ML Anthology

Automatic Differentiation of Damaged and Unharmed Grapes Using RGB Images and Convolutional Neural Networks

Jonas Bömer, Laura Zabawa, Philipp Sieren, Anna Kicherer, Lasse Klingbeil, Uwe Rascher, Onno Muller, Heiner Kuhlmann, Ribana Roscher
ECCVW 2020 pp. 347-359
doi:10.1007/978-3-030-65414-6_24 /eccvw/2020/bomer2020eccvw-automatic/

Abstract

Knowledge about the damage of grapevine berries in the vineyard is important for breeders and farmers. Damage to berries can be caused for example by mechanical machines during vineyard management, various diseases, parasites or abiotic stress like sun damage. The manual detection of damaged berries in the field is a subjective and labour-intensive task, and automatic detection by machine learning methods is challenging if all variants of damage should be modelled. Our proposed method detects regions of damaged berries in images in an efficient and objective manner using a shallow neural network, where the severeness of the damage is visualized with a heatmap. We compare the results of the shallow, fully trained network structure with an ImageNet-pretrained deep network and show that a simple network is sufficient to tackle our challenge. Our approach works on different grape varieties with different berry colours and is able to detect several cases of damaged berries like cracked berry skin, dried regions or colour variations.

PDF ECCVW Semantic Scholar

Cite

Text

Bömer et al. "Automatic Differentiation of Damaged and Unharmed Grapes Using RGB Images and Convolutional Neural Networks." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-65414-6_24

Markdown

[Bömer et al. "Automatic Differentiation of Damaged and Unharmed Grapes Using RGB Images and Convolutional Neural Networks." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/bomer2020eccvw-automatic/) doi:10.1007/978-3-030-65414-6_24

BibTeX

@inproceedings{bomer2020eccvw-automatic,
  title     = {{Automatic Differentiation of Damaged and Unharmed Grapes Using RGB Images and Convolutional Neural Networks}},
  author    = {Bömer, Jonas and Zabawa, Laura and Sieren, Philipp and Kicherer, Anna and Klingbeil, Lasse and Rascher, Uwe and Muller, Onno and Kuhlmann, Heiner and Roscher, Ribana},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {347-359},
  doi       = {10.1007/978-3-030-65414-6_24},
  url       = {https://mlanthology.org/eccvw/2020/bomer2020eccvw-automatic/}
}