Abstract:
Completeness of rice grain inspection is one of the methods to check the rice grain for ensuring the quality of the rice grain after being sorted according to the required standard and no other contaminants such as rice, grits, soil, and stone. Along with collecting data of the grain in a statistical way for use in the inspection and development of the efficiency of the separation process to be of high quality. This thesis proposes to check the completeness of the rice grains that have been sorted by using image processing principles and adapted to process images from a normal webcam camera. In addition, the Microsoft Visual C# 2017 was used for processing the
signals by analyzing the output signals of webcam camera. In the experiment is divided into two forms, non-overlapping rice grain inspection. And overlapping rice grain inspection. In this system, it is highly effective and gives the results of accuracy and
inspection of non-overlapping grain cases which are divided into four cases: inspection 50 perfect rice grain, 50 imperfect rice grain, 50 rice grain in 1:1 ratio between the perfect and imperfect rice grain and 40 rice grain in 3:1, 1:1, and 1:3 ratio between the perfect and imperfect rice grain. From the experimental result of four cases, the error rates were 0.2%, 0%, 1.4%, and 1.11%, respectively, while the average of process error was 0.82%.