Гучид У.Д.   Цагаан бөө Ө.Д.   Hong C.H.   Ванчиг Л.Б.   Бадарч А.Б.   Далхаа Ш.Д.  

Citrus fruit quality classification based on size using digital image processing

Докладчик: Гучид У.Д.

Quality inspection and classification of agricultural products are an important component of agricultural production and marketing. A new computer vision algorithm for quality classification in citrus fruits based on size for a single tree was developed in this study. The image properties of area, perimeter, and diameter for the citrus fruits were measured by pixels. In order to estimate citrus fruit size in a realistic manner the ratios of diameter, perimeter and area pixels values in relation to actual size were determined. Total of 1860 citrus fruit were grouped based on the rule, which is based on diameter, perimeter, and area pixels. Results of the grouping by diameter, perimeter, and area were compared with results of survey research for citrus fruit size as conducted by the Jeju Citrus Commission. Comparative results demonstrate that the citrus fruit diameter pixels of the image demonstrate a more accurate size than the other two pixels values, i.e., perimeter and area.

К списку докладов