Magnetic grains are the crucial constituent of Nd-Fe-B magnet in electric vehicle (EV) driven motor. Hot-deformed manufacturing process is taken to enhance the coercivity of Nd-Fe-B magnet and enable it to reach the higher heat resistance of EV driven motor. The evaluation of specific parameters pertaining to the hot-deformed manufacturing process relies on the analysis of magnetic grain profiles. However, the current analysis procedure encompassing profile extraction, is conducted manually. To meet this challenge, we design and develop a computer vision system to assist the extraction of magnetic grain profile by incorporating the resolution-enhancing preprocess and refining the existing edge detection step. To evaluate the performance of our proposed computer vision system, a series of experiments have been conducted to validate the result completeness, assess the time consumption, and compare the prevailing methods of similar properties. The comprehensive appraisal demonstrates that the accuracy and processing time of our proposed computer vision system align with the desired industrial requirements.