Using hyperspectral imaging to identify and classify large microplastic contamination in industrial composting processes

HIGHLIGHTS

• What: The sensitivity, specificity, F1 score and overall accuracy of the classification models were calculated to assess and compare the performance of each model . The authors focused on various parameters the authors could measure using image processing techniques: darkness, size, color, and contamination level. The experiments have shown that PLS-DA model can accurately detect a wide range of conventional (non-compostable) plastics that are typically found to contaminate compost during IC processing including PET, PP, and PE. The authors compared three different spectral pre-processing methods (SNV + MC, SG + MC, and SG + SNV + MC) to improve . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.