracy is shown on publicly available dataset 94.71% and 98.68% for RBC & its abnormalities detection and WBC respectively.

/pdf/microscopic-blood-smear-segmentation-and-classification-36n364v3ms.pdf

Microscopic Blood Smear Segmentation and Classification Using Deep Contour Aware CNN and Extreme Machine Learning

White blood cell (WBC) counting analysis in blood smear images using various color segmentation methods

Computer Aided System for Red Blood Cell Classification in Blood Smear Image

Development of Reverse Vending Machine (RVM) Framework for Implementation to a Standard Recycle Bin

A significant number of individuals with severe motor impairments are unable to control their wheelchair using a standard joystick. Even when they can facilitate the control input, navigation in a confined space or crowded environments is still a great challenge. Here we propose a wheelchair framework that enables the user to issue the command via a multi-input hands free interface (HFI), which subsequently assists him/her to overcome difficult circumstances using a multimodal control strategy. Initially the HFI inputs are analysed to infer the desired control mode and the user command. Then environmental information is perceived using a combination of laser and Kinect sensors for determining all possible obstacle locations and outputting a safety map around the wheelchair's vicinity. Eventually, the user's command is validated with the safety map to moderate the final motion, which is collision free and the best for the user's preference. The proposed method can reduce the burden of severe impairment users when controlling wheelchairs by continuously monitoring the surroundings and can make them move easily according to the users' intention.

Enhancing Wheelchair Manoeuvrability for Severe Impairment Users

In white blood cell (WBC) diagnosis, the most crucial measurement parameter is the WBC counting. Such information is widely used to evaluate the effectiveness of cancer therapy and to diagnose several hidden infection within human body. The current practice of manual WBC counting is laborious and a very subjective assessment which leads to the invention of computer aided system (CAS) with rigorous image processing solution. In the CAS counting work, segmentation is the crucial step to ensure the accuracy of the counted cell. The optimal segmentation strategy that can work under various blood smeared image acquisition conditions is remain a great challenge. In this paper, a comparison between different segmentation methods based on color space analysis to get the best counting outcome is elaborated. Initially, color space correction is applied to the original blood smeared image to standardize the image color intensity level. Next, white blood cell segmentation is performed by using combination of several color analysis subtraction which are RGB, CMYK and HSV, and Otsu thresholding. Noises and unwanted regions that present after the segmentation process is eliminated by applying a combination of morphological and Connected Component Labelling (CCL) filter. Eventually, Circle Hough Transform (CHT) method is applied to the segmented image to estimate the number of WBC including the one under the clump region. From the experiment, it is found that G-S yields the best performance.

/pdf/white-blood-cell-counting-analysis-of-blood-smear-images-34yqgwlvo7.pdf

White blood cell counting analysis of blood smear images using various segmentation strategies

Red blood cells (RBCs) counting in blood smear image is very important to diagnose blood related diseases such as malaria and anemia before a proper treatment can be proposed. The conventional practice for such procedure is executed manually by pathologist under light microscope. However, manual visual inspection is laborious task and depends on subjective assessment which leads to variation in the RBC counting especially when there are many clumped RBC areas. In this paper a computer-aided systems is proposed to automate the process of counting the RBC from the blood smear image by considering an overlapping constraint. Initially RBCs region are extracted from the background by using global threshold method applied on green channel color image. Next, noise and holes in the RBCs are abolished by utilizing morphological filter and connected component labeling. Following that, information from the RBCs’ area is extracted to determine single and overlapping RBC region. The former region can be counted directly while the latter need to be process further to estimate the number of individual cells. In this paper, two estimators which are Distance transform and Hough transform are utilized to count cells in the clumped regions. Eventually, the total RBCs is found by summing up information from the single cell number and from the estimator. The proposed method has been tested on blood cell images and it demonstrates that Hough transform is more reliable to predict number of total RBCs.

Razali Tomari

Papers

Computer Aided System for Red Blood Cell Classification in Blood Smear Image

Development of Reverse Vending Machine (RVM) Framework for Implementation to a Standard Recycle Bin

Enhancing Wheelchair Manoeuvrability for Severe Impairment Users

White blood cell counting analysis of blood smear images using various segmentation strategies

Red blood cell counting analysis by considering an overlapping constraint