single-jc.php

JACIII Vol.23 No.2 pp. 261-267
doi: 10.20965/jaciii.2019.p0261
(2019)

Paper:

A Sketch Recognition Algorithm Based on Bayesian Network and Convolution Neural Network

Xiang Hou

School of Intelligent Manufacturing, Sichuan University of Arts and Science
No.519 Tashi Road, Dazhou, Sichuan 635000, China

Received:
May 27, 2018
Accepted:
July 24, 2018
Published:
March 20, 2019
Keywords:
Bayesian network, stroke grouping, convolution neural network, sketch recognition
Abstract
A Sketch Recognition Algorithm Based on Bayesian Network and Convolution Neural Network

The accurate crowd counting statistics in scenic spots

Most of the existing sketch recognition algorithms are used to restrict the user’s drawing habits to achieve the stroke grouping and recognition. In order to solve the problem, a new sketch recognition algorithm based on Bayesian network and convolution neural network (CNN) is proposed. First, the input sketch is processed by Gaussian low-pass filter and a smoother stroke can be obtained. The stroke of continuous input is divided, then the Bayesian network and CNN are performed on stroke recognition respectively. The recognition result of Bayesian network is adopted when the reliability of stroke is larger than the threshold, otherwise recognition result of CNN will be adopted. The experiment result shows that the proposed algorithm is effective in circuit symbol recognition. The recognition rate was achieved 80.34% in the drawing process, and the final recognition rate was achieved 93.48%.

Cite this article as:
X. Hou, “A Sketch Recognition Algorithm Based on Bayesian Network and Convolution Neural Network,” J. Adv. Comput. Intell. Intell. Inform., Vol.23, No.2, pp. 261-267, 2019.
Data files:
References
  1. [1] D. Rubine, “Specifying Gestures by Example,” ACM SIGGRAPH on Computer Graphics, Vol.25, No.4, pp. 329-337, 1991.
  2. [2] S. Simhon and G. Dudek, “Sketch Interpretation and Refinement Using Statistical Models,” Proc. 15th Eurographics Conf. on Rendering Techniques (EGSR 04), pp. 23-32, 2004.
  3. [3] G. Fang, L. He, and F. Kong, “Research on Technologies of Computer Aided Sketching Design,” Computer Engineering, Vol.32, No.18, pp.1 2, 2006.
  4. [4] D. Anderson, C. Bailey, and M. Skubic, “Hidden Markov model symbol recognition for sketch-based interfaces,” AAAI Fall Symp., 2004.
  5. [5] T. Kurtoglu and T. F. Stahovich, “Interpreting Schematic Sketches Using Physical Reasoning,” Proc. of AAAI Spring Symp. on Sketch Understanding, pp. 78-85, 2002.
  6. [6] T. M. Sezgin and R. Davis, “HMM-based efficient sketch recognition,” Proc. of the 10th Int. Conf. on Intelligent User Interfaces, pp.281-283, 2005.
  7. [7] M. J. Fonseca, C. Pimentel, and J. A. Jorge, “CALI: An Online Scribble Recognizer for Calligraphic Interfaces,” Proc. of AAAI Spring Symp. on Sketch Understanding, pp. 51-58, 2002.
  8. [8] L. Gennari, L. B. Kara, T. F. Stahovich, and K. Shimada, “Combining Geometry and Domain Knowledge to Interpret Hand-drawn Diagrams,” Computers & Graphics, Vol.29, No.4, pp. 547-562, 2005.
  9. [9] Z. Sun, G. Feng, and R. Zhou, “Techniques for Sketch-Based User Interface: Review and Research,” J. of Computer-Aided Design & Computer Graphics, Vol.17, No.9, pp. 1889-1899, 2005.
  10. [10] Z. Sun, X. Xu, J. Sun, and X. Jin, “Sketch-Based Graphic Input Tool for Conceptual Design,” J. of Computer-Aided Design & Computer Graphics, Vol.15, No.9, pp. 1145-1152, 2003.
  11. [11] B. Song et al., “Three-Tiered Recognition Method of Pen-Based Sketch,” J. of Computer-Aided Design & Computer Graphics, Issue 6, pp. 753-758, 2004.
  12. [12] C. Alvarado and R. Davis, “Dynamically constructed Bayes nets for multi-domain sketch understanding,” ACM SIGGRAPH 2007 courses, Article No.33, 2007.
  13. [13] S.-Z. Liao, X.-J. Wang, and J.-L. Lu, “An Incremental Bayesian Approach to Sketch Recognition,” Proc. of 2005 Int. Conf. on Machine Learning and Cybernetics, Vol.7, pp. 4549-4553, 2005.
  14. [14] L.-W. Jin, Z.-Y. Zhong, Z. Yang, Z.-C. Xie, and J. Sun, “Applications of Deep Learning for Handwritten Chinese Character Recognition: A Review,” Acta Automatica Sinica, Vol.42, No.8, pp. 1125-1141, 2016.
  15. [15] A. S. Razavian, H. Azizpour, J. Sullivan and S. Carlsson, “CNN features off-the-shelf: an astounding baseline for recognition,” 2014 IEEE Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 512-519, 2014.
  16. [16] J. Vijay, S. Mita, Z. Liu, and B. Qi, “Pedestrian detection in thermal images using adaptive fuzzy C-means clustering and convolutional neural networks,” Proc. of 2015 14th IAPR Int. Conf. on Machine Vision Applications (MVA), pp. 246-249, 2015.
  17. [17] J. Cai, J. Y. Cai, X. D. Liao, et al., “Preliminary study on hand gesture recognition based on convolutional neural network,” Computer Systems & Applications, Vol.24, No.4, pp. 113-117, 2015.
  18. [18] Y. Goldberg, “Neural network methods for natural language processing,” Synthesis Lectures on Human Language Technologies, Vol.10, No.1, pp. 1-309, 2017.
  19. [19] G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science, Vol.313, No.5786, pp. 504-507, 2006.
  20. [20] M.’A. Ranzato, C. Poultney, S. Chopra, and Y. LeCun, “Efficient learning of sparse representations with an energy-based model,” Proc. of the 19th Int. Conf. on Neural Information Processing Systems, pp. 1137-1144, 2007.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, IE9,10,11, Opera.

Last updated on Apr. 22, 2019