Semantic image segmentation using fully convolutional neural networks with multi-scale images and multi-scale dilated convolutions.
Duc My VoSang-Woong LeePublished in: Multim. Tools Appl. (2018)
Keyphrases
- multiscale
- image segmentation
- edge detection
- multiple scales
- image analysis
- segmentation scheme
- scale space
- segmentation algorithm
- convolutional neural networks
- image data
- natural images
- keypoints
- grey level
- image processing
- segmentation method
- unsupervised segmentation
- input image
- wavelet transform
- image features
- ground truth
- image classification
- segmenting images
- object recognition
- segmented images
- coarse to fine
- convolutional network
- medical imaging
- image retrieval
- gaussian filter
- image database
- image collections
- image fusion
- feature extraction
- edge detector
- fine scale
- semantic categories
- image registration
- image segmentation algorithms
- image segmentation algorithm
- region growing
- region segmentation
- active contours
- image regions
- level set method
- local binary pattern
- image representation
- segmented regions
- unsupervised image segmentation
- adaptive thresholding
- image segmentations
- markov random field model
- image structure
- computer vision