Advertisement

Recognition of Text Commands and Control of the Mobile Robot Starter Kit 2.0

  • Wacław Banaś
  • Bartłomiej NalepaEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 934)

Abstract

This article presents an algorithm for recognizing text commands and how to send information about a text command to a mobile robot Starter Kit 2.0. The first chapters deal with methods of reading image from Kinect sensors, colour palette changes, thresholds, and central moments calculations. The methods for finding closed contours in the analysed image are presented. Then it shows how to divide the text into rows. Each line was also divided into singular letters that were sent to the defined function. Letter recognition was accomplished by creating a new black image and by embedding the characteristic points. Then the image containing the letter was compared to the standard image using the AND operation. The results were compared with the library created with the description of the point’s characteristic for each letter. All image processing was done in Python with the Raspbian Jessie. Python has also added libfreenect and OpenCV libraries. The last chapter shows how to communicate between Raspberry Pi3 and the mobile robot Starter Kit 2.0.

Keywords

Robot LabVIEW Vision 

References

  1. 1.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 2 edn. Prentice Hall, Upper Saddle RiverGoogle Scholar
  2. 2.
    Documentation of the OpenCV library. http://docs.opencv.org/3.1.0/d6/d00/tutorial_py_root.html. Accessed 27 June 2017
  3. 3.
    Documentation of the libfreenect library. https://github.com/OpenKinect/libfreenect. Accessed 27 June 2017
  4. 4.
    Documentation of the NumPy library. https://docs.scipy.org/doc/numpy-dev/reference/. Accessed 27 June 2017
  5. 5.
    Banaś, W., Ćwikla, G., Foit, K., et al.: Experimental determination of dynamic parameters of an industrial robot. In: IOP Conference Series: Materials Science and Engineering, vol. 227, p. 012012 (2017)Google Scholar
  6. 6.
    Banaś, W., Ćwikla, G., Foit, K., et al.: Modelling of industrial robot in LabView robotics. In: IOP Conference Series: Materials Science and Engineering, vol. 227, p. 012012 (2017)Google Scholar
  7. 7.
    Hryniewicz, P., Banaś, W., Foit, K., et al.: Modelling cooperation of industrial robots as multi-agent systems. In: IOP Conference Series: Materials Science and Engineering, vol. 227, p. 012061 (2017)Google Scholar
  8. 8.
    Banaś, W., Gwiazda, A., Monica, Z., et al.: Analysis of the position of robotic cell components and its impact on energy consumption by robot. In: IOP Conference Series: Materials Science and Engineering, vol. 145, p. 052017 (2016)Google Scholar
  9. 9.
    Banaś, W., Gwiazda, A., Monica, Z., et al.: Modelling and simulation tooling controlled by the PLC in the robot cell in NX. In: IOP Conference Series: Materials Science and Engineering, vol. 145, p. 052016 (2016)Google Scholar
  10. 10.
    Sit, A., Kihara, D.: Comparison of image patches using local moment invariants. IEEE Trans. Image Process.  https://doi.org/10.1109/TIP.2014.2315923
  11. 11.
    Huang, Z., Leng, J.: Analysis of Hu’s moment invariants on image scaling and rotation. ECU Publications Pre.  https://doi.org/10.1109/ICCET.2010.5485542
  12. 12.
    Hamdaoui, F., Sakly, A., Mtibaa, A.: An efficient multi level thresholding method for image segmentation based on the hybridzation of modified PSO and Otsu’s method. Springer International Publishing Switzerland.  https://doi.org/10.1007/978-3-319-11017-2_29
  13. 13.
    Recognizing digits with OpenCV and Python. https://www.pyimagesearch.com/2017/02/13/recognizing-digits-with-opencv-and-python/. Accessed 06 Apr 2018

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Institute of Engineering Processes Automation and Integrated Manufacturing Systems, Faculty of Mechanical EngineeringSilesian University of TechnologyGliwicePoland

Personalised recommendations