AUTHOR=Jin Xin , Wang Chenglin , Chen Kaikang , Ji Jiangtao , Liu Suchwen , Wang Yawei 

TITLE=A Framework for Identification of Healthy Potted Seedlings in Automatic Transplanting System Using Computer Vision

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2021.691753

DOI=10.3389/fpls.2021.691753

ISSN=1664-462X

ABSTRACT=Automatic seedling transplanting is of great significance for the vegetable cultivation factory. Accurate and efficient identification of healthy seedlings is the fundamental process of the automatic seedlings transplanting. This paper proposed a computer vision-based identification framework of healthy seedlings. Vegetable seedlings were planted in trays in the form of potted seedlings. Two color indexes were proposed for seedling image preprocessing. An optimal thresholding method based on the genetic algorithm and a three-dimensional block-matching algorithm (BM3D) were applied to denoise and segment the tray seedling image. The leaf areas of the seedlings were measured by machine vision technology to detect the growing status and position information of tray seedling. An algorithm of smart identification of healthy vegetable seedlings (SIHVS) was proposed for identifying the healthy seedlings. By comparing the identification effect of 273 vegetable seedling images, the identification accuracy of the proposed framework is 94.33% higher than the comparison method 89.37%.