Transcription of Real-time Scene Text Detection with Differentiable ...
{{id}} {{{paragraph}}}
Example: bankruptcy
Real-time Scene Text Detection with Differentiable ...
Real-time Scene Text Detection with Differentiable BinarizationMinghui Liao1 , Zhaoyi Wan2 , Cong Yao2, Kai Chen3,4, Xiang Bai1 1 Huazhong University of Science and Technology,2 Megvii,3 Shanghai Jiao Tong University,4 Onlyou segmentation-based methods are quite popular inscene text Detection , as the segmentation results can more ac-curately describe Scene text of various shapes such as curvetext. However, the post-processing of binarization is essen-tial for segmentation-based Detection , which converts proba-bility maps produced by a segmentation method into bound-ing boxes/regions of text. In this paper, we propose a mod-ule named Differentiable Binarization (DB), which can per-form the binarization process in a segmentation network. Op-timized along with a DB module, a segmentation network canadaptively set the thresholds for binarization, which not onlysimplifies the post-processing but also enhances the perfor-mance of text Detection .
from the background, but also separate text instances which are closely jointed. Some examples are illustrated in Fig.7. The reasons that DB improves the performance can be explained by the backpropagation of the gradients. Lets take the binary cross-entropy loss as an example. Define f(x) = 1 1+e kx + +) + + +
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: