Figures index

From

Diagnostics of Product Defects by Clustering and Machine Learning Classification Algorithm

Kamil Židek, Vladislav Maxim

Journal of Automation and Control. 2015, 3(3), 96-100 doi:10.12691/automation-3-3-11
  • Figure 1. Dataset suitable for DBSCAN algorithm
  • Figure 2. Example of multi-layer perceptron for classification
  • Figure 3. Extraction of parameters to partially dependent layers
  • Figure 4. Principle algorithm of errors recognition
  • Figure 5. Classification of errors by teaching and prediction
  • Figure 6. Experimental vision and image processing stand
  • Figure 7. GUI for error parameter extraction by image processing
  • Figure 8. Samples used for experiments.
  • Figure 9. Picture from left: Clear data, Kmeans, DBSCAN
  • Figure 10. Teaching and prediction reliability for 1000 samples