Scene Text Detection

Detecting text regions in natural scene images

Datasets

Results

accuracy

Canonical metric

Canonical Benchmark

coco-text

Dataset from Papers With Code

Primary metric: accuracy

Leading models on coco-text.

Rank	Model	f-measure	Year	Source
1	TCM	65.9	2026	paper
2	PANet (Joint)	64.5	2026	paper
3	LRANet	61.7	2026	paper
4	DPText-DETR	61.6	2026	paper
5	MAEDet	60.6	2026	paper
6	DBNet	60.5	2026	paper
7	DBNet++	59.5	2026	paper
8	SRFormer	59.4	2026	paper
9	FCENet	57.9	2026	paper
10	PSENet	56.0	2026	paper

11 datasets tracked for this task.

Other tasks in Computer Vision.