Scene Text Detection On Icdar 2015

评估指标

F-Measure

FPS

Precision

Recall

评测结果

各个模型在此基准测试上的表现结果

					Paper Title	Repository
TextFuseNet (ResNeXt-101)	92.23	-	93.96	90.56	TextFuseNet: Scene Text Detection with Richer Fused Features	-
CharNet H-88 (multi-scale)	91.55	-	92.65	90.47	Convolutional Character Networks
CharNet H-88 (single-scale)	90.97	-	89.99	91.98	Convolutional Character Networks
CharNet H-50 (multi-scale)	90.16	-	90.9	89.44	Convolutional Character Networks
SBD	90.1	-	92.1	88.2	Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection
CharNet H-57 (multi-scale)	90.06	-	91.43	88.74	Convolutional Character Networks
FOTS MS	89.84	-	91.85	87.92	FOTS: Fast Oriented Text Spotting with a Unified Network
CharNet H-50 (single-scale)	89.7	-	91.15	88.3	Convolutional Character Networks
CharNet H-57 (single-scale)	89.66	-	88.88	90.45	Convolutional Character Networks
PMTD	89.33	-	91.3	87.43	Pyramid Mask Text Detector
GNNets	88.52	-	90.41	86.71	Geometry Normalization Networks for Accurate Scene Text Detection
FOTS	87.99	-	91	85.17	FOTS: Fast Oriented Text Spotting with a Unified Network
DB-ResNet-50 (1152)	87.3	-	91.8	83.2	Real-time Scene Text Detection with Differentiable Binarization
DBNet++ (ResNet-50) (1152)	87.3	10	90.9	83.9	Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion
SPCNET	87.2	-	88.7	85.8	Scene Text Detection with Supervised Pyramid Context Network
FAST-B-1280	87.1	15.7	89.7	84.6	FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation
PSENet-1s	87.1	-	88.7	85.5	Shape Robust Text Detection with Progressive Scale Expansion Network
SAST	86.91	-	86.72	87.09	A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
CRAFT	86.9	-	89.8	84.3	Character Region Awareness for Text Detection
FAST-B-896	86.3	31.8	89.2	83.6	FAST: Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation

0 of 43 row(s) selected.

Command Palette

Scene Text Detection On Icdar 2015

评估指标

评测结果