• Journal of Biosystems Engineering
• /
• 제28권3호
• /
• pp.231-238
• /
• 2003

Rose and chrysanthemum are the most popular flowers in Korean floriculture. Sorting flowers is a labor intensive operation in cultivation of the cut flowers and needed to be mechanized. Machine vision is one of the promising solutions for this purpose. This study was carried out to develop hardware and software of a cut flower sorting system using machine vision and to test its performance. Results of this study were summarized as following; 1. Length of the cut flower measured by the machine vision system showed a good correlation with actual length of the flower at a level of the coefficients of determination (R$^2$) of 0.9948 and 0.9993 for rose and chrysanthemum respectively and average measurement errors of the system were about 2% and 1% of the shortest length of the sample flowers. The experimental result showed that the machine vision system could be used successfully to measure length of the cut flowers. 2. Stem diameter of the cut flowers measured by the machine vision system showed a correlation with actual diameter at the coefficients of determination (R$^2$) of 0.8429 and 0.9380 for rose and chrysanthemum respectively and average measurement errors of the system were about 15% and 7.5% of the shortest diameter of the sample flowers which could be a serious source of error in grading operation. It was recommended that the error rate should be considered to set up grading conditions of each class of the cut flowers. 3. Bud maturity of 20 flowers each judged using the machine vision system showed a coincidence with the judgement by inspectors at ranges of 80%∼85% and 85%∼90% for rose and chrysanthemum respectively. Performance of the machine vision system to judge bud maturity could be improved through setting up more precise criteria to judge the maturity with more samples of the flowers. 4. Quality of flower judged by stem curvature using the machine vision system showed a coincidence with the judgement by inspectors at 90% for good and 85% for bad flowers of both rose and chrysanthemum. The levels of coincidence was considered as that the machine vision system used was an acceptable system to judge the quality of flower by stem curvature.