Leaf Vein Segmentation Method of Soybean Leaf Image

School of Information Engineering, Nanjing University of Finance and Economics,

Clc Number:

Fund Project:

Natural Science Foundation of Jiangsu Province; Major Natural Science Research Projects of Universities in Jiangsu Province; Open Fund of Hubei Key Laboratory of Intelligent Robots; Research Innovation Program for Postgraduates of Jiangsu Province

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments

    Leaf vein segmentation is an important step in leaf pattern analysis, which is of great significance for soybean variety identification and phenotype research. On account of the complicated leaf texture of soybean and the low contrast of the leaf area where the veins are located, it is generally impossible to achieve ideal segmentation results only by using gray information to segment leaf vein. This paper presents a means of soybean vein segmentation combining multi-scale gray unconstrained hit-or-miss transform (UHMT) algorithm and the processing method based on the hue data of HSI color space. In this means, the gray information in RGB color space and the hue data in HSI color space are used to segment the global leaf veins and local primary and secondary veins from soybean leaf image separately. The former uses iterative threshold segmentation to extract the leaf area, and eliminates interference factors such as the outer contour and the petiole of the leaf through expansion and corrosion, and obtains the leaf area image. Then, the multi-scale gray UHMT algorithm is used to obtain the global leaf vein image. Contraposing the matter of poor segmentation effect of primary and secondary veins, the latter uses hue data to enlarge the discrepancies in gray value between veins pixels and other pixels to realize the segmentation of local primary and secondary veins. The obtained global and local vein images are fused into the final soybean leaf vein image. This paper uses soybean leaf images in the soybean leaf image database, SoyCultivar, to verify the effectiveness of the algorithm. The results indicate that this algorithm is better than the existing leaf vein segmentation methods, not only can extract soybean leaf veins completely, but also can well eliminate the background, leaf contours, petiole and other irrelevant components.

    Cited by
Get Citation
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
  • Received:July 24,2021
  • Revised:August 25,2021
  • Adopted:August 31,2021
  • Online: October 19,2021
  • Published:
You are the firstVisitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063