Drought is being annually exacerbated by recent global warming, leading to crucial damage of crop growth and final yields. Soybean, one of the most consumed crops worldwide, has also been affected in the process. The development of a resistant cultivar is required to solve this problem, which is considered the most efficient method for crop producers. To accelerate breeding cycles, genetic engineering and high-throughput phenotyping technologies have replaced conventional breeding methods. However, the current novel phenotyping method still needs to be optimized by species and varieties. Therefore, we aimed to assess the most appropriate and effective phenotypes for evaluating drought stress by applying a high-throughput image-based method on the nested association mapping (NAM) population of soybeans. The acquired image-based traits from the phenotyping platform were divided into three large categories-area, boundary, and color-and demonstrated an aspect for each characteristic. Analysis on categorized traits interpreted stress responses in morphological and physiological changes. The evaluation of drought stress regardless of varieties was possible by combining various image-based traits. We might suggest that a combination of image-based traits obtained using computer vision can be more efficient than using only one trait for the precision agriculture.
Keywords: RGB phenotyping; abiotic stress response; digital image analysis; image processing; phenotyping platform system.