Unsupervised anomaly detection with compact deep features for wind turbine blade images taken by a drone.
Yinan WangRyota YoshihashiRei KawakamiShaodi YouTohru HaranoMasahiko ItoKatsura KomagomeMakoto IidaTakeshi NaemuraPublished in: IPSJ Trans. Comput. Vis. Appl. (2019)
Keyphrases
- image features
- wind turbine
- test images
- image database
- image classification
- input image
- keypoints
- highly discriminative
- binary codes
- image regions
- image retrieval
- feature set
- feature space
- anomaly detection
- object recognition
- feature extraction
- feature vectors
- gabor filters
- wind speed
- high dimensional
- fault diagnosis
- data structure
- knowledge base
- decision making
- computer vision