Defect detection and defect grading method for agricultural products

• Main Authors: SUN WEI, XIONG HAOMIN, ZHOU TING
• Format: Patent
• Language: Chinese; English
• Published: 27.10.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MEASURING; PHYSICS; TESTING

The invention relates to the field of agricultural product defect detection and defect grading, and provides an agricultural product defect detection and defect grading method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring to-be-detected fruit images of a plurality of visual angles shot by a camera on a to-be-detected fruit; inputting each to-be-detected fruit image into a trained first defect identification model for identification, and obtaining a fruit area graph and a defect area graph of each to-be-detected fruit image; the defect area graph at the moment is possibly a suspected defect area; in order to further confirm whether the defect area graphs have defect areas or not, secondary defect identification is carried out on each defect area graph, and the defect grade of the fruit to be detected is obtained. And the accuracy of defect identification and defect grading of the agricultural products is improved. 本申请涉及农产品的缺陷检测和缺陷等级划分领域，提供了一种农产品的缺陷检测和缺