Corn kernel crush rate online detection method and device based on machine vision

• Main Authors: YIN CHUNYUAN, LIU ZHIXIANG, BAI XIAOPING, GAO LEI, YANG LIANG, XIONG FENG, LIU JIANBANG, WANG ZHUO
• Format: Patent
• Language: Chinese; English
• Published: 05.06.2018
• Subjects: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MEASURING; PHYSICS; TESTING

The invention relates to a corn kernel crush rate online detection method and device based on machine vision. The method comprises the following steps: obtaining corn kernels distributed in a single layer by a box body structure; collecting corn kernels images by an industrial CCD camera and carrying out sharpening, de-noising and edge detection to obtain the corn kernel edge contour feature; separating the crushed corn kernels and intact corn kernels by employing threshold segmentation and binarization processing; analyzing the images by a fuzzy clustering method to extract the crushed corn kernel characteristics; and matching the template with a standard crushed corn kernel template to obtain the quantity of the crushed corn kernels and calculating the crush rate, and displaying the crush rate on a vehicle-mounted terminal. The device comprises a detection box body unit, an image acquisition unit, an image processing unit, a data transmission unit, and a vehicle-mounted control and display unit. The units a