In a previous study, a fresh chili destemming system has been proposed, and the TCS3200 color sensor was used as low-cost equipment in the arrangement section of the system. However, the working and installing parameters have not yet been investigated in detail. This study focused on investigating the optimal working conditions of TCS3200 on the fresh chili destemming system. The study included three experiments including the effect of the red and green color channels, the effect of the height between the sensor and fruits, and the effect of the running velocity on the received signal level of the sensor. A total of 260 ripen fruits were chosen to test. The results showed that the red channel generated a stronger signal than the green one. The optimal height from the sensor to the fruits was obtained at 25 mm, and the maximum conveyor velocity is limited to 100 mm/s. This study helps to determine the optimal operating parameters and enhance the working ability of a low-cost sensor. However, the high-speed pushing actuating mechanism should be developed in further works.

Destemming fresh chilli fruit (Capsicum) in large productivity is necessary, especially in the Mekong Delta region. Several studies have been done to solve this problem with high applicability, but a certain percentage of the output consisted of cracked fruits, thus reducing the quality of the system. The manual sorting results in high costs and low quality, so it is necessary that automatic grading is performed after destemming. This research focused on developing a method to identify and classify cracked chilli fruits caused by the destemming process. The convolution neural network (CNN) model was built and trained to identify cracks; then, appropriate control signals were sent to the actuator for classification. Image processing operations are supported by the OpenCV library, while the TensorFlow data structure is used as a database and the Keras application programming interface supports the construction and training of neural network models. Experiments were carried out in both the static and working conditions, which, respectively, achieved an accurate identification rate of 97 and 95.3%. In addition, a success rate of 93% was found even when the chilli body is wrinkled due to drying after storage time at 120 hours. Practical results demonstrate that the reliability of the model was useful and acceptable.

No abstract

No abstract

No abstract