Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

A Computer Vision-Based Banknote Recognition System for the Blind with an Accuracy of 98% on Smartphone Videos

  • Received : 2019.04.23
  • Accepted : 2019.05.29
  • Published : 2019.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a computer vision-based banknote recognition system intended to assist the blind. This system is robust and fast in recognizing banknotes on videos recorded with a smartphone on real-life scenarios. To reduce the computation time and enable a robust recognition in cluttered environments, this study segments the banknote candidate area from the background utilizing a technique called Pixel-Based Adaptive Segmenter (PBAS). The Speeded-Up Robust Features (SURF) interest point detector is used, and SURF feature vectors are computed only when sufficient interest points are found. The proposed algorithm achieves a recognition accuracy of 98%, a 100% true recognition rate and a 0% false recognition rate. Although Korean banknotes are used as a working example, the proposed system can be applied to recognize other countries' banknotes.

Keywords

CPTSCQ_2019_v24n6_67_f0001.png 이미지

Fig. 1. A conceptual schematic of the banknote recognition system

CPTSCQ_2019_v24n6_67_f0002.png 이미지

Fig. 2. Reference regions on Korean banknotes indicated by red boxes

CPTSCQ_2019_v24n6_67_f0003.png 이미지

Fig. 3. Sample frames from the video test dataset

CPTSCQ_2019_v24n6_67_f0004.png 이미지

Fig. 4. Input video frame (left) and it’s corresponding foreground binary matrix (right)

CPTSCQ_2019_v24n6_67_f0005.png 이미지

Fig. 5. Rejection of SURF descriptor false matches. (a) SURF descriptor matches (b) After applying a 2-KNN ratio test (0.6) (c) After discarding matches with Euclidean distance > 0.2 (d) After discarding features with more than 1 match

CPTSCQ_2019_v24n6_67_f0006.png 이미지

Fig. 6. Descriptor matches during a video sequence showing the front of a Chon-won (₩1000) banknote

Table 1. Video test dataset used in the experiments

CPTSCQ_2019_v24n6_67_t0001.png 이미지

Table 2. Banknote recognition results

CPTSCQ_2019_v24n6_67_t0002.png 이미지

References

  1. "Blindness and vision impairment," http://www.who.int/mediacentre/factsheets/fs282/ (accessed Apr. 10, 2019)
  2. "Number of Registered Disabled Persons," http://kosis.kr/statHtml/statHtml.do?orgId=117&tblId=DT_11761_N004&conn_path=I2 (accessed Apr. 10, 2019)
  3. Bay, H., et al., "Speeded-up robust features (SURF)," Computer vision and image understanding, Vol. 110, No. 3, pp. 346-359, Nov. 2008. https://doi.org/10.1016/j.cviu.2007.09.014
  4. Pawade, D., P. Chaudhari, and H. Sonkambale, "Comparative study of different paper currency and coin currency recognition method," International Journal of Computer Applications, Vol. 66, No. 23, Jan. 2013.
  5. Hinwood, A., P. Preston, G. Suaning, and N. Lovell, "Bank note recognition for the vision impaired," Australasian Physics & Engineering Sciences in Medicine, Vol. 29, No. 2, pp. 229-233, June 2006. https://doi.org/10.1007/BF03178897
  6. Singh, S., S. Choudhury, K. Vishal, and C.V. Jawahar, "Currency recognition on mobile phones," 2014 22nd International Conference on Pattern Recognition, IEEE, pp. 2661-2666, Aug. 2014.
  7. Hasanuzzaman, F.M., X. Yang, and Y. Tian, "Robust and effective component-based banknote recognition for the blind," IEEE Transactions on Systems, Man, and Cybernetics, Vol. 42, No. 6, pp. 1021-1030, Apr. 2012. https://doi.org/10.1109/TSMCC.2011.2178120
  8. Dunai Dunai, L., Chillaron Perez, M., Peris-Fajarnes, G., and Lengua Lengua, I., "Euro Banknote Recognition System for Blind People," Sensors, Vol. 17, No. 1, pp. 1-14, Jan. 2017. https://doi.org/10.1109/JSEN.2017.2761499
  9. Garcia-Lamont, F., J. Cervantes, and A. Lopez, "Recognition of Mexican banknotes via their color and texture features," Expert Systems with Applications, Vol. 39, No. 10, pp. 9651-9660, Aug. 2012. https://doi.org/10.1016/j.eswa.2012.02.132
  10. Ren, Y., M. Nguyen, and W.Q. Yan, "Real-Time Recognition of Series Seven New Zealand Banknotes," International Journal of Digital Crime and Forensics (IJDCF), Vol. 10, No. 3, pp. 50-65, July 2018. https://doi.org/10.4018/IJDCF.2018070105
  11. Ko, B.C., "A Brief Review of Facial Emotion Recognition Based on Visual Information," Sensors, Vol. 18, No. 2, pp. 1-20, Jan. 2018. https://doi.org/10.1109/JSEN.2018.2870228
  12. Pham, T.D., D.T. Nguyen, C. Park, and K.R. Park, "Deep Learning-Based Multinational Banknote Type and Fitness Classification with the Combined Images by Visible-Light Reflection and Infrared-Light Transmission Image Sensors," Sensors, Vol. 19, No. 4, pp. 1-28, Feb. 2019. https://doi.org/10.1109/JSEN.2019.2925985
  13. Hofmann, M., P. Tiefenbacher, and G. Rigoll. "Background segmentation with feedback: The Pixel-Based Adaptive Segmenter," Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE, June 2012.
  14. Viola, P. and M. Jones, "Rapid object detection using a boosted cascade of simple features," Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, Dec. 2001.
  15. Lowe, D.G., "Distinctive image features from scale-invariant keypoints," International journal of computer vision, Vol. 60, No. 2, pp. 91-110, Nov. 2004. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  16. Zhou, W., H. Li, and Q. Tian, "Multimedia Content-Based Visual Retrieval," Academic Press Library in Signal Processing, Vol. 5, pp. 383-416, Jan. 2014. https://doi.org/10.1016/B978-0-12-420149-1.00012-0
  17. Muja, M. and D. Lowe, "Fast approximate nearest neighbors with automatic algorithm configuration," International Conference on Computer Vision Theory and Applications VISAPP, Vol. 2, pp. 331-340, Feb. 2009.
  18. Krizhevsky, A., I. Sutskever, and G.E. Hinton, "Imagenet classification with deep convolutional neural networks," Advances in neural information processing systems, pp. 1097-1105, Dec. 2012.