DOI QR코드

DOI QR Code

Deep Learning Based Tree Recognition rate improving Method for Elementary and Middle School Learning

  • Choi, Jung-Eun (School of Software Education, Ewha Womans University) ;
  • Yong, Hwan-Seung (Dept. of Computer Science & Engineering, Ewha Womans University)
  • 투고 : 2019.10.10
  • 심사 : 2019.12.13
  • 발행 : 2019.12.31

초록

본 연구의 목적은 수업 시 스마트기기에 적용할 수 있는 나무 이미지를 인식하고 분류하여 정확도를 측정할 수 있는 효율적인 모델을 제안하는 것이다. 2015개정 교육과정으로 개정되면서 초등학교 4학년 과학교과서의 학습 목표에서 스마트 기기 사용한 식물 인식이 새롭게 추가 되었다. 특히 나무 인식의 경우 다른 사물 인식과 달리 수형, 수피, 잎, 꽃, 열매의 부위별 특징이 있으며, 계절에 따라 모양 및 색깔의 변화를 거치므로 인식률에 차이가 존재한다. 그러므로 본 연구를 통해 컨볼루션 신경망 기반의 사전 학습된 인셉션V3모델을 이용하여 재학습 전 후의 나무 부위별 인식률을 비교한다. 또한 각 나무의 유형별 이미지 정확도를 결합시키는 방식을 통해 효율적인 나무 분류 방안을 제시하며 교육현장에서 사용하는 스마트기기에 적용 할 수 있을 것이라 기대한다.

The goal of this study is to propose an efficient model for recognizing and classifying tree images to measure the accuracy that can be applied to smart devices during class. From the 2009 revised textbook to the 2015 revised textbook, the learning objective to the fourth-grade science textbook of elementary schools was added to the plant recognition utilizing smart devices. In this study, we compared the recognition rates of trees before and after retraining using a pre-trained inception V3 model, which is the support of the Google Inception V3. In terms of tree recognition, it can distinguish several features, including shapes, bark, leaves, flowers, and fruits that may lead to the recognition rate. Furthermore, if all the leaves of trees may fall during winter, it may challenge to identify the type of tree, as only the bark of the tree will remain some leaves. Therefore, the effective tree classification model is presented through the combination of the images by tree type and the method of combining the model for the accuracy of each tree type. I hope that this model will apply to smart devices used in educational settings.

키워드

참고문헌

  1. Jin Hyung Kim, Fourth Industrial Revolution, Education in the Age of Artificial Intelligence. STSS The Sustainability Science Society Conference, Vol. 2016, No. 6, pp. 21-29, 2016.
  2. YungJun Lee, Prepare for the introduction of the 2015 Revised Information Curriculum. The Korean Society Of Computer And Information, Vol. 23, No. 2, pp. 1-8, 2015.
  3. Korean Ministry of Education, "(Elementary School) Science 4-2," Seoul: Visang education, 2018.
  4. Korean Ministry of Education, "(Elementary School 3-4 Grade) Science 4-2," Seoul: Miraen, 2014.
  5. Heeok Heo, Hyeonwoo Lee, Hyeonjin Kim, Kyu Yon Lim, Eui Sung Kang, Investigation on teachers' understanding of SMART education in Jeollanamdo. The Korean Association Of Computer Education Conference Presentations, Vol. 17, No. 1, pp. 3-7, 2013.
  6. Yu Hwan Kim, Jeong Yoo soo, Chung Yun-su, Kil-Houm Park, Age Estimation Method based on Comparative Convolutional Neural Network using Inception Module. Journal of Korean Institute of Intelligent Systems, Vol. 2, No. 3, pp. 193-200, 2018. DOI: 10.5391/jkiis.2018.28.3.193
  7. Vladimir V. Mokeev, On Application of Convolutional Neural Network for Classification of Plant Images. Global Smart Industry Conference(GloSIC), pp. 1-6, 2018. DOI: 10.1109/glosic.2018.8570141
  8. Titus J. Brinker, Achim Hekler, Alexander H. Enk, et al, A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. European Journal of Cancer, Vol. 111, pp. 148-154, 2019. https://doi.org/10.1016/j.ejca.2019.02.005
  9. YoonJoo Cho, Deep Learning Technology and Applications in the IoT Industry. Industrial Engineering Magazine, Vol. 26, No. 1, pp. 15-20, 2019.
  10. PictureThisAI Application., https://www.picturethisai.com
  11. PlantSnap Application, https://www.plantsnap.com
  12. Naver Application SmartLens, https://blog.naver.com/naver_search/221047954593
  13. Weol-Youg Kim, Seung-Jung Shin, Large orchard apple classification system. The Journal of the Convergence on Culture Technology (JCCT), Vol. 4, No. 4, pp. 393-399, 2018. https://doi.org/10.17703/JCCT.2018.4.4.393
  14. Gunmyung Lee, "Artificial intelligence : From Turing Test to Deep Learning," Paju: Saengneung. Publication, 2018.
  15. Tensorflow Github, https://github.com/tensorflow/hub