Research map / Detection and segmentation / Open-set and few-shot detection
Coded Illumination and Imaging for Fluorescence Based Classification
Yuta Asano, Misaki Meguro, Chao Wang, Antony Lam, Yinqiang Zheng, Takahiro Okabe, Imari Sato
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use a learned coded illuminant instead of a fixed 5000K LED | SVM classifier with RGB weights · Acacia vs. Canadian Clover honey | pixel classification accuracy (%): 50.00% -> 91.17% | Improved |
| use a learned coded illuminant instead of a fixed incandescent light | SVM classifier with RGB weights · Acacia vs. Orange honey | pixel classification accuracy (%): 40.00% -> 78.26% | Improved |
| use a learned coded illuminant instead of a fixed incandescent light | SVM classifier with RGB weights · Canadian Clover vs. Orange honey | pixel classification accuracy (%): 45.00% -> 52.03% | Improved |
| use a learned coded illuminant instead of fixed 5000K LED | SVM classifier with RGB weights · Scotch vs. Cognac | pixel classification accuracy (%): 66.67% -> 100.00% | Improved |
| use a learned coded illuminant instead of fixed 5000K LED | SVM classifier with RGB weights · Bourbon vs. Brandy | pixel classification accuracy (%): 66.67% -> 71.44% | Improved |
| use a learned coded illuminant instead of fixed 5000K LED | SVM classifier with RGB weights · Whisky vs. Brandy | pixel classification accuracy (%): 66.67% -> 93.00% | Improved |
| use a learned coded illuminant instead of fixed 5000K LED | SVM classifier with RGB weights · Whisky vs. Bourbon | pixel classification accuracy (%): 52.58% -> 61.10% | Improved |
| use a learned coded illuminant instead of fixed incandescent light | SVM classifier with RGB weights · Whisky vs. Scotch | pixel classification accuracy (%): 55.00% -> 77.30% | Improved |
| use a learned coded illuminant instead of fixed 5000K LED | SVM classifier with RGB weights · Scotch vs. Bourbon | pixel classification accuracy (%): 50.00% -> 58.16% | Improved |
| realize the coded illuminant with a programmable light source instead of the ideal simulated illuminant | Coded illuminant · Acacia vs. Canadian Clover honey | pixel classification accuracy (%): 92.69% -> 85.96% | Hurt |
| realize the coded illuminant with a programmable light source instead of the ideal simulated illuminant | Coded illuminant · Bourbon vs. Scotch | pixel classification accuracy (%): 85.06% -> 85.75% | No clear effect |
| move from binary to four-class classification with a single illuminant | Coded illuminant · Four-class alcohol classification | pixel classification accuracy (%): 51.04% to 68.93% | Mixed |
Closest papers by meaning
- Reflectance and Fluorescence Spectral Recovery via Actively Lit RGB Images (TPAMI 2016 · similarity 0.83)
- One-Shot Recognition of Any Material Anywhere Using Contrastive Learning with Physics-Based Rendering (ICCV 2023 · similarity 0.83)
- Separating Reflective and Fluorescent Components Using High Frequency Illumination in the Spectral Domain (TPAMI 2016 · similarity 0.82)
- PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors (NeurIPS 2025 · similarity 0.80)
- Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior (CVPR 2024 · similarity 0.80)
- Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation (NeurIPS 2024 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
