Spatially Variant Convolutional Autoencoder Based on Patch Division for Pill Defect Detection.
Sora KimYoungjae JoJungchan ChoJiwoo SongYounyoung LeeMinsik LeePublished in: IEEE Access (2020)
Keyphrases
- defect detection
- spatially variant
- restricted boltzmann machine
- mathematical morphology
- multiscale
- image patches
- spatially varying
- morphological filters
- morphological operators
- deep learning
- structuring elements
- feature extraction
- b spline
- sparse coding
- signal and image processing
- translation invariant
- maximum likelihood estimation
- gray scale
- gray level images
- natural images
- pattern recognition
- image enhancement
- machine learning
- conditional random fields
- low resolution
- higher order
- semi supervised
- feature vectors