IoT-based Automatic Sorting of Objects that are Transparent Translucent and Opaque using the Effect of Light

Transparent, translucent and opaque materials have different medium levels that can represent different classes. Object management systems are mainly detecting and sorting three different types of materials that are transparent, translucent, and opaque including glass, plastic, and others such as labeled bottles. However, there have been some systems capable of detecting transparent, translucent, and opaque materials, but these systems can only differentiate transparent, translucent, and opaque materials without any kind of size determination. This research system can differentiate between the transparent, translucent, opaque, and others using photoresist or sensors and laser beam with shape detection method based on open CV classification. The findings indicate that the accuracy of detection is 82.27% for the opaque objects placed on the conveyor. However, the translucent detection true percentage is 60.06% where a moving object was detected while there was a translucent object over the conveyor. The accuracy of object detection as one of the main components of this system was also tested. The accuracy percentage yields that the accuracy of the system in detection of moving object, transparent, translucent, and other materials are as 77.64%, 66.11%, and 80.27%. However, the system malfunction in a low laser range of below 600nm and the system is limited to differentiate certain labeled materials. The system overall length approximately reaches 114CM and the detection unit can’t accept the materials that exceed 30CMin height.