ISO/TR 20498-5:2019

TECHNICAL ISO/TR
REPORT 20498-5
First edition
2019-01
Corrected version
2019-12
Traditional Chinese medicine —
Computerized tongue image analysis
system —
Part 5:
Method of acquisition and
expression of tongue colour and
tongue coating colour
Médecine traditionnelle chinoise — Système d’analyse d’images
numérisées de la langue —
Partie 5: Méthode d'acquistion et expression de la couleur de la
langue et du revêtement de la langue
Reference number
ISO/TR 20498-5:2019(E)
©
ISO 2019

---------------------- Page: 1 ----------------------
ISO/TR 20498-5:2019(E)

COPYRIGHT PROTECTED DOCUMENT
© ISO 2019
All rights reserved. Unless otherwise specified, or required in the context of its implementation, no part of this publication may
be reproduced or utilized otherwise in any form or by any means, electronic or mechanical, including photocopying, or posting
on the internet or an intranet, without prior written permission. Permission can be requested from either ISO at the address
below or ISO’s member body in the country of the requester.
ISO copyright office
CP 401 • Ch. de Blandonnet 8
CH-1214 Vernier, Geneva
Phone: +41 22 749 01 11
Fax: +41 22 749 09 47
Email: copyright@iso.org
Website: www.iso.org
Published in Switzerland
ii © ISO 2019 – All rights reserved

---------------------- Page: 2 ----------------------
ISO/TR 20498-5:2019(E)

Contents Page
Foreword .iv
Introduction .v
1 Scope . 1
2 Normative references . 1
3 Terms and definitions . 1
4 Colour calibration of the acquisition device . 2
4.1 Choice of colour space . 2
4.2 Calibration of the acquisition device . . 2
4.2.1 General. 2
4.2.2 Whiteboard calibration . 2
4.2.3 Colour calibration . 3
5 Methods of digital representation of tongue colour and coating colour .4
5.1 Clustering method . 4
5.2 Histogram method . 4
5.3 Mean value method . 5
Annex A (informative) Validity of tongue image acquisition and analysis .6
Annex B (informative) Example for representation of tongue colour and coating colour .10
Bibliography .16
© ISO 2019 – All rights reserved iii

---------------------- Page: 3 ----------------------
ISO/TR 20498-5:2019(E)

Foreword
ISO (the International Organization for Standardization) is a worldwide federation of national standards
bodies (ISO member bodies). The work of preparing International Standards is normally carried out
through ISO technical committees. Each member body interested in a subject for which a technical
committee has been established has the right to be represented on that committee. International
organizations, governmental and non-governmental, in liaison with ISO, also take part in the work.
ISO collaborates closely with the International Electrotechnical Commission (IEC) on all matters of
electrotechnical standardization.
The procedures used to develop this document and those intended for its further maintenance are
described in the ISO/IEC Directives, Part 1. In particular, the different approval criteria needed for the
different types of ISO documents should be noted. This document was drafted in accordance with the
editorial rules of the ISO/IEC Directives, Part 2 (see www .iso .org/ directives).
Attention is drawn to the possibility that some of the elements of this document may be the subject of
patent rights. ISO shall not be held responsible for identifying any or all such patent rights. Details of
any patent rights identified during the development of the document will be in the Introduction and/or
on the ISO list of patent declarations received (see www .iso .org/ patents).
Any trade name used in this document is information given for the convenience of users and does not
constitute an endorsement.
For an explanation of the voluntary nature of standards, the meaning of ISO specific terms and
expressions related to conformity assessment, as well as information about ISO's adherence to the
World Trade Organization (WTO) principles in the Technical Barriers to Trade (TBT) see www .iso .org/
iso/ foreword .html.
This document was prepared by Technical Committee ISO/TC 249, Traditional Chinese medicine.
This corrected version of ISO/TR 20498-5:2019 incorporates the following corrections:
— The upper and lower limits of some domains in A.2 have been reversed to correct editorial errors.
A list of all the parts in the ISO 20498 series can be found on the ISO website.
Any feedback or questions on this document should be directed to the user’s national standards body. A
complete listing of these bodies can be found at www .iso .org/ members .html.
iv © ISO 2019 – All rights reserved

---------------------- Page: 4 ----------------------
ISO/TR 20498-5:2019(E)

Introduction
As one of the most distinctive traditional Chinese medicine diagnosis methods, tongue diagnosis is a
method of inspecting the patient’s tongue and its coating to determine his or her disease or syndrome.
With growing global demand for traditional Chinese medicine, there is an increasing demand for
international medicine and academic exchanges on tongue diagnosis as well as tongue-related devices.
Traditional tongue diagnosis, mainly dependent on the practitioner’s visual observation and text
description, often varies with the practitioner’s experience, environmental changes and other factors,
which makes it difficult to make an accurate diagnosis and archive the tongue image. Therefore, it is
necessary to quantify and digitize the tongue manifestation.
With modern scientific knowledge and technology, the practitioner’s subjective judgement about
tongue manifestation has gradually developed into an objective determination by computerized tongue
image analysis system (CTIS) with a standard calculation method. According to statistics, more and
more traditional Chinese medicine practitioners have come into contact with and used a device for
tongue diagnosis, which undoubtedly plays a leading role in the promotion of tongue-related products
worldwide. Thus, it is of the utmost urgency to standardize the CTIS, which will bring benefits to
companies involved in the trade of tongue-related devices and to people assisting with CTIS.
Therefore, as one of the five parts of the ISO 20498 series, this document intends to quantify and digitize
the tongue manifestation used in the CTIS, which is of great importance to the international trade and
service of CTIS, thus increasing business profit.
© ISO 2019 – All rights reserved v

---------------------- Page: 5 ----------------------
TECHNICAL REPORT ISO/TR 20498-5:2019(E)
Traditional Chinese medicine — Computerized tongue
image analysis system —
Part 5:
Method of acquisition and expression of tongue colour and
tongue coating colour
1 Scope
This document describes a method of acquisition of tongue image and expression of tongue colour and
coating colour by computerized tongue image analysis system (CTIS).
This document does not cover the clinical tongue diagnosis result.
2 Normative references
There are no normative references in this document.
3 Terms and definitions
For the purposes of this document, the following terms and definitions apply.
ISO and IEC maintain terminological databases for use in standardization at the following addresses:
— ISO Online browsing platform: available at https:// www .iso .org/ obp
— IEC Electropedia: available at http:// www .electropedia .org/
3.1
tongue body
muscles and vessels of the tongue
3.2
tongue coating
layer of fur-like substance stuck on the tongue
3.3
tongue colour
colour of the tongue body
3.4
coating colour
colour of the tongue coating
3.5
tongue image
digital image acquired by the device
© ISO 2019 – All rights reserved 1

---------------------- Page: 6 ----------------------
ISO/TR 20498-5:2019(E)

3.6
L*a*b* colour space
three-dimensional, approximately uniform colour space, produced by plotting, in rectangular
coordinates L*, a*, b*
Note 1 to entry: The quantity L* is a measure of the lightness, where L* = 0 corresponds to black and L* = 100
corresponds to the perfect reflecting diffuser. Visually, the quantities a* and b* represent respectively the red-
green and yellow-blue axes in colour space, such that:
— +a* is a measure of the degree of redness;
— −a* is a measure of the degree of greenness;
— +b* is a measure of the degree of yellowness;
— −b* is a measure of the degree of blueness.
If both a* and b* are equal to zero, the test piece is grey.
[SOURCE: CIE 17.4, 845-03-56, ISO 5631-2:2015, 3.6, modified — "of the test piece" has been removed
and "achromatic" has been replaced with "grey".]
3.7
standard colour chart
apparatus consisting of 24 single colour patches used for the evaluation of colour calibration of CTIS
Note 1 to entry: The colour chart in this document is supplied by Pantone. It can be replaced when a new special
colour chart made for tongue colour is available.
4 Colour calibration of the acquisition device
4.1 Choice of colour space
With the help of L*a*b* colour space's special features, white balance calibration can be done by setting
the white balance parameter on the camera before taking the photo or adjusting during post-processing.
This is because L* represents lightness, which is completely independent of a* and b* (represented
colour), and thus the adjustment of the L* does not affect image colour data.
In view of image compatibility, the parameter ranges of various tongue colour and tongue coating colour
calculated in L*a*b* colour space can be converted to any other colour space by conversion formulas.
4.2 Calibration of the acquisition device
4.2.1 General
In order to reflect realistic tongue colour information in the tongue image, chromatic aberration
resulting from the acquisition device itself should be adjusted. Therefore, the prerequisite procedure
for tongue image analysis is to calibrate the device hardware characteristics. The calibration is made in
two steps. The first is whiteboard calibration, and then colour calibration.
4.2.2 Whiteboard calibration
As one of the factors affecting colour calibration, the determination of the camera's shooting mode is an
important part of tongue image acquisition, which has a close association with whether the collected
data are real or not. Once fixed in a certain mode (except AUTO mode), the system error of colour is
relatively constant. Therefore, once colour distortion is determined under the current mode, the
adjustment value is also determined.
Tongue colour analysis needs high-quality images, so it is necessary to check if the auto white balance
by the camera is valid enough for our research. Most commercial cameras can adjust the white balance
2 © ISO 2019 – All rights reserved

---------------------- Page: 7 ----------------------
ISO/TR 20498-5:2019(E)

automatically by the software installed in them. A method named whiteboard calibration is offered in
this document to meet users’ needs for colour high-fidelity images. This method is also useful for those
cameras that cannot adjust the white balance automatically.
Whiteboard calibration is carried out using the following steps:
1) Take pictures of a standard whiteboard with the device.
2) Select 24 points that are distributed evenly and calculate colour deviation Δe for each using
i
Formula (1) and average deviation ΔE using Formula (2).
3) Adjust the white balance value according to the average deviation value.
4) Repeat steps 1), 2) and 3) until the colour deviation value is less than 5.
Single deviation:
**22 *2
L*a*b* colour space:ΔΔe =+LaΔΔ+ b (1)
i
Average deviation:
1
ΔΔE=∑ e (2)
i
24
The suggested sample points are positioned in Figure 1:
Figure 1 — Position of sample points for whiteboard calibration
4.2.3 Colour calibration
Colour calibration in L*a*b* colour space is carried out using the following steps:
1) Take pictures of 24 kinds of colour on a standard colour chart with the device.
2) Calculate the real L*a*b* value for the tongue image by linear interpolation. Take L* component as an
example. For each pixel in a tongue image, its real L value (L ) will be calculated using Formula (3).
r
LL− LL−
gg0 g1 g0
= (3)
LL− LL−
rr0 r1 r0
In Formula (3), L represents the raw L* value from the image. L comes from a certain pixel of tongue
g g
image. L and L are calibration points coming from the image of the colour chart. L and L
g0 g1 r0 r1
represent the value of the colour chart. For any L* value from any pixel in the tongue image, the two
closest calibration points are found and the L will be calculated.
r
© ISO 2019 – All rights reserved 3

---------------------- Page: 8 ----------------------
ISO/TR 20498-5:2019(E)

A sketch is shown in Figure 2. Point X and Y are the reference points on the colour chart. L and L are
r0 r1
respectively the L*value of Point X and Y according to colour chart (here subscript r refers to real
value). L and L are raw L* value coming from the photo of reference point on the colour chart (here
g0 g1
subscript g refers to acquired value).
Figure 2 — A sketch of linear interpolation
Here linear interpolation is used for the calibration of the acquisition device since the referenced colour
chart can only supply 24 kinds of colour. For pixels which drop between two calibration points, there
should be a method to calculate deviation for correcting image. In this case, linear interpolation is a
simple and accurate method to do the work. Annex A provides an example of linear interpolation for
certain CTIS.
Because of the short distance between the device and the tongue, the collected image geometric
distortion is very small, so geometric correction is excluded.
5 Methods of digital representation of tongue colour and coating colour
5.1 Clustering method
The clustering method can be used for tongue colour representation. k-means clustering is a method
of vector quantization, originally from signal processing, which is popular for cluster analysis in data
mining.
...