Image-based leaf parameter measurement method

• Main Authors: KONG XIANGLING, FU JINGLUN, SHI JIAJUN, CUI ZEYANG
• Format: Patent
• Language: Chinese; English
• Published: 30.08.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses an image-based leaf parameter measurement method, which comprises the following steps of: on the basis of computer vision, preprocessing an input leaf original image, improving a visual effect and edge identification accuracy, carrying out background segmentation to obtain contour point information of a leaf, extracting a skeleton of the leaf image by adopting a skeleton extraction algorithm, and carrying out image segmentation on the skeleton of the leaf image; a mean camber line function and a thickness distribution function of a blade profile are calculated through curve fitting, blade profile parameters are calculated according to geometric features of the blade, an original image of the blade is used as prior information, an optimization algorithm is adopted to perform secondary accurate measurement on a primary measurement result, and the measurement precision is improved. The method is fast and flexible to use and high in accuracy, the relative measurement error is smaller than