Welcome | Publications | Research | Industry | Teaching | Biography
UofT Logo (Small)
Mahdi Marsousi
Academic Affiliation:
Multimedia Processing Lab, 
Electrical and Computer Eng. Dept., 
University of Toronto,
Toronto, ON, Canada
Industrial Affiliation:
Research Engineer,
Research and Development Department,
Magna Electronics Inc.,
1 Kenview Blvd, Suite 200,
Brampton, ON, L6T 5E6, Canada
Contact Information:
Academic email:
Work email: 
Email: marsousi@gmail.com
Cell-phone: (647) 967-1585

Mahdi is currently a research engineer at the research and development department at Magna Vectrics Inc., working on driver assistance systems. His work focus is on algorithm design for automated parking based on ultrasound and vision sensors (Read more). He also works on designing a computer assisted medical diagnostic system for trauma patient based on processing three-dimensional ultrasound imagery (Read more). Mahdi's reasearching areas of interest include algorithm design, image and signal processing, medical image processing and analysis, biomedical signal processing, computer vision, sparse representation via dictionary learning, statistical and probabilistic approaches for image processing, and machine learning. As an advantage, Mahdi carries both strong academic research background and industrial research and development experiences. This helps him to design algorithms based on advanced theory that fits within the industrial requirement including computational cost efficiency, robustness against environmental changes, accuracy and repeatability of results, and ease of maintenance.

Download my CV here.

Research highlights:
Computer-assisted medical diagnostic system for trauma patients in emergency situation

Due to limitations of healthcare services in emergency situations, abdominal bleeding causes a large number of preventable deaths each year around the world. Saving a trauma patient's life requires rapid diagnosis, which is not usually available in emergency situations. This is the thesis of this research that a computer-assisted algorithm based on 3D ultrasound imagery can offer a solution ... Read more
Co-object detection-segmentation using dictionary learning in sparse representation

The tasks of automated object detection and segmentation in 2D and 3D images have been receiving an increasing attention and interest during the last years, because they both are needed in new computer-assisted solutions, such as driver-assistant system, self-driving vehicles, robotic vision, and medical diagnostic tools... Read more
2016 (c) Copy-right preserved, Welcome | Publications | Research | Industry | Biography