Automated body condition scoring of dairy cows using 3-dimensional feature extraction from multiple body regions

Machine vision technology has been used in automated body condition score (BCS) classification of dairy cows. The current vision-based classifications use information acquired from a limited number of body regions of the cow. Our study aimed to improve automated BCS classification by including multiple body condition–related features extracted from 3 viewpoints in 8 body regions. The data set of this study included 44 lactating cows with their BCS evenly distributed over the scale of BCS from 1.5 to 4.5 units. The body images of these cows were recorded over 2 consecutive days using 3-dimensional cameras positioned to view the cow from the top, right side, and rear. Each image was automatically processed to identify anatomical landmarks on the body surface. Around these anatomical landmarks, the bony prominences and body surface depressions were quantified to describe 8 body condition–related features. A manual BCS of each cow was independently assigned by 2 trained assessors using the same predefined protocol. With the extracted features as inputs and manual BCS as the reference, we built a nearest-neighbor classification model to classify BCS and obtained an overall classification sensitivity of 0.72 using a 10-fold cross-validation. We conclude that the sensitivity of automated BCS classification has been improved by expanding the selection of body condition–related features extracted from multiple body regions.     

Potential for estimation of body condition scores in dairy cattle from digital images

Body condition scoring, an indirect measure of the level of subcutaneous fat in dairy cattle, has been widely adopted for research and field assessment or for management purposes on farms. The feasibility of utilizing digital images to determine body condition score (BCS) was assessed for lactating dairy cows at the Scottish Agricultural College Crichton Royal Farm. Two measures of BCS were obtained by using the primary systems utilized in the United Kingdom (UK-BCS) and the United States (USBCS). Means were 2.12 (±0.35) and 2.89 (±0.40), modes were 2.25 and 2.75, and ranges were 1.0 to 3.5 and 1.5 to 4.5 for the UKBCS (n = 2,346) and USBCS (n = 2,571), respectively. Up to 23 anatomical points were manually identified on images captured automatically as cows passed through a weigh station. Points around the hooks were easier to identify on images than points around pins and the tailhead. All identifiable points were used to define and formulate measures describing the cow's contour. For both BCS systems, hook angle, posterior hook angle, and tailhead depression were significant predictors of BCS. When the full data set testing only the angles around the hooks was used, 100% of predicted BCS were within 0.50 points of actual USBCS and 92.79% were within 0.25 points; and 99.87% of predicted BCS were within 0.50 points of actual UKBCS and 89.95% were within 0.25 points. In a reduced data set considering only observations in which the tailhead depression angle was available, adding the tailhead depression to models did not improve model predictions. The relationships of the calculated angles with USBCS were stronger than those with UKBCS. This research demonstrates the potential for using digital images for assessing BCS. Future efforts should explore ways to automate this process by using a larger number of animals to predict scores accurately for cows across all levels of body condition.     

Association between body condition genomic values and feed intake,milk production,and body weight in French Holstein cows

Body condition score (BCS) offers a good estimate of the amount of stored fat on the body, and its variations can be used as a proxy for energy balance. Many countries have implemented a genomic evaluation of BCS, including France, where estimated breeding values are based on an individual BCS determination during the first lactation. In this article, we investigate the degree to which this genomic estimated breeding value based on a single phenotype record per cow might reflect different profiles of body reserves throughout lactation and be used to predict, and perhaps limit, their mobilization during early lactation. We also investigate whether selection on BCS affects other traits. A data set including 686 lactations of 435 Holstein cows from 3 experimental farms not used in the reference population for genomic evaluation was used to estimate the effects of the BCS direct genomic value (iBCS) on BCS, body weight, feed intake, milk production, and fat and protein contents throughout the lactation period. For each trait, the model included different iBCS regressions and an effect of the direct genomic value of the trait itself when available. It thus appeared that cows with a positive iBCS always had a higher BCS than negative iBCS cows, whatever the lactation stage, and that this difference increased during the first 6 mo to reach a difference of 0.8 point. A similar effect was seen regarding body weight, but it was the opposite for milk production, with negative iBCS cows producing slightly more milk (difference of about 3% over lactation). Feed intake increased slightly faster at the beginning of lactation for cows with positive iBCS. Therefore, iBCS is a promising tool that could help to limit intense mobilization during early lactation. Should feed efficiency be included in the breeding goal, greater attention should be paid to BCS to avoid further body mobilization in early lactation.     

Genetics of body condition score in New Zealand dairy cows

Body condition score (BCS) data were collected on 169,661 first-parity cows from herds participating in progeny testing schemes and linear type assessment. Genetic and residual variances for BCS estimated across time using a quadratic random regression model were found to be largest at the start of lactation. Heritability estimates ranged from 0.32 to 0.23 from d 1 to 200 of lactation, with a mean of 0.26. Genetic correlations between BCS and other traits were estimated using 2 approaches: 1) a multivariate analysis that included BCS and live weight, both adjusted for stage of lactation; 270-d cumulative yields of milk, fat, and protein; average somatic cell score; and 2 measures of fertility; and 2) a bivariate random regression analysis in which BCS was considered to be a longitudinal trait across time, with the same measurements as in approach 1 for all other traits. Genetic correlations of BCS with the 2 fertility traits were 0.43 and 0.50 using the multivariate analysis; the corresponding random regression estimates between BCS as a longitudinal trait across time and 2 measures of fertility were 0.35 to 0.44 and 0.40 to 0.49, and tended to increase with stage of lactation. Genetic correlations estimated using the random regression model fluctuated around the multivariate estimates for live weight and somatic cell score, which were 0.50 and −0.12, respectively. Genetic correlations estimated using the multivariate analysis of BCS with fat and protein yields were close to zero. With the random regression model, genetic correlations between BCS and fat and protein yields were positive at d 1 of lactation (0.16 and 0.08, respectively) and were negative by d 200 of lactation (−0.25 and −0.20, respectively). In pastoral production systems, such as those typical in New Zealand, there appears to be an advantage in the total lactation yields of fat and protein for cows of higher BCS in early lactation, which is likely to be because these cows have body reserves that are available to be mobilized in later lactation, when feed resources are sometimes limited.     

Effect of body condition change and health status during early lactation on performance and survival of Holstein cows

Body condition score (BCS) and disease records are commonly available in dairy operations. However, the effect of BCS changes (ΔBCS) considering specific health profiles has not been investigated extensively. The objective of this study was to assess the effects of different levels of ΔBCS on fertility, milk yield, and survival of Holstein cows diagnosed with reproductive disorders (REP; dystocia, twins, retained fetal membranes, metritis, and clinical endometritis), other health disorders (OTH; subclinical ketosis, left displaced abomasum, lameness, clinical mastitis, and respiratory disease), or with no disease events (HLT) within 40 days in milk (DIM). Data included lactation information from 11,733 cows calving between November 2012 and October 2014 in 16 herds across 4 geographical regions in the United States (Northeast, Midwest, Southwest, Southeast). Cows were evaluated for BCS at 5 ± 3 DIM (BCS5) and at 40 ± 3 DIM (BCS40) and the difference between BCS40 and BCS5 was classified as excessive loss of BCS (EL; ΔBCS ≤−0.75), moderate loss (ML; ΔBCS = −0.5 to −0.25), no change (NC; ΔBCS = 0), or gain of BCS (GN; ΔBCS ≥0.25). Multivariable logistic regression was used for assessing potential associations between the outcomes of interest and ΔBCS and health. The effect of the interaction term ΔBCS by health group was not statistically significant for any of the study outcomes. The odds of resumption of ovarian cyclicity (ROC), in GN, NC, and ML cows were 1.94 (95% CI: 1.57–2.40), 1.59 (1.28–1.97), and 1.27 (1.10–1.47) times greater than the odds of ROC in EL cows, respectively. The odds of pregnancy at 150 DIM (P150) in GN cows were 1.61 (1.20–2.17) times greater than the odds of P150 in EL cows. Cows with REP or OTH disorders had smaller odds of ROC compared with HLT cows [REP: OR = 0.65 (0.56–0.76) and OTH: OR = 0.79 (0.68–0.92)]. For pregnancy outcomes, REP cows had smaller odds of pregnancy at the first artificial insemination compared with HLT cows [0.70 (0.58–0.84)]. Similarly, REP cows had smaller odds of being diagnosed pregnant by 150 and 305 DIM compared with HLT cows [P150: 0.73 (0.59–0.87), P305: 0.58 (0.49–0.69)]. Overall, average daily milk within the first 90 DIM was greater in EL (39.5 ± 1.13 kg/d) and ML (38.9 ± 1.11 kg/d) cows than in NC (37.8 ± 1.12 kg/d) and GN (36.2 ± 1.12 kg/d) cows. On the other hand, average daily milk within the first 90 DIM was lower in REP (37.0 ± 1.11 kg/d) cows compared with OTH (38.7 ± 1.12 kg/d) and HLT cows (38.6 ± 1.11 kg/d). The magnitude of ΔBCS and the health status of early lactation cows should be considered when assessing subsequent cow performance and survival.     

Genetic correlations among body condition score, yield, and fertility in first-parity cows estimated by random regression models.

Twenty type classifiers scored body condition (BCS) of 91,738 first-parity cows from 601 sires and 5518 maternal grandsires. Fertility data during first lactation were extracted for 177,220 cows, of which 67,278 also had a BCS observation, and first-lactation 305-d milk, fat, and protein yields were added for 180,631 cows. Heritabilities and genetic correlations were estimated using a sire-maternal grandsire model. Heritability of BCS was 0.38. Heritabilities for fertility traits were low (0.01 to 0.07), but genetic standard deviations were substantial, 9 d for days to first service and calving interval, 0.25 for number of services, and 5% for first-service conception. Phenotypic correlations between fertility and yield or BCS were small (-0.15 to 0.20). Genetic correlations between yield and all fertility traits were unfavorable (0.37 to 0.74). Genetic correlations with BCS were between -0.4 and -0.6 for calving interval and days to first service. Random regression analysis (RR) showed that correlations changed with days in milk for BCS. Little agreement was found between variances and correlations from RR, and analysis including a single month (mo 1 to 10) of data for BCS, especially during early and late lactation. However, this was due to excluding data from the conventional analysis, rather than due to the polynomials used. RR and a conventional five-traits model where BCS in mo 1, 4, 7, and 10 was treated as a separate traits (plus yield or fertility) gave similar results. Thus a parsimonious random regression model gave more realistic estimates for the (co)variances than a series of bivariate analysis on subsets of the data for BCS. A higher genetic merit for yield has unfavorable effects on fertility, but the genetic correlation suggests that BCS (at some stages of lactation) might help to alleviate the unfavorable effect of selection for higher yield on fertility.     

Describing the body condition score change between successive calvings: a novel strategy generalizable to diverse cohorts

The objective of this study was to explore the derivation of a mathematical model that adequately describes the intercalving body condition score (BCS) profile in dairy cows and is robust and applicable to different animal cohorts. The data used to generate the function were 75,352 daily BCS records across 3,209 lactations in 1,172 cows from a research herd in New Zealand. Mean daily BCS (scale 1 to 10) across all data were plotted and 4 distinct phases were observed. The functional form used to describe the pattern and quantify its features comprised the sum of the 4 phase functions created from intercepts, rates of change, approximate timing of phase transition points, and the sharpness of these transition points in the BCS profile. The generality and applicability of the described model were tested across substrata of BCS at calving and parity. A second data set consisting of a multiyear study comparing cows fed a total mixed ration (TMR) or grazing fresh pasture was compiled from a different research farm. This data set consisted of 4,112 BCS records from 211 lactations on 95 cows. The third data set was a collation of data from another multiyear experiment comparing animal performance under different stocking rates. The data set consisted of 12,414 BCS test-day records on 564 lactations from 287 cows. The presented model is robust and applicable to different animal cohorts, explaining between 29 and 79% of variation depending on the cohort studied. A notable second period of negative energy balance was evident in all grazing cows during midlactation, irrespective of calving BCS, parity, or stocking rate, but did not appear in cows fed TMR. The amount of BCS lost postcalving and nadir BCS were positively correlated with calving BCS, with fatter cows at calving losing more BCS postcalving but remaining at a greater BCS at nadir. Primiparous cows calved at a greater BCS than multiparous cows, as dictated by management protocols, but they failed to regain BCS postnadir as effectively as their multiparous counterparts. Results may highlight the need for preferential feeding of younger cows during late lactation, at least in grazing systems, to ensure that they achieve the required calving BCS at second calving. Cows receiving TMR lost BCS at a slower rate than cows on pasture but for a longer period; the amount of BCS lost between calving and nadir did not differ between the different feeding treatments. Calving BCS declined with increasing stocking rate, and the rates of both loss and gain were negatively affected by stocking rate. The presented model accurately identified biological attributes of the intercalving BCS profile of different groups of cows.     

基于卷积神经网络的机织物密度均匀性检测

针对目前基于机器视觉的机织物密度自动检测时织物检测视野小、精度低、品种适应性差的问题,提出一种基于多尺度卷积神经网络的检测方法.首先设计了一套离线图像采集系统连续采集织物图像,并建立一个包含详细织物参数的织物图像数据集;然后采用一种具有不同大小局部感受野的多尺度卷积神经网络适应不同大小的织物结构特征,定位纱线位置;最后...     

Monitoring the respiratory behavior of multiple cows based on computer vision and deep learning

Automatic respiration monitoring of dairy cows in modern farming not only helps to reduce manual labor but also increases the automation of health assessment. It is common for cows to congregate on farms, which poses a challenge for manual observation of cow status because they physically occlude each other. In this study, we propose a method that can monitor the respiratory behavior of multiple cows. Initially, 4,000 manually labeled images were used to fine-tune the YOLACT (You Only Look At CoefficienTs) model for recognition and segmentation of multiple cows. Respiratory behavior in the resting state could better reflect their health status. Then, the specific resting states (lying resting, standing resting) of different cows were identified by fusing the convolutional neural network and bidirectional long and short-term memory algorithms. Finally, the corresponding detection algorithms (lying and standing resting) were used for respiratory behavior monitoring. The test results of 60 videos containing different interference factors indicated that the accuracy of respiratory behavior monitoring of multiple cows in 54 videos was >90.00%, and that of 4 videos was 100.00%. The average accuracy of the proposed method was 93.56%, and the mean absolute error and root mean square error were 3.42 and 3.74, respectively. Furthermore, the effectiveness of the method was analyzed for simultaneous monitoring of respiratory behavior of multiple cows under movement, occlusion disturbance, and behavioral changes. It was feasible to monitor the respiratory behavior of multiple cows based on the proposed algorithm. This study could provide an a priori technical basis for respiratory behavior monitoring and automatic diagnosis of respiratory-related diseases of multiple dairy cows based on biomedical engineering technology. In addition, it may stimulate researchers to develop robots with health-sensing functions that are oriented toward precision livestock farming.     

Heritabilities and correlations among body condition score,dairy form and selected linear type traits

The objectives of this study were to estimate the heritability of body condition score (BCS) with data that could be used to generate genetic evaluations for BCS in the US, and to estimate the relationship among BCS, dairy form and selected type traits. Body condition score and linear type trait records were obtained from Holstein Association USA Inc. Because BCS was a new trait for classifiers, scoring distribution and accuracy was not normal. Records from 11 of 29 classifiers were eliminated to generate a data set that should represent BCS data recorded in the future. Edited data included 128,478 records for analysis of first lactation cows and 207,149 records for analysis of all cows. Heritabilities and correlations were estimated with ASREML using sire models. Models included age at calving nested within lactation, 5th order polynomials of DIM, fixed herd-classification visit effects and random sire and error. Genetic correlation estimates were generated between first lactation data that had records from 11 classifiers removed and data with no classifiers removed. Genetic correlation estimates were 0.995 and above between data with and without classifiers removed for scoring distributions, but heritability estimates were higher with the classifiers edited from the data. Heritability estimates for type traits and final score were similar to previously reported estimates. The heritability estimate for BCS was 0.19 for first lactation cows and 0.22 for all cows. The genetic correlation estimate for first lactation cows between BCS and dairy form was -0.73, whereas the genetic correlation estimate between BCS and strength was 0.72. Genetic correlation estimates were nearly identical when cows from all lactations were included in the analyses. Body condition score had a genetic correlation with final score closer to zero (0.08) than correlations of final score with dairy form, stature or strength.     

Relationships among international body condition scoring systems

Scoring body condition and assessing changes in the body condition of dairy cattle have become strategic tools in both farm management and research. Consequently, body condition score (BCS) is being researched extensively throughout the world. However, international sharing, comparing, and use of data generated are limited because different BCS systems exist. In the United States and Ireland a 5-point BCS system is used for dairy cows, whereas Australia and New Zealand use 8- and 10-point scales, respectively. The New Zealand 10-point scale was compared with the scoring systems in the United States, Ireland, and Australia by trained assessors. Cows were assessed visually in the United States and Australia, and in Ireland, cows were assessed by palpating key areas of the cow's body (n = 154, 110, and 120, respectively). Data were analyzed by regression. Significant positive linear relationships were found between the New Zealand 10-point scale and the other scoring systems: US 5-point scale, r(2) = 0.54; Irish 5-point scale, r(2) = 0.72; and Australian 8-point scale, r(2) = 0.61. Those relationships must be interpreted cautiously because respective BCS within a given country were by just one experienced evaluator in each country in comparison to a separate evaluator scoring all cows in all counties using the New Zealand 10-point scale. Also, few very thin or very fat cows limit evaluation across extremes of BCS. However, differences between systems were not accurately predicted by simple mathematical calculations. The relationship may be closer for New Zealand and Ireland (r(2) = 0.72) because both of those scoring systems include palpation of individual body parts, whereas visual evaluation is done in Australia and the United States. The current study is the first to examine relationships among differing BCS systems. These results may be useful for comparing/extrapolating research findings from different countries.     

Effects of close-up body condition score and selenium-vitamin E injection on lactation performance,blood metabolites,and oxidative status in high-producing dairy cows

High-producing dairy cows with high pre-calving body condition score (BCS) are more susceptible to metabolic disorders and oxidative stress. The aim of present study was to evaluate the effects of close-up BCS and 3 times Se-vitamin E (SeE) injection on BCS change, blood metabolites, oxidative status, and milk yield in high-producing Holstein cows. A total of 136 multiparous cows were divided into 2 groups based on their BCS including high (HB = 4.00 ± 0.20) and moderate (MB = 3.25 ± 0.25) at 3 wk before expected calving time. Then, each group was divided into 2 subgroups: 3 rounds of SeE injection at 21 d before, and 0 and 21 d after calving (+SeE), and no SeE injection (?SeE). Four final experimental groups were HB+SeE, MB+SeE, HB?SeE, and MB?SeE (34 cows each). Results indicated that interaction effect of BCS and SeE affected serum glucose, and the MB+SeE group had the highest level. The HB cows lost more BCS compared with MB cows during the postcalving period. Moreover, serum insulin concentration increased after SeE injection. The HB cows had higher serum nonesterified fatty acids at 14 d after calving. The MB cows tended to have higher activity of blood glutathione peroxidase over the study period. Furthermore, the SeE-injected cows tended to have higher activity of blood glutathione peroxidase at 28 d after calving. Serum albumin level was increased by SeE injection. The HB cows had greater milk production than MB cows, and SeE-injected cows tended to have higher milk fat percentage and higher fat:protein ratio compared with nonsupplemented cows. It was concluded that SeE injection had beneficial effects on some blood metabolites, albumin as a blood antioxidative parameter, and lactation performance in high-producing dairy cows, especially cows with moderate close-up BCS.     

Calving body condition score affects indicators of health in grazing dairy cows

The objectives of this study were to determine the effect of calving body condition score (BCS) on cow health during the transition period in a pasture-based dairying system. Feed inputs were managed during the second half of the previous lactation so that BCS differed at drying off (BCS 5.0, 4.0, and 3.0 for high, medium, and low treatments, respectively: a 10-point scale); feed allowance was managed after cows were dried off, such that the BCS differences established during lactation remained at the subsequent calving (BCS 5.5, 4.5, and 3.5; n = 20, 18, and 19, for high, medium, and low treatments, respectively). After calving, cows were allocated pasture and pasture silage to ensure grazing residuals >1,600 kg of DM/ha. Milk production was measured weekly; blood was sampled regularly pre- and postpartum to measure indicators of health, and udder and uterine health were evaluated during the 6 wk after calving. Milk weight, fat, protein, and lactose yields, and fat content increased with calving BCS during the first 6 wk of lactation. The effect of calving BCS on the metabolic profile was nonlinear. Before calving, cows in the low group had lower mean plasma β-hydroxybutyrate and serum Mg concentrations and greater mean serum urea than cows in the medium and high BCS groups, which did not differ from each other. During the 6 wk after calving, cows in the low group had lower serum albumin and fructosamine concentrations than cows in the other 2 treatment groups, whereas cows in the low- and medium-BCS groups had proportionately more polymorphonucleated cells in their uterine secretions at 3 and 5 wk postpartum than high-BCS cows. In comparison, plasma β-hydroxybutyrate and nonesterified fatty acid concentrations increased linearly in early lactation with calving BCS, consistent with a greater negative energy balance in these cows. Many of the parameters measured did not vary with BCS. The results highlight that calving BCS and, therefore, BCS through early lactation are not effective indicators of functional welfare, with the analyses presented indicating that both low and high BCS at calving will increase the risk of disease: cows in the low group were more prone to reproductive compromise and fatter cows had an increased risk of metabolic diseases. These results are important in defining the welfare consequences of cow BCS.     

Relationships between fertility and postpartum changes in body condition and body weight in lactating dairy cows

The relationship between energy status and fertility in dairy cattle was retrospectively analyzed by comparing fertility with body condition score (BCS) near artificial insemination (AI; experiment 1), early postpartum changes in BCS (experiment 2), and postpartum changes in body weight (BW; experiment 3). To reduce the effect of cyclicity status, all cows were synchronized with Double-Ovsynch protocol before timed AI. In experiment 1, BCS of lactating dairy cows (n = 1,103) was evaluated near AI. Most cows (93%) were cycling at initiation of the breeding Ovsynch protocol (first GnRH injection). A lower percentage pregnant to AI (P/AI) was found in cows with lower (≤2.50) versus higher (≥2.75) BCS (40.4 vs. 49.2%). In experiment 2, lactating dairy cows on 2 commercial dairies (n = 1,887) were divided by BCS change from calving until the third week postpartum. Overall, P/AI at 70-d pregnancy diagnosis differed dramatically by BCS change and was least for cows that lost BCS, intermediate for cows that maintained BCS, and greatest for cows that gained BCS [22.8% (180/789), 36.0% (243/675), and 78.3% (331/423), respectively]. Surprisingly, a difference existed between farms with BCS change dramatically affecting P/AI on one farm and no effect on the other farm. In experiment 3, lactating dairy cows (n = 71) had BW measured weekly from the first to ninth week postpartum and then had superovulation induced using a modified Double-Ovsynch protocol. Cows were divided into quartiles (Q) by percentage of BW change (Q1 = least change; Q4 = most change) from calving until the third week postpartum. No effect was detected of quartile on number of ovulations, total embryos collected, or percentage of oocytes that were fertilized; however, the percentage of fertilized oocytes that were transferable embryos was greater for cows in Q1, Q2, and Q3 than Q4 (83.8, 75.2, 82.6, and 53.2%, respectively). In addition, percentage of degenerated embryos was least for cows in Q1, Q2, and Q3 and greatest for Q4 (9.6, 14.5, 12.6, and 35.2% respectively). In conclusion, for cows synchronized with a Double-Ovsynch protocol, an effect of low BCS (≤2.50) near AI on fertility was detected, but change in BCS during the first 3 wk postpartum had a more profound effect on P/AI to first timed AI. This effect could be partially explained by the reduction in embryo quality and increase in degenerate embryos by d 7 after AI in cows that lost more BW from the first to third week postpartum.     

Short communication: Genetic relationship between calving traits and body condition score before and after calving in Canadian Ayrshire second-parity cows

The objective of this study was to investigate the genetic relationship between body condition score (BCS) and calving traits (including calving ease and calf survival) for Ayrshire second-parity cows in Canada. The use of random regression models allowed assessment of the change of genetic correlation from 100 d before calving to 335 d after calving. Therefore, the influence of BCS in the dry period on subsequent calving could be studied. Body condition scores were collected by field staff several times over the lactation in 101 herds from Québec and calving records were extracted from the official database used for Canadian genetic evaluation of calving ease. Daily heritability of BCS increased from 0.07 on d 100 before calving to 0.25 at 335 d in milk. Genetic correlations between BCS at different stages ranged between 0.59 and 0.99 and indicated that genetic components for BCS did not change much over lactation. With the exception of the genetic correlation between BCS and direct calving ease, which was low and negative, genetic correlations between BCS and calving traits were positive and moderate to high. Correlations were the highest before calving and decreased toward the end of the ensuing lactation. The correlation between BCS 10 d before calving and maternal calving ease was 0.32 and emphasized the relationship between fat cows before calving with dystocia. Standards errors of the genetic correlations estimates were low. Genetic correlations between BCS and calf survival were moderate to high and favorable. This indicates that cows with a genetically high BCS across lactation would have a greater chance of producing a calf that survived (maternal calf survival) and that they would transmit genes that allow the calf to survive (direct calf survival).     

Within- and across-person uniformity of body condition scoring in Danish Holstein cattle

Body condition scores (BCS) are very useful for dairy herd management and breeding programs, but the consistency and quality of recordings made by consultants in the field are unknown. The objectives of this study were 1) to estimate the agreement in BCS within and among practicing dairy veterinarians and 2) to provide an indication of the effects of training and the value of calibration, and of what efforts need to be made to obtain a validity and precision in BCS adequate for management purposes. A total of 2,230 scores were recorded by 51 practicing dairy veterinarians and 6 highly trained instructors. The 6 instructors were cross-trained to validate calibration consistency in assigning BCS. Each individual scored approximately 20 cows twice, with the second scoring occurring approximately 2.5 h after the first. Between the 2 recordings, the respective instructors conducted a training session for the practicing veterinarians using other cows. A weighted kappa coefficient was used to assess agreement among and within classifiers. Excellent agreement (kappa ≥0.86) was documented between repeated BCS recorded for the same cows by the highly trained instructors. In addition, the BCS provided by multiple classifiers from the instructor team appeared to be comparable across herds and classifiers. This legitimizes the use of BCS for benchmarking at both the cow and the herd level. The within-classifier and between-classifier kappa values were in the ranges of 0.22 to 0.75 and 0.17 to 0.78, respectively, in the group of practicing dairy veterinarians. Many of the veterinarians provided estimates of average BCS that differed considerably from the BCS recorded by the instructors. Between-classifier comparisons of herd BCS are not warranted unless a validation has been performed. If scores are collected by multiple classifiers with varying experience, a valid but imprecise estimate of the true population mean of BCS may be obtained if classifiers are inexperienced. The limited training effort used in this study seemed to have brought about substantial improvement in the validity and precision of the BCS determined by practicing veterinarians, compared with the BCS recorded on the same cows by highly trained classifiers.     

Associations among patterns in daily body weight, body condition scoring, and reproductive performance in high-producing dairy cows

The objective was to investigate the associations between body condition scores (BCS) and daily body weight (BW) in the first 150 d of lactation (DIM) and reproductive performance in high-producing dairy cows. Data included automated daily BW measurements and BCS of 2,020 Israeli Holstein cows from 7 commercial farms. Individual BW series were smoothed using penalized cubic splines, and variables representing BW patterns were generated. The presence of 7- and 21-d cycles in BW was determined using time-series analysis. Associations between BW and BCS and conception at first artificial insemination (AI) were analyzed using generalized estimating equations. Multivariate survival analysis was used for associations between BW and BCS and the calving-to-first AI interval, first AI-to-conception interval, and calving-to-conception interval. First-parity cows that lost ≥12% and second-parity cows that lost ≥15% of their BW from calving to nadir BW were less likely to conceive at first AI. Cows without 7-d cycles in BW were 1.48 times more likely to conceive at first AI relative to cows with 7-d cycles. The odds of conceiving at first AI increased by 53% for each additional unit in BCS from 40 to 60 DIM. In the multivariate survival analysis, a BCS of ≤2.5 between 40 and 60 DIM, the percentage of BW lost from calving to nadir BW, and a BW loss of ≥7% from calving to 10 DIM were associated with reduced reproductive performance. The presence of 21-d cycles in BW was associated with high reproductive performance in first-parity [odds ratio (OR) = 1.18] and second-parity cows (OR = 1.22). The presence of 7-d cycles in BW was associated with low reproductive performance in first-parity cows (OR = 0.77), but not in older cows. Based on previous findings and on the associations found in this study, we postulate that 21-d cycles are probably related to the sexual cycle and could be used as a proxy for assessing ovarian activity. Variables representing relative BW loss (%) were better predictors for impaired reproductive performance than those representing absolute BW loss (kg) and may be more suitable for estimating individual adaptation to negative energy balance in herds for which automated daily BW is available.     

基于机器视觉的透明包装袋真空封口纹理缺陷检测方法

目的:解决由于目前在食品包装领域采用人工抽检方式导致的真空封口质检难以长时间连续作业，易发生漏检、错检，检测准确率稳定性不可靠等问题。方法:提出了一种基于机器视觉的透明包装袋真空封口纹理检测方法代替人工检测。利用ROI区域提取、仿射变换和局部二值化模式等算法进行图像预处理，凸显出纹理特征。在此基础之上，利用灰度共生矩阵分析“良好”和“缺陷”封口纹理图像特征设置灰度共生矩阵参数，将纹理特征的均匀性与共生灰度矩阵特征量相关联。最后，以灰度共生矩阵特征量作为SVM分类器的输入量，通过计算对封口缺陷进行识别与分类。结果:该在线检测方法对透明包装袋真空封口的缺陷检测结果与人工质量结果对比同一性高达97.5%。结论:该方法具备较高的检测准确率和较好的实用性，可满足在线检测的需求。     

基于机器视觉的卷烟爆珠在线检测系统设计

目的：针对卷烟爆珠的质量检测,设计和构建融上料传送、机器视觉图像处理及不合格品剔除功能为一体的卷烟爆珠质量检测系统。方法：通过改进类间方差法对爆珠单颗粒图像进行提取,通过灰度分析、非线性度变换及改进最小外接圆等算法,实现爆珠质量自动化检测,在完成图像自动化检测之后,通过设计的不合格品剔除机构进行剔除,并开展爆珠质量检测的重复试验和应用分析。结果：该系统对不合格爆珠的异色、异行、破损总误检率低于3%,能精确剔除不合格爆珠且系统稳定可靠。结论：基于机器视觉的卷烟爆珠在线检测系统设计,能完成对爆珠质量的自动化在线检测,提高了检测速度与准确度。