Development of an automatic cow body condition scoring using body shape signature and Fourier descriptors

Abstract

Body condition evaluation is a common tool to assess energy reserves of dairy cows and to estimate their fatness or thinness. This study presents a computer-vision tool that automatically estimates cow's body condition score. Top-view images of 151 cows were collected on an Israeli research dairy farm using a digital still camera located at the entrance to the milking parlor. The cow's tailhead area and its contour were segmented and extracted automatically. Two types of features of the tailhead contour were extracted: (1) the angles and distances between 5 anatomical points; and (2) the cow signature, which is a 1-dimensional vector of the Euclidean distances from each point in the normalized tailhead contour to the shape center. Two methods were applied to describe the cow's signature and to reduce its dimension: (1) partial least squares regression, and (2) Fourier descriptors of the cow signature. Three prediction models were compared with manual scores of an expert. Results indicate that (1) it is possible to automatically extract and predict body condition from color images without any manual interference; and (2) Fourier descriptors of the cow's signature result in improved performance (R(2)=0.77).

Rear shape in 3 dimensions summarized by principal component analysis is a good predictor of body condition score in Holstein dairy cows

“…Therefore, few research groups (Ferguson et al, 2006;Bewley et al, 2008;Halachmi et al, 2008, Negretti et al, 2008Azzaro et al, 2011;Bercovich et al, 2013;Weber et al, 2014) have attempted to automate BCS to achieve a more objective and less time-consuming method. Directly scoring body condition on 2-dimensional (2D) images is as efficient as standard BCS, but is still as subjective and labor consuming as the latter (Ferguson et al, 2006).…”

“…Instead of using partial characteristics of the shape and keeping the rear shape in the common 2D space, Azzaro et al (2011) and Bercovich et al (2013) dealt with whole information kept in the rear shape. Azzaro et al (2011) used principal component analysis (PCA) and Bercovich et al (2013) compared partial least square regression (PLSR) and Fourier descriptors (FD).…”

“…Azzaro et al (2011) used principal component analysis (PCA) and Bercovich et al (2013) compared partial least square regression (PLSR) and Fourier descriptors (FD). These 3 methods are efficient tools commonly used in shape processing (Vranic and Saupe, 2001;Allen et al, 2003;Zion et al, 2007).…”

Advances in Automatic Detection of Body Condition Score of Cows: A Mini Review

“…In the Table 1 ii. Mostly, there are two types of models used: regression analysis models (as in) [10][11][12][13][14][15][16] and algorithms that measure cow's body angularity (as in) [17][18][19] according to the hypothesis that the body shape of a fatter cow is rounder than that of a thin cow. Moreover, three automation levels are described.…”

“…In the lowest level are, 10,12,15 which require to manually identify anatomical points in the images to extract characteristics to develop the estimation models. In the medium level are, 11,13,20 where the input images used are manually selected, but the rest of the process is automatic. Finally, in the highest level are, 14,[16][17][18][19] where the process is completely automated.…”