Estimating Pig Weight with Digital Image Processing using Deep Learning

In pig production, food processing and profitability ratios can be assessed by detecting live weight of live pigs in real time. Traditional pig weight detection often requires direct contact with pigs, which is limited by low efficiency and can result in even death. Detecting the weight of non-contact pigs has become a challenge in pig production for decades. The proposed system offers significant features such as color, texture, centroid, major axis length, minor axis length, eccentricity and area. For recognition for estimation weight of pig, we use statistics from the original database with neural network. Analysis of experimental results of contactless pig weight estimation as well.