Research map / Detection and segmentation / CNN features
Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration
Read the paperCheck 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 |
|---|---|---|---|
| Use SDNet instead of the strongest registration baseline, VoxelMorph | stroke registration · CCSEDB | mDis: 5.352 -> 4.469 | Helped |
| Use SDNet instead of the strongest registration baseline, VoxelMorph | stroke registration · CCSEDB | mBIou: 0.609 -> 0.637 | Helped |
| Use SDNet instead of the strongest registration baseline, VoxelMorph | stroke registration · RHSEDB | mDis: 7.531 -> 5.553 | Helped |
| Use SDNet instead of the strongest registration baseline, VoxelMorph | stroke registration · RHSEDB | mBIou: 0.527 -> 0.614 | Helped |
| Use the proposed stroke extraction pipeline instead of PathMatchNet | Chinese character stroke extraction · CCSEDB | mIOU_m: 0.692 -> 0.924 | Helped |
| Use the proposed stroke extraction pipeline instead of PathMatchNet | Chinese character stroke extraction · CCSEDB | mIOU_um: 0.842 -> 0.926 | Helped |
| Use the proposed stroke extraction pipeline instead of PathMatchNet | Chinese character stroke extraction · RHSEDB | mIOU_m: 0.654 -> 0.917 | Helped |
| Use the proposed stroke extraction pipeline instead of PathMatchNet | Chinese character stroke extraction · RHSEDB | mIOU_um: 0.815 -> 0.93 | Helped |
| Add prior information to SegNet (ablation) | SegNet · CCSEDB | mIOU: 0.735 -> 0.917 | Helped |
| Add prior information to SegNet (ablation) | SegNet · RHSEDB | mIOU: 0.768 -> 0.908 | Helped |
| Add prior information to ExtractNet (ablation) | ExtractNet · CCSEDB | mIOU_m: 0.567 -> 0.924 | Helped |
| Add prior information to ExtractNet (ablation) | ExtractNet · RHSEDB | mIOU_m: 0.556 -> 0.917 | Helped |
Closest papers by meaning
- Fully Convolutional Network Based Skeletonization for Handwritten Chinese Characters (AAAI 2018 · similarity 0.84)
- A Multi-Style Chinese Characters Writing Intelligent Tool Based on Small-scale Training Data (AAAI 2025 · similarity 0.80)
- Decoupling Layout from Glyph in Online Chinese Handwriting Generation (ICLR 2025 · similarity 0.79)
- Towards Automated Chinese Ancient Character Restoration: A Diffusion-Based Method with a New Dataset (AAAI 2024 · similarity 0.79)
- DeepCalliFont: Few-Shot Chinese Calligraphy Font Synthesis by Integrating Dual-Modality Generative Models (AAAI 2024 · similarity 0.79)
- An Exemplar-based Framework for Chinese Text Recognition (AAAI 2025 · 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.