Tree Health Assessment from UAV Images: Improving Object Detection and Classification Using Hard Negative Mining and Semi-Supervised Autoencoder.
Hela JemaaWassim BouachirBrigitte LeblonArmand LaRocqueAta HaddadiNizar BouguilaPublished in: CRV (2023)
Keyphrases
- image classification
- semi supervised
- object detection
- object classification
- image data
- image analysis
- image features
- three dimensional
- input image
- image database
- object recognition
- classification accuracy
- supervised learning
- support vector machine
- image retrieval
- similarity measure
- computer vision
- object categories
- semi supervised classification
- multi class
- image registration
- support vector
- pigmented skin lesions
- thematic mapper
- detecting objects
- restricted boltzmann machine
- skin lesion
- machine learning
- labeled and unlabeled data
- classification trees
- co training
- feature selection
- segmentation method
- training samples
- unlabeled data
- multi view
- text classification