DOI QR코드

DOI QR Code

A Finger Counting Method for Gesture Recognition

제스처 인식을 위한 손가락 개수 인식 방법

  • Lee, DoYeob (Department of Computer Engineering, Sejong University) ;
  • Shin, DongKyoo (Department of Computer Engineering, Sejong University) ;
  • Shin, DongIl (Department of Computer Engineering, Sejong University)
  • Received : 2015.10.26
  • Accepted : 2016.01.19
  • Published : 2016.04.30

Abstract

Humans develop and maintain relationship through communication. Communication is largely divided into verbal communication and non-verbal communication. Verbal communication involves the use of a language or characters, while non-verbal communication utilizes body language. We use gestures with language together in conversations of everyday life. Gestures belong to non-verbal communication, and can be offered using a variety of shapes and movements to deliver an opinion. For this reason, gestures are spotlighted as a means of implementing an NUI/NUX in the fields of HCI and HRI. In this paper, using Kinect and the geometric features of the hand, we propose a method for recognizing the number of fingers and detecting the hand area. A Kinect depth image can be used to detect the hand region, with the finger number identified by comparing the distance of outline and the central point of a hand. Average recognition rate for recognizing the number of fingers is 98.5%, from the proposed method, The proposed method would help enhancing the functionality of the human computer interaction by increasing the expression range of gestures.

인간은 의사소통을 통해서 상호관계를 유지시키고 발전시켜나간다. 의사소통은 크게 언어적 의사소통과 비언어적 의사소통으로 나뉜다. 언어적 의사소통은 말 또는 글을 사용하는 것이고 비언어적 의사소통은 몸동작으로 의사를 전달하는 것이다. 우리는 일상생활에서 대화를 할 때 말과 더불어 제스처를 함께 사용한다. 제스처는 비언어적 의사소통에 속하며, 다양한 형태와 움직임으로 의사를 전달할 수 있다. 이러한 이유로 제스처는 HCI 분야와 HRI 분야에서 NUI/NUX를 구현하기 위한 수단으로 각광받고 있다. 본 논문에서는 키넥트와 손의 기하학적인 특징을 사용하여 손 영역 검출과 손가락 개수를 인식하는 방법을 제안한다. 키넥트가 제공하는 깊이 영상을 이용하여 영상에서 손 영역을 검출하고 손의 윤곽선과 중점의 거리를 비교하여 손가락 개수를 파악한다. 본 논문에서 제안한 방법에 따른 손가락 개수 인식률은 평균 98.5%이고 수행시간은 0.065ms이다. 이 방법은 기존의 연구와 비교 했을 때, 인식 속도가 빠르며, 복잡도가 O(n),으로써 성능 또한 우수하다. 향후 이를 통해 제스처의 인식 가능한 범위를 증가시켜 보다 컴퓨터와 인간의 상호작용이 수월해지는데 도움이 될 것이다.

Keywords

References

  1. J.L Applegate, G.B Leichty, "Managing interpersonal relationships : Social cognitive and strategic determinants of competence," In R. N. Bostrom(Ed.), Competence in communication : A multidisciplinary approach, 1984, pp. 33-56.
  2. Su jin Chae, "The Importance of Nonverbal Communication Skills," Korean J Med Educ 2010 Jun, 2010, pp. 149-150. http://dx.doi.org/10.3946/kjme.2010.22.2.149
  3. J.P. Wachs, M. Kolsch, H. Stern and Y. Edan, "Vision-based hand gesture applications," Communications of the ACM, vol. 55, 2011, pp. 60-71. http://dx.doi.org/10.4016/26819.01
  4. Sang Yun Park, Eung Joo Lee, "Hand Gesture Recognition Algorithm Robust to Complex Image," Journal of Korea Multimedia Society, Vol.13, No.7, July, 2010, pp. 1000-1015. http://www.koreascience.or.kr/article/ArticleFullRecord.j sp?cn=MTMDCW_2010_v13n7_1000
  5. Lauri Connelly, Yicheng Jia, Maria L. Taro, Mary Ellen Stoykov, Robert V. Kenyon, Derek G. Kamper, "A Pneumatic Glove and Immersive Virtual Reality Environment for Hand Rehabilitative Training After Stroke," IEEE Trans. Neural Systems and Rehabilitation Engineering, vol.18, issue 5, 2010, pp. 551-559. http://dx.doi.org/10.1109/tnsre.2010.2047588
  6. M. Chen, L. Mummert, P. Pillai, A. Hauptmann, and R. Sukthankar, "Controlling your TV with gestures," Proc. Int'l. Conf. Multimedia Information Retrieval, 2010, pp. 405-408. http://dx.doi.org/10.1145/1743384.1743453
  7. H. P. Jain and A. Subramanian, "Real-time upper-body human pose estimation using a depth camera," Technical Report, HPL-2010-190, HP Laboratories, 2010. http://dx.doi.org/10.1007/978-3-642-24136-9_20
  8. Woon-Soo Choi, Yong-Hwan Cho, Joon-suk Lee, "3-D Gesture Recognition Research using CUDA and Improved Hybrid Neural Networks," Korea Entertainment Industry Association 2011 Annual Spring Conference on Computational Intelligence, 2011, pp. 172-180. http://www.dbpia.co.kr/Article/NODE01789961
  9. Junyeong Choi, Seiheui Han, Hanhoon Park and Jong-Il Park, "A Study on Providing Natural Two-handed Interaction Using a Hybrid Camera," The Third Interaction Conference on Digital Information Processing and Communications(ICDIPC 2013), 2013, pp. 484-484. http://sdiwc.net/digital-library/a-study-on-providing-natur al-twohanded-interaction-using-a-hybrid-camera.html
  10. Junyeong Choi, Byung-Kuk Seo, Daeseon Lee, Hanhoon Park and Jong-Il Park, "RGB-D Camera-based Hand Shape Recognition for Human-robot Interaction," Robotics(ISR), 2013 44th International Symposium on IEEE, 2013, pp.1-2. http://dx.doi.org/10.1109/isr.2013.6695627
  11. L. Raheja Jadish , Chaudhary Ankit, Singal Kunal, "Tracking of Fingertips and Centers of Palm using KINECT," 2011 Third International Conference on Computational Intelligence, Modelling and Simulation(CIMSiM), 2011, pp. 248-252. http://dx.doi.org/10.1109/cimsim.2011.51
  12. Hongyong Tao, Youling Yu, "Finger Tracking and Gesture Interaction with Kinect," IEEE 12th International Conference on Computer and Information(CIT), 2012, pp. 214-218. http://dx.doi.org/10.1109/cit.2012.62
  13. Hanhoon Park, Junyeong Choi, Jong-Il Park and Kwang-Seok Moon, "A Study on Hand Region Detection for Kinect-Based Hand Shape Recognition," Journal of Broadcast Engineering, Volume 18 , Issue 3, 2013, pp.393-400. http://dx.doi.org/10.5909/jbe.2013.18.3.393
  14. J. Choi, H. Park, and J.-I. Park, "Hand shape recognition using distance transform and shape decomposition," Proc. of ICIP'11, 2011, pp. 3666-3669. http://dx.doi.org/10.1109/icip.2011.6116497
  15. C.Cao, Y. Sun, R. Li, and L. Chen, "hand posture recognition via joint feature sparse representation," Optical Engineering, vol. 50, no. 12, 2011, pp. 127210. http://dx.doi.org/10.1117/1.3662884

Cited by

  1. Multi-stage Template Matching for One Hand Numerical Gesture Recognition vol.16, pp.5, 2018, https://doi.org/10.14801/jkiit.2018.16.5.15
  2. 인터렉티브 디지털 사이니지를 위한 손 인식 인터페이스 개발 vol.22, pp.3, 2017, https://doi.org/10.9723/jksiis.2017.22.3.001
  3. Finger-Counting-Based Gesture Recognition within Cars Using Impulse Radar with Convolutional Neural Network vol.19, pp.6, 2016, https://doi.org/10.3390/s19061429
  4. Chinese Hand Number Gesture Recognition by Enhanced Multi-stage Template Matching vol.17, pp.8, 2019, https://doi.org/10.14801/jkiit.2019.17.8.115
  5. 손가락 인식을 기반으로 한 로봇청소기 제어기술 vol.15, pp.1, 2020, https://doi.org/10.13067/jkiecs.2020.15.1.139
  6. Development of a Parcel-Level Land Boundary Extraction Algorithm for Aerial Imagery of Regularly Arranged Agricultural Areas vol.13, pp.6, 2016, https://doi.org/10.3390/rs13061167