A Two-Step Phenotypic Parameter Measurement Strategy for Overlapped Grapes under Different Light Conditions

Phenotypic characteristics of fruit particles, such as projection area, can reflect the growth status and physiological changes of grapes. However, complex backgrounds and overlaps always constrain accurate grape border recognition and detection of fruit particles. Therefore, this paper proposes a two-step phenotypic parameter measurement to calculate areas of overlapped grape particles. These two steps contain particle edge detection and contour fitting. For particle edge detection, an improved HED network is introduced. It makes full use of outputs of each convolutional layer, introduces Dice coefficients to original weighted cross-entropy loss function, and applies image pyramids to achieve multi-scale image edge detection. For contour fitting, an iterative least squares ellipse fitting and region growth algorithm is proposed to calculate the area of grapes. Experiments showed that in the edge detection step, compared with current prevalent methods including Canny, HED, and DeepEdge, the improved HED was able to extract the edges of detected fruit particles more clearly, accurately, and efficiently. It could also detect overlapping grape contours more completely. In the shape-fitting step, our method achieved an average error of 1.5% in grape area estimation. Therefore, this study provides convenient means and measures for extraction of grape phenotype characteristics and the grape growth law.

Effect of Season, Parity and Stage of Lactation on Productive Performance of Sahiwal Cattle

The study was conducted to understand the effect of season, parity and stage of lactation on productive performance of Sahiwal cattle. The data of productive traits of 133 Sahiwal cattle from 2016 to 2018 maintained at the Livestock Research Center, Karnal, Haryana, were used for this study. The production data were analyzed using least-square procedures based on season, parity and stage of lactation. Results indicated that the parity had significant (p less than 0.05) influence on monthly milk yield (MMY) whereas, the stage of lactation had highly significant (P less than 0.01) influence on monthly milk yield (MMY) and test day milk yield (TDMY). However, there was no significant effect of season on different productive performance traits in Sahiwal cattle. The phenotypic parameter estimates indicated that the parity and stage of lactation of cattle can be used as a selection tool for improvement of productive traits considering its high positive phenotypic correlations with succeeding productive traits in Sahiwal cows.

Genetic and phenotypic parameter on fertility traits of Red Chittagong Cattle in Bangladesh

The fertility of Red Chittagong Cattle (RCC) of Bangladesh was studied using data from 122 animals from four herds. The least squares means of female fertility traits were 1.4 ± 0.1, 72.6 ± 3.6% and 85.0 ± 2.0%, respectively, for number of services per pregnancy, first service pregnancy rate and overall pregnancy rate. The least squares mean of non-return rate to first service of bull was 58.7 ± 5.1%. The factor having a significant effect on female fertility was herd, while parity had no effect. Herd and parity of dam, season of service and sire had no effect on non-return rate to first service of bull. The heritability of fertility traits were very low: values were 0.07 ± 0.04, 0.03 ± 0.04, 0.05 ± 0.04 and 0, respectively, for number of services per pregnancy, first service pregnancy rate, overall pregnancy rate and non-return rate to first service of bull. The corresponding repeatability values were 0.18 ± 0.08, 0.08 ± 0.07, 0.13 ± 0.08 and -0.07 ± 0.02, respectively. This study reveals the fertility to be good. However, better reproductive management may enhance the overall herd fertility of RCC. DOI: http://dx.doi.org/10.3329/bvet.v29i2.14347 Bangl. vet. 2012. Vol. 29, No. 2, 78-89