Razali Tomari

Razali Tomari

orcid

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2014 in Procedia Computer Science
Verified
Journal Article
Open access
RTRazali Tomari
Razali Tomari
WZWan Nurshazwani Wan Zakaria
Wan Nurshazwani Wan Zakaria
MJMuhammad Mahadi Abdul Jamil
Muhammad Mahadi Abdul Jamil
FNFaridah Mohd Nor
Faridah Mohd Nor
NFNik Farhan Nik Fuad
Nik Farhan Nik Fuad
In vitro identification and counting of red blood cells (RBCs) 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 identification and counting. In this paper a computer-aided systems is proposed to automate the process of detection and identification of RBC from blood smear image. 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’ are extracted based on its geometrical properties. Eventually, the RBCs were classified as normal/abnormal by using Artificial Neural Network (ANN) classifier. The proposed method has been tested on blood cell images and demonstrates a reliable and effective system for classifying normal and abnormal RBC

1 October 2014
Verified
Conference Paper
Closed access
MWMohd Helmy Abd Wahab
Mohd Helmy Abd Wahab
AKAeslina Abdul Kadir
Aeslina Abdul Kadir
RTRazali Tomari
Razali Tomari
MJMohamad Hairol Jabbar
Mohamad Hairol Jabbar
Nowadays, the trend is clear that the use of pervasive computing technology has taken place to improve waste management by providing electronic system which utilizing radio frequency identification at bin level. In this paper, we proposed a smart recycle bin application based on information in the smart card to automatically calculate the weight of waste and convert the weight into point then store it into the card. The wastes are tracked by smart bins using a RFID-based system integrating the web-based information system at the host server. Two crucial features of the selective sorting process can be improved using this approach. First, the user is assisted in the application of material waste classification. Second, the smart bin knows its content and can report back to the rest of the recycling chain.

1 January 2012 in Procedia Engineering
Verified
Journal Article
Open access
RTRazali Tomari
Razali Tomari
YKYoshinori Kobayashi
Yoshinori Kobayashi
YKYoshinori Kuno
Yoshinori Kuno
Users with severe motor impairment may find it difficult to operate a wheelchair when they are in tight space (e.g., passing doorway) or when avoiding obstacles since they cannot command the wheelchair by means of a conventional joystick. Here we propose a framework that can assist users to overcome such circumstances using a hierarchical semi-autonomous control strategy. Initially multimodal user inputs based on momentary switch and yaw head angle are analyzed to decide a maneuvering mode and assign the direction of travel. Then, environmental information is perceived using the combination of a laser range finder and the Kinect sensor for determining safety map around wheelchair's vicinity. Eventually, the user's inputs are provided to the navigation planner along with the safety map to moderate motion that is collision free and the best for user preference. Experimental results demonstrate the feasibility of the proposed approach

1 February 2013 in International Journal of Advanced Robotic Systems
Verified
Journal Article
Open access
PDF file
RTRazali Tomari
Razali Tomari
YKYoshinori Kobayashi
Yoshinori Kobayashi
YKYoshinori Kuno
Yoshinori Kuno
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.

1 January 2017 in AIP Conference Proceedings
Verified
Conference Paper
Closed access
SSSyadia Nabilah Mohd Safuan
Syadia Nabilah Mohd Safuan
RTRazali Tomari
Razali Tomari
WZWan Nurshazwani Wan Zakaria
Wan Nurshazwani Wan Zakaria
NONurmiza Othman
Nurmiza Othman
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.

1 August 2012
Verified
Conference Paper
Closed access
RTRazali Tomari
Razali Tomari
YKYoshinori Kobayashi
Yoshinori Kobayashi
YKYoshinori Kuno
Yoshinori Kuno
Autonomous robotic wheelchairs are normally used in human-shared environments and hence they need to move in a safe and comfortable way. Here, we propose a framework that enables such motions in real indoor environments. Initially human regions are detected and tracked from head cues information. Next, the tracking attributes is interpreted for modeling human's comfort zone (CZ) based on human interaction rules rooted from Proxemics concept. Finally, the wheelchair's trajectory is generated by respecting the CZ and simultaneously avoiding in place obstacle. Experimental results demonstrate the feasibility of the proposed framework.