Conference PaperPDF Available

Automatic Testing of Color Blindness

Authors:

Abstract and Figures

Color Blindness can be challenging as well as cumbersome for a person when he is doing different works like driving a vehicle, purchasing clothes, testing strips for hard water, pH in laboratory, cooking etc. About 8% of men (mainly) are suffering from color blindness. The objective of this work is to investigate the problem in perspective of image processing and propose a model that not only detects color blindness but also provide details of the band in which he is colorblind. This is a fully automated system that works in an interactive mode with the patient and no external intervention is required. We have tested our system on some colorblind person and obtained encouraging results.
Content may be subject to copyright.
Automatic Testing of Color Blindness
S. Dey1, S. Roy2 and K. Roy3
1Dept. of IT, Camellia Institute of Technology
2Dept. of Biotech & Medical Engg., NIT Rourkella
3Dept. of Comp. Sc., West Bengal State University, Barasat, India
kaushik_mrg@hotmail.com
Abstract
Color Blindness can be challenging as well as
cumbersome for a person when he is doing different
works like driving a vehicle, purchasing clothes,
testing strips for hard water, pH in laboratory,
cooking etc. About 8% of men (mainly) are suffering
from color blindness. The objective of this work is to
investigate the problem in perspective of image
processing and propose a model that not only detects
color blindness but also provide details of the band in
which he is colorblind. This is a fully automated
system that works in an interactive mode with the
patient and no external intervention is required. We
have tested our system on some colorblind person and
obtained encouraging results.
1. Introduction
Color blindness (color vision deficiency) is a
condition in which certain colors cannot be
distinguished, and is most common due to an inherited
condition. Red/Green color blindness is by far the most
common form, about 99%, and causes problems in
distinguishing reds and greens. Another color
deficiency Blue/Yellow also exists, but is rare and there
is no commonly available test for it.
Inherited color blindness is most common, affects
both eyes, and does not worsen over time. This type is
found in about 8% of males and 0.4% of females. These
color problems are linked to the X chromosome and are
almost always passed from a mother to her son.
Color blindness may be partial (affecting only some
colors), or complete (affecting all colors). Complete
color blindness is very rare. Those who are completely
color blind often have other serious eye problems as
well.
1.1 Some major problems of color blindness
Weather forecasts
Bi-color and tri-color LEDs
Traffic lights, and worst of all, Caution
lights
Color observation by others
Purchasing clothing
Cooking and foods
1.2 Signs and Symptoms
The symptoms of color blindness are dependent on
several factors, such as whether the problem is
congenital, acquired, partial, or complete.
Difficulty distinguishing reds and greens
(most common)
Difficulty distinguishing blues and greens
(less common)
The symptoms of more serious inherited
color vision problems and some types
acquired problems may include:
Objects appear as various shades of gray
(this occurs with complete color blindness
and is very rare)
Reduced vision
Nystagmus
1.3 Treatment
There is no treatment or cure for color blindness.
Those with mild color deficiencies learn to associate
colors with certain objects and are usually able to
identify color as everyone else. However, they are
unable to appreciate color in the same way as those
with normal color vision.
2. Types of Color Blindness
There are various types of color blindness. They are
mainly categorized in two categories:
2.1 Anomalous Trichromacy - A mild shift in the
sensitivity of pigments of the cones. It is of three kinds.
2.1.1 Protanomaly (one out of 100 males): Shades of
red appear weaker in depth and brightness.
Protanomaly is referred to as "red-weakness", an apt
description of this form of color deficiency. Any
redness seen in a color by a normal observer is seen
more weakly by the protanomalous viewer, both in
terms of its "coloring power" (saturation, or depth of
color) and its brightness.
2.1.2 Deuteranomaly (five out of 100 of males): Shades
of green appear weaker .Let the deuteranomalous
person adjust your television and he would add more
green and subtract red. He is considered "green weak".
Similar to the protanomalous person, he is poor at
discriminating small differences in hues in the red,
orange, yellow, green region of the spectrum.
2.1.3 Tritanomaly - very rare case where shades of
blue appear weaker.
2.2 Dichromacy - Great deficiency or missing
completely one of the cones. It is of three kinds and it is
more common compared to Anomalous Trichromacy. A
person with normal color vision and with Dichromacy
type of color blindness is shown in Fig.1(a-d).
2.2.1 Protanopia (one out of 100 males): Shades of red
are greatly reduced, if present at all, in depth and
brightness .For the protanope, the brightness of red,
orange, and yellow is much reduced compared to
normal. For example see Fig.1(b).
2.2.2 Deuteranopia (one out of 100 males): Shades of
green are greatly reduced, if present at all, in depth and
brightness.The deuteranope suffers the same hue
dis crimination problems as the protanope, but without
the abnormal dimming. For example see Fig.1(c).
2.2.3 Tritanopia - very rare case where shades of blue
are greatly reduced, if present at all, in depth and
brightness. For example see Fig.1(d).
(a)
(b)
(c)
(d)
Fig. 1: The colors of the rainbow as viewed by
a person with a) normal vision b) Protanopia c)
Deuteranopia d) Tritanopia color blindness[10].
3. What Wavelength Goes With Color?
Our eyes are sensitive to light which lies in a very
small region of the electromagnetic spectrum labeled
"visible light". This "visible light" corresponds to a
wavelength range of 400 - 700 nanometers (nm) and a
color range of violet through red. The human eye is not
capable of "seeing" radiation with wavelengths outside
the visible spectrum. The visible colors from shortest to
longest wavelength are: violet, blue, green, yellow,
orange, and red. Ultraviolet radiation has a shorter
wavelength than the visible violet light. Infrared
radiation has a longer wavelength than visible red light.
The white light is a mixture of the colors of the visible
spectrum. Black is a total absence of light.
Earth's most important energy source is the Sun.
Sunlight consists of the entire electromagnetic
spectrum. The detailed distribution of such spectrum
is shown in Fig.2.
Fig. 2: Wavelength of different color [11].
4. Existing Color Blindness Test
Ishihara Test: The most famous colorblindness test
was created by Dr. Shinobu Ishihara of University of
Tokyo. If we visit an ophthalmologist we will most
likely be given some variations of this test.
Waggoner Test: A variant of this test specially
designed for pre-school children using shapes instead
of numbers has been created and is sold by Dr. Terrace
L. Waggoner of the Staff Naval Hospital Pensacola. His
site also contains a wealth of general information about
color vision deficiencies.
Yee Test: Arson’s friend and collaborator Nick Yee
even takes this test a step further on his wave site by
including a graphic that reveals one thing to the color
blind and to those with normal vision. This test does
not constitute medical advice.
Clauset Test: This is an unique and very interesting
variant to most conventional colorblind tests has been
developed by Aaron Clauset of Haveford College.
Unlike most tests, which requires good color vision,
only colorblind people can pass this tests.
4.1 Limitations of the Existing Models
There are several color blindness test model
available in the market. All are good in their places. The
most common test done for color blindness people is
Ishihara test. If we visit an ophthalmologist we will
most likely be given some variation of this test. Here a
man is subjected to some pictures of numbers
consisting of doted pixels of various colors. If he can
not identify it then it proves that he has color blindness
in some color.
This test model tells only if a person is color blind or
not. On the other hand this test is not designed for all
categories of man. This test does not tell anything
about the band of colors where he/she is color
blindness.
The next test model is Waggoner model. This test
model is specially designed for pre-school children
using shapes instead of numbers.
In this test model some shapes of different colors
comes to the pre-school children and they identify the
shapes. If children do not identify shapes, then this
proves that the children are colorblind. This test does
not tell anything about the band of colors where he/she
is color blindness.
The next test model is Clauset test model. Unlike
most tests, which require good color vision, only the
colorblind people can pass on this test.
The next test model is Yee test model. Arson’s friend
and collaborator Nick Yee even takes this test a step
further on his website by including a graphic that
reveals one thing to the color blind and to those with
normal vision. This test does not constitute medical
advice.
The other entire existing model tests for some
categories of people. There is no such common test
model, which can test for color blindness for all people.
5. Proposed system
The implementation of this proposed system is
based on the idea that a color blind person can’t
differentiate between similar colors in which he is color
blind. For this we have considered digital eight (8). As
it consists of 7 lines and depending on absent of one or
more lines it is converted into different digits. For
example if the middle line is absent it will be zero (0)
instead of eight (8). We have carefully designed the
lines of this number and also backgrounds of this lines.
The various buttons are also designed keeping in mind
the possible numbers/shapes will be seen by a color
blind person. We have taken utmost care to consider all
types of possibility in respect to colorblindness. It is
converted to a full fledge program for easy installation
and execution in windows platform.
The program works as follows:
Step 1: A screen will appear to the person that
instructs how to operate the system. And in second
step he has to fill up some personal documents.
Step 2: First image comes to the person. There are
two figures, one is foreground figure and another is
background figure. The person has to identify the
foreground figure (see Fig.3).
Step 3: If he can identify ‘8’ from the previous
image, one identical image with different foreground
and background color will appears to him. Again if he
identify ‘8’ as previous, another identical image come
for the another type of color blindness. If again he can
identify the number ‘8’, a report is generated that
shows that he is not color blind.
Step 4: Suppose he identifies the foreground figure
as ‘0’ in Step 2, then an image appears to him to tell
what to do in the next step.
Step 5: After reading the message, which appears to
him, he presses the ‘OK’ button. Then the ‘No’ button
is to be clicked repeatedly up to when he can identify
the number ‘8’ from the foreground image. Then when
he can identify the number ‘8’ properly, the ‘Yes’
button is to be clicked (see Fig.4).
Fig. 3: First screen shot
Fig. 4: Intermediate screen shot
Step 6: After reading the message that appears to
him, he presses the ‘OK’ button. Now again the same
process is to be done for the second half of the
wavelength. When he can identify the number ‘8’ the
‘Yes’ button is to be pressed as follows (see Fig.5).
Step 7: Finally the test report appears that shows
the final range of color blindness (see Fig.6).
Fig. 5: Intermediate screen shot
Fig. 6: Final report of colorblindness
6. Experimental Results and Conclusions
This program was tested on about 500 people and
out of them we have tested on 20 people who have
color vision problem to some extent. We have got a
satisfactory result using our program. Our program tells
two things, one is the man is color blind or not and if he
is color blind then at what range of wavelength he is
color blind and also what type of color blindness he
has. We have also consulted doctors to validate the
result obtained by our program. We have not only
tested the result but also the band in which he is
colorblind.
There are so many tests on color blindness that can
tell weather a person is color blind or not but we could
not find any system that can reveal the band of region
where the person is colorblind. This project is built for
identification the band of region where a colorblind
people cannot identify a particular portion of color.
This is an automatic system where every man can test
himself whether he is colorblind or not and if he is
colorblind than he can know in which band of color he
is colorblind. We have tested on 500 people and have
got encouraging results.
References
[1] C. E. Martin, J. G. Keller, S. K. Rogers, and M. Kabrisky,
“Color Blindness and a Color Human Visual System Model”,
IEEE, Vol. 30, No. 4, pp. 494 500, 2000.
[2] S. Yang and Y. M. Ro, Visual Contents Adaptation For
Color Vision Deficiency, Vol.1, pp. 453-460, pp. 453-456,
2003.
[3] S. Liu, W. Ma, D. Schalow, and K. Spruill, “Improving
Web Access for Visually Impaired Users”, IEEE Computer
Society, pp. 28-33, 2004.
[4] V. A. Kovalev, “Towards Image Retrieval for Eight
Percent of Color-Blind Men” IEEE, Vol.2, pp. 943 946,
2004.
[5] Y. K. Kim, K. W. Kim X. Yang, “Real Time Traffic Light
Recognition System for Color Vision Deficiencies” IEEE, pp.
76-81, 2007.
[6] G. Biernson and A. W. Snyder, “A Model of Vision
Employing Optical Mode Patterns for Color Discrimination”,
Vol. ssc-4, No. 2, pp. 173-181, 1968.
[7]http://www.toledo-
bend.com/colorblind/aboutcb.asp#frustrations
[8]http://www.stlukeseye.com/Conditions/ColorBlindness.as
p#s
[9]http://colorvisiontesting.com/color2.htm
[10]http://www.colormatters.com/v_colorblind.html
[11]http://eosweb.larc.nasa.gov/EDDOCS/Wavelengths_for_
Colors.html
[12]http://www.copresco.com/links/colblind.htm
ResearchGate has not been able to resolve any citations for this publication.
Conference Paper
Full-text available
About 8% of men (but not women) are suffering from color blindness. The objective of this work was to investigate the problem of image retrieval based on color cooccurrence features when comparing normal vision and three kinds of color blindness (dichromasia): protanopia, deuteranopia, and tritanopia. Original database comprises 12000 images that were also converted into three dichromatic versions using the Vischeck simulation tool. Results of 48000 queries were used to study influence of color blindness on retrieval results. Principal component analysis, multidimensional scaling, hierarchical clustering, support vector machines, and statistical methods were employed for investigating feature space distortions associated with color blindness.
Conference Paper
Color blindness can be challenging as well as cumbersome for a person especially when driving a vehicle. In this paper, a real time traffic light recognition system based on computer vision will be described that improves the safety of drivers who are color-blind. The system consists of a digital video camera and a portable PC that helps the system to detect and track red, green, and yellow traffic lights. The paper will explain how the RGB component adjustment, thresholding algorithm, and median filter are used to recognize traffic lights. In order for the system to handle illumination changes by weather and time, a simple adaptation method has been developed. For future use, the portable system has been simplified since audio has been added to the current system, which helps to inform the traffic light the driver is color-blind.
Conference Paper
In this paper, we propose methods to adapt colors on the visual content for people with color vision deficiency. The proposed adaptation consists of two parts: adaptations for dichromat and anomalous trichromat. The adaptation for dichromats aims to give them better color information, while the adaptation for anomalous trichromats aims to give them original color. To verify the proposed methods, we used both quantitative and qualitative measurements. Experimental results showed that the proposed adaptation enhanced color information readability of the people with color vision deficiency.
An evaluation is given of the postulate that color discrimination is achieved by the sensing of optical mode patterns excited in the retinal cones. Results are presented from analyses of the patterns and spectral responses of the optical modes. It is shown that these modes qualitatively have the proper characteristics required to satisfy the color discrimination properties of human vision. This postulate results in simple and natural explanations for the primary causes of color blindness.
Article
Technology advances and the continuing convergence of computing and telecommunications have made an unprecedented amount of information available to the public. For many people with disabilities, however, accessibility issues limit the impact of such widespread availability. Of the many types of disabilities-mobility, hearing, and learning impairments, for example-vision impairments are most pervasive in the general population, especially among seniors. The world's rapidly aging population is redefining visually impaired, which refers to individuals with low vision (that is, people for whom ordinary eyeglasses, contact lenses, or intraocular lens implants don't provide clear vision), color blindness, and blindness. In 1998, the US Congress amended the Rehabilitation Act, strengthening provisions covering access to government-posted information for people with disabilities. As amended, Section 508 requires federal agencies to ensure that all assets and technologies are accessible and usable by employees and the public, regardless of physical, sensory, or cognitive disabilities. Most current assistive technologies for visually impaired users are expensive, difficult to use, and platform dependent. A new approach by the US National Library of Medicine (NLM), National Institutes of Health (NIH), addresses these weaknesses by locating the assistive capability at the server, thus freeing visually impaired individuals from the software expense, technical complexity, and substantial learning curve of other assistive technologies. NLM's Senior Health Web site (http://nihseniorhealth.gov), a talking Web (a Web application that presents Web content as speech to users), demonstrates the approach's effectiveness.
Article
A physiologically motivated human color visual system model which represents visual information with one brightness component (A) and two chromatic components (C<sub>1</sub> and C<sub>2</sub>) is used to create stimuli for testing the color perception of deuteranomalous trichromats. Two experiments are performed. Using simple ramp patterns, the first experiment finds that three deuteranomalous trichromat test subjects can distinguish variations only in the C<sub>2</sub> component of the color vision model. This finding is further tested in the second experiment: a set of paired comparison preference tests. Two altered versions of each of three natural color images are prepared by setting either one of the color components to a constant over the full image. Pairs of an original and a distorted image are presented to the test subjects, and they are asked to indicate which image they prefer. The experimental results indicate that the C<sub>1</sub> channel is severely attenuated in the deuteranomalous trichromat test subjects, and that nearly all their color sensation is mediated by the C<sub>2</sub> channel of the color vision model