Vision-Based White Radish Phenotypic Trait Measurement with Smartphone Imagery

White radish is a nutritious and delectable vegetable that enjoyed globally. Conventional techniques for monitoring growth are arduous time-consuming, encouraging the development of novel methods quicker measurements greater sampling density. This research introduces mathematical model working on high-resolution images to measure radish’s biophysical properties automatically. A color calibration was performed dataset using checker panel minimize impact varying light conditions RGB images. Subsequently, Mask-RCNN trained effectively segment different components radishes. The observations segmented results included leaf length, width, root length shoulder color, peel color. automated real-life these were then conducted compared with actual results. validation results, based set white samples, demonstrated models’ effectiveness in utilizing quantifying phenotypic traits. average accuracy method confirmed be 96.2% when manual method.