MSc Thesis Proposal Announcement of Muhammad Fahad Zafar:"Webcam based Optical Mark Reader for Grading Assessments"

 

Date: Friday September 30, 2022 

Time:  11:30am – 12:30pm 

Location: Lambton Tower, Room 3105 

Reminder: Two-part attendance required: Part I (QR code) and Part II (sign in sheet)

 

Optical Mark Recognition (OMR) is a process of retrieving information from the forms where users put marks in particular locations. OMR technique has been improved significantly since its inception, moving from specialized hardware-based solutions to more adaptable and sophisticated software-based solutions using a scanner. Recently, webcam-based software solutions have emerged because of their affordability and ease of use. In this thesis, we propose an improved webcam-based OMR solution for grading the student tests given on a specifically formatted answer sheet. Various image processing techniques will be applied to reach efficient and effective grading, resolving technical problems stemming from various factors like image orientation, skewness, and irregular illumination. In particular, we propose a new variant of the Otsu binarization technique for image segmentation to separate the background and foreground effectively. The proposed grading solution aims at maximizing the criteria for acceptable operations so that 100% accurate grading among those accepted ones can be achieved. The evaluation of the proposed method will be two-fold: (i) the proposed variant of Otsu will be compared with the original Otsu and another Otsu variant for its effectiveness in background separation; (ii) the grading solution will be compared with the state-of-the-art webcam-based solutions where the individual contribution of each applied image processing technique to the grading enhancement will be identified. 

 

Keywords: Optical Mark Recognition, Image Processing, OpenCV 

Internal Reader: Dr. Imran Ahmad            

External Reader: Dr. Fazle Baki    

Advisor: Dr. Jessica Chen