• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.2
• /
• pp.428-434
• /
• 2015

A new tongue examination model by using color analysis according to the taste division of tongue. The proposed system consists of a tongue image acquisition in a predefined template, taste region segmentation, color distribution analysis and abnormality decision of tongue by color analysis using Hue-Saturation histograms and the part of a mobile application service. We divided 4 basic taste(bitter, sweet, salty and sour) regions and performed color distribution analysis targeting each region under HSI(Hue Saturation Intensity) color model. To minimize the influence of illumination, the histograms of H and S components only except U are utilized. Using the analyzed results, the abnormality is discriminated by the criteria of the histogram range of normal tongues. Finally, a self tongue diagnosis system which can be used anytime and anywhere on mobile environment.

• Journal of Korean Medicine Rehabilitation
• /
• v.32 no.1
• /
• pp.73-87
• /
• 2022

Objectives We aimed to characterize the results obtained from Korean medical examinations and questionnaires on the quality of sleep. Methods The quality of sleep was measured using the Pittsburgh sleep quality index in 400 subjects. Afterwards, heart rate variability (HRV) measurements were done, along with the analyses for tongue color, teeth marks, and tongue coating through the tongue diagnosis system. A questionnaire about body's heat, cold and sweating conditions, and the perceived stress scale (PSS) were performed. Finally, correlations between all these indicators and the sleep quality were analyzed. Results As the quality of sleep decreased, the sympathetic nervous system was stimulated. The subjects who had the blue-purple colored tongue experienced decreased quality of sleep. The quality of sleep was also deteriorated in the subjects who usually feel cold and hot easily, sweat a lot, and feel a lot of discomfort. According to the PSS questionnaire, the higher the stress level is, the lower was the quality of sleep. Conclusions We obtained meaningful results by comprehensively analyzing the sleep quality, HRV, tongue diagnosis, heat and cold conditions, sweating, and stress conditions. In particular, the sleep quality had a significant correlation with the rest of the indicators.

• 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.

• 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.

• Advances in Traditional Medicine
• /
• v.6 no.2
• /
• pp.112-120
• /
• 2006

The purpose of this study was to analyze whether quantitative evaluation of the color of the tongue substance using $L^*a^*b^*$ color coordinates system could minimize the problems arising from the different illuminating conditions or not. In controlled 4 different illuminating conditions (by natural light, flashlight, f-number, shutter speed),12 healthy subjects were photographed of their tongue substance through a digital camera (C-2100uz, Olympus Co.), both on the top surface and on the bottom surface of the tongue substance by two examiners, twice at 3 day intervals. Clinician evaluation was also performed grading the redness of the tongue substance in the form of 5-points scale by 6 clinicians. As a result, there was no significant difference in color differences between the color of the tongue substance and the reference red card in the 4 different illuminating conditions. Intra-rater reliability was satisfied and even though limitedly, inter-rater reliability was satisfied. Color differences were significantly correlated with the results by the clinicians, although they were applicable limitedly to specific illuminating conditions. Our results indicate that the application of the color differences in tongue diagnosis could not only evaluate the color information quantitatively, but also minimize the problems arising from the different illuminating conditions and that there was the significant difference in the visual evaluation of the red color of the tongue substance, both between the clinicians and between the illuminating conditions.

• The Journal of Korean Medicine
• /
• v.31 no.1
• /
• pp.23-29
• /
• 2010

Objective: The aim of this prospective, case-controlled study was to assess the difference of the amount of tongue coating between halitosis and non-halitosis patients using a digital tongue diagnosis system (DTDS). Methods: Sixty-five patients complaining of oral malodor were recruited for the study. The level of volatile sulfur compounds (VSC) in the oral cavity of the patients was measured by a portable gas chromatography. All patients were then divided into two groups, the halitosis group ($H_2S{\geq}1.5ng$/10ml, or $CH_3SH{\geq}0.5ng$/10ml) and the non-halitosis group ($H_2S$<1.5ng/10ml and $CH_3SH$<0.5ng/10ml), according to the VSC level criteria published by Tonzetich. Tongue images of the two groups were acquired and analyzed by DTDS, followed by the analysis of the tongue coating scores. Results: The tongue coating scores of the halitosis group were significantly higher than of the non-halitosis group (P=0.033). Furthermore, the difference of the posterior tongue coating between the two groups was more significant (P=0.000). Conclusions: Halitosis patients were shown to have a thicker tongue coating than those in the non-halitosis group. Moreover, the posterior dorsum of the tongue should be observed more cautiously when dealing with halitosis patients. Also, the progress and state of the patient's symptom of halitosis as diagnosed objectively by the portable gas chromatography could also possibly be analyzed instead by the DTDS tongue coating score.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.10 no.2
• /
• pp.141-146
• /
• 2016

In this paper, we apply limited area mask operation and active contour model to accurately detect tongue area outline in tongue diagnosis system. To accurately analyze the properties of the tongue, first, the tongue area to be detected. Therefore an effective segmentation method for detecting the edge of tongue is very important. It experimented with tongue image DB consists of 20~30 students 30 people. Experiments on real tongue image show the good performance of this method. Experimental results show that the proposed method extracts object boundaries more accurately than existing methods without mask operation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.221-228
• /
• 2014

The color and shape of the tongue reflect the physiological and clinico-pathological condition of the body. Recently, various tongue image acquisition devices have been developed for accurate diagnosis based on quantitative and objective tongue features. Since a color information is essential for tongue diagnosis, the performance of an illuminator is very important for the tongue image acquisition device. In this study, we developed an indirect illumination, which is possible to improve a homogeneity of light intensities on the tongue surface, and evaluated its performances. In order to realize the indirect illumination (II), a semi-ellipsoidal solid structure (SESS) for the light reflex was located in the system, and two high-brightness white LEDs were placed for illuminating the areas under frontal camera in the SESS. The tongue surface was illuminated by reflected light from the SESS. The light homogeneity induced by three different illuminations including the II was evaluated by calculating coefficient of variation (CV) of illuminance of five regions. The II showed less than 0.01 of CV and the direct illumination (DI) and the direct illumination with a light diffusion plate (DILDP) showed 0.16 and 0.13, respectively. The reflexed pixel ratios of tongue phantom images show 5.76%, 4.22%, 1.79% for the DI, the DILDP and the II, respectively. The homogeneity of a tongue phantom was evaluated by calculating CV of mean pixel values of six different tongue regions, and showed less than 0.06 in the II. If the II technique apply to tongue diagnosis system, it is expected to improve diagnostic accuracy in clinic.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.27 no.5
• /
• pp.683-687
• /
• 2013

Evacuation disorder(ED) is frequently observed in the elderly people. In this study, we investigated the tongue color properties in the elderly. 327 subjects were participated in this study and classified into normal group (n=95) and ED group (n=23) by two Korean Oriental Medicine doctors. The tongue images were acquired by using computerized tongue diagnosis system, and its color were linearly corrected base on CIE $L^*a^*b^*$ values of 12 color samples. The tongue region was segmented from acquired image and divided into two regions along the vertical direction. In order to estimate color properties of the tongue, a color histogram was calculated for the root region based on the CIE $L^*$ and $a^*$ values, and differences of color histogram values between normal and ED groups were computed based on the Mann-Whitney U test. As results, pixels corresponding to typical colors of the pale tongue and thin tongue coating were significantly more distributed in ED than those in normal group(p<0.05). The tongue color of the root region in ED was revealed to be different from those in healthy subjects.

• Journal of Sasang Constitutional Medicine
• /
• v.19 no.3
• /
• pp.156-175
• /
• 2007

1. Objectives and Methods This study was performed to know the relationship between Sasang Constitution and characteristics of ordinary symptoms, inspection diagnosis of face and tongue. There were 666 participants(280 men and 386 women) who answered Sasang Constitutional Checkup list and were taken pictures of faces and tongues. Sasang Constitution was diagnosed by only PSSC(Phonetic System for Sasang Constitution). Distribution of Sasang Constitution and X2 test, kappa value for agreement were calculated using SPSS 10.0. 2. Results From characteristics of ordinary symptoms' point of view, Taeeumin had loud voices, big body shapes and easily sweated themselves. They felt good after sweating and had warm hands and feet. And their upper back, shoulders and chest were, they thought, well developed. They were apt to have meals quickly and overeat themselves. Soyangin and Soeumin had thin body shapes and were difficult to sweat themselves and felt powerless after sweating. They had cold hands and feet. Especially, Soeumin was apt to have meals slowly and a little amounts. They walked so fast. Soyangin was introvert and had developed their abdomen and waist. 'Looking heavy and steady' was higher in Taeeumin, 'delicate and modest' was higher in Soeumin(42.8%) and Soyangin(36.1 %) in first impression. It was thought to be difficult to discriminate Soyangin from Soeumin in first impression and make a notion of right Soyangin's first impression. Soyangin had pinky tongue color and little tongue fur whereas Soeumin had red tongue color and whitish tongue fur. Taeeumin had whitish tongue fur too. 3. Conclusions To diagnose Sasang Constitution much effectively, PSSC results and comprehensive Sasang Constitutional Checkup list extracted from effective Questionnaire items and Face and Tongue Inspection Diagnosis are thought to be needed.