Cow udder detection in thermal images of cows
Author | Affiliation | |
---|---|---|
Patašius, Martynas | ||
Date |
---|
2016-11-24 |
Bibliogr.: p. 140-141
Introduction. Mastitis (inflammation of the udder) causes agricultural businesses significant losses - for example, it is estimated that it costs USA 11% of milk production. The mastitis detection methods that are currently used generally depend on analysis of milk. It is likely that methods based on thermal imaging would be faster and encourage more testing. There are numerous papers exploring the use of thermal imges. However, the automated detection of udder, which would be the first step towards using those images, hasn't received much attention. Thus this paper discusses possible ways to detect udder in thermal images and suggests a method based on marker guided watershed transform. materials and methods. 491 image of 37 Lithuanian Black and White cows taken using FLIR T-640 camera have been used for research. Out of them, 33 images were marked manually (Fig. 1) for use as "golden standard". Different udder detection methods were compared using sensitivity specificity: S= TP:TP+FN (1), Sp=TN:TN+FP (2) and Matthews correlation coefficient: MCC= TP... [...].