Automatic Sheep Weight Estimation Based on K-Means Clustering and Multiple Linear Regression

Abstract

Using a balance to estimate sheep’s weight is inefficient and time consuming. Sheep’s weight also fluctuates with many factors such as pregnancy, lactation, and gut fill. However, linear measurements are not highly affected by such type of factors. Therefore, in this paper, sheep weight was determined by calculating linear measurements from sheep images using visual analysis techniques. The system starts, followed by applying the K-means clustering for sheep segmentation. Then, biggest blob detection along with morphological analysis take place. After that breadth and width of sheep are extracted. Weight is then estimated from the linear dimensions using a regression function learned from the data-set. In the experiments, sheep weight estimation was tested on data set of 104 side images for 52 sheep. For performance evaluation, R-squared was measured and it reached 0.99. High accuracy of 98.75% was also achieved.