期刊名称：Lecture Notes in Engineering and Computer Science
印刷版ISSN：2078-0958
电子版ISSN：2078-0966
出版年度：2018
卷号：2233&2234
页码：320-323
出版社：Newswood and International Association of Engineers
摘要：Today worldwide trending in precision dairy
farming is becoming more focus on an individual cow welfare
and health rather than group management by using modern
technologies including image processing techniques. In such
cases, individual cow identification is one of the fundamental
ingredients for the success of modern dairy farming. Thus, in
this paper we shall explore and examine how image processing
technologies can be utilized in analyzing and identifying
individual cows along with deep learning techniques. This
system is mainly focus on the identification of individual cow
based on the black and white pattern of the cow’s body. In our
system, firstly we detect the cow’s body which have been placed
on the Rotary Milking Parlour by using the inter-frame
differencing and horizontal histogram based approach. Then,
we crop the cow’s body region by using the predefined distance
value. Finally, the cropped images are used as input data for
training the deep convolutional neural network for the
identification of individual cow’s pattern. The experiments are
performed on the self-collected cow video dataset which have
been taken at the large-scale ranch in Oita Prefecture, Japan.
According the experimental result, our system got the accuracy
of 86.8% for automatic cropping of cow’s body region and
97.01% for cow’s pattern identification. The result shows that
our system can automatically recognize each individual cow’s
pattern very well.
关键词：cow identification; deep learning; edge
detection; horizontal histogram
