Because milk is an important food source of national, so the research with the dairy cow-related has been subject to a high degree of attention. The body structures of the high-yielding dairy cows and low-yielding dairy cows in, especially the body structures with breast related have significant differences, after a long period of research and practice, the importance of body structures and milk production performance has been referred to the same status. However, due to cow breast shape evaluation is done manually, so time-consuming and accuracy is not high, Meanwhile because manual inspection often need contacts with the cows, so cows can cause stress to reflect, and affect their production. Analysis of the features Cow’s breast shape based on computer vision is expected to become an effective means to solve these problems.Therefore, this research using computer vision and reverse engineering, the cow’s breast shape characteristics of measurement and analysis, to explore efficient, non-contact method of assessing cow breast shape characteristics. Compared with manual measurement, the method is simple and fast, efficient, avoid subjective factors, and because no physical contact with cows, so cows can minimize the stress response. Breast shape features analysis method proposed in this paper, and the proposed method is expected to summarized the characteristics of high producing dairy cows breast shape, and shape characteristics of milk performance analysis to provide an effective means.This method is in the use of computer vision and image processing technology for breast cows on the basis of three-dimensional point cloud, point cloud by analyzing the distribution of breast milk cow dairy summarized the overall characteristics of the breast; Followed by, the3D point cloud is been closed used to by the closed-algorithm, and the slicing method will3D point cloud closed to vehicular traffic is converted to a set of parallel plane scattered points, so the three-dimensional shape analysis is converted to two-dimensional curve analysis; Finally, fitting curve use the point, enabling the cow breast shape analysis is possible. Finally curve fitting using the parallel plane, enabling the cow breast shape analysis is possible.Currently, the laboratory has completed the phase of the study, the next stage of plans to collect a large number of dairy cows in vivo morphological characteristics, internal organizational structure characteristics, and milk performance in-depth study. |