PT Unknown
AU Henry Velesaca
   Raul Mira
   Patricia Suarez
   Christian X. Larrea
   Angel Sappa
TI Deep Learning Based Corn Kernel Classification
BT 1st International Workshop and Prize Challenge on Agriculture-Vision: Challenges & Opportunities for Computer Vision in Agriculture
PY 2020
AB This paper presents a full pipeline to classify sample sets of corn kernels. The proposed approach follows a segmentation-classification scheme. The image segmentation is performed through a well known deep learningbased approach, the Mask R-CNN architecture, while the classification is performed hrough a novel-lightweight network specially designed for this task—good corn kernel, defective corn kernel and impurity categories are considered. As a second contribution, a carefully annotated multitouching corn kernel dataset has been generated. This dataset has been used for training the segmentation and the classification modules. Quantitative evaluations have beenperformed and comparisons with other approaches are provided showing improvements with the proposed pipeline.
ER