Research map / Detection and segmentation / CNN features
MCMLSD: A Dynamic Programming Approach to Line Segment Detection
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 |
|---|---|---|---|
| combine probabilistic Hough line detection with Markov-chain dynamic programming for segment localization | MCMLSD · YorkUrbanDB test | recall at 90 segments: 0.62; 48% higher than the next-best method | Helped |
| combine probabilistic Hough line detection with Markov-chain dynamic programming for segment localization | MCMLSD · YorkUrbanDB test | maximum recall: 0.80 versus 0.57 | Helped |
| use MCMLSD instead of LSD | line segment detection · YorkUrbanDB test | precision at the same recall: 0.27 -> 0.40 | Helped |
| rank segments by posterior probability alone (ablation) | MCMLSD · YorkUrbanDB training | recall | Hurt |
| multiply posterior probability by segment length (ablation) | MCMLSD · YorkUrbanDB training | recall | Helped |
| rank by posterior odds of fully ON versus fully OFF (ablation) | MCMLSD · YorkUrbanDB training | recall | Helped |
| rank by the sum of ON-state marginal posterior probabilities (ablation) | MCMLSD · YorkUrbanDB training | recall | Helped |
Closest papers by meaning
- ScaleLSD: Scalable Deep Line Segment Detection Streamlined (CVPR 2025 · similarity 0.86)
- Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation (CVPR 2025 · similarity 0.85)
- Improving Transformer Based Line Segment Detection with Matched Predicting and Re-ranking (AAAI 2025 · similarity 0.84)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.84)
- Stratify or Die: Rethinking Data Splits in Image Segmentation (NeurIPS 2025 · similarity 0.84)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · similarity 0.84)
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.