Ishihara's Tests for Colour Deficiency
Authentic and accurate images of Ishihara's test plates
Just because it's black in the dark,
Oh, doesn't mean there's no colors.
— Laleh (Colors)
Authentic and color-accurate images of Ishihara's test plates for colour deficiency.
I provide high-resolution bitmaps and SVG files for each plate. I also provide the position, size, and color of each circle on each test plate.
Can this information be used to make fakes? Yes, but at least they'll be really good ones. Also, please don't.
If you're interested to learn more about colorblindess and the mathematics behind it, see my Designing for Color Blindness, Palettes for Color Blindness and Math of Color Blindness.
And turn those lines of confusion into understanding!
contents
Authentic and color-corrected images of Ishihara's test plates for color deficiency. These were photographed (methods) from the 38 plate book.
The plates are 12 × 12 cm. The circular pattern of dots on each plate is approximately 9 cm in diameter.
Image archives include all the plates and images of the Gretag-Macbeth colorchecker at various stages of color correction.
400 × 400 pixels (84 dpi).
400 × 400 pixels (84 dpi), 2,419 × 2,419 pixels (512 dpi), and SVG.
The SVG files contain links to the hires images.
You didn't just come here for the images. You want to know the position, size, and color of each circle on each test plate.
There are 25,090 circles across all 38 plates. The number of circles on each plate is: 1 (588), 2 (735), 3 (676), 4 (655), 5 (672), 6 (744), 7 (660), 8 (782), 9 (721), 10 (758), 11 (724), 12 (542), 13 (579), 14 (771), 15 (723), 16 (593), 17 (586), 18 (735), 19 (594), 20 (607), 21 (570), 22 (734), 23 (714), 24 (636), 25 (603), 26 (661), 27 (650), 28 (667), 29 (688), 30 (720), 31 (592), 32 (725), 33 (581), 34 (623), 35 (638), 36 (648), 37 (616), and 38 (579).
This file contains the position, radius, and RGB color of these circles, sorted by plate (ascending), radius (descending), x position (ascending). The circles were identified with this code, applied to my high-resolution color-corrected photographs of each plate. The RGB color in the SVG file is the average RGB value across pixels in each circle.
The units are arbitrary. Each SVG canvas is 2,419 × 2,419 pixels and corresponds to 12 × 12 cm.
# plate x y radius R G B 1 1313 835 53 253.06855718292303 138.0174509192895 82.55936428794017 1 1554 1543 53 254.0174509192895 134.86631349330008 80.13804923652228 1 1558 1172 53 253.7310688688065 135.0819569959489 80.92489872234341 1 1659 753 53 253.2848239326893 135.6849485821128 81.9164848862574 1 1667 1507 53 253.87815518853225 134.71019009037082 80.34340916173262 1 1722 904 53 253.27454035525085 136.30850732315363 81.9460891243378 ...
Consequences of missing data
Either I've been missing something or nothing has been going on. —Karen Elizabeth Gordon
Missing data are everywhere. Subjects may decline to participate in a survey or fail to answer sensitive questions. A cell culture might fail due to contamination. Instrument failures or mishandling of a sample may lead to missing observations. But why are missing data a problem?
This month, we begin a series of articles about practical and statistical aspects of missing data. We'll see that missing data can increase variability and introduce bias and we will ask whether anything can be done to mitigate these consequences. It turns out that, in the case where we know nothing about the missing subjects, no mitigation is possible. We must accept higher variability and, if we have a suspicion that the missing subjects aren’t completely random, possible bias as well.
Tanujit Dey, T., Lipsitz, S.R., Fitzmaurice, G., Krzywinski, M. & Altman, N. (2026) Points of significance: Consequences of missing data. Nat. Methods 23 (in print).
Double Robustness
It is not certain that everything is uncertain. —Blaise Pascal
We have already explored how we can mitigate bias caused by confounding variables in observational studies using propensity score (PS) matching (PSM) and propensity score weighting (PSW). However, any statistical model is only as good as its assumptions and, if it is specified incorrectly, it can itself produce biased estimates of the treatment effect.
This month, we explore double robustness, a powerful statistical concept that provides a valuable “safety net” against the risk of an incorrect model. It offers two opportunities, instead of just one, to obtain a valid estimate of the treatment effect — making it possible to draw credible causal inferences from observational data without having to depend on a single set of modeling assumptions.
Kurz, C.F., Krzywinski, M. & Altman, N. (2026) Points of significance: Double Robustness. Nat. Methods 23:868–869.
Nature Biotechnology cover
My cover design on the 7 April 2026 Nature Biotechnology issue shows the dendrogram that represents a cluster of uniquely expressed (or downregulated) genes in human naive stem cells induced from such cells. Within each dendrogram block, the genomic barcode sequence (sampled from Supplementary Table 1) is depicted with a Code 39 barcode. The highlighted barcode is one of those used for cell isolation.
Ishiguro S. et al. A multi-kingdom genetic barcoding system for precise clone isolation (2026) Nature Biotechnology 44:616–629.
Browse my gallery of cover designs.
Happy 2026 π Day—
Art for the 5%
Celebrate π Day (March 14th) and enjoy the art — but only if you're part of the 5%.
Go ahead, see what you can't see.
Ishihara's Tests for Colour Deficiency
Authentic and accurate images of Ishihara's test plates photographed (and lovingly color-corrected) from the 38-plate Ishihara's Tests for Colour Deficiency.
I also provide the position, size, and color of each circle on each test plate.
