A voting-based ensemble deep learning method focusing on image augmentation and preprocessing variations for tuberculosis detection.
Erdal TasciCaner UluturkAybars UgurPublished in: Neural Comput. Appl. (2021)
Keyphrases
- preprocessing
- voting method
- segmentation method
- deep learning
- test images
- image regions
- segmentation algorithm
- lighting conditions
- similarity measure
- probabilistic model
- input image
- region of interest
- computer vision
- multiscale
- image segmentation
- image features
- image retrieval
- object detection
- text mining
- text classification
- model selection
- high dimensional
- pairwise
- training set
- conditional random fields
- image content
- training data
- image processing
- feature selection