Research map / Detection and segmentation / CNN features
Image Splicing Detection via Camera Response Function Analysis
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add absolute intensity and gradient values to IGH (ablation) | IGH CNN · CUISDE | accuracy: 0.943 -> 0.97 | Helped |
| add absolute intensity and gradient values to IGH (ablation) | IGH CNN · SpLogo | accuracy: 0.972 -> 0.99 | Helped |
| add absolute intensity and gradient values to IGH (ablation) | IGH CNN · Combine | accuracy: 0.979 -> 0.978 | Hurt |
| add absolute intensity and gradient values to IGH (ablation) | IGH SVM · CUISDE | accuracy: 0.924 -> 0.940 | Helped |
| add absolute intensity and gradient values to IGH (ablation) | IGH SVM · SpLogo | accuracy: 0.972 -> 0.972 | No clear effect |
| add absolute intensity and gradient values to IGH (ablation) | IGH SVM · Combine | accuracy: 0.937 -> 0.951 | Helped |
| use CNN classification on IGH instead of SVM classification on IGH | IGH classifier · CUISDE | accuracy: 0.940 -> 0.97 | Helped |
| use CNN classification on IGH instead of SVM classification on IGH | IGH classifier · SpLogo | accuracy: 0.972 -> 0.99 | Helped |
| use CNN classification on IGH instead of SVM classification on IGH | IGH classifier · Combine | accuracy: 0.951 -> 0.978 | Helped |
| classify edge patches directly instead of using IGH features | CNN · CUISDE | accuracy: 0.888 -> 0.97 | Helped |
| use a multi-scale IGH for large blur (ablation) | IGH edge classification · SpLogo | edge classification | Helped |
Closest papers by meaning
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.84)
- SAFIRE: Segment Any Forged Image Region (AAAI 2025 · similarity 0.84)
- CatmullRom Splines-Based Regression for Image Forgery Localization (AAAI 2024 · similarity 0.84)
- DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization (CVPR 2024 · similarity 0.83)
- Reinforced Multi-teacher Knowledge Distillation for Efficient General Image Forgery Detection and Localization (AAAI 2025 · similarity 0.83)
- Rescind: Countering Image Misconduct in Biomedical Publications with Vision-Language and State-Space Modeling (AAAI 2026 · similarity 0.83)
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.