抄録
A machine vision system with double lighting and an image processing algorithm were developed to detect undesirable objects in the paddy as it is being harvested to provide information for adjustment of parameter settings by the operator and automate combine harvester procedures. The system consisted of a web camera, a double lighting system (frontlight and backlight), an image acquisition, and image analysis algorithm. Images captured by this system were used for detection of undesirable objects (long rachis branches, grass and leaves, straw and stalks) and damaged grain (brown rice and cracked rice). Evaluation of the results demonstrate the proposed detection algorithm had a detection correlation of determination, R2 greater than 0.70 for detection of each of the undesirable objects. Future application of this system in the field could help the operator of the combine harvester to improve the efficiency and adjustment of automated harvesting procedures, as well as the quality of the harvested paddy.
