Deep Learning based Corn Kernel Classification
| Autor: | Christian X. Larrea, Raúl Mira, Angel D. Sappa, Henry O. Velesaca, Patricia L. Suarez |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Scheme (programming language)
0209 industrial biotechnology food.ingredient Computer science business.industry Pipeline (computing) Deep learning Pattern recognition 02 engineering and technology Image segmentation Corn kernel Sample (graphics) Task (computing) 020901 industrial engineering & automation food 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence business computer computer.programming_language |
| Zdroj: | CVPR Workshops |
| DOI: | 10.1109/cvprw50498.2020.00041 |
| Popis: | 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 learning-based approach, the Mask R-CNN architecture, while the classification is performed through 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 multi-touching corn kernel dataset has been generated. This dataset has been used for training the segmentation and the classification modules. Quantitative evaluations have been performed and comparisons with other approaches are provided showing improvements with the proposed pipeline. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|