Machine Vision-Based Detection and Removal of Foreign Materials During Processing of Finished Tea

Tea industries face the challenge of foreign substances, both organic and inorganic, contaminating their processed tea. These materials can enter the tea during various stages, posing risks to customers and the company's reputation. Manual sorting, the traditional method for removing foreign matter, is time-consuming, labor-intensive, and prone to errors. To address this problem, this paper proposes a machine vision-based solution. It involves capturing continuous images of processed tea as it moves through a vibratory bed. These images are analyzed using a single board computing device to detect visible foreign matter on the tea. When foreign substances are identified, pneumatic valves in the vibratory bed open a small window, allowing the contaminated tea leaves to be released, while the clean tea continues to pass through and collect in a storage container at the end. The solution employs a modular approach, enabling multiple vision inspection modules to be controlled through a single graphical user interface (GUI) on a desktop, meeting the high throughput requirements of tea industries. Experiments conducted on Orthodox tea varieties confirm the proposed solution meets industry standards for accuracy and throughput. By implementing this machine vision-based approach, tea processing companies can enhance customer safety, maintain loyalty, and prevent recalls or rejections, while significantly reducing labor and time involved in manual sorting processes.