Hyperspectral reconstruction from RGB images for vein visualization
Bibliographic record
Abstract
A hyperspectral camera captures a scene in many frequency bands across the spectrum, providing rich information and facilitating numerous applications. The potential of hyperspectral imaging has been established for decades. However, to date hyperspectral imaging has only seen success in specialized and large-scale industrial and military applications. This is mainly due to the high cost of hyperspectral cameras (upwards of $20K) and the complexity of the acquisition system which makes the technology out of reach for many commercial and end-user applications. In this paper, we propose a deep learning based approach to convert RGB image sequences taken by regular cameras to (partial) hyperspectral images. This can enable, for example, low-cost mobile phones to leverage the characteristics of hyperspectral images in implementing novel applications. We show the benefits of the conversion model by designing a vein localization and visualization application that traditionally uses hyperspectral images. Our application uses only RGB images and produces accurate results. Vein visualization is important for point-of-care medical applications. We collected hyperspectral data to validate the proposed conversion model. Experimental results demonstrate that the proposed method is promising and can bring some of the benefits of expensive hyperspectral cameras to the low-cost and pervasive RGB cameras, enabling many new applications and enhancing the performance of others. We also evaluate the vein visualization application and show its accuracy.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".