AUT LibraryAUT
View Item 
  •   Open Research
  • AUT Faculties
  • Faculty of Design and Creative Technologies (Te Ara Auaha)
  • School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau
  • View Item
  •   Open Research
  • AUT Faculties
  • Faculty of Design and Creative Technologies (Te Ara Auaha)
  • School of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, Pāngarau
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Hyper-spectral imaging for the discrimination of milk powder

Munir, MT; Young, BR; Wilson, DI
Thumbnail
View/Open
Munir _3135283.pdf (1.149Mb)
Permanent link
http://hdl.handle.net/10292/9093
Metadata
Show full metadata
Abstract
Hyper-spectral imaging (HSI) is an emerging, hybrid process analytical technology,

combining imaging and spectroscopic techniques for food quality monitoring and assessment. While

this technique has recently proved popular for food quality assessment in the fruit and seafood

industries, there are only a few reported applications of HSI in the dairy industry. The interest in HSI is

due to its ability to process a considerable amount of spectral data over a spatial dimension. In this

work we analysed three plants all making a specific valuable milk powder. However the milk powder

produced by each plant is different and each plant has different key equipment types such as the

dryer. It is hypothesised that there is a causal relationship here. In this paper, the potential application

of HSI to discriminate between the milk powders produced at the three different plants is presented,

specifically with respect to the prediction and monitoring of functional properties such as dispersibility

and solubility. Principal component analysis (PCA) was applied on hyper-spectral data extracted from

milk powder samples from the three plants. The results showed that the major discrimination between

milk powders produced by the different factories occur in principal components (PC) 2 and 3, and not

in the first PC as this component correlates to milk powder morphology. Furthermore, the potential of

the HSI technique to classify the powder as either on or off-spec at close to real time speeds is

explored. The current limitations of this process analytical technique and potential future

developments involving HSI in the dairy industry are also discussed.
Keywords
Hyper-spectral imaging; Milk powder; Principal component analysis
Date
September 27, 2015
Source
Asian Pacific Confederation of Chemical Engineering held at Melbourne Convention and Exhibition Centre (MCEC), Victoria, Australia, Melbourne, Australia, 2015-09-27 to 2015-10-01, published in: APCChE 2015 Congress
Item Type
Conference Contribution
Publisher
Asia Pacific Confederation of Chemical Engineering (APCChe)
Publisher's Version
http://www.apcche2015.org/
Rights Statement
NOTICE: this is the author’s version of a work that was accepted for publication. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in (see Citation). The original publication is available at (see Publisher's Version).

Contact Us
  • Admin

Hosted by Tuwhera, an initiative of the Auckland University of Technology Library

 

 

Browse

Open ResearchTitlesAuthorsDateSchool of Engineering, Computer and Mathematical Sciences - Te Kura Mātai Pūhanga, Rorohiko, PāngarauTitlesAuthorsDate

Alternative metrics

 

Statistics

For this itemFor all Open Research

Share

 
Follow @AUT_SC

Contact Us
  • Admin

Hosted by Tuwhera, an initiative of the Auckland University of Technology Library