Real-Time Defect Detection Monitoring System For Extrusion-based 3D Food Printing Using Internet of Things

Quality control remains a significant challenge in 3D food printing, in which defects during the printing process will lead to resource and time wastage. This work proposes a novel approach integrating cameras, image processing, and supervised machine learning to autonomously assess the quality of 3D food printed items. At crucial stages of the printing process, images of partially manufactured parts are captured and analyzed based on its geometry. Utilizing smartphones and the Internet of Things for efficient monitoring, the designed system aims to minimize material wastage, a prevalent concern in the creative food industry. The monitoring tool employs a 3D printer embedded with Raspberry Pi and a primary camera, with image processing carried out by the Obico plugin on Raspberry Pi to issue commands for real-time performance monitoring. The implementation of this technology not only addresses early defect detection but also enhancing food design and minimizing environmental impact, presenting promising prospects for the future of the food industry.