TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Scene Text Detection	ICDAR 2015	PAN	F-Measure	85.9	# 22
Scene Text Detection	ICDAR 2015	PAN	Precision	90.8	# 13
Scene Text Detection	ICDAR 2015	PAN	Recall	81.5	# 26
Scene Text Detection	ICDAR 2017 MLT	PAN	Precision	80	# 9
Scene Text Detection	ICDAR 2017 MLT	PAN	Recall	69.8	# 7
Scene Text Detection	ICDAR 2017 MLT	PAN	F-Measure	74.3%	# 5
Scene Text Detection	SCUT-CTW1500	PAN	F-Measure	85	# 6
Scene Text Detection	SCUT-CTW1500	PAN	Precision	86.8	# 7
Scene Text Detection	SCUT-CTW1500	PAN	Recall	83.2	# 7
Scene Text Detection	SCUT-CTW1500	PAN	FPS	65.2	# 5

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn-with-pyramid-attention-network-for/scene-text-detection-on-scut-ctw1500)](https://paperswithcode.com/sota/scene-text-detection-on-scut-ctw1500?p=mask-r-cnn-with-pyramid-attention-network-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn-with-pyramid-attention-network-for/scene-text-detection-on-icdar-2017-mlt-1)](https://paperswithcode.com/sota/scene-text-detection-on-icdar-2017-mlt-1?p=mask-r-cnn-with-pyramid-attention-network-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/mask-r-cnn-with-pyramid-attention-network-for/scene-text-detection-on-icdar-2015)](https://paperswithcode.com/sota/scene-text-detection-on-icdar-2015?p=mask-r-cnn-with-pyramid-attention-network-for)`

Mask R-CNN with Pyramid Attention Network for Scene Text Detection

22 Nov 2018 · Zhida Huang, Zhuoyao Zhong, Lei Sun, Qiang Huo ·

In this paper, we present a new Mask R-CNN based text detection approach which can robustly detect multi-oriented and curved text from natural scene images in a unified manner. To enhance the feature representation ability of Mask R-CNN for text detection tasks, we propose to use the Pyramid Attention Network (PAN) as a new backbone network of Mask R-CNN. Experiments demonstrate that PAN can suppress false alarms caused by text-like backgrounds more effectively. Our proposed approach has achieved superior performance on both multi-oriented (ICDAR-2015, ICDAR-2017 MLT) and curved (SCUT-CTW1500) text detection benchmark tasks by only using single-scale and single-model testing.

PDF Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

Curved Text Detection

Scene Text Detection

Text Detection

Datasets

ssd ICDAR 2015

SCUT-CTW1500

ICDAR 2017

Results from the Paper

Edit

Ranked #6 on Scene Text Detection on SCUT-CTW1500

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Scene Text Detection	ICDAR 2015	PAN	F-Measure	85.9	# 22	Compare
			Precision	90.8	# 13	Compare
			Recall	81.5	# 26	Compare
Scene Text Detection	ICDAR 2017 MLT	PAN	Precision	80	# 9	Compare
			Recall	69.8	# 7	Compare
			F-Measure	74.3%	# 5	Compare
Scene Text Detection	SCUT-CTW1500	PAN	F-Measure	85	# 6	Compare
			Precision	86.8	# 7	Compare
			Recall	83.2	# 7	Compare
			FPS	65.2	# 5	Compare

Methods

Add Remove

Convolution • Mask R-CNN • RoIAlign • RPN • Softmax

Edit Social Preview

Mask R-CNN with Pyramid Attention Network for Scene Text Detection

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove