Principal Component Regression of Near?infrared Reflectance Spectra for Beef Tenderness Prediction

Park, B.; Chen, Y. R.; Hruschka, W. R.; Shackelford, S. D.; Koohmaraie, M.

doi:10.13031/2013.6087

Cited by 60 publications

(32 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, the wavelengths from 1400 to 1625 nm were less useful than the wavelengths from 1000 to 1400 nm in discriminating beef tenderness variations. These findings were in agreement with the results reported by Hildrum et al [26] and Park et al [44] on modeling NIR spectra for beef tenderness prediction. Also, the reflectance values of the steaks were less than 3% beyond 1400 nm due to water absorption (Fig.…”

Section: Discussionsupporting

confidence: 93%

See 1 more Smart Citation

Partial least squares analysis of near-infrared hyperspectral images for beef tenderness prediction

Naganathan

Grimes

Subbiah

et al. 2008

Sens. & Instrumen. Food Qual.

View full text Add to dashboard Cite

Tenderness is a primary determinant of consumer satisfaction of beef steaks. The objective of this study was to implement and test near-infrared (NIR) hyperspectral imaging to forecast 14-day aged, cooked beef tenderness from the hyperspectral images of fresh ribeye steaks (n = 319) acquired at 3-5 day post-mortem. A pushbroom hyperspectral imaging system (wavelength range: 900-1700 nm) with a diffuse-flood lighting system was developed. After imaging, steaks were vacuum-packaged and aged until 14 days postmortem. After aging, the samples were cooked and slice shear force (SSF) values were collected as a tenderness reference. After reflectance calibration, a Region-of-Interest (ROI) of 150 9 300 pixels at the center of longissimus muscle was selected. Partial least squares regression (PLSR) was carried out on each ROI image to reduce the dimension along the spectral axis. Gray-level textural co-occurrence matrix analysis with two quantization levels (64 and 256) was conducted on the PLSR bands to extract second-order statistical textural features. These features were then used in a canonical discriminant model to predict three beef tenderness categories, namely tender (SSF B 205.80 N), intermediate (205.80 N \ SSF \ 254.80 N), and tough (SSF C 254.80 N). The model with a quantization level of 256 performed better than the one with a quantization level of 64. This model correctly classified 242 out of 314 samples with an overall accuracy of 77.0%. Fat, protein, and water absorption bands were identified between 900 and 1700 nm. Our results show that NIR hyperspectral imaging holds promise as an instrument for forecasting beef tenderness.

show abstract

Section: Discussionsupporting

confidence: 93%

“…VIA systems were used to relate image textural features to beef muscle structure [24,43], while near-infrared spectroscopic systems were used to relate spectral reflectance measurements to chemical composition of beef [26,44]. In this study, hyperspectral imaging was implemented for beef tenderness prediction.…”

Section: Introductionmentioning

confidence: 99%

Partial least squares analysis of near-infrared hyperspectral images for beef tenderness prediction

Naganathan

Grimes

Subbiah

et al. 2008

Sens. & Instrumen. Food Qual.

View full text Add to dashboard Cite

show abstract

“…The best results were achieved in predicting the tenderness of beef. Park et al applied PCR on NIR reflectance spectra of beef to predict its tenderness [172]. It was found that tough meat has an overall higher absorption than tender meat at all wavelengths.…”

Section: Grain Quality Inspectionmentioning

confidence: 99%

Near-infrared spectroscopy and imaging in food quality and safety

Wang

Paliwal

2007

Sens. & Instrumen. Food Qual.

143

View full text Add to dashboard Cite

Over the last two decades, near-infrared spectroscopy (NIRS) has established itself as a non-destructive analytical technique in a variety of disciplines. However, recent technological advancements in hardware design and data mining techniques have unleashed the potential of NIRS to become a tool of choice for routine analyses of agricultural products. The current paper synthesizes the status of NIRS in the agri-food industry in terms of hardware and software development as well as the direction in which the NIRS research is headed. An extensive review of literature reveals that the emphasis on hardware development is focused on developing compact, robust, and portable spectrometers and hyperspectral imaging (HSI) systems. The software development on the other hand is geared towards developing better preprocessing, analyses, and modeling techniques using chemometrics, support vector machines, and artificial neural networks. The four main agri-food sectors identified to be the beneficiaries of this research revolution are grain quality monitoring; postharvest handling of fruits and vegetables; identification of contaminants in animal produce and feed; and food safety and authenticity. Apart from discussing the aforementioned topics, the paper also provides food scientists some working knowledge on parameters crucial to the performance of spectral and imaging systems. It is expected that further development of NIRS will help agricultural and food scientists to enhance the quality and safety of our food.

show abstract

“…Mitsumoto et al (1991) pioneered the use of spectroscopy for beef tenderness prediction and obtained an accuracy of 68% in predicting tenderness. Subsequently several additional studies reported moderate to promising results in predicting beef tenderness (Hildrum et al, 1994(Hildrum et al, , 1995Rødbotten et al, 2001;Park et al, 1998;Jeyamkondan and Kranzler, 2003;Liu et al, 2003). However, contradictory results have been reported in the literature regarding the use of spectroscopy for beef tenderness prediction.…”

Section: Introductionmentioning

confidence: 99%

“…VIA systems were used to relate image textural features to beef muscle structure (Zheng et al, 2006;Du and Sun, 2006), while spectroscopic systems were used to relate spectral reflectance measurements to chemical composition of beef (Park et al, 2001;Hildrum et al, 1994). VIA and spectroscopy are two promising nondestructive methods, but have achieved only limited success for predicting beef tenderness.…”

Section: Introductionmentioning

confidence: 99%