Pig growth and conformation monitoring using image analysis

Machine vision can be used to collect images of pigs and analyse them to id entify and measure specific areas and dimensions related to their growth, s hape and hence conformation. This information could improve the stockman's ability to maximize production efficiency and also to monitor health by def ecting abnormalities in growth rates. This work introduces fully automated algorithms which find the plan view outline of animals in a normal housing situation, divide the outline into major body components and measure specif ied dimensions and areas. Special attention is paid to determining whether the results are sufficiently repeatable to be useful in estimating these pa rameters. Problems in compensating for changes in the optical geometry are outlined and methods proposed to deal with them. The repeatability of the i mage analysis process coupled with the subsequent signal processing for out lier rejection gives s.e. values on areas of < 0.005 and on linear dimensio ns of < 0.0025. For example the plan view area less head and neck (A4) can be used to predict the weight of the group of pigs at 34 kg, 66 kg and 98 k g with standard errors of 0.25 kg, 0.17 kg and 0.39 kg respectively when us ing manual weighing results to calibrate the system. If an individual pig i s weighed once at 75 days (e.g. 34 kg) to calibrate the A4-to-weight relati onship, subsequent A4 measurements can be used to predict its weight when 1 25 days old (approx. 80 kg) to within l kg. This matches the accuracy of th e manual weighing system used in the trials. The effect of pig gender on th e area to weight relationships is not significant (P = 0.074), but there is a small yet significant gender effect with the linear dimensions.