A FAST AND EFFECTIVE SEGMENTATION ALGORITHM WITH AUTOMATIC REMOVAL OF INEFFECTIVE FEATURES ON TONGUE IMAGES

Authors

  • Nur Diyana Kamarudin Embedded System Research Lab, Department of Electronics System Engineering, Malaysia-Japan International Institute of Technology, Malaysia
  • Chia Yee Ooi Embedded System Research Lab, Department of Electronics System Engineering, Malaysia-Japan International Institute of Technology, Malaysia
  • Tadaaki Kawanabe Oriental Medicine (Kampo) Research Center, Kitasato University, Japan
  • Xiaoyu Mi Fujitsu Laborataries Ltd., Japan
  • Hiroshi Odaguchi Oriental Medicine (Kampo) Research Center, Kitasato University, Japan
  • Toshihiko Hanawa Oriental Medicine (Kampo) Research Center, Kitasato University, Japan
  • Fuminori Kobayashi Embedded System Research Lab, Department of Electronics System Engineering, Malaysia-Japan International Institute of Technology, Malaysia

DOI:

https://doi.org/10.11113/jt.v78.7129

Keywords:

Kampo medicine, tongue diagnosis, segmentation algorithm, threshold brightness analysis, tongue color analysis

Abstract

In computerized tongue diagnostic system, tongue body color has been one of the essential features that contain rich information for diagnosing disease. However, tongue body color measurement can be influenced by the tongue coating color and other ineffective features such as significant coatings, shadows, teeth mark and crackles. This paper presents a fast processing segmentation algorithm using Hue, Saturation and Value (HSV) color space transformation to segment and remove these ineffective features aiming to have an accurate color measurement for online diagnosis. The newly devised Brightness Conformable Multiplier (BCM) has been proposed to automatically adjust the threshold brightness based on three conditions of lower perioral area’s brightness, ; when  is smaller than its standard deviation,  is greater than its standard deviation and otherwise. Besides, the Modified Sequential Algorithm (MSA) has been proposed to offer fast processing algorithm of 1.445 seconds and better segmentation. The successful segmentation rate was recorded as 90%. Furthermore, color measurement is carried out on the segmented samples and the analysis showed that the dispersion range of tongue body color measurement is small. This indicates a convincing result as the color boundary among light red, red and deep red tongue has been determined precisely. 

References

Yamamoto, S. 2011. Regional Image Analysis of the Tongue Color Spectrum. International Joint Conference of Computer Assisted Radiology and Surgery (J CARS). 6: 143-152.

Nakaguchi, T., K. Takeda, Y. Ishikawa, T. Oji, S. Yamamoto, N. Tsumura, K. Ueda, K. Nagamine, T. Namiki, and Y. Miyake. 2015. Proposal for a New Noncontact Method for Measuring Tongue Moisture to Assist in Tongue Diagnosis and Development of the Tongue Image Analyzing System which can Separately Record the Gloss Components of the Tongue. BioMed Research International. 2015: 10.

Yamamoto, S., N. Tsumura, T. Nakaguchi, T. Namiki, Y. Kasahara, K. Ogawa-Ochiai, K. Terasawa, and Y. Miyake. 2011. Principal Component Vector Rotation of the Tongue Color Spectrum To Predict “Mibyou†(Disease-Oriented State). International Journal of Computer Assisted Radiology and Surgery. 6(2): 209-215.

Yamamoto, S., Y. Ishikawa, T. Nakaguchi, K. Ogawa-Ochiai, N. Tsumura, Y. Kasahara, T. Namiki, and Y. Miyake. 2012. Temporal Changes in Tongue Color as Criterion for Tongue Diagnosis in Kampo Medicine. Research in Complementary Medicine. 19(2): 80-85.

Oji, T., T. Namiki, T. Nakaguchi, K. Kaeda, K. Takeda, M. Nakamura, H. Okamoto, and Y. Hirasaki. 2014. Study of Factors Involved in Tongue Color Diagnosis by Kampo Medical Practitioners Using the Farnsworth-Munsell 100 Hue Test and Tongue Color Images. Evidence-Based Complementary and Alternative Medicine. 2014: 9.

Watsuji, T., S. Masaki, S. Shinohara, F. Fukuda, T. Yano, and T. Mineo. 2008. Availability of The Health Evaluation on Oriental Medicine as Integrative Medicine In The Health Screening. Biomedical Fuzzy System Association. 2008(21): 88-91.

Sato, Y. 2005. Introduction to Kampo: Japanese Traditional Medicine. Japan: Elsevier.

Morohashi, M., and Maeda, M. 2003. Crosspoint between Western and Kampo Medicines in Dermatological Field: Analysis by using Various Measurement Useful Instruments for Establishment of Evidence-based Medicine (EBM). Japanese Journal of Oriental Medicine. 54(3): 591-592.

Odaguchi, H., A. Wakasugi, H. Ito, H. Shoda, Y. Gono, K. Sung-Joon, M. Endo, T. Oikawa, F. Sakai, and T. Hanawa. 2007. Statistical Analysis of the Findings in Patients Responded to Goshuyuto. Kampo Medicine. 58(6):1099-1105.

Wei, C. C., C. H. Wang, and S. W. Huang. 2010. Using Threshold Method to Separate the Edge, Coating and Body of Tongue In Automatic Tongue Diagnosis. Sixth International Conference on Networked Computing and Advanced Information Management (NCM). 1-12.

Xiaoqiang, L., L. Jide, and W. Dan. 2014. Automatic Tongue Image Segmentation Based on Histogram Projection and Matting. IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

Yu-cheng, H., C. Ying-ching, L. Lun-chien, and J. Y. Chiang. 2010. Automatic Tongue Feature Extraction. International Conference on Computer Symposium (ICS). 936-941.

Jian-qiang, D., L. Yang-sheng, Z. Ming-feng, Z. Kang, and D. Cheng-hua. 2008. A Novel Algorithm of Color Tongue Image Segmentation Based on HSI. International Conference on BioMedical Engineering and Informatics (BMEI). 733-737.

Liu, Z., D. Zhang, Y. Jing-qi, L. Qing-li, and T. Qun-lin. 2007. Classification of Hyperspectral Medical Tongue Images for Tongue Diagnosis. Computerized Medical Imaging and Graphics. 31(8): 672-678.

Manolakis, D. and G. Shaw. 2002. Detection Algorithms for Hyperspectral Imaging Applications. IEEE Signal Processing Magazine. 19(1): 29-43.

Li, Q. and Z. Liu. 2009. Tongue Color Analysis and Discrimination Based on Hyperspectral Images. Computerized Medical Imaging and Graphics. 33(3): 217-221.

Li, Q., H. Liu, Y. Guan, and L. Xu. 2011. Sublingual Vein Extraction Algorithm Based on Hyperspectral Tongue Imaging Technology. Computer Medical Imaging and Graph. 35(3):179-185.

Shi, M., G. Li, and F. Li. 2013. C2G2FSnake: Automatic Tongue Image Segmentation Utilizing Prior Knowledge. SCI CHINA Inform Science. 9: 1-14.

Miaojing, S., L. Guozheng, L. fufeng, and X. Chao. 2012. A Novel Tongue Segmentation Approach Utilizing Double Geodesic Flow. 7th International Conference on Computer Science & Education (ICCSE). 21-25.

Shengyang, Y., Y. Jie, W. Yonggang, and Z. Yan. 2007. Color Active Contour Models Based Tongue Segmentation in Traditional Chinese Medicine. The 1st International Conference on Bioinformatics and Biomedical Engineering (ICBBE). 1065-1068.

Li, W., S. Hu, S. Wang, and S. Xu. 2009. Towards the Objectification of Tongue Diagnosis: Automatic Segmentation of Tongue Image. Conference Proc IEEE Ind. Electron. 2009: 2121-2124.

Chao, L. and S. Dongcheng. 2012. A Prior Knowledge-Based Algorithm for Tongue Body Segmentation. International Conference on Computer Science and Electronics Engineering (ICCSEE).646-649.

Pang, B., D. Zhang, and K. Wang. 2005. The Bi-Elliptical Deformable Contour and Its Application to Automated Tongue Segmentation in Chinese Medicine. IEEE Transactions on Medical Imaging. 24(8): 946-956.

Xingzheng, W., B. Zhang, Y. Zhimin, W. Haoqian, and D. Zhang. 2013. Statistical Analysis of Tongue Images for Feature Extraction and Diagnostics. IEEE Transactions on Image Processing. 22(12): 5336-5347.

Miao-jing, S., L. Guo-zheng. L. Fufeng, and X. Chao. 2014. Computerized Tongue Image Segmentation via the Double Geo-Vector Flow. Chinese Medicine. 9(1): 1-10.

Andrew, A. M. 2001. Practical Algorithms for Image Analysis: Description, Examples, and Code, by Michael Seul, Lawrence O'Gorman and Michael J. Sammon. Cambridge University Press. Robotica. 19(1):109-111.

Sawabe, Y., T. Matsunaga, and S. Rokugawa. 2006. Automated Detection and Classification of Lunar Craters using Multiple Approaches. Advances in Space Research. 37(1): 21-27.

Xingzheng, W. and D. Zhang. 2010. An Optimized Tongue Image Color Correction Scheme. IEEE Transactions on Information Technology in Biomedicine. 14(6): 1355-1364.

Bala, R., G. Sharma, V. Monga, and J. P. Van De Capelle. 2005. Two-Dimensional Transforms for Device Color Correction and Calibration. IEEE Transactions on Image Processing. 14(8): 1172-1186.

Jiatuo, X., T. Liping, Z. Zhifeng, and Q. Xipeng. 2008. A Medical Image Color Correction Method Based on Supervised Color Constancy. IEEE International Symposium on IT in Medicine and Education (ITME).

Xingzheng, W. and D. Zhang. 2013. A New Tongue Color Checker Design by Space Representation for Precise Correction. IEEE Journal of Biomedical and Health Informatics. 17(2): 381-391.

Young-Chang, C. and J. F. Reid. 1996. RGB Calibration for Color Image Analysis in Machine Vision. IEEE Transactions on Image Processing. 5(10): 1414-1422.

Wangmeng, Z., W. Kuanquan, D. Zhang, and Z. Hongshi. 2004. Combination of Polar Edge Detection and Active Contour Model for Automated Tongue Segmentation. Third International Conference on Image and Graphics (ICIG'04).

Downloads

Published

2016-07-25

Issue

Vol. 78 No. 8: August 2016

Section

Science and Engineering

License

Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.

How to Cite

A FAST AND EFFECTIVE SEGMENTATION ALGORITHM WITH AUTOMATIC REMOVAL OF INEFFECTIVE FEATURES ON TONGUE IMAGES. (2016). Jurnal Teknologi, 78(8). https://doi.org/10.11113/jt.v78.7129