TY - GEN
T1 - Deep-Learning Based Image Super-Resolution for Enhanced Root Hair Visualization and Root Traits Analysis
AU - Mishra, Divya
AU - Chemweno, Sharon
AU - Hadar, Ofer
AU - Lazarovitch, Naftali
AU - Ephrath, Jonathan E.
N1 - Publisher Copyright:
© 2023 SPIE. All rights reserved.
PY - 2023/1/1
Y1 - 2023/1/1
N2 - The arrangement of plant roots and their overall structure, known as root system architecture (RSA), plays an important role in acquiring water and nutrients essential for plant growth and development. Moreover, the RSA demonstrates remarkable adaptability to environmental stresses, making it a central factor in plant adaptation. Root traits, including root length, root diameter, root length density (RLD), and the presence of root hairs, play a crucial role in optimizing resource utilization within the soil and enhancing productivity. In particular, root hairs play a crucial role in the overall health and functioning of plants. These microscopic, hair-like structures extend from the surface of root cells and greatly increase the root’s surface area, which accounts for approximately 70% of the total root area. The characteristics of root hairs, such as their length and density, significantly enhance soil nutrients and water uptake. Considering these advantages, it is difficult to observe root hairs in a scene with low resolution. Therefore, we proposed a study using deep learning-based image super-resolution methods as a pre-processing step that helps to reconstruct finer details and structures within the root hairs, leading to a more accurate representation of their morphology, to understand the improvement in the response of root hairs under different environmental conditions and their impact on nutrient and water uptake, models need to be evolved.
AB - The arrangement of plant roots and their overall structure, known as root system architecture (RSA), plays an important role in acquiring water and nutrients essential for plant growth and development. Moreover, the RSA demonstrates remarkable adaptability to environmental stresses, making it a central factor in plant adaptation. Root traits, including root length, root diameter, root length density (RLD), and the presence of root hairs, play a crucial role in optimizing resource utilization within the soil and enhancing productivity. In particular, root hairs play a crucial role in the overall health and functioning of plants. These microscopic, hair-like structures extend from the surface of root cells and greatly increase the root’s surface area, which accounts for approximately 70% of the total root area. The characteristics of root hairs, such as their length and density, significantly enhance soil nutrients and water uptake. Considering these advantages, it is difficult to observe root hairs in a scene with low resolution. Therefore, we proposed a study using deep learning-based image super-resolution methods as a pre-processing step that helps to reconstruct finer details and structures within the root hairs, leading to a more accurate representation of their morphology, to understand the improvement in the response of root hairs under different environmental conditions and their impact on nutrient and water uptake, models need to be evolved.
KW - Deep learning
KW - Image Super-resolution
KW - Image analysis
KW - Minirhizotron technique
KW - Root hair analysis
KW - Root hairs image enhancement
KW - Root phenotyping
UR - http://www.scopus.com/inward/record.url?scp=85177867709&partnerID=8YFLogxK
U2 - 10.1117/12.2687786
DO - 10.1117/12.2687786
M3 - Conference contribution
AN - SCOPUS:85177867709
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Remote Sensing for Agriculture, Ecosystems, and Hydrology XXV
A2 - Neale, Christopher M.
A2 - Maltese, Antonino
PB - SPIE
T2 - Remote Sensing for Agriculture, Ecosystems, and Hydrology XXV 2023
Y2 - 3 September 2023 through 6 September 2023
ER -