Graphics Reference
In-Depth Information
Automatic Classification of Human Embryo Microscope
Images Based on LBP Feature
Liang Xu 1 , Xuefeng Wei 1,2 , Yabo Yin 3 , Weizhou Wang 4 ,
Yun Tian 3,* , and Mingquan Zhou 3
1 College of Information Engineering, Huanghuai University, Zhumadian, China
2 College of Information Engineering, Wuhan University of Technology, Wuhan, China
xl66315@163.com, jkxwlsy@126.com
3 College of Information Science & Technology, Beijing Normal University, Beijing, China
yinyabo0612@163.com, tianyun@bnu.eud.cn, mqzhou@bnu.edu.cn
4 Assisted reproductive medical centerNavy General HospitalPLA, Beijing, China
wangweizhou12@126.com
Abstract. It is significant in-vitro fertilization (IVF) to automatically evaluate
the implantation potential for embryos with a computer. In this essay, an auto-
matic classification algorithm based on local binary pattern (LBP) feature and
the support vector machine (SVM) algorithm is presented to classify the emb-
ryo images which will suggest whether the image is suitable for the implanta-
tion. The LBP operator is first time to be used to extract the texture feature of
embryo images, and it is verified that the feature has the capacity of making two
types of images linearly separable. Furthermore, a classifier based on the SVM
algorithm is designed to determine the best projection direction for classify
embryo images in the LBP feature space. Experiments were made with 6-fold
cross validation over 185 images, and the result demonstrates that the proposed
algorithm is capable of automatically classifying the embryo images with accu-
racy and efficiency.
Keywords: Embryo image, classification, local binary pattern and support vec-
tor machine.
1 Introduction
With the development of science and technology, IVF (in-vitro fertilization) technol-
ogy has become one of the main methods of treating infertility[1]. Although IVF
technology has made great progress, the efficiency of IVF still needs improvement.
A great challenge that the embryologists face is how to recognize the most viable
embryo to be implanted. Currently, the embryologists evaluate the implantation po-
tential of embryos by visual examination and their evaluation is totally subjective. To
solve this problem, automatic evaluation of embryo's quality with the help of embryo
images before transferring by computer-aided method and then selecting the optimal
* Corresponding author.
 
Search WWH ::




Custom Search