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.

An Automated Determination System for Beef Quality Evaluation using VIS/NIR Spectroscopy and Imaging Technology

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

Citation:  2011 Louisville, Kentucky, August 7-10, 2011  1110763.(doi:10.13031/2013.37299)
Authors:   Xiaoyu Tian, Yang Xu, Yongyu Li, Yankun Peng, Xiuying Tang
Keywords:   Beef tenderness, Reflectance spectrum, Image processing, MLR

Tenderness is an important parameter for beef quality judgment. Our objective was to establish an VIS/NIR system spectroscopy and imaging technology for detection of fresh beef tenderness. A CCD Industrial camera was placed in front of optical fiber probe, controlled to taking image and monitoring walking position of target by photoelectric sensor to ensure system got enough effective information, and then the optical fiber probe was used to carry out the reflectance values of steaks. After measuring tenderness reference value by Warner Bratzler Shear Force (WBSF), multi-linear regression (MLR) analysis was used to establish prediction models for tenderness. Nine wavelengths with higher correlation coefficients (r) were selected as feature wavebands for predicting the WBSF of steaks. And then MLR models based on these optimal wavelengths was able to predict WBSF with r = 0.80 and RMSEv=4.27, which indicated that the prediction model was acceptable. The result showed that the prediction model with feature wavebands had good accuracy and stability. This research mainly integrated imaging and VIS/NIR spectroscopy, which accomplished the beef steak information acquisition, real-time processing and detection.

(Download PDF)    (Export to EndNotes)