CADGrader: Automatically Grade CAD

BlinkToText offers a form of independence to paralyzed people. The software platform converts eye blinks to text. Every feature of the software can be controlled by eye movement. Thus, the software can be independently operated by paralyzed people. Using the software, patients can record messages, recite those messages aloud, and send the messages to others. The software can be run on any low end computer, from a Raspberry Pi to an IBM Thinkpad. The software uses computer vision and Haar cascades to detect eye blinking and convert the motion into text. The program uses language modelling to predict the next words that the user might blink. The software can be easily customized for each patient as well. Blink to Text is free open source software. It is distributed under the MIT Permissive Free Software License. CADGrader is an automatic grading tool currently in use at McMaster University. CADGrader is used by all first year engineering students.

CADGrader is a grading software that automatically marks CAD assignments. CADGrader offers tools for both educators and students of ENG 1C03. With CADGrader, instructors can instantly mark hundreds of CAD assignments. CADGrader stores each submission’s grade and other relevant information in a secure database. Educators can view and subjectively grade each assignment, in CADGrader as well. Additionally, CADGrader calculates every student’s cumulative average in the course. Administrators can easily download this information from the website. Students can use CADGrader to refine their design skills. Students can attempt to model practice assignments, on the CADGrader website. CADGrader provides realtime feedback of the practice submissions. These practice assignments can be chosen/changed by the administrators.

Front End(JQuery, Electron, Three.js), Back End(Node.JS, Python(NumPy, CGI Module), AJAX, MySQL, PHP)

Presented at:
-Hamilton Maker Fair 2017
-Toronto Maker Festival 2017

CADGrader Website May 2017-Current Hamilton Mini MakerFaire 2017 Toronto MakerFestival 2017

Project All Python JavaScript Electron Node.js MySQL PHP Electron