An Image Recognition Algorithm for Defect Detection of Underground Pipelines Based on Convolutional Neural Network.
Xiaodong YanXiaogang SongPublished in: Traitement du Signal (2020)
Keyphrases
- recognition algorithm
- defect detection
- input image
- convolutional neural network
- image features
- multiscale
- single image
- image data
- image retrieval
- image segmentation
- image classification
- image matching
- low level
- hausdorff distance
- feature extraction
- region of interest
- feature points
- machine learning
- visual features
- neural network
- d objects
- high resolution