ANN APPROACH FOR ESTIMATION OF COW WEIGHT DEPENDING ON PHOTOGRAMMETRIC BODY DIMENSIONS

Abstract

In this study, it was aimed to determine the body measurement of Holstein cows through Photogrammetry method and to estimate live weight (LW) by means of artificial neural network (ANN) using the body measurements. For this purpose, a camera shooting environment was formed in a dairy cattle farm where a large number of cows were kept. Firstly, digital photos of each animal were synchronously taken from different directions with Canon EOS400D photo taking units. At the same time, body dimensions, wither height (WH), hip height (HH), body length (BL), hip width (HW) of cows were manually measured using laser meter and measuring stick. LWs of cows were weighed by a weighing scale and the data was automatically saved on a computer. In the second stage, these photos were analyzed by the Image Analysis (IA) software developed in Delphi programming language and body measurements were computed. Manually measured values were very close to IA results. Finally, ANN system was developed by using these body measurements. This system was developed by using Matlab software. Weights which were estimated with the developed knowledge-based system and weighed by the platform scale were compared. The correlation coefficient was calculated (r=0.99). Consequently, there was a statistically meaningful relationship between the compared data. The developed system can be used confidently and the system on which experiments were performed can successfully be modeled.