ABSTRACT
Tongue image extraction is a primary and fundamental step in the objectification of the tongue diagnoses of traditional Chinese medicine. Aiming at the problems that some methods need to adjust parameters by manual and their accuracy and efficiency are not high, in this paper, a kind of novel concurrent d-search algorithm fusing multi-dimensional information is proposed for the application of tongue image extraction in order to realize automatic, fast and accurate tongue image extraction. In our method, original tongue image is considered as a pixel network. Starting from the seed pixel of central region, according to the intensity, hue and relative position information of the pixels of tongue image, a novel d-search algorithm is utilized to search tongue body region in original tongue image. Because tongue coating is surrounded by tongue substance in most cases, we propose a novel position operator to decide whether current pixel is surrounded by tongue substance in our d-search algorithm so as to extract tongue image with coating accurately. In the same time, to improve the efficiency of our algorithm, the original tongue image is divided into several regions (i.e. sub-images), concurrent techniques are utilized to search different tongue regions separately, so as to get the tongue image templates of different regions quickly, and then they are combined into one template. In addition, morphological operators including closing and opening are applied to the template after combination, so that small holes in the template image can be filled. In the end, an and operation is applied to the ultimate template and original tongue image, in order to get extracted tongue image. In our study, we conduct the comparison experiments of 4 methods including the method of manual extraction, our method, tongue image extraction based on greedy rules and tongue image extraction based on random walk. The comparison experiments are conducted from the aspects of accuracy and efficiency. The tongue images of the 5 typical kinds of colors including light red, light white, red, deep red and purple are utilized to test the 3 methods. Furthermore, a tongue image with thick white coating and a tongue image with thick yellow coating are also utilized to test the 3 methods. These tongue image samples cover all kinds of tongue colors and include tongue images with or without tongue coating. Therefore, the results of our tests are persuasive. In comparative experiments, our method achieves quite good effect in the aspect of accuracy and is superior to the current 2 methods in the aspect of efficiency, which can meet the accuracy and efficiency requirements of the objectification of tongue diagnoses. And we have implemented automatic tongue image extraction without adjusting any parameters by manual.
- Wei Yuan and Changsong Liu. 2019. Cascaded CNN for real-time tongue segmentation based on key points localization. In Proceedings of 4th IEEE International Conference on Big Data Analytics (ICBDA), Suzhou, 303--307. DOI: 10.1109/ICBDA.2019.8712834.Google ScholarCross Ref
- Yushan Xue, Xiaoqiang Li, Pin Wu, Jide Li, Lu Wang and Weiqin Tong. 2018. Automated tongue segmentation in Chinese medicine based on deep learning. Lecture Notes in Computer Science, 11307, 542--553. DOI: https://doi.org/10.1007/978-3-030-04239-4_49.Google ScholarDigital Library
- Jiang Li, Baochuan Xu, Xiaojuan Ban, Ping Tai and Boyuan Ma. 2017. A tongue image segmentation method based on enhanced HSV convolutional neural network. Lecture Notes in Computer Science, 10451, 252--260. DOI: https://doi.org/10.1007/978-3-319-66805-5_32.Google ScholarCross Ref
- Meng Liu, Xiting Wang, Lu Zhou, Libo Tan, Jie Li, Jing Guan and Feng Li. 2019. Study on extraction and recognition of Traditional Chinese Medicine tongue manifestation based on deep learning and migration learning. Journal of Traditional Chinese Medicine, 60, 10, 30--35. DOI: 10.13288/j.11-2166/r.2019.10.007.Google Scholar
- Liran Wang, Yiping Tang, Peng Chen, Xia He and Gongping Yuan. 2018. Two-phase convolutional neural network design for tongue segmentation. Journal of Image and Graphics, 23, 10, 1571--1581. DOI: CNKI: SUN: ZGTB.0.2018-10-012.Google Scholar
- Panling Qu, Hui Zhang, Li Zhuo, Jing Zhang and Guoying Chen. 2017. Automatic tongue image segmentation for traditional Chinese medicine using deep neural network. Lecture Notes in Computer Science, 10361, 247--259. DOI: https://doi.org/10.1007/978-3-319-63309-1_23.Google ScholarCross Ref
- Zhihua Su, Jianguo Wei, Qiang Fang, Jianrong Wang and Kiyoshi Honda. 2018. Tongue segmentation with geometrically constrained snake model. In Proceedings of the Annual Conference of the International Speech Communication Association, Hyderabad, 3117--3121. DOI: 10.21437/Interspeech.2018-1108.Google ScholarCross Ref
- Saparudin, Erwin and Muhammad Fachrurrozi. 2016. Tongue segmentation using active contour model. In Proceedings of 3rd IAES International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), Semarang, 190. DOI: 10.1088/1757-899X/190/1/012041.Google Scholar
- Jingwei Guo, Yikang Yang, Qingwei Wu, Jionglong Su and Fei Ma. 2016. Adaptive active contour model based automatic tongue image segmentation. In Proceedings of 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), Datong, 1386--1390. DOI: 10.1109/CISP-BMEI.2016.7852933.Google ScholarCross Ref
- Mingfeng Zhu and Jianqiang Du. 2011. A novel approach for color tongue image fast segmentation based on level sets. Advanced Materials Research, 341--342, 714--719. DOI: https://doi.org/10.4028/www.scientific.net/AMR.341-342.714.Google Scholar
- Muhammad Fachrurrozi, Erwin, Saparudin, Nur Rahma Dela, Yenita Mahyudin and Hardians Kesuma Putra. 2019. Tongue image segmentation using hybrid multilevel otsu thresholding and harmony search algorithm. Journal of Physics Conference Series, 1196, 1. DOI: 10.1088/1742-6596/1196/1/012072.Google ScholarCross Ref
- Bin Liu, Guangqin Hu, Xinfeng Zhang and Yiheng Cai. 2018. Application of an improved grab cut method in tongue image segmentation. Lecture Notes in Computer Science, 10956, 484--495. DOI: 10.1007/978-3-319-95957-3_51.Google ScholarDigital Library
- Yishuan Huang, Qi Zhang and Zhanpeng Huang. 2018. Tongue image segmentation based on the sub-block region growing algorithm. In Proceedings of 5th International Conference on Information Science and Control Engineering (ICISCE), Zhengzhou, 578--581. DOI: 10.1109/ICISCE.2018.00125.Google Scholar
- Zuoyong Li, Zhaochai Yu, Weixia Liu, Yong Xu, Daoqiang Zhang and Yong Cheng. 2017. Tongue image segmentation via color decomposition and thresholding. In Proceedings of 4th International Conference on Information Science and Control Engineering (ICISCE), Changsha. DOI: 10.1109/CISP-BMEI.2017.8302207.Google ScholarCross Ref
- Tao Xie, Chunming Xia, Feifei Chen, Shengli Zhang and Yue Zhang. 2016. A method of tongue image segmentation based on kernel FCM. In Proceedings of 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI), Datong, 319--324. DOI: 10.1109/CISP-BMEI.2016.7852729.Google ScholarCross Ref
- Mingfeng Zhu, Jianqiang Du, Kang Zhang and Chenghua Ding. 2009. A novel approach for tongue image extraction based on combination of color and space information. In Proceedings of International Conference on Bioinformatics and Biomedical Engineering (ICBBE), Beijing. DOI: 10.1109/ICBBE.2009.5162213.Google ScholarCross Ref
- Mingfeng Zhu and Jianqiang Du. 2013. A novel approach for color tongue image extraction based on random walk algorithm. Applied Mechanics and Materials, 462--463, 338--342. DOI: 10.4028/www.scientific.net/AMM.462-463.338.Google Scholar
- Mingfeng Zhu, Jianqiang Du, Chenghua Ding and Yangming He. 2015. Improved fast random walk tongue image extraction algorithm. Journal of Computer-Aided Design & Computer Graphics, 27, 4, 633--639. DOI: CNKI: SUN: JSJF.0.2015-04-009.Google Scholar
Index Terms
- Fast Tongue Image Extraction Fusing Multi-dimensional Information and Concurrent D-search Algorithm
Recommendations
Multi-stage Multi-modalities Fusion of Lip, Tongue and Acoustics Information for Speech Recognition
AICCC '23: Proceedings of the 2023 6th Artificial Intelligence and Cloud Computing ConferenceThe ultrasound tongue imaging (UTI) and lip video are commonly used to capture the acoustic clue to obtain the visual articulatory information of speakers. However, single signal of UTI or lip video cannot completely represent the pronunciation process ...
Deep unsupervised endoscopic image enhancement based on multi-image fusion
Highlights- For the first time,the advantages of Gamma derived image, CLAHE derived image and LIME derived image arecombinedwith a deep learning networktoobtainenhanced ...
Abstract Background and objectiveA deep unsupervised endoscopic image enhancement method is proposed based on multi-image fusion to achieve high quality endoscope images from poorly illuminated, low contrast and color deviated ...
The Research of Image Mosaic Techniques Based on Optimized SIFT Algorithm
RSVT '19: Proceedings of the 2019 International Conference on Robotics Systems and Vehicle TechnologyImage mosaic refers to the process of stitching multiple images those have overlapping areas of small perspective and low resolution into a panoramic image with high resolution and wide perspective through the corresponding image registration and fusion ...
Comments