MicroCrack-Net: A Deep Neural Network With Outline Profile-Guided Feature Augmentation and Attention-Based Multiscale Fusion for MicroCrack Detection of Tantalum Capacitors.
Mingyang ChengChuqiao XuJunliang WangWenjun ZhangYaqin ZhouJie ZhangPublished in: IEEE Trans. Aerosp. Electron. Syst. (2022)
Keyphrases
- multiscale
- neural network
- decision level fusion
- feature level
- image fusion
- automatic detection
- artificial neural networks
- false positives
- canny edge detection
- object detection
- detection accuracy
- multi modal fusion
- feature fusion
- detection rate
- visual attention
- detection algorithm
- anomaly detection
- image features
- pattern recognition
- edge detection
- false alarms
- matching score
- adaboost classifier
- information fusion
- neural network model
- natural images
- detection method
- feature vectors
- image registration
- feature space
- affine invariant
- fusion methods
- fusion method
- multiple features
- face detection
- multi sensor
- neural nets
- prediction model
- scale space
- wavelet coefficients
- back propagation