Description
Quantifying tar spot of corn intensity has traditionally been conducted by human raters through visual-based estimations. However, this traditional method is costly in terms of time and labor and prone to rater subjectivity. Furthermore, an objective, accurate and high throughput method for quantifying stromata on corn leaves is currently unavailable. Two datasets can be found here: one dataset which contains the images that were used to develop and improve the stromata contour detection algorithm (SCDA). Another dataset contains 466 RGB images of corn leaves acquired at the Pinney Purdue Agricultural Center (PPAC), Indiana and used as data for proof of concept case study to demonstrate the utility of the presented algorithm (SCDA).
Cite this work
Researchers should cite this work as follows:
- Da-Young Lee; Dong-Yeop Na; Carlos Gongora-Canul; Sriram Baireddy; Brenden Lane; Cruz, A. P.; Fernández-Campos, M. S.; Nathan M. Kleczewski; Darcy E. P. Telenko; Edward J. Delp; Goodwin, S.; Christian D. Cruz (2021). Contour-based detection and quantification of tar spot stromata using RGB images of maize leaves. (Version 2.0). Purdue University Research Repository. doi:10.4231/SCQM-M479
Tags
Notes
Contains an additional dataset comprised of 466 RGB corn leaf images which were acquired throughout six timepoints at Pinney Purdue Agricultural Center (PPAC), Indiana. Furthermore, the number of stromata and the proportion of maize leaf covered by tar spot stromata analyzed through the SCDA and mask R-CNN are included in the form of excel sheets.