Improving prediction of total viable counts in pork based on hyperspectral scattering technique

Feifei Tao; Yankun Peng; Yulin Song; Hui Guo; Kuanglin Chao

doi:10.1117/12.923007

4 May 2012 Improving prediction of total viable counts in pork based on hyperspectral scattering technique

Feifei Tao, Yankun Peng, Yulin Song, Hui Guo, Kuanglin Chao

Proceedings Volume 8369, Sensing for Agriculture and Food Quality and Safety IV; 83690A (2012) https://doi.org/10.1117/12.923007
Event: SPIE Defense, Security, and Sensing, 2012, Baltimore, Maryland, United States

Abstract

A hyperspectral scattering technique was investigated for predicting the total viable counts (TVC) of pork in the article. Fresh pork was purchased from a local market and stored at 4°C for 1-15 days. Totally 35 samples were used in the experiment and 2-4 samples were taken out randomly each day for collecting hyperspectral images and reference microbiological tests. Gompertz function was applied to fit the scattering profiles of pork and Teflon, and the fitting results were pretty good in the spectral range of 470-1010 nm. Both individual parameters and integrated parameters were explored to develop the multi-linear regression models for predicting pork TVC, and the results indicated that individual Gompertz parameter α was superior to other individual parameters, while the integrated parameters can perform better. The best result for predicting pork TVC was achieved by the form of (α, β, ε), with the RCV of 0.963. The study demonstrated that hyperspectral scattering technique combined with Gompertz function was potential for rapid determination of pork TVC, and would be a valid tool for monitoring the quality and safety attributes of meat in the future.

Citation Download Citation

Feifei Tao, Yankun Peng, Yulin Song, Hui Guo, and Kuanglin Chao "Improving prediction of total viable counts in pork based on hyperspectral scattering technique", Proc. SPIE 8369, Sensing for Agriculture and Food Quality and Safety IV, 83690A (4 May 2012); https://doi.org/10.1117/12.923007

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