1. THE HYPERSPECTRAL IMAGING APPROACH
Giuseppe Bonifazi
Workshop

2. ACTIONS C.1&C.2 - Process and product monitoring based on hyperspectral imaging
HyperSpectral Imaging (HSI) is an innovative technology developed in recent years that combines the advantages of spectroscopy and imaging techniques.
In the last years there was a strong increase in applications including off-line / on-line inspection at industrial scale in different sectors.
Image source:
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 2

3. ACTIONS C.1&C.2 - Process and product monitoring based on hyperspectral imaging
Spectral signature of a single pixel
All individual spatial and spectral images could be picked up from the hypercube and the spectrum of each pixel of the image in a specific position can be extracted
One spectral image of n pixels for all the investigated wavelengths (λ)
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 3

4. ACTIONS C.1&C.2 – The selected HSI devices
Hyperspectral Imaging Characterization
SISUChema XL™ Chemical Imaging Workstation
Operation mode:
push-broom
Spectral range:
SWIR: nm
Spectral sampling and (resolution)
6.3nm
Active pixel:
320 (spatial) x 240 (spectral) pixels
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

5. ACTIONS C.1&C.2 – The selected HSI devices
Hyperspectral Imaging Characterization
Hyperspectral architecture Specim ImSpectorTM V10
Hyperspectral architecture Specim ImSpectorTM N17E
Operation mode:
push-broom
Spectral range:
VIS-NIR: nm
Spectral sampling and (resolution)
5 nm
Active pixel:
320 (spatial) x 240 (spectral) pixels
Operation mode:
push-broom
Spectral range:
NIR: nm
Spectral sampling and (resolution)
5nm
Active pixel:
320 (spatial) x 240 (spectral) pixels
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

6. Actions C.1-C.2 - Sample Acquisition
ACTION C.1: HyperSpectral Imaging (HSI) Characterization
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

7. Actions C.1-C.2: Hyperspectral data processing
Spectral data have been analysed using the PLS_Toolbox 7. 0 (Eigenvector Research Inc.) running inside Matlab™ environment (version ).
Spectra preprocessing
PCA applied for data exploration
PLS applied for spectra correlation with curing time and different measured chemical parameters
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

8. Raw Hyperspectal images of a) IT-BC; b) IT-FOR and c) IT-UOW
Actions C.1&C.2 – Results on raw materials from the different countries (Action B.1)
CY-UOW Sample
IT-FOR Sample
Step 1: Waste raw materials collected from Italy, Spain and Cyprus were utilized to train the HSI system to correctly classify them.
Step 2: Hyperspectral images of different organic waste were elaborated using the 3 different HSI devices.
Step 3: Spectra preprocessing and PCA classification model were applied for the classification of different organic matrices.
1 cm
Applied pretreatment:
SNV
Mean Center b) a) c)
Raw Hyperspectal images of a) IT-BC; b) IT-FOR and c) IT-UOW
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

9. Raw materials: Italian samples Reflectance spectra (1000-1700 nm)
Actions C.1&C.2 – Results on raw materials from the different countries (Action B.1)
Raw materials: Italian samples Reflectance spectra ( nm)
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

10. Actions C.1&C.2 – Results on raw materials from the different countries (Action B.1)
Italian Raw Materials a) b) c) a) b) c)
Raw Hyperspectal images of a) IT-BC; b) IT-FOR and c) IT-UOW
Applied pretreatment:
SNV
Mean Center a) b) c)
a) IT-BC
c) IT-UOW
Pretreated Hyperspectal images of a) IT-BC; b) IT-FOR and c) IT-UOW
b) IT-FOR
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 10

11. Raw materials: FOR samples Reflectance spectra (1000-1700 nm)
Actions C.1&C.2 – Results on raw materials from the different countries (Action B.1)
Raw materials: FOR samples Reflectance spectra ( nm)
CY-FOR_V2
ES-FOR
IT-FOR
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

12. Actions C.1&C.2 – Results on raw materials from the different countries (Action B.1)
PCA score plots (PC1 vs. PC2) related to the different FOR samples coming from Italy, Spain and Cyprus acquired in the NIR ( nm) wavelength field.
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 12

13. Italian samples at different curing times
Actions C.1&C.2 – Results from lab-scale plants in the different countries (Action B.2)
Italian samples at different curing times
Average reflectance spectra of the different Italian samples acquired in the NIR ( nm) wavelength field
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

14. Italian samples at different curing times
Actions C.1&C.2 – Results from lab-scale plants in the different countries (Action B.2)
Italian samples at different curing times
PCA score plots (PC1 vs. PC2) related to the different Italian samples (IT-UFVB-5050-T0; IT-UFVB-5050-T20; IT-UFVB-5050-T40 and IT-UFVB-5050-T60) acquired in the NIR ( nm) wavelength field
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

15. Actions C.1&C.2 – Results from lab-scale plants in the different countries (Action B.2)
Process Monitoring by HSI
PLS for different curing times (Italian samples)
t = 60 days
t = 40 days
t = 20 days
t = 0 days
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 15

16. Actions C.1&C.2 – Results from lab-scale plants in the different countries (Action B.2)
Product Monitoring by HSI
Prediction of chemical parameters (Italian samples)
Humidity (%)
Phosphatase (µmol INTF g-1 h-1)
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 16

17. Actions C.1&C.2 – Results from lab-scale plants in the different countries (Action B.2)
Product Monitoring by HSI
Prediction of chemical parameters (Italian samples)
Soluble Organic Nitrogen (ppm)
Soluble Organic Carbon (%)
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 17

18. Product Monitoring by HSI
Actions C.1&C.2 – Results from pilot-scale plants in the different countries (Action B.3)
Product Monitoring by HSI
PCA (Spanish samples)
Source Sample
ES-UFVB-6040 T90
Sample Hypercube
PCA: background removal
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 18

19. Process Monitoring by HSI
Actions C.1&C.2 – Results from pilot-scale plants in the different countries (Action B.3)
Process Monitoring by HSI
Raw and preprocessed spectra at t = 0 and t = 90 days (Spanish samples)
Average raw spectra
Preprocessing applied: Smoothing (window 11)+ Second derivative (window 15)+ Mean center
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 19

20. Process Monitoring by HSI PCA and Loadings (Spanish samples)
Actions C.1&C.2 – Results from pilot-scale plants in the different countries (Action B.3)
Process Monitoring by HSI
PCA and Loadings (Spanish samples)
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 20

21. Actions C.1&C.2 – Results from pilot-scale plants in the different countries (Action B.3)
Product Monitoring by HSI
Prediction of chemical parameters: Soluble Organic Nitrogen (%)
Italian samples
Spanish samples
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 21

22. Actions C.1&C.2 – Results from pilot-scale plants in the different countries (Action B.3)
Product Monitoring by HSI
Prediction of chemical parameters: Soluble Organic Carbon (%)
Italian samples
Spanish samples
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 22

23. Actions C.1&C.2 – Results from pilot-scale plants in the different countries (Action B.3)
Product Monitoring by HSI
Prediction of chemical parameters: EC (mS/cm)
Italian samples
Spanish samples
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015 23

24. Product Monitoring by HSI
Actions C.3 – Results from agriculture application in Italy (Action B.4)
Product Monitoring by HSI
PCA (Italian samples)
- Barley
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

25. Process Monitoring by HSI Raw and preprocessed spectra
Actions C.3 – Results from agriculture application in Italy (Action B.4)
Process Monitoring by HSI
Raw and preprocessed spectra
Average raw spectra
Preprocessing applied: Smoothing (window 15)+ First derivative (window 15)+ Mean center
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

26. Actions C. 3 – Results from agriculture application in Italy (Action B
PCA score plots (PC1 vs. PC2) related to Barley samples acquired in the NIR ( nm) wavelength field.
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

27. Product Monitoring by HSI
Actions C.4 – Results from agriculture application in Spain (Action B.5)
Product Monitoring by HSI
PCA (Spanish samples)
- Potato
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

28. Process Monitoring by HSI Raw and preprocessed spectra
Actions C.4 – Results from agriculture application in Spain (Action B.5)
Process Monitoring by HSI
Raw and preprocessed spectra
Average raw spectra
Preprocessing applied: Smoothing (window 15)+ Second derivative (window 15)+ Mean center
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

29. Actions C. 4 – Results from agriculture application in Spain (Action B
PCA score plots (PC1 vs. PC2) related to Potato samples acquired in the NIR ( nm) wavelength field.
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

30. Product Monitoring by HSI
Actions C.5 – Results from agriculture application in Cyprus (Action B.6)
Product Monitoring by HSI
PCA (Cypriot samples)
- Melon
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

31. Process Monitoring by HSI Raw and preprocessed spectra
Actions C.5 – Results from agriculture application in Cyprus (Action B.6)
Process Monitoring by HSI
Raw and preprocessed spectra
Average raw spectra
Preprocessing applied: Smoothing (window 11)+ Second derivative (window 19)+ Mean center
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

32. Actions C.5 – Results from agriculture application in Cyprus (Action B.6)
PCA score plots (PC1 vs. PC2) related to Potato samples acquired in the NIR ( nm) wavelength field.
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

33. Conclusions Actions B.1&C.1-C.2
The HSI approach allowed to outline the difference existing among the investigated raw material samples both in terms of composition (i.e. UOW, FOR and BC) and origin (i.e.: Italy, Spain and Cyprus), with the only exception of Italian and Spanish BC.
Actions B.2&C.1-C.2
Good correlation between spectral behavior in the NIR wavelength range of the different collected samples from the lab-scale plants in the different countries and curing time and the main measured chemical parameters (humidity, soluble carbon, soluble nitrogen, and phosphatase) were obtained.
Actions B.3&C.1-C.2
Good correlation between spectral behavior in the NIR wavelength range of the different collected samples from the pilot-scale plants in the different countries and the main measured chemical parameters (soluble carbon, soluble nitrogen and electrical conductivity) were obtained.
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015

34. Conclusions Actions B.4&C.3
The HSI approach allowed to outline the difference crops existing from different thesis in the agriculture application in Italy.
Actions B.5&C.4
The HSI approach allowed to outline the difference crops existing from different thesis in the agriculture application in Spain.
Actions B.6&C.5
The HSI approach allowed to outline the difference crops existing from different thesis in the agriculture application in Cyprus.
RESAFE Project
Workshop
Faenza (Italy)
December 14, 2015