Binocular stereoscopic vision detection method for appearance quality of crisp strawberries

• Main Authors: ZHU TAIHAI, PAN LEIQING, YANG JUN, CHEN FEI, FAN ANQI
• Format: Patent
• Language: Chinese; English
• Published: 30.12.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a binocular stereoscopic vision detection method for strawberry crisp appearance quality. The binocular stereoscopic vision detection method comprises the following steps: 1) selecting strawberry crisp samples; 2) measuring the volume of the strawberry crisp by using a volume substitution method; (3) establishing a sensory evaluation model of the strawberry crisp sample by adopting a fuzzy mathematics method; 4) building a binocular stereoscopic vision system to collect binocular images of strawberry crispness; 5) adopting image processing software; 6) matching corresponding pixel points in the binocular image by using a stereo matching algorithm; 7) performing data processing; 8) establishing a regression prediction model of the image extraction volume and the actually measured volume for the analyzed strawberry crispness; (9) respectively importing the feature data into three models, namely a PLS-DA model, an SVM-C model and a VGG16 model; (10) verifying the three models, namely the