Google Glass app for colorblind individuals and people with impaired vision
1. www.tugraz.at
Institute of Information Systems and Computer Media
OmniColor
Google Glass app for colorblind individuals and
people with impaired vision
December 15th, 2016
Georg Lausegger, BSc.
3. 3
Motivation
Motivation
Fig. 1: Raw meat
Fig. 2: Clothes
Fig. 3: Traffic Lights, taken from wikipedia.org1
Fig. 4: Bananas, taken from banabay.com2
(1) https://de.wikipedia.org/wiki/Ampel , (2) http://www.banabay.com/press-room/going-green/
Georg Lausegger, BSc.,
December 15th, 2016
3/16
4. 4
Colorblindness
Colorblindness
Human Eye
Consists of rods and cones
Cones classified in three different types
L (long-) wavelength (Red)
M (middle-) wavelength (Green)
S (short-) wavelength (Blue)
Colorblindness = lack or disfunction of one or more
cone type(s)
Georg Lausegger, BSc.,
December 15th, 2016
4/16
6. 6
Colorblindness
Colorblindness Testing Methods
Color arrangement test
Ishihara color plate test
Fig. 6: Color arrangement test, taken from
color-blindness.com4
Fig. 7: Ishihara color plate test, taken from
color-blindness.com4
(4) http://www.color-blindness.com/
Georg Lausegger, BSc.,
December 15th, 2016
6/16
7. 7
Colorblindness
Daltonization
Doesn’t affect each pixel
Color shifting algorithm
Algorithm consisting of 4 steps:
RGB to LMS color space
Simulation of the specific color blindness type
Calculate compensation
Convert LMS values back to RGB
Georg Lausegger, BSc.,
December 15th, 2016
7/16
8. 8
Smartglasses
Devices
Smartphones
+ computation power
+ distribution
+ costs
- handfree navigation
- availability
Smartglasses
+ handfree navigation
+ availability
- computation power
- distribution
- costs
Georg Lausegger, BSc.,
December 15th, 2016
8/16
9. 9
Smartglasses
Google Glass
Optical Head-mounted
display
Released in February
2013
Upgraded Model(2GB
RAM)
costs ∼1500$
Input via voice
commands, touchpad or
head gestures
Fig. 8: Sergey Brin wearing Google Glass, taken from
Andrew Kelly/Reuters5
(5) http://www.computerworld.com/article/2495675/personal-technology/google-s-sergey-brin-rips-smartphones–
shows-off-glass.html
Georg Lausegger, BSc.,
December 15th, 2016
9/16
10. 10
OmniColor Prototype
OmniColor Prototype
Non-real time
All computations performed on Glass
No network connection required
Uses OpenCV library
OmniColor Flow Design
Georg Lausegger, BSc.,
December 15th, 2016
10/16
11. 11
Evaluation and Results
Evaluation
Ishihara color plate test
without OmniColor
with OmniColor
Individual appointments
14 Participants
Five colorblind people
Nine people with normal
color vision
Fig. 9: Ishihara color plate test performed
with by participant with OmniColor
Georg Lausegger, BSc.,
December 15th, 2016
11/16
12. 12
Evaluation and Results
Results (Colorblinds)
Participant
age
CVD* Without OmniColor With OmniColor
36 protanomaly 7/17 12/17
48 protanomaly 2/17 11/17
37 protanomaly 3/17 12/17
28 protanomaly 7/17 13/17
41 protanomaly 8/17 14/17
Tab. 1: Results of the Ishihara color plate test performed by colorblind participants
*Color Vision Deficiency
Georg Lausegger, BSc.,
December 15th, 2016
12/16
13. 13
Outlook
Outlook
Hardware issues with Google Glass
Google Glass discontinued in January 2015
Great potential of smartglasses
Further work
Other approaches and algorithms
Performance optimization (offloading)
Support for other Android Smartglasses
Georg Lausegger, BSc.,
December 15th, 2016
13/16
14. 14
Thank you for your
attention!
Georg Lausegger, BSc.,
December 15th, 2016
14/16
15. 15
References I
[1] David Flatla and Carl Gutwin. “SSMRecolor: Improving Recoloring Tools with Situation-specific
Models of Color Differentiation”. In: Proceedings of the SIGCHI Conference on Human Factors in
Computing Systems. CHI ’12. Austin, Texas, USA: ACM, 2012, pp. 2297–2306. ISBN:
978-1-4503-1015-4. DOI: 10.1145/2207676.2208388. URL:
http://doi.acm.org/10.1145/2207676.2208388.
[2] Jia-Bin Huang et al. “IEEE Int’l Conf on Acoustics, Speech and Signal Processing, (ICASSP
2009)”. In: Image Recolorization For The Colorblind. Apr. 2009.
[3] Luke Jefferson and Richard Harvey. “An Interface to Support Color Blind Computer Users”. In:
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. CHI ’07. San
Jose, California, USA: ACM, 2007, pp. 1535–1538. ISBN: 978-1-59593-593-9. DOI:
10.1145/1240624.1240855. URL: http://doi.acm.org/10.1145/1240624.1240855.
[4] D. S. Khurge and B. Peshwani. “Modifying Image Appearance to Improve Information Content for
Color Blind Viewers”. In: Computing Communication Control and Automation (ICCUBEA), 2015
International Conference on. Feb. 2015, pp. 611–614. DOI: 10.1109/ICCUBEA.2015.125.
[5] Viet Nguyen and Marco Gruteser. “First Experiences with GOOGLE GLASS in Mobile Research”.
In: GetMobile: Mobile Comp. and Comm. 18.4 (Jan. 2015), pp. 44–47. ISSN: 2375-0529. DOI:
10.1145/2721914.2721931. URL: http://doi.acm.org/10.1145/2721914.2721931.
[6] H´elio M. de Oliveira, J. Ranhel, and R. B. A. Alves. “Simulation of Color Blindness and a Proposal
for Using Google Glass as Color-correcting Tool”. In: CoRR abs/1502.03723 (2015). URL:
http://arxiv.org/abs/1502.03723.
Georg Lausegger, BSc.,
December 15th, 2016
15/16
16. 16
References II
[7] Brooke E. Schefrin. “Diagnosis of Defective Colour Vision, by Jennifer Birch, Oxford University
Press, New York, 1993, Paperback, 187 pp., $35.00.” In: Color Research & Application 19.6
(1994), pp. 484–484. ISSN: 1520-6378. DOI: 10.1002/col.5080190608. URL:
http://dx.doi.org/10.1002/col.5080190608.
[8] N. A. Semary and H. M. Marey. “An evaluation of computer based color vision deficiency test:
Egypt as a study case”. In: Engineering and Technology (ICET), 2014 International Conference
on. Apr. 2014, pp. 1–7. DOI: 10.1109/ICEngTechnol.2014.7016817.
Georg Lausegger, BSc.,
December 15th, 2016
16/16