Real-world Pill Segmentation based on Superpixel Merge using Region Adjacency Graph

Sudhir Sornapudi, R. Joe Stanley, Jason Hagerty, William V. Stoecker

2017

Abstract

Misidentified or unidentified prescription pills are an increasing challenge for all caregivers, both families and professionals. Errors in pill identification may lead to serious or fatal adverse events. To respond to this challenge, a fast and reliable automated pill identification technique is needed. The first and most critical step in pill identification is segmentation of the pill from the background. The goals of segmentation are to eliminate both false detection of background area and false omission of pill area. Introduction of either type of error can cause errors in color or shape analysis and can lead to pill misidentification. The real-world consumer images used in this research provide significant segmentation challenges due to varied backgrounds and lighting conditions. This paper proposes a color image segmentation algorithm by generating superpixels using the Simple Linear Iterative Clustering (SLIC) algorithm and merging the superpixels by thresholding the region adjacency graphs. Post-processing steps are given to result in accurate pill segmentation. The segmentation accuracy is evaluated by comparing the consumer-quality pill image segmentation masks to the high quality reference pill image masks.

References

  1. Achanta, R., Shaji, A., and Smith, K. (2012). SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. Pattern Analysis and Machine Intelligence, 34(11):2274-2281.
  2. Boykov, Y. Y. and Jolly, M. P. (2001). Interactive graph cuts for optimal boundary amp; region segmentation of objects in n-d images. In Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on, volume 1, pages 105-112 vol.1.
  3. Caban, J. J., Rosebrock, A., and Yoo, T. S. (2012). Automatic identification of prescription drugs using shape distribution models. In 2012 19th IEEE International Conference on Image Processing, pages 1005-1008.
  4. Comaniciu, D. and Meer, P. (2002). Mean Shift: A Robust Approach Toward Feature Space Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5):603-619.
  5. Dailymedplus (2016). Medicos consultants. http://www.dailymedplus.com. Last accessed on Aug 28, 2016.
  6. Drugs.com (2016). Pill identifier. https://www.drugs.com/imprints.php. Last accessed on Aug 28, 2016.
  7. Felzenszwalb, P. F. and Huttenlocher, D. P. (2004). Efficient graph-based image segmentation. International Journal of Computer Vision, 59(2):167-181.
  8. Kanungo, T., Mount, D. M., Netanyahu, N. S., Piatko, C. D., Silverman, R., and Wu, A. Y. (2002). An efficient k-means clustering algorithm: analysis and implementation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7):881-892.
  9. (2016). National library : Pill image recognition http://pir.nlm.nih.gov/challenge/. Last on May 31, 2016.
  10. Pillbox (2016). Prototype pill identification system. http://pillbox.nlm.nih.gov/. Last accessed on Aug 28, 2016.
  11. Shi, J. and Malik, J. (2000). Normalized Cuts and Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8):888-905.
  12. Tremeau, A. and Colantoni, P. (2000). Regions adjacency graph applied to color image segmentation. IEEE Transactions on Image Processing, 9(4):735-744.
  13. van der Walt, S., Schönberger, J. L., Nunez-Iglesias, J., Boulogne, F., Warner, J. D., Yager, N., Gouillart, E., Yu, T., and the scikit-image contributors (2014). scikit-image: image processing in Python. PeerJ, 2:e453.
  14. WebMD (2016). Pill identification. http://www.webmd.com/pillidentification/default.html. Last accessed on Aug 28, 2016.
  15. Xu, R. and Wunsch, D. (2005). Survey of clustering algorithms. IEEE Transactions on Neural Networks, 16(3):645-678.
Download


Paper Citation


in Harvard Style

Sornapudi S., Joe Stanley R., Hagerty J. and V. Stoecker W. (2017). Real-world Pill Segmentation based on Superpixel Merge using Region Adjacency Graph . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-225-7, pages 182-187. DOI: 10.5220/0006135801820187


in Bibtex Style

@conference{visapp17,
author={Sudhir Sornapudi and R. Joe Stanley and Jason Hagerty and William V. Stoecker},
title={Real-world Pill Segmentation based on Superpixel Merge using Region Adjacency Graph},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={182-187},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006135801820187},
isbn={978-989-758-225-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, (VISIGRAPP 2017)
TI - Real-world Pill Segmentation based on Superpixel Merge using Region Adjacency Graph
SN - 978-989-758-225-7
AU - Sornapudi S.
AU - Joe Stanley R.
AU - Hagerty J.
AU - V. Stoecker W.
PY - 2017
SP - 182
EP - 187
DO - 10.5220/0006135801820187