whai362/PSENet

Health v2 · maintenance only

Adoption not part of the score

1186 stars · 338 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of PSENet, a progressive scale expansion network for robust scene text detection. It includes training, testing, and evaluation scripts for benchmarks like ICDAR 2015, Total-Text, and CTW1500.

Use cases

• detect text in natural scene images
• train a scene text detection model on ICDAR 2015
• evaluate text detection on Total-Text and CTW1500 benchmarks
• extract text regions from photos before OCR
• benchmark PSENet against other text detection methods
• fine-tune a pretrained text detection checkpoint

When to choose

• you need a proven scene text detection model with published benchmark results
• you want the official reference implementation of the PSENet paper
• you work with PyTorch and standard text detection datasets
• you need pretrained checkpoints for ICDAR 2015, Total-Text, or CTW1500

When to avoid

• you need text recognition (OCR) rather than detection only
• you want a maintained production framework - the project recommends MMOCR instead
• you need Python 2 compatibility or very recent PyTorch versions
• you require commercial support or frequent updates

Facets

library · maturity maintenance

computer-vision ocr machine-learning deep-learning computer-vision image-processing machine-learning artificial-intelligence python scene-text-detection psenet pytorch icdar2015 total-text ctw1500 research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="whai362/PSENet")