A prototype on-line AOTF hyperspectral image acquisition system for tenderness assessment of beef carcasses. (June 2015)

• Record Type: Journal Article
• Authors: Konda Naganathan, Govindarajan; Cluff, Kim; Samal, Ashok; Calkins, Chris R.; Jones, David D.; Lorenzen, Carol L.; Subbiah, Jeyamkondan
• Is Part Of: Journal of food engineering. Volume 154(2015:Jun.)
• Page Start: 1
• Page End: 9
• Publication Date: 2015-06
• Subjects: Beef grading -- Acousto-optic tunable filter -- Discriminant model -- Textural features -- Feature selection -- Principal component analysis; Food industry and trade -- Periodicals; Food -- Analysis -- Periodicals; Aliments -- Industrie et commerce -- Périodiques; Aliments -- Analyse -- Périodiques; Aliments -- Recherche -- Périodiques; 664.005
• DOI: 10.1016/j.jfoodeng.2014.12.015
• Languages: English
• ISSNs: 0260-8774

Abstract

Highlights: The prototype on-line AOTF hyperspectral system acquired beef hyperspectral images on-line. On an average, hyperspectral beef image acquisition time was four seconds. Images acquired at 2-day postmortem predicted the 14-day tenderness with 87.8% accuracy in a third-party true validation. The prospect of converting this prototype on-line system to a commercial real-time system is high. Successful implementation of this technology will add value to beef products. Abstract: A prototype on-line acousto-optic tunable filter (AOTF)-based hyperspectral image acquisition system ( λ = 450–900 nm) was developed for tenderness assessment of beef carcasses. Hyperspectral images of ribeye muscle on stationary hanging beef carcasses ( n = 338) at 2-day postmortem were acquired in commercial beef slaughter or packing plants. After image acquisition, a strip steak was cut from each carcass, vacuum packaged, aged for 14 days, cooked, and slice shear force tenderness scores were collected by an independent lab. Beef hyperspectral images were mosaicked together and principal component (PC) analysis was conducted to reduce the spectral dimension. Six different textural feature sets were extracted from the PC images and used in Fisher's linear discriminant model to classify beef samples into two tenderness categories: tender and tough. The pooled feature model performed better than the other models with a tender certification accuracy of 92.9% and 87.8% in cross-validation and third-party true validation, respectively. Two additional metrics namely overall accuracy and a custom defined metric called accuracy index, were used to compare the tenderness prediction models.