Jennifer Young

Prediction of pork color attributes using computer vision system.

Color image processing and regression methods were utilized to evaluate color score of pork center cut loin samples. One hundred loin samples of subjective color scores 1 to 5 (NPB, 2011; n=20 for each color score) were selected to determine correlation values between Minolta colorimeter measurements and image processing features. Eighteen image color features were extracted from three different RGB (red, green, blue) model, HSI (hue, saturation, intensity) and L*a*b* color spaces. When comparing Minolta colorimeter values with those obtained from image processing, correlations were significant (P<0.0001) for L* (0.91), a* (0.80), and b* (0.66). Two comparable regression models (linear and stepwise) were used to evaluate prediction results of pork color attributes. The proposed linear regression model had a coefficient of determination (R(2)) of 0.83 compared to the stepwise regression results (R(2)=0.70). These results indicate that computer vision methods have potential to be used as a tool in predicting pork color attributes.

Prediction of pork loin quality using online computer vision system and artificial intelligence model

The objective of this project was to develop a computer vision system (CVS) for objective measurement of pork loin under industry speed requirement. Color images of pork loin samples were acquired using a CVS. Subjective color and marbling scores were determined according to the National Pork Board standards by a trained evaluator. Instrument color measurement and crude fat percentage were used as control measurements. Image features (18 color features; 1 marbling feature; 88 texture features) were extracted from whole pork loin color images. Artificial intelligence prediction model (support vector machine) was established for pork color and marbling quality grades. The results showed that CVS with support vector machine modeling reached the highest prediction accuracy of 92.5% for measured pork color score and 75.0% for measured pork marbling score. This research shows that the proposed artificial intelligence prediction model with CVS can provide an effective tool for predicting color and marbling in the pork industry at online speeds.

Predicting pork loin intramuscular fat using computer vision system

The objective of this study was to investigate the ability of computer vision system to predict pork intramuscular fat percentage (IMF%). Center-cut loin samples (n = 85) were trimmed of subcutaneous fat and connective tissue. Images were acquired and pixels were segregated to estimate image IMF% and 18 image color features for each image. Subjective IMF% was determined by a trained grader. Ether extract IMF% was calculated using ether extract method. Image color features and image IMF% were used as predictors for stepwise regression and support vector machine models. Results showed that subjective IMF% had a correlation of 0.81 with ether extract IMF% while the image IMF% had a 0.66 correlation with ether extract IMF%. Accuracy rates for regression models were 0.63 for stepwise and 0.75 for support vector machine. Although subjective IMF% has shown to have better prediction, results from computer vision system demonstrates the potential of being used as a tool in predicting pork IMF% in the future.

Effect of lower-energy, higher-fiber diets on pigs divergently selected for residual feed intake when fed higher-energy, lower-fiber diets

Residual feed intake (RFI) is the difference between observed and predicted feed intake of an animal, based on growth and maintenance requirements. In Yorkshire pigs, divergent selection for increased (Low RFI) and decreased (High RFI) RFI was carried out over 10 generations (G) while feeding a corn- and soybean-meal-based, higher-energy, lower-fiber (HELF) diet. In G8 to G10, representing 4 replicates, barrows and gilts (n = 649) of the RFI lines were fed the HELF diet and a diet incorporating coproducts that were lower in energy and higher in dietary fiber (LEHF). The diets differed in ME, 3.32 vs. 2.87 Mcal/kg, and in neutral detergent fiber (NDF), 9.4% vs. 25.9%, respectively. The impact of the LEHF diet on 1) performance and growth, 2) diet digestibility, 3) genetic parameter estimates, and 4) responses to selection for RFI, when fed the HELF, was assessed. In general, the LEHF diet reduced the performance of both lines. When fed the HELF diet, the Low RFI pigs had lower (P < 0.05) ADFI (-12%), energy intake (-12%), ADG (-6%), and backfat depth (-12%); similar (P > 0.05) loin muscle area (LMA; +5%); and greater (P < 0.05) feed efficiency (i.e., 8% higher G:F and 7% lower RFI) than the High RFI line. These patterns of line differences were still present under the LEHF diet but differences for ADFI (-11%), energy intake (-10%), G:F (+2%), and RFI (-6%) were reduced compared to the HELF diet. Apparent total tract digestibility (ATTD) of the HELF and LEHF diets was assessed using 116 barrows and gilts from G8. When fed the HELF diet, ATTD of DM, GE, N, and NDF were similar between lines (P ≥ 0.27), but when fed the LEHF diet, the Low RFI pigs had greater digestibility (7%, 7%, 10%, and 32%) than the High RFI line (P ≤ 0.04). To measure responses to selection for RFI and estimate genetic parameters, data from all 10 generations were used (HELF; n = 2,310; LEHF, n = 317). Heritability estimates of performance traits ranged from 0.19 to 0.63, and genetic correlations of traits between diets were high and positive, ranging from 0.87 (RFI) to 0.99 (LMA). By G10, RFI in the Low RFI line was 3.86 and 1.50 genetic SD lower than in the High RFI line when fed the HELF and LEHF diets, respectively. Taken together, the results of this study demonstrate that responses to selection for RFI when fed a HELF diet are not fully realized when pigs are fed an extremely LEHF diet. Thus, feeding diets that differ from those used for selection may not maximize genetic potential for feed efficiency.

Genomewide association analysis of sow lactation performance traits in lines of Yorkshire pigs divergently selected for residual feed intake during grow–finish phase

Lactation is an economically and biologically important phase in the life cycle of sows. Short generation intervals in nucleus herds and low heritability of traits associated with lactation along with challenges associated with collecting accurate lactation performance phenotypes emphasize the importance of using genomic tools to examine the underlying genetics of these traits. We report the first genomewide association study (GWAS) on traits associated with lactation and efficiency in 2 lines of Yorkshire pigs that were divergently selected for residual feed intake during grow-finish phase. A total of 862 farrowing records from 2 parities were analyzed using a Bayesian whole genome variable selection model (Bayes B) to locate 1-Mb regions that were most strongly associated with each trait. The GWAS was conducted separately for parity 1 and 2 records. Marker-based heritabilities ranged from 0.03 to 0.39 for parity 1 traits and from 0.06 to 0.40 for parity 2 traits. For all traits studied, around 90% of genetic variance came from a large number of genomic regions with small effects, whereas genomic regions with large effects were found to be different for the same trait measured in parity 1 and 2. The highest percentage of genetic variance explained by a 1-Mb window for each trait ranged from 0.4% for feed intake during lactation to 4.2% for back fat measured at farrowing in parity 1 sows and from 0.2% for lactation feed intake to 5.4% for protein mass loss during lactation in parity 2 sows. A total of thirteen 1-Mb nonoverlapping windows were found to explain more than 1.5% of genetic variance for either a single trait or across multiple traits. These 1-Mb windows were on chromosomes 2, 3, 6, 7, 8, 11, 14, 15, 17, and 18. The major positional candidate genes within 1 Mb upstream and downstream of these windows were , (SSC2), (SSC6) (SSC7), (SSC8), (SSC11), (SSC14), (SSC17). Further validation studies on larger populations are required to validate these findings and to improve our understanding of the biology and complex genetic architecture of traits associated with sow lactation performance.

Effect of Season, Transport Length, Deck Location, and Lairage Length on Pork Quality and Blood Cortisol Concentrations of Market Hogs.

Simple Summary Transport of hogs is a routine practice in the swine industry. Loading pigs onto the trailer, transporting them to the plant, and having them wait in an unfamiliar pen at the plant prior to slaughter are all stressful to the pigs. Seasonal changes in temperatures can also affect the amount of stress a hog is subjected to during transport to market. Therefore, the objective of this study was to investigate the effect of transportation and lairage conditions on stress, evaluated by measuring serum cortisol concentrations, and the effect on pork quality. Abstract The objective of this study was to investigate the effects of seasonal environment, transport conditions, and time in lairage on pork quality and serum cortisol concentrations. Market hogs were slaughtered during winter (n = 535), spring (n = 645), summer (n = 644), and fall (n = 488). Within season, hogs were randomly assigned to treatments in a 2 × 2 × 2 factorial arrangement, with 2 deck locations (top vs. bottom) and 2 transport and lairage durations (3 h vs. 6 h). Blood samples were collected at exsanguination for analysis of cortisol concentration. Loins were collected at 24 h postmortem for pork quality assessment. Season and deck did not have a main effect on cortisol concentrations or pork quality. Hogs transported 6 h had increased cortisol concentrations (103.0 vs. 95.5 ng/mL; P < 0.001) and decreased L* (52.49 vs. 52.69; P = 0.09), b* (6.28 vs. 6.36; P = 0.03), and hue angle (20.70 vs. 20.95; P = 0.03) compared to hogs transported 3 h. Hogs subjected to 6 h of lairage had increased 24-h pH (5.69 vs. 5.66; P = 0.005), a* (16.64 vs. 16.48; P < 0.0001), b* (6.42 vs. 6.22; P < 0.0001), saturation (17.85 vs. 17.64; P < 0.0001), and hue angle (21.01 vs. 20.65; P = 0.002) and decreased L* (52.49 vs. 52.69; P = 0.07) when compared to hogs subjected to 3 h of lairage.