TY - JOUR

T1 - Self-Supervised Leaf Segmentation under Complex Lighting Conditions

AU - Lin, Xufeng

AU - Li, Chang-Tsun

AU - Adams, Scott

AU - Kouzani, Abbas Z.

AU - Jiang, Richard

AU - He, Ligang

AU - Hu, Yongjian

AU - Vernon, Michael

AU - Doeven, Egan H.

AU - Webb, Lawrence

AU - Mcclellan, Todd

AU - Guskic, Adam

N1 - This is the author’s version of a work that was accepted for publication in Pattern Recognition. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Pattern Recognition, 135, 2023 DOI: 10.1016/j.patcog.2022.109021

PY - 2023/3/31

Y1 - 2023/3/31

N2 - As an essential prerequisite task in image-based plant phenotyping, leaf segmentation has garnered increasing attention in recent years. While self-supervised learning is emerging as an effective alternative to various computer vision tasks, its adaptation for image-based plant phenotyping remains rather unexplored. In this work, we present a self-supervised leaf segmentation framework consisting of a self-supervised semantic segmentation model, a color-based leaf segmentation algorithm, and a self-supervised color correction model. The self-supervised semantic segmentation model groups the semantically similar pixels by iteratively referring to the self-contained information, allowing the pixels of the same semantic object to be jointly considered by the color-based leaf segmentation algorithm for identifying the leaf regions. Additionally, we propose to use a self-supervised color correction model for images taken under complex illumination conditions. Experimental results on datasets of different plant species demonstrate the potential of the proposed self-supervised framework in achieving effective and generalizable leaf segmentation.

AB - As an essential prerequisite task in image-based plant phenotyping, leaf segmentation has garnered increasing attention in recent years. While self-supervised learning is emerging as an effective alternative to various computer vision tasks, its adaptation for image-based plant phenotyping remains rather unexplored. In this work, we present a self-supervised leaf segmentation framework consisting of a self-supervised semantic segmentation model, a color-based leaf segmentation algorithm, and a self-supervised color correction model. The self-supervised semantic segmentation model groups the semantically similar pixels by iteratively referring to the self-contained information, allowing the pixels of the same semantic object to be jointly considered by the color-based leaf segmentation algorithm for identifying the leaf regions. Additionally, we propose to use a self-supervised color correction model for images taken under complex illumination conditions. Experimental results on datasets of different plant species demonstrate the potential of the proposed self-supervised framework in achieving effective and generalizable leaf segmentation.

KW - Self-supervised learning

KW - Convolutional neural networks

KW - Image-based plant phenotyping

KW - Leaf segmentation

KW - Color correction

KW - Cannabis

U2 - 10.1016/j.patcog.2022.109021

DO - 10.1016/j.patcog.2022.109021

M3 - Journal article

VL - 135

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

M1 - 109021

ER -