Real-time Scene Text Detection with Differentiable Binarization

20 Nov 2019 Minghui Liao Zhaoyi Wan Cong Yao Kai Chen Xiang Bai

Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text. However, the post-processing of binarization is essential for segmentation-based detection, which converts probability maps produced by a segmentation method into bounding boxes/regions of text... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Scene Text Detection ICDAR 2015 DB-ResNet-50 (1152) F-Measure 87.3 # 13
Precision 91.8 # 5
Recall 83.2 # 18
Scene Text Detection MSRA-TD500 DB-ResNet-50 (736) Recall 79.2 # 2
Precision 91.5 # 1
F-Measure 84.9 # 1
Scene Text Detection SCUT-CTW1500 Ours-ResNet50 (1024) F-Measure 83.4 # 4
Scene Text Detection Total-Text DB-ResNet-50 (800) F-Measure 84.7% # 5

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