Physical and Statistical Models for Optical Imaging of Food Quality - - PowerPoint PPT Presentation

▶
physical and statistical models for optical imaging of
SMART_READER_LITE
LIVE PREVIEW

Physical and Statistical Models for Optical Imaging of Food Quality - - PowerPoint PPT Presentation

Nov 25, 2022 169 likes •395 views

Physical and Statistical Models for Optical Imaging of Food Quality National Food Institute Day 20 May 2016 Jeppe Revall Frisvad Associate Professor DTU Compute Why inspect food quality? Consumers expect Large diversity of food

slide-1
SLIDE 1

Physical and Statistical Models for Optical Imaging of Food Quality

National Food Institute Day

20 May 2016 Jeppe Revall Frisvad Associate Professor DTU Compute

slide-2
SLIDE 2

Why inspect food quality?

  • Consumers expect

– Large diversity of food products – Uniformly high quality – Fulfillment of both culinary and nutritional demands – Highest food safety standards

  • We need efficient quality assessment and

inline process control.

http://niemagazine.com/consumers-dictate-natural-sensory-qualities/

slide-3
SLIDE 3

Why optical imaging?

  • Food appearance carries information on

– Size, shape, and color (obviously) – Organoleptic parameters (flavor, taste) – Texture, stability, and mouthfeel – Moisture content and storability – Ingredients: amounts of constituents

  • Computer vision sensors enable noninvasive

inline monitoring of food appearance.

slide-4
SLIDE 4

Optical imaging methods

  • Multispectral imaging
  • Hyperspectral imaging

Transmission filters Controled illumination Pushbroom Acousto-Optic Tuneable Filter (AOTF) VidemeterLab Static Light Scattering (SLS) instrument

example example

slide-5
SLIDE 5

Optical imaging methods

  • Grating-based X-ray imaging
slide-6
SLIDE 6

Multispectral imaging

200 300 400 600 500 700 800 900 1000 near-infrared (NIR) ultraviolet (UV) nm

N images

  • btained at

N specific wavelengths

slide-7
SLIDE 7

Example: biscuit quality

  • a. Biscuit with water drop in the centre (sRGB)
  • b. Spectrally extracted water absorption map
  • c. Predicted %Moisture from 8 spectral image features

versus the %Moisture from evaporation device.

a. b. c.

slide-8
SLIDE 8

Example: biscuit quality

  • Normalized canonical discriminant

analysis for measuring

– browning index – glazing vs. non-glazing

bluish – conforming yellow/red – higher browning darker gray – glazing lighter gray – non-glazing

slide-9
SLIDE 9

Example: meat study with DMRI

Raw Cooked Meat samples Minolta colorimeter VideometerLab

slide-10
SLIDE 10

Example: meat study with DMRI

  • Both instruments discriminate between

raw and cooked meat.

  • Problems in using a colorimeter:

– Integrates over large surface patch (misses variations). – Light penetration depth too large (not good for bright red meat at early days of display). – No spectroscopy.

  • Computer vision systems

solve these problems.

colorimeter projector

slide-11
SLIDE 11

Example: Salami study with DuPont

  • Salami fermentation process after production.

Days: Days: 2 3 9 14 21 42 Segmentation

  • f background

and of meat from fat

slide-12
SLIDE 12

Example: Salami study with DuPont

  • Statistical meat color scale

– Darker blue is fresh meat – Yellow and orange represent fermented meat

Days: 2 42 Significant color difference between chilled and non-chilled.

slide-13
SLIDE 13

Hyperspectral imaging

lab setup in situ setup sample image

(log transformed, false colours) Milk (1.5% ), at 900 nm

slide-14
SLIDE 14

Example: milk fermentation

  • Spectroscopy for measuring scattering and

absorption properties.

reduced scattering [1/cm] absorption [1/cm] wavelength [nm] wavelength [nm]

extract profile spectroscopy infer optical properties yogurt milk

  • blique incidence

reflectometry

slide-15
SLIDE 15

Example: milk fermentation

Statistical profile analysis for estimating viscosity Physical model for particle sizing based on optical properties

slide-16
SLIDE 16

Grating-based X-ray imaging

  • When we need to investigate subsurface features.
  • Three contrast mechanisms are used in grating-based

imaging:

slide-17
SLIDE 17

Example: heated meat products

  • Evaluating heat induced changes of micro-

structure and cooking loss.

Meat emulsion Beef

Raw Boiled Lard Sunflower

  • il
slide-18
SLIDE 18

Example: detecting foreign objects

1 2 3 4 5 6 7 8 Absorption Phase contrast Dark field 1 2 3 4 5 6 7 8 Combined multimodal intensity and texture features give best detection results.

Normal food model Detection rates

slide-19
SLIDE 19

Conclusion

  • Optical imaging is very useful when moving toward

more and better automation in food quality control.

  • Choice of instrument is important:

– VideometerLab is good for detecting spectroscopic differences between different sample regions. – Static light scattering (SLS) is good for detecting emulsion differences in seemingly similar substances. – Grating-based X-ray imaging is good for detecting foreign objects or subsurface/volumetric features.

slide-20
SLIDE 20

Credits

  • Camilla Himmelstrup Trinderup (postdoc, DTU Compute)
  • Otto Højager Attermann Abildgaard (PhD, DTU Compute Alumnus)
  • Hildur Einarsdóttir (PhD student, DTU Compute)
  • Jens Michael Carstensen (Associate Professor, DTU Compute)
  • Line Harder Clemmensen (Associate Professor, DTU Compute)
  • Jacob Lercke Skytte (postdoc, DTU Food)
  • Sara Sharifzadeh (PhD, DTU Compute Alumna)
  • Knut Conradsen (Professor, DTU Compute)
  • Anders Bjorholm Dahl (Head of Image Section, DTU Compute)
  • Bjarne Ersbøll (Head of Statistics Section, DTU Compute)
  • Rasmus Larsen (Head of Department, DTU Compute)
  • Research projects: CIFQ and NEXIM
slide-21
SLIDE 21

Thank you for your attention

  • Computing milk appearance using light scattering

by fat and protein particles.

water vitamin B2 casein milk fat skimmed reduced fat whole constituents products