Development of an Algorithm for the Embryo Location of Seed by using Machine Vision

기계시각을 이용한 대립종자의 씨눈위치 판정알고리즘 개발

  • Published : 2004.06.01

Abstract

This study was conducted to develop an algorithm for the embryo location in seed by using machine vision. The topic of this research is to detect the embryo location in seed regardless of seed supply direction. In order to detect the embryo location in Cham Bak, Tuktojwa and Hukjong, the effect of seed posture in the supply line was investigated. When the seed posture angle of Chambak from horizontal direction was $30^{\circ}$, the detection accuracy for embryo location was 77.8%, while detection accuracy was 100% for the $0^{\circ}$ or $15^{\circ}$. When seed posture angle of Tuktojwa was $30^{\circ}$ from the horizontal direction, the detection accuracy was 89.5% and it was 100% for the $0^{\circ}$ and $15^{\circ}$. Embryo location detection accuracy for the Hukjong was 94.4% when the seed posture angle from the horizontal direction is $30^{\circ}$, and it was 100% for the $0^{\circ}$ and $15^{\circ}$. When seeds are fed into the posturing and seeding line, the seed postures within $30^{\circ}$ with mechanical means, and at most $15^{\circ}$ seed stand posture. the developed algorithm can detect the embryo position in the seed. So, this embryo detection system is very useful tool in the posturing and seeding line.

대립종자의 자동정렬파종기의 씨눈위치 자동판정장치를 개발하기 위한 연구로서 수행된 이 연구는 기계 시각을 이용하여 대립종자의 씨눈 위치가 공급 방향을 기준으로 앞 또는 뒤쪽 어느 쪽에 위치해 있는지를 검출하기 위함이다. 참박, 특토좌, 흑종에 대한 씨눈위치를 판정하기 위하여 종자의 공급자세에 따른 판정정도를 조사하였다. 참박의 경우 공급자세가 $30^{\circ}$ 경우에는 77.8%의 정확도를 나타냈지만,$ 0^{\circ}$$15^{\circ}$때는 100% 검출 정확도를 나타내었다. 특토좌의 경우 공급자세 $30^{\circ}$에서 89.5%, $0^{\circ}$$15^{\circ}$에서는 100%의 판정 정확도가 나타났다. 흑종의 경우에 있어서는 공급자세 $30^{\circ}$에서 94.4%이었고 나머지는 100%의 정확도를 나타냈다. 따라서 정렬파종장치의 공급부에서 종자가 공급될 때 기계적인 메카니즘으로 $30^{\circ}$ 이상 기울어지는 것을 방지할 수 있고 $15^{\circ}$까지 기울어진다 해도 씨눈위치를 판정할 수 있기 때문에 향후 파종장치의 한 부분으로서 사용할 수 있을 것으로 판단되었다.

Keywords

References

  1. Choi, D.K., S.C. Cho, C.S. Lee, S.H. Park, H.J. Kim, T.K. Kang, C.K. Kim, and T.Y. Kwak 2001. Development of a metering device for the garlic planter. J. of the Korean Society for Agricultural Machinery 26(6): 525-534 (In Korean)
  2. Hwang, H., S.C. Kim, and K.D. Ko 1999. Development of prototype automatic grafting system for fruitbearing vegetables. J. of the Korean Society for Agricultural Machinery 24(3):217-224 (In Korean)
  3. Kim, C.S., M.S. Kim, and K.D. Kim 1999. Image processing algorithm for robotic plug-seedling transplanter. J. of the Korean Society for Agricultural Machinery 24(1):51-88 (In Korean)
  4. Min, Y.B., S.T. Kim, and T.S. Chung 2000. Optimum operating conditions of a vaccum nozzle seeder. J. of the Korean Society for Agricultural Machinery 25(6): 463-470 (In Korean)
  5. Park, W.K., D.K. Choi, and Y.K. Kim 2001. Development of a garlic clove planter(1) - survey for planting condition and physical properties of garlic clove -. J. of the Korean Society for Agricultural Machinery 26(6): 495-502(In Korean)
  6. Rhee, J.Y., Y.Y. Kim, and S.R. Park 2000. Speed control of DC motor for roller type seeder. J. of the Korean Society for Agricultural Machinery 25(5):351- 358 (In Korean)
  7. Son, J.R., C.H. Kang, K.S. Han, S.R. Jung, and K.Y. Kwon 2001. Recognition of missing and bad seedlings via color image processing. J. of the Korean Society for Agricultural Machinery 26(3):253-262 (In Korean)