Image Technology and Matrix-Geometric Method for Automatic Dairy Cow Body Condition Scoring
-
- ZIN Thi Thi
- Faculty of Engineering, University of Miyazaki
-
- TIN Pyke
- International Relation Center, University of Miyazaki
-
- HORII Yoichiro
- Faculty of Agriculture, University of Miyazaki
-
- KOBAYASHI Ikuo
- Faculty of Agriculture, University of Miyazaki
Search this article
Abstract
<p>Dairy cow body condition scoring is a key task in nearly every aspect of modern precision dairy farming. It is important in managing the health and welfare of dairy cattle, optimizing milk yields and split meals (feeding systems), determining the timing of heat and reproduction peaks, as well as successful calving. Accurate body condition scoring ensures profitability. However, the majority of dairy farmers do not perform body condition scoring on a regular basis due to the lack of automation, and when they do, the process is time-consuming and very subjective. This paper proposes an automatic and efficient dairy cow body scoring system using image technology and the matrix-geometric method. Fusing image technology and the matrix-geometric method into a hybrid system provides a new and efficient technique for dairy cow body condition scoring. In order to do so, firstly, anatomical cow body points are extracted from the rear views and top views of cow images. Then the geometric properties of the extracted anatomical points are transformed into a Markov chain matrix to determine the body condition scores. For a confirmation of the validity of the proposed method, some experimental results are shown by using a public cow body condition database.</p>
Journal
-
- International Journal of Biomedical Soft Computing and Human Sciences: the official journal of the Biomedical Fuzzy Systems Association
-
International Journal of Biomedical Soft Computing and Human Sciences: the official journal of the Biomedical Fuzzy Systems Association 24 (1), 29-37, 2019
Biomedical Fuzzy Systems Association
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390287363458043392
-
- NII Article ID
- 130007998976
-
- ISSN
- 2424256X
- 21852421
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Disallowed