A deep learning approach combining instance and semantic segmentation to identify diseases and pests of coffee leaves from in-field images.
Lucas M. TassisJoão E. Tozzi de SouzaRenato A. KrohlingPublished in: Comput. Electron. Agric. (2021)
Keyphrases
- deep learning
- semantic segmentation
- weakly supervised
- image database
- input image
- image classification
- image features
- object recognition
- image understanding
- superpixels
- image set
- image annotation
- unsupervised learning
- multiple images
- segmentation method
- conditional random fields
- named entities
- bounding box
- partial occlusion
- region of interest
- computer vision
- spatial information
- image regions
- image segmentation