Automated discomfort detection for premature infants in NICU using time-frequency feature-images and CNNs.
Yue SunDeedee KommersTao TanWenjin WangXi LongCaifeng ShanCarola van PulRonald M. AartsPeter AndriessenPeter H. N. de WithPublished in: Medical Imaging: Computer-Aided Diagnosis (2020)
Keyphrases
- image features
- image data
- image database
- input image
- detection rate
- image analysis
- image classification
- ground truth
- image registration
- digital mammography
- test images
- image collections
- feature vectors
- invariant features
- false detections
- feature representation
- detection method
- fully automatic
- image processing
- three dimensional
- image quality
- signal processing
- feature set
- object detection
- automated segmentation
- cellular neural networks
- traffic signs
- automated analysis
- complex background
- image retrieval
- false positives
- object categories
- computer vision
- image regions
- segmentation method