An automated, high-throughput method for standardizing image color profiles to improve image-based plant phenotyping

Abstract

High-throughput phenotyping has emerged as a powerful method for studying plant biology. Large image-based datasets are generated and analyzed with automated image analysis pipelines. A major challenge associated with these analyses is variation in image quality that can inadvertently bias results. Images are made up of tuples of data called pixels, which consist of R, G, and B values, arranged in a grid. Many factors, for example image brightness, can influence the quality of the image that is captured. These factors alter the values of the pixels within images and consequently can bias the data and downstream analyses. Here, we provide an automated method to adjust an image-based dataset so that brightness, contrast, and color profile is standardized. The correction method is a collection of linear models that adjusts pixel tuples based on a reference panel of colors. We apply this technique to a set of images taken in a high-throughput imaging facility and successfully detect variance within the image dataset. In this case, variation resulted from temperature-dependent light intensity throughout the experiment. Using this correction method, we were able to standardize images throughout the dataset, and we show that this correction enhanced our ability to accurately quantify morphological measurements within each image. We implement this technique in a high-throughput pipeline available with this paper, and it is also implemented in PlantCV.

Plant phenotyping relevance

植物画像の色・明るさ補正法を開発し、形態計測の精度向上と高スループット解析パイプラインへの実装を示しており、フェノタイピング手法が中心である。

Code and data availability

The paper's image standardization C++ code is publicly deposited on GitHub, and the paper-specific phenotyping assets (original and corrected plant images, R scripts, and numerical data) are publicly downloadable from the Danforth Center phenotyping site; the method is also implemented in PlantCV (GitHub and Zenodo-ach