Common ragweed is a plant species causing allergic and asthmatic symptoms in humans. To control its propagation, an early identification system is needed. However, due to its similar appearance with mugwort, proper differentiation between these two weed species is important. Therefore, we propose a method to discriminate common ragweed and mugwort leaves based on digital images using bag of visual words (BoVW). BoVW is an object-based image classification that has gained acceptance in many areas of science. We compared speeded-up robust features (SURF) and grid sampling for keypoint selection. The image vocabulary was built using K-means clustering. The image classifier was trained using support vector machines. To check the robustness of the classifier, specific model runs were conducted with and without damaged leaves in the trainings dataset. The results showed that the BoVW model allows the discrimination between common ragweed and mugwort leaves with high accuracy. Based on SURF keypoints with 50% of 788 images in total as training data, we achieved a 100% correct recognition of the two plant species. The grid sampling resulted in slightly less recognition accuracy (98 to 99%). In addition, the classification based on SURF was up to 31 times faster.

The objective of this study was to quantify the genetic variation in carcass cuts predicted using digital image analysis in commercial cross-bred cattle. The data set comprised 38 404 steers and 14 318 heifers from commercial Irish herds. The traits investigated included the weights of lower value cuts (LVC), medium value cuts (MVC), high value cuts (HVC), very high value cuts (VHVC) and total meat weight. In addition, the weights of total fat and total bones were available on the steers. Heritability of carcass cut weights, within gender, was estimated using an animal linear model, whereas genetic and phenotypic correlations among cuts were estimated using a sire linear model. Carcass weight was included as a covariate in all models. In the steers, heritability ranged from 0.13 (s.e. = 0.02) for VHVC to 0.49 (s.e. = 0.03) for total bone weight, and in the heifers heritability ranged from 0.15 (s.e. = 0.04) for MVC to 0.72 (s.e. = 0.06) for total meat weight. The coefficient of genetic variation for the different cuts varied from 1.4% to 3.6%. Genetic correlations between the different cut weights were all positive and ranged from 0.45 (s.e. = 0.08) to 0.89 (s.e. = 0.03) in the steers, and from 0.47 (s.e. = 0.14) to 0.82 (s.e. = 0.06) in the heifers. Genetic correlations between the wholesale cut weights and carcass conformation ranged from 0.32 (s.e. = 0.06) to 0.45 (s.e. = 0.07) in the steers, and from 0.10 (s.e. = 0.12) to 0.38 (s.e. = 0.09) in the heifers. Genetic correlations between the same wholesale cut traits in steers and heifers ranged from 0.54 (s.e. = 0.14) for MVC to 0.79 (s.e. = 0.06) for total meat weight; genetic correlations between carcass weight and carcass classification for conformation and fat score in both genders varied from 0.80 to 0.87. The existence of genetic variation in carcass cut traits, coupled with the routine availability of predicted cut weights from digital image analysis, clearly shows the potential to genetically improve carcass value.