American Society of Agricultural and Biological Engineers



Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Spoilage Detection of Chilled Meat during Shelf Life by using Hyperspectral Imaging Technique

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  Paper number  131587037,  2013 Kansas City, Missouri, July 21 - July 24, 2013. (doi: http://dx.doi.org/10.13031/aim.20131587037) @2013
Authors:   Leilei Zhang, Yankun Peng, Sagar Dhakal, Feifei Tao, Yulin Song, Songwei Zhao
Keywords:   Chilled Meat TVC Pseudomonas Hyperspectral Imaging Technique Shelf Life Non-invasive

Abstract. Safety quality of pork meat is desired by costumers, who require freshness of meat to be maintained during shelf life in storage. Among different reasons, microorganisms are the most common cause for the spoilage of chilled pork during shelf life. Pseudomonas is one of the dominant bacteria species which multiplies during storage at 4 oC. The research was focused to develop optical technology based on hyperspectral imaging technology to detect spoilage of chilled pork meat rapidly and non-invasively. Fifty four pork meat samples were bought from local market, vacuum packed and stored in refrigerator at 4 oC. Hyperspectral scattering image in the range of 400nm to 1100nm were collected from 3 different samples on each day. After the collection of hyperspectral data, the microbiological characteristics such as Total Viable Counts (TVC) and Pseudomonas spp. were determined by standard method as reference value. The scattering profiles were fitted by four-parameter Gompertz function.Based on the hyperspectral data and reference value, prediction model was developed using support vector machines (SVM) regression. Moreover, a single prediction model for pork shelf life was established by a combination of TVC and growth of Pseudomonas spp. The model thus develop yielded regression coefficient of 0.93 for pork spoilage. The result obtained in the research demonstrates that the hyperspectral technology is precise and reliable method for rapid, non-invasive, real time detection of chilled pork quality during its shelf life.

(Download PDF)    (Export to EndNotes)