Shape Robust Text Detection with Progressive Scale Expansion Network

Scene text detection has witnessed rapid progress especially with the recent development of convolutional neural networks. However, there still exists two challenges which prevent the algorithm into industry applications... (read more)

PDF Abstract CVPR 2019 PDF CVPR 2019 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Scene Text Detection ICDAR 2015 PSENet-1s F-Measure 85.7 # 19
Precision 86.9 # 23
Recall 84.5 # 15
Scene Text Detection ICDAR 2017 MLT PSENet (ResNet-152) Precision 75.35 # 13
Recall 69.18 # 8
F-Measure 72.13% # 11
Scene Text Detection SCUT-CTW1500 PSENet-1s F-Measure 82.2 # 5
Precision 84.8 # 5
Recall 79.7 # 7
Scene Text Detection Total-Text PSENet-4s F-Measure 79.6%% # 12
Precision 84.5 # 7
Recall 75.2 # 9

Methods used in the Paper


METHOD TYPE
Average Pooling
Pooling Operations
Residual Connection
Skip Connections
ReLU
Activation Functions
1x1 Convolution
Convolutions
Batch Normalization
Normalization
Bottleneck Residual Block
Skip Connection Blocks
Global Average Pooling
Pooling Operations
Residual Block
Skip Connection Blocks
Kaiming Initialization
Initialization
Max Pooling
Pooling Operations
Convolution
Convolutions
ResNet
Convolutional Neural Networks