Wood Defect Detection Based on Depth Extreme Learning Machine
| Autor: | Xiaolin Zhou, Ding Fenglong, Yutu Yang, Zhongkang Hu, Ying Liu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION detection Image processing 02 engineering and technology lcsh:Technology 01 natural sciences Convolutional neural network lcsh:Chemistry genetic algorithm 0202 electrical engineering electronic engineering information engineering General Materials Science Cluster analysis lcsh:QH301-705.5 Instrumentation Extreme learning machine Fluid Flow and Transfer Processes Artificial neural network lcsh:T business.industry Process Chemistry and Technology Deep learning 010401 analytical chemistry General Engineering Pattern recognition lcsh:QC1-999 0104 chemical sciences Computer Science Applications wood defect lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 Feature (computer vision) ELM 020201 artificial intelligence & image processing Artificial intelligence lcsh:Engineering (General). Civil engineering (General) business CNN lcsh:Physics |
| Zdroj: | Applied Sciences, Vol 10, Iss 7488, p 7488 (2020) Applied Sciences Volume 10 Issue 21 |
| ISSN: | 2076-3417 |
| Popis: | The deep learning feature extraction method and extreme learning machine (ELM) classification method are combined to establish a depth extreme learning machine model for wood image defect detection. The convolution neural network (CNN) algorithm alone tends to provide inaccurate defect locations, incomplete defect contour and boundary information, and inaccurate recognition of defect types. The nonsubsampled shearlet transform (NSST) is used here to preprocess the wood images, which reduces the complexity and computation of the image processing. CNN is then applied to manage the deep algorithm design of the wood images. The simple linear iterative clustering algorithm is used to improve the initial model the obtained image features are used as ELM classification inputs. ELM has faster training speed and stronger generalization ability than other similar neural networks, but the random selection of input weights and thresholds degrades the classification accuracy. A genetic algorithm is used here to optimize the initial parameters of the ELM to stabilize the network classification performance. The depth extreme learning machine can extract high-level abstract information from the data, does not require iterative adjustment of the network weights, has high calculation efficiency, and allows CNN to effectively extract the wood defect contour. The distributed input data feature is automatically expressed in layer form by deep learning pre-training. The wood defect recognition accuracy reached 96.72% in a test time of only 187 ms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|