Objective assessment of improved visibility with digital image enhancement for the visually impaired
Bibliographic record
Abstract
Purpose: Observers with visual impairment show subjective preferences for pictures that are digitally enhanced with generic filters and specially-designed filters. The purpose of this study was to use a measure of performance to demonstrate improved visibility of images that have been enhanced. Methods: Nine subjects with maculopathy were recruited. The range of digital filters included generic filters (high pass or un-sharp mask, contrast enhancement, Sobel edge enhancement, DoG convolution), and custom-devised filters (Peli contrast enhancement and filters based on contrast sensitivity and supra-threshold contrast matching results). The filters were applied to two groups of images (14 faces and 14 general scenes). Using subjective comparisons and ratings of perceived visibility of filtered images compared to unfiltered images, the best two filters were obtained for each subject. These two best filters were applied to another two groups of images (32 faces with four facial expressions and 7 general scenes). For the face images, subjects were required to recognize facial expressions (anger, disgust, fear, or sadness). Eight questions were generated for each general scene image. Percent correct was calculated for both sets of images comparing filtered and unfiltered images. Results: Image enhancement improved performance both with facial expression recognition (paired t-test, p = 0.004) and questions about general scenes (6 or 7 out of 9 subjects show significant improvement - paired t-test, p[[lt]]0.05). Conclusion: This study demonstrates that it is possible to measure improvements in visibility with digital image enhancement and that digital enhancement with a variety of generic and custom-devised filters improves visibility measured both subjectively and objectively for people with maculopathy.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".