Prediction of beef palatability from colour,marbling and surface texture features of longissimus dorsi

The palatability of beef has been investigated with digital imaging systems on numerous previous occasions. In the current study, a novel approach was applied using high magnification imaging to develop surface texture features and an alternative colour space greyscale to express muscle surface texture. An automatic segmentation method was applied to develop colour and marbling features and best regression model subsets were selected automatically with genetic algorithms. Results indicated that accurate modelling of beef acceptability with regression models was possible with r² up to 0.95. Modelling of acceptability using high magnification images proved more successful than modelling with low magnification images. Linear models performed well compared to non-linear models. Other sensory measurements particularly TPA hardness were more difficult to model, although an accurate model of juiciness was developed. Addition of non-linear terms did not give large improvements except for juiciness.     

Prediction of beef eating quality from colour,marbling and wavelet texture features

Beef longissimus dorsi colour, marbling fat and surface texture are long established properties that are used in some countries by expert graders to classify beef carcasses, with subjective and inconsistent decision. As a computer vision system can deliver objective and consistent decisions rapidly and is capable of handling a greater variety of image features, attempts have been made to develop computerised predictions of eating quality based on these and other properties but have failed to adequately model the variation in eating quality. Therefore, in this study, examination of the ribeye at high magnification and consideration of a broad range of colour and marbling fat features was used to attempt to provide better information on beef eating quality. Wavelets were used to describe the image texture of the beef surface at high magnification rather than classical methods such as run lengths, difference histograms and co-occurrence matrices. Sensory panel and Instron analyses were performed on duplicate steaks to measure the quality of the beef. Using the classical statistical method of partial least squares regression (PLSR) it was possible to model a very high proportion of the variation in eating quality (r² = 0.88 for sensory overall acceptability and r² = 0.85 for 7-day WBS). Addition of non-linear texture terms to the models gave some improvements.     

Prediction of beef eating quality from colour, marbling and wavelet texture features

Beef longissimus dorsi colour, marbling fat and surface texture are long established properties that are used in some countries by expert graders to classify beef carcasses, with subjective and inconsistent decision. As a computer vision system can deliver objective and consistent decisions rapidly and is capable of handling a greater variety of image features, attempts have been made to develop computerised predictions of eating quality based on these and other properties but have failed to adequately model the variation in eating quality. Therefore, in this study, examination of the ribeye at high magnification and consideration of a broad range of colour and marbling fat features was used to attempt to provide better information on beef eating quality. Wavelets were used to describe the image texture of the beef surface at high magnification rather than classical methods such as run lengths, difference histograms and co-occurrence matrices. Sensory panel and Instron analyses were performed on duplicate steaks to measure the quality of the beef. Using the classical statistical method of partial least squares regression (PLSR) it was possible to model a very high proportion of the variation in eating quality (r² = 0.88 for sensory overall acceptability and r² = 0.85 for 7-day WBS). Addition of non-linear texture terms to the models gave some improvements.     

Comparison of various wavelet texture features to predict beef palatability

The wavelet transform can be used to characterise the surface texture of beef images in a more efficient manner than classical algorithms such as co-occurrence and run lengths. Features extracted from wavelet decompositions have been used to develop predictive models of important palatability attributes. A variety of common wavelet transforms were considered (biorthogonal, reverse biorthogonal, discrete Meyer, Daubechie, symmetric modified Daubechie and Coifman modified Daubechie) to search for the most useful texture features. A classic run length and co-occurrence algorithm was used for comparison. Using the same data analysis methods for each wavelet type, predictive models of beef acceptability, tenderness, juiciness, flavour and hardness were developed. Genetic algorithms succeeded in finding more accurate models than stepwise and manual elimination except for hardness. An accurate model of flavour (r² = 0.84) was computed. A good model of overall acceptability (r² = 0.79) was computed that fell just short of an important benchmark of accuracy. An encouraging model of juiciness (r² = 0.71) was computed showing that with additional palatability information juiciness might be accurately modelled. Tenderness proved difficult to model with only the classic model satisfying stability criteria and a poorer result (r² = 0.64) meaning substantial additional palatability information is required for accurate modelling. Hardness was particularly difficult to model. The biorthogonal wavelet produced the best model for three palatability measurements but the symmetric modified Daubechie wavelet produced the best model of overall acceptability and thus must be viewed as the most useful wavelet type.     

The relationship of physiological maturity and marbling judged according to Korean grading system to meat quality traits of Hanwoo beef females

Fifty seven carcasses from Hanwoo beef females were randomly selected by official meat graders and were sorted into three levels of maturity and marbling. Carcass data was collected for back fat thickness, longissimus area, carcass weight, meat colour, fat colour, marbling score, yield and quality grades. Mature carcasses had more yellow fat, coarser texture, a larger longissimus muscle area and lower quality grades and marbling scores (P<0.05). Carcasses with a higher marbling score had thicker fat and a higher quality grade. Carcasses with low marbling had a higher yield grade and a coarser texture (P<0.05). Higher marbling scores corresponded with lower cook and drip loss values for longissimus steaks. As the maturity of carcass was increased, the redness and lightness of meat and the yellowness of fat all tended to increase. Tenderness, flavour and overall acceptability scores for the older maturity group were lower than for younger and intermediate groups. Marbling was significantly (P<0.01) correlated with quality grade, crude fat content, cook and drip losses, and Warner-Bratzler shear force. The maturity level was also significantly (P<0.01) correlated with quality grade, fat colour, texture score, number of calves produced and milk teeth, meat redness and yellowness, fat yellowness, and Warner-Bratzler shear force. Results indicate that a low marbling group and older maturity group based on Korean grading system could negatively influence carcass traits and beef qualities of Hanwoo beef female.     

Correlation of consumer assessment of longissimus dorsi beef palatability with image colour,marbling and surface texture features

A new study was conducted to apply computer vision methods successfully developed using trained sensory panel palatability data to new samples with consumer panel palatability data. The computer vision methodology utilized the traditional approach of using beef muscle colour, marbling and surface texture as palatability indicators. These features were linked to corresponding consumer panel palatability data with the traditional approach of partial least squares regression (PLSR). Best subsets were selected by genetic algorithms. Results indicate that accurate modelling of likeability with regression models was possible (r² = 0.86). Modelling of other important palatability attributes proved encouraging (tenderness r² = 0.76, juiciness r² = 0.69, flavour r² = 0.78). Therefore, the current study provides a basis for further expanding computer vision methodology to correlate with consumer panel palatability data.     

Image texture features as indicators of beef tenderness

Image processing techniques were developed to predict cooked-beef tenderness from fresh-beef image characteristics. Cattle from different finishing treatments were processed in a commercial plant. Two short loin steaks were sampled from each carcass; one used for sensory evaluation and the other for imaging. The samples varied significantly in both US quality grades and sensory tenderness scores. Color, marbling and texture features were extracted from the beef images. Statistical and neural network analyses were performed to relate the image features to sensory tenderness scores. Image texture features were found to be useful indicators of beef tenderness. Partial least squares and neural network models were able to predict beef tenderness from color, marbling and image texture features to R(2)-values up to 0.70.     

Modeling of pre-treatment protocols for frozen pineapple slices

Optimization of pretreatments - blanching and additives was carried out for frozen pineapple slices using response surface methodology (RSM). The effect of pre-treatments viz. blanching medium (10-20° Brix sucrose solution), calcium chloride (1000-2000 ppm) and ascorbic acid (200-400 ppm) was studied on hardness (N), colour (L*), syneresis (%) and sensory attributes (colour, aroma, taste, overall acceptability) of the frozen slices after thawing. A Central Composite Rotatable Design (CCRD) was used with six experiments at the central point. The data obtained were analysed employing multiple regression technique to generate suitable mathematical models. Quadratic models were found to fit well (R², 96.72-99.99%) in describing the effect of variables on the responses studied. Optimization of the pretreatments was carried out by maximizing the hardness, L* and sensory responses while keeping the syneresis at minimum level. Compromised optimum values for blanching medium, calcium chloride and ascorbic acid levels were found to be 17° Brix, 1493 ppm and 300 ppm; respectively. The experimental and predicted values showed high correlation coefficients. The optimized pretreatment was found to be helpful in maintaining the quality of frozen pineapple slices in terms of texture, colour and syneresis.     

Effect of varying the gas headspace to meat ratio on the quality and shelf-life of beef steaks packaged in high oxygen modified atmosphere packs

Beef steaks (M. longissimus dorsi) were stored in modified atmosphere packs (MAP) (80% O₂:20% CO₂) with gas headspace to meat ratios of 2:1, 1:1 and 0.5:1 for 14 days at 4 °C. The pH, surface colour, texture and microbiology of beef steaks were unaffected (P > 0.05) by varying the gas headspace to meat ratio. APLSR (ANOVA-partial least squares regression) and jack-knife uncertainty testing indicated that lipid oxidation (TBARS) was significantly positively correlated with days 10 (P < 0.05) and 14 (P < 0.001) of storage. Chemical and sensory detection of lipid oxidation in beef steaks were in agreement on day 14 of storage. The sensory quality and acceptability of beef steaks were similar in gas headspace to meat ratios of 2:1 or 1:1 and unacceptable in 0.5:1. Results indicate that pack size and gas volume can be reduced without negatively affecting fresh beef quality and shelf-life.     

Automatic segmentation of beef longissimus dorsi muscle and marbling by an adaptable algorithm

An algorithm for automatic segmentation of beef longissimus dorsi (LD) muscle and marbling has been developed. The algorithm used simple thresholding to remove the background and then used clustering and thresholding with contrast enhancement via a customised greyscale to remove marbling. It was possible to attain lean muscle free of obvious marbling or background pixels where specular reflection could be effectively mitigated. Features of the automatically derived LD muscle and marbling images were compared to corresponding features of LD muscle and marbling images derived with a segmentation method requiring manual completion. Very strong correlations (up to r = 1) were found between the colour features of both sets of LD muscle images. Strong correlations (up to r = 0.96) were found between the features of both sets of marbling images. The automatic segmentation method has shown its good ability to approximate colour and marbling features. The algorithm has adaptable parameters and can be retailored to suit different image acquisition environments.     

Evaluation of transglutaminase and caseinate for a novel formulation of beef patties enriched in healthier lipid and dietary fiber

The food intake in developed countries is characterized by a deficient consumption of n-3 fatty acids and fiber. In this study, modified beef patties enriched with polyunsaturated n-3 fatty acids and fiber were developed. The texture profile was compared to traditional beef patties, showing lower values for all parameters except springiness. To improve its texture, pretreatments using transglutaminase (TG) and sodium caseinate (C) were assayed by response surface methodology. Mathematical models were obtained and used to determine the effect of TG, C, temperature and time of pretreatment on the texture of beef patties. The overall optimization indicated that a pretreatment with 0.1 U/g of TG at 40 °C for 17 min allowed to have a traditional texture for beef patties enriched in n-3 PUFAs and fiber. The models showed that the addition of caseinate was not needed. Minimal effects of pretreatment were observed on composition, color and cooking loss of the product.     

基于图像纹理特征的牛肉嫩度预测方法研究

在经过图像预处理,背最长肌与大理石花纹的分割,并实现大理石花纹特征值的提取后,利用灰度共生矩阵提取4个对嫩度剪切力贡献较大的纹理特征参数,并统计这些参数应用多元线性回归建立牛肉嫩度剪切力预测模型。结果表明：可见光下利用纹理特征预测牛肉嫩度的方法能够以96%的准确率实现嫩度剪切力等级的预测,具有较高的商用开发价值。     

Predicting beef tenderness using color and multispectral image texture features

The objective of this study was to investigate the usefulness of raw meat surface characteristics (texture) in predicting cooked beef tenderness. Color and multispectral texture features, including 4 different wavelengths and 217 image texture features, were extracted from 2 laboratory-based multispectral camera imaging systems. Steaks were segregated into tough and tender classification groups based on Warner-Bratzler shear force. The texture features were submitted to STEPWISE multiple regression and support vector machine (SVM) analyses to establish prediction models for beef tenderness. A subsample (80%) of tender or tough classified steaks were used to train models which were then validated on the remaining (20%) test steaks. For color images, the SVM model correctly identified tender steaks with 100% accurately while the STEPWISE equation identified 94.9% of the tender steaks correctly. For multispectral images, the SVM model predicted 91% and STEPWISE predicted 87% average accuracy of beef tender.     

Potential prediction of the microbial spoilage of beef using spatially resolved hyperspectral scattering profiles

Spoilage in beef is the result of decomposition and the formation of metabolites caused by the growth and enzymatic activity of microorganisms. There is still no technology for the rapid, accurate and non-destructive detection of bacterially spoiled or contaminated beef. In this study, hyperspectral imaging technique was exploited to measure biochemical changes within the fresh beef. Fresh beef rump steaks were purchased from a commercial plant, and left to spoil in refrigerator at 8 °C. Every 12 h, hyperspectral scattering profiles over the spectral region between 400 and 1100 nm were collected directly from the sample surface in reflection pattern in order to develop an optimal model for prediction of the beef spoilage, in parallel the total viable count (TVC) per gram of beef were obtained by classical microbiological plating methods. The spectral scattering profiles at individual wavelengths were fitted accurately by a two-parameter Lorentzian distribution function. TVC prediction models were developed, using multi-linear regression, on relating individual Lorentzian parameters and their combinations at different wavelengths to log₁₀(TVC) value. The best predictions were obtained with r² = 0.95 and SEP = 0.30 for log₁₀(TVC). The research demonstrated that hyperspectral imaging technique showed potential for real-time and non-destructive detection of bacterial spoilage in beef.     

Predicting beef tenderness using color and multispectral image texture features

The objective of this study was to investigate the usefulness of raw meat surface characteristics (texture) in predicting cooked beef tenderness. Color and multispectral texture features, including 4 different wavelengths and 217 image texture features, were extracted from 2 laboratory-based multispectral camera imaging systems. Steaks were segregated into tough and tender classification groups based on Warner–Bratzler shear force. The texture features were submitted to STEPWISE multiple regression and support vector machine (SVM) analyses to establish prediction models for beef tenderness. A subsample (80%) of tender or tough classified steaks were used to train models which were then validated on the remaining (20%) test steaks. For color images, the SVM model correctly identified tender steaks with 100% accurately while the STEPWISE equation identified 94.9% of the tender steaks correctly. For multispectral images, the SVM model predicted 91% and STEPWISE predicted 87% average accuracy of beef tender.     

EFFECTS OF PHYSIOLOGICAL MATURITY OF BEEF AND MARBLING OF RIB STEAKS ON EATING QUALITY

SUMMARY— Selected characteristics of beef rib steaks representing three physiological maturity levels and two marbling levels were investigated. Paired steaks at the 1lth thoracic vertebra were used to obtain cooking time and losses, palatability scores, Warner-Bratzter shear values, and selected histological data. In addition, steaks from the left 7th and right 8th thoracic vertebrae positions were used to measure cooking time and losses, Warner-Bratzfer shear values, waterholding capacity, pH, color-difference, and total moisture. Ether extract was obtained for raw longissimus dorsi at the 12th thoracic vertebra. Maturity and marbling affected told moisture (P < 0.001), quantity of fat in raw muscle (histological measurement, P < 0.01). ether extract (P < 0.001). and dripping losses (7th and 8th thoracic vertebrae P < 0.001). Other factors were not affected significantly. Maturity and marbling, at levels represented, had little effect on palatability of the steaks, although generally, measurements for fat content were higher and those for moisture lower at the higher marbling level. Most correlation coefficients for overall acceptability and histological measurements were low. Tenderness had more influence on the overall acceptability of the meat than flavor or juiciness. Moderate to high relationships occurred between cooking time and both initial weight of steaks and cooking losses. Generally, waterholding capacity was not related to pH, total moisture, or cooking losses. Correlation coefficients for pH vs. shear value and pH vs. color-difference were low.     

Effect of different Duroc line sires on carcass composition, meat quality and dry-cured ham acceptability

Carcasses of 399 malignant hyperthermia gene free pigs from crosses sired by three types of Duroc (Virgen de la Fuente, DU1; Diputación de Teruel, DU2; DanBred, DU3) were analyzed for carcass and meat quality. Carcass leanness and fat parameters were measured at the last rib and at the space between the 3rd and 4th last ribs counting from the last one. Weights, pH, electrical conductivity, colour and intramuscular fat were also measured. A sample of 133 legs per cross were processed by dry-curing. The ham portion including Biceps femoris, Semimembranosus and Semitendinosus muscles was evaluated for instrumental texture and colour, biochemical and sensory analyses and acceptability (trained panel and consumers). DU3 carcasses were well conformed but lean. DU1 carcasses had a lower conformation but higher marbling. DU2 carcasses were intermediate. Dry-cured hams from DU1-sired pigs had a higher overall acceptability, although fat content influenced a consumers group negatively. Leaner DU3 hams had the lowest acceptability.     

Eating quality of “Vitela Tradicional do Montado”-PGI veal and Mertolenga-PDO veal and beef

Physicochemical and sensory characteristics were measured in veal and beef from the Portuguese Mertolenga breed having 3 quality labels as follows: Mertolenga-PDO beef and veal which apply to purebred animals and “Vitela Tradicional do Montado”-PGI veal which applies to crossbred animals. Measurements were made in longissimus lumborum muscle aged for 6 days. The temperature 3 h post-mortem (T₃), cooking losses and Warner–Bratzler shear force (WBSF) reflected carcass weight (CW) differences between groups. The pigment content was influenced by age, with beef having higher values than veal. WBSF correlated negatively with intramuscular fat in Mertolenga-PDO beef, but not on veal. WBSF correlated positively with cooking losses and negatively with myofibrillar fragmentation index, tenderness, juiciness and overall acceptability. Cooking losses and juiciness were the main contributors for the tenderness differences. Vitela Tradicional do Montado-PGI and Mertolenga-PDO veal had lighter colour and were considered tender. The three meat types were well discriminated based on pH_u, a* and C* parameters by canonical discriminant analysis.     

Sensory evaluation of new lines of oca (Oxalis tuberosa) grown in New Zealand

Five new and one local cultivar of oca or New Zealand yam (Oxalis tuberosa) were evaluated by a consumer-type panel for appearance, flesh colour, flavour, texture and overall acceptability of raw, steamed and baked tubers. The intensity, ‘just right’ or liking scores were analysed using the proportional odds model. Skin and flesh colour of tubers were also measured objectively using a colorimeter. For raw oca, panellists preferred bright red tubers, but size was also important. Flesh colour, bitterness and mealiness were important variables which described the overall acceptability of steamed oca, while only flesh colour and bitterness were important variables for baked oca. Cultivars which had flesh colour described as ‘bright yellow’, flavour as ‘no bitter taste’, and a ‘very slightly mealy’ texture were more preferred. Cultivars with higher yellow/blue (b¹) and chroma (c¹) values for cooked tuber skin and flesh colours were more acceptable.     

Association of polymorphisms at DGAT1, leptin, SCD1, CAPN1 and CAST genes with color,marbling and water holding capacity in meat from beef cattle populations in Sweden

The objective of this study was to investigate the associations of single nucleotide polymorphisms (SNPs) at five candidate genes with meat pH, color, marbling and water holding capacity (WHC) in young bulls from five beef breeds (n = 243) in Sweden. The UASMS2 polymorphism at the leptin gene and the SNPs at the Stearoyl-CoA desaturase 1 gene (SCD1.878) and μ-calpain gene (CAPN1:c.947) were associated with variation in meat color traits after 6 days of exposure to air. The K232A polymorphism at the diacylglycerol O-acyltransferase 1 (DGAT1) gene and the CAPN1:c.947 SNP were associated with level of beef marbling. There was no association between the SNP at the calpastatin gene (CAST:c.155) and meat quality traits, nor was there any association of the tested SNPs with WHC traits and pH value.