Broadband diffuse reflection spectroscopy and linear discriminant analysis enabling a non-destructive milk identification

Indy Magnus; Tarique Hasan; Hugo Thienpont; Lien Smeesters

doi:10.1117/12.3017601

20 June 2024 Broadband diffuse reflection spectroscopy and linear discriminant analysis enabling a non-destructive milk identification

Indy Magnus, Tarique Hasan, Hugo Thienpont, Lien Smeesters

Author Affiliations +

Proceedings Volume 12999, Optical Sensing and Detection VIII; 1299915 (2024) https://doi.org/10.1117/12.3017601
Event: SPIE Photonics Europe, 2024, Strasbourg, France

Abstract

Milk is one of the most important dietary products thanks to its high nutritional value and economic importance, but unfortunately also among the top products facing food fraud and adulteration. Authentication of milk is therefore of high importance, motivating the development of novel sensing techniques. We present the use of broadband diffuse reflection spectroscopy (400 – 1700 nm) in combination with Linear Discriminant Analysis (LDA) to achieve a rapid and nondestructive milk identification. Two case-studies are presented: (1) the differentiation between whole/high fat cow milk, semi-skimmed cow milk and skimmed cow milk, and (2) the differentiation between semi-skimmed regular cow milk and lactose-free milk. Considering a hold-out test set, classification performances exceeding 99.8% were achieved. Consequently, we believe these presented results contribute to an improved milk classification, enhancing food quality monitoring.

Conference Presentation

Citation Download Citation

Indy Magnus, Tarique Hasan, Hugo Thienpont, and Lien Smeesters "Broadband diffuse reflection spectroscopy and linear discriminant analysis enabling a non-destructive milk identification", Proc. SPIE 12999, Optical Sensing and Detection VIII, 1299915 (20 June 2024); https://doi.org/10.1117/12.3017601

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available