Font Size: a A A

Research On Viability Detection Of Egg Embryo And Sorting System Based On Machine Vision

Posted on:2011-10-15Degree:MasterType:Thesis
Country:ChinaCandidate:Y H WangFull Text:PDF
GTID:2178360308476102Subject:Control theory and control engineering
Abstract/Summary:PDF Full Text Request
At present, preparation of influenza vaccine usually adopts the way of culturing viruses in the embryo of eggs. In the process of virus acquisition, it will cause security problem if the necrosis embryos are not reject effectively. Therefore, identifying fertility of egg embryos before virus acquisition is of great importance. Nowadays, domestic manufacturer are detecting eggs artificially with a candling lamp, which is of great labour intensity, low efficiency and accuracy. In order to improve the current situation, it is necessary to establish a sorting system of identifying fertility of egg embryo based on machine vision.Firstly, the way of how to judge whether the egg embryos are necrosis or not based on machine vision is studied systematically. Compared with several ways of filtering methods, median filtering is used to strengthen the images of egg embryos with the consideration of the system environment; and then use local adaptive segmentation based on histogram-based WFCM to segment the image under the consideration of particularity of the images of egg embryos; the noise existing in the image after separating used morphology method to de-noise and enhance the character of the image; compared with the two algorithm of thinning, the fast thinning algorithm based thinning repair is used to thin the image; detect the fertility by counting the number of the blood-vessels.Secondly, identifying fertility of egg embryo and sorting system based on machine vision has been established. The optimum light source condition, background color, and the choice of camera, lens and the style of image collection card have been confirmed, and the image collection of egg embryos and sorting function of necrosis embryo is realized based on the gripping device controled by PLC.Finally, software system integration has laid the foundation of further research in identifying fertility of egg embryo and sorting system. On the basis of this detection system, a lot of egg embryos are tested, and the experimental results show that this system offers the advantages of high detection accuracy, low undetected error rate and false detected rate, realize the nondestructive testing of egg embryo,and meet the special requirements of vaccine preparation.
Keywords/Search Tags:Machine vision, Identifying fertility, Morphology, Thinning algorithm, Sorting system
PDF Full Text Request
Related items