• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.15 no.2
• /
• pp.149-158
• /
• 2011

Objectives: The objective of this study is to compare the colour intensity of tongue body and that of tongue coat under the visible light and the ultraviolet light. Methods: We selected 7 subjects with completely or partially peeled tongue coat among the recruited 94 adults for the experiment. We took each tongue picture under the visible light and the ultraviolet light (315-400 nm) and then extracted sample images from the tongue body and tongue coat regions. Mean, median and mode of colour intensity from the sample images were calculated in 256 RGB system. Results: The green and the blue colour intensities of the tongue coats were significantly higher than those of the tongue bodies under the visible light. In all channels, the red, green and blue, the colour intensities of the tongue coats were significantly higher than those of the tongue bodies under the ultraviolet light. The colour differences between tongue coats and tongue bodies under the ultraviolet light were significantly higher than the colour differences under the visible light. Especially the colour difference under the ultraviolet light was highest in the green channel. Conclusions: We suggested that green colour image of the RGB system taken under the ultraviolet light could be used for more easy separating tongue coat region from tongue body.

• Journal of Biomedical Engineering Research
• /
• v.44 no.4
• /
• pp.242-254
• /
• 2023

Although upper respiratory tract infections (URTIs) are common diseases, there have been no studies of their relationship with the indices obtained from tongue image analyses. The purpose of this study was to identify a tongue index through an analysis of tongue images (TIs) showing significant changes before and after treatment in patients with URTIs. A computerized tongue image acquisition system was developed to acquire TIs from subjects in the same environment. An image was taken from each of 39 URTI patients and 39 healthy controls. For the patients, images were acquired before and after treatment to identify changes. The tongue area was classified into a tongue body and a tongue coating, and the coating ratio between the two areas, the average value of the colour of each area, and teeth marks were calculated. No significant difference was observed in age or sex between the URTI patients and control participants. Heart rates were slightly different. The analysis of TIs showed that the luminance of the tongue coating and the coating area ratio were decreased, while the reddish value of the tongue body at the centre area increased as the treatment progressed. Tongue coating and body in URTIs had different colour and shape from those in the normal. It is expected that this result will contribute not only to the objectification of traditional Chinese medicine but also to diagnostic methods that do not involve face-to-face physician visit during the pandemic.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.34 no.4
• /
• pp.191-200
• /
• 2020

The purpose of this pilot study was to examine the effect of tongue color change due to food ingestion on tongue diagnosis by both Korean Medicine doctors and digital tongue diagnosis system. In order to obtain objective and quantitative data, we used digital camera to collect the data. Prior to our investigation, we conducted a brief survey of 26 Korean Medicine doctors and found out that tongue diagnosis is frequently used and food-stained tongue could be commonly observed in clinics. Depending on their color, viscosity, and amount of intake, various foods caused stains with different colors and thicknesses. Also, duration and amount of food stain on tongue were different from person to person. Since coffee-stained tongue was the most frequently observed one in clinics according to the survey, we used coffee to evaluate the effect of food-stained tongue on tongue diagnosis. Korean Medicine doctors tended to interpret coffee-stained tongue as having yellow tongue coat but their judgement on tongue body color did not differ in spite of the coffee stains. Meanwhile, tongue diagnosis system algorithm tended to judge coffee-stained tongue as having normal but yellowish tongue coat and reddish tongue body. Altogether, food color on tongue can influence tongue diagnosis outcomes. Further research is needed in order to develop more efficient tongue diagnosis algorithm and digital medical service system.

• The Journal of the Society of Stroke on Korean Medicine
• /
• v.9 no.1
• /
• pp.1-7
• /
• 2008

Objectives : We questioned whether the tongue diagnosis is effective for judging seriousness of cerebrovascular accidents. This study is about the relationship between tongue diagnosis and National Institute of Health Stroke Scale(NIHSS) in acute stroke patients. Methods : 738 subjects were recruited from the patients admitted to the department of internal medicine at Kyung-Hee University oriental medical center, Kyung-Hee University East-West Neo Medical Center, Kyungwon university Incheon oriental medical center, Kyungwon university Songpa oriental medical center and DongGuk university Ilsan oriental medical center from April 2007 to August 2008. We looked at the tongue as in three dimensions of tongue color, tongue fur color and tongue body. And, we calculated NIHSS means according to the subtypes of three dimensions. Results : 1. In the Tongue color, from the most commom to least common colors were pale red, red, pale, bluish purple, and ect. The NIHSS mean score of red is significantly higher than pale and pale red. 2. In the Tongue fur color, white fur was the most common, and then yellow fur, etc. There is no significant difference among three subtypes in the NIHSS mean score. 3. In the Tongue body, etc. is the most common, followed by teeth-marked tongue, enlarged tongue, blood patchy tongue, and mirror tongue. The NIHSS mean score of teeth-marked tongue is significantly lower than blood patchy tongue and mirror tongue. Conclusions : The tongue color and the tongue body are useful indexes for judging seriousness of cerebrovascular accidents presented by NIHSS. But in our study, the tongue fur color was not useful. Further study is necessary on the tongue fur.

• Journal of Multimedia Information System
• /
• v.6 no.2
• /
• pp.99-106
• /
• 2019

In traditional Chinese medical (TCM) science, tongue images can be observed for medical diagnosis; however, the tongue diagnosis of TCM is influenced by the subjective factors of doctors, and the diagnosis results vary from person to person. Quantitative TCM tongue diagnosis can improve the accuracy of diagnosis and increase the application value. In this paper, digital image processing and pattern recognition technologies are employed on mobile device to classify tongue images collected in different health states. First, through grayscale integral projection processing, the trough is found to localize the tongue body. Then the tongue body image is transferred from RGB color space to HSV color space, and the average H and S values are considered as the color features. Finally, the diagnosis results are obtained according to the relationship between the color characteristics and physical symptoms.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.30 no.5
• /
• pp.320-326
• /
• 2016

Tongue diagnosis is convenient and non-invasive method to examine the body's functional condition, and it has been frequently used in traditional Korean Medicine (KM). The aim of this study was to investigate the difference of the tongue color assessed by computerized tongue image analysis system (CTIS) between the common cold (CC) patients and healthy subjects. A total of 85 participants, including 45 CC patients without organic diseases and 40 healthy subjects, were asked to complete the CC symptom questionnaire. A tongue image was acquired by using CTIS. Color differences in Commission Internationale de l'Eclairage (CIE) L*, a* and b* between the CC patient group and the control group were analyzes by using paired t-test analysis. The variable CIE b* of the tongue body was significantly lower in CC than that in controls (P=0.019). The variable CIE L* of the tongue coating was significantly higher in CC than that in controls (P=0.032). In CC, the color of the tongue body seems to be changed to intense red color. The color of the tongue coating seems to be changed to thick fur. The present study demonstrated that the CTIS can be used as a diagnostic and monitoring tool for the objective and standardized evaluation of common cold in clinics.

• The Journal of Internal Korean Medicine
• /
• v.36 no.3
• /
• pp.348-360
• /
• 2015

Objectives From observing the tongue of a patient, one can assess the health status; this method has been frequently used in traditional Korean Medicine (KM) clinics. In particular, KM posits that the color of the tongue is highly related to digestive functions. In this study, the color of tongue and heart rate variability (HRV) were compared between chronic dyspepsia (CD) patients and healthy subjects. Methods Healthy subjects and CD patients with functional dyspepsia (FD), gastroesophageal reflux disease (GERD), or chronic gastritis (CG) were enrolled for the study. Profile view images of the tongue were acquired by using a computerized tongue image acquisition system (CTIS). The color of the tongue body was extracted from the non-coated region on the tongue images. Results Color differences in CIE L*a*b* color space between the three sub-types of CD patients and healthy subjects were analyzed by using multiple linear regression analysis with age and sex as the factors. The variable b* was significantly lower in GERD patients than in the controls (p=0.017). Variable a* was significantly lower in CG than in the controls (p=0.03). No significant difference was seen between FD and controls. In GERD, the tongue body seems to be intense red in color; in CG, pale red. Frequency domain analysis showed that HF was significantly lower in GERD patients than in the controls (p=0.041). Conclusions The color of the tongue body and HF of HRV can be used for diagnosing digestive functions in health care.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.945-961
• /
• 2019

Tongue diagnosis is one of the most important diagnostic methods in Traditional Chinese Medicine (TCM). Tongue image segmentation aims to extract the image object (i.e., tongue body), which plays a key role in the process of manufacturing an automated tongue diagnosis system. It is still challenging, because there exists the personal diversity in tongue appearances such as size, shape, and color. This paper proposes an innovative segmentation method that uses image thresholding, gray projection and active contour model (ACM). Specifically, an initial object region is first extracted by performing image thresholding in HSI (i.e., Hue Saturation Intensity) color space, and subsequent morphological operations. Then, a gray projection technique is used to determine the upper bound of the tongue body root for refining the initial object region. Finally, the contour of the refined object region is smoothed by ACM. Experimental results on a dataset composed of 100 color tongue images showed that the proposed method obtained more accurate segmentation results than other available state-of-the-art methods.

• Korean Journal of Oriental Medicine
• /
• v.14 no.3
• /
• pp.89-95
• /
• 2008

A tongue shows physiological and clinicopathological changes of inner organs. Visual inspection of a tongue is not only convenient but also non-invasive. To develop an automat ic tongue diagnosis system for an objective and standardized diagnosis, the separation of the tongue are a from a facial image and the detection of coatings, spots and cracks are inevitable but difficult since the colors of a tongue, lips, and skin in a mouth as well as those of tongue furs and body are similar. The propose d method includes preprocessing with down-sampling and edge enhancement, over-segmentation, detecting positions with a local minimum over shading from the structure of a tongue, and correcting local minima or detecting edge with color difference. The proposed method produces the region of a segmented tongue, and then decomposes the color components of the region into hue, saturation and brightness, resulting in classifying the regions of tongue furs(coatings) into kinds of coatings and substance and segmenting them. Spots are detected by using local maxima and the variation of saturation, and cracks are searched by using local minima and the directivity of dark areas in brightness. The results illustrate the segmented region with effective information, excluding a non-tongue region and also give us accurate discrimination of coatings and the precise detection of spots and cracks. It can be used to make an objective and standardized diagnosis for an u-Healthcare system as well as a home care system.

• The korean journal of orthodontics
• /
• v.23 no.2 s.41
• /
• pp.179-197
• /
• 1993

Tongue posture at rest position of Class III malocclusion is very important in malocclusion and phonation. Because Class III malocclusion shoves low tongue position, speech defect is commonly occured. This study was attempted to evaluate the correlationship between the tongue posture at rest position and during /s/ phonation and facial skeleton in centric occlusion. Thirty subjects with Class III malocclusion who had no orofacial defects such as cleft palate, medical history of neurologic pathology, hearing defect and any previous speech therapy were selected. Ninety sheets of lateral cephalometric radiographs taken at rest position, during /s/ phonation and centric occlusion were traced, measured and statistically analysed. The results obtained were as follows ; 1. In Class III malocclusion, the posture of tongue was positively correlated with the position of hyoid body. The hyoid body was positioned anteriorly and inferiorly as the vertical facial skeleton was increased in centric occlusion. 2. In Class III malocclusion, the vertical position of tongue tip at rest position was not correlated with facial skeleton in centric occlusion, but the horizontal position had low correlation with mandibular body length, APDI, and $\underline{1}$ to SN. 3. In Class III malocclusion, there was the tendency that the dorsal position of the tongue was lowered as the vertical facial skeleton was increased. 4. In Class III malocclusion, the vertical and horizontal position of tongue tip during /s/ phonation was not correlated with facial skeleton in centric occlusion.