MétaCan
Menu
Back to cohort
Record W2021380298 · doi:10.1145/2399193.2399197

Situation-Specific Models of Color Differentiation

2012· article· en· W2021380298 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueACM Transactions on Accessible Computing · 2012
Typearticle
Languageen
FieldPhysics and Astronomy
TopicColor Science and Applications
Canadian institutionsUniversity of Saskatchewan
Fundersnot available
KeywordsComputer scienceArtificial intelligenceRGB color modelTrichromacyComputer visionColor vision

Abstract

fetched live from OpenAlex

Color is commonly used to represent categories and values in computer applications, but users with Color-Vision Deficiencies (CVD) often have difficulty differentiating these colors. Recoloring tools have been developed to address the problem, but current recolorers are limited in that they work from a model of only one type of congenital CVD (i.e., dichromatism). This model does not adequately describe many other forms of CVD (e.g., more common congenital deficiencies such as anomalous trichromacy, acquired deficiencies such as cataracts or age-related yellowing of the lens, or temporary deficiencies such as wearing tinted glasses or working in bright sunlight), and so standard recolorers work poorly in many situations. In this article we describe an alternate approach that can address these limitations. The new approach, called Situation-Specific Modeling (SSM), constructs a model of a specific user’s color differentiation abilities in a specific situation, and uses that model as the basis for recoloring digital presentations. As a result, SSM can inherently handle all types of CVD, whether congenital, acquired, or environmental. In this article we describe and evaluate several models that are based on the SSM approach. Our first model of individual color differentiation (called ICD-1) works in RGB color space, and a user study showed it to be accurate and robust (both for users with and without congenital CVD). However, three aspects of ICD-1 were identified as needing improvement: the calibration step needed to build the situation-specific model, and the prediction steps used in recoloring were too slow for real-world use; and the results of the model’s predictions were too coarse for some uses. We therefore developed three further techniques: ICD-2 reduces the time needed to calibrate the model; ICD-3 reduces the time needed to make predictions with the model; and ICD-4 provides additional information about the degree of differentiability in a prediction. Our final result is a model of the user’s color perception that handles any type of CVD, can be calibrated in two minutes, and can find replacement colors in near-real time ( ~ 1 second for a 64-color image). The ICD models provide a tool that can greatly improve the perceptibility of digital color for many different types of CVD users, and also demonstrates situation-specific modeling as a new approach that can broaden the applicability of assistive technology.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.784
Threshold uncertainty score0.359

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.045
GPT teacher head0.300
Teacher spread0.255 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it