Corpus ID: 6118239

Improving Text Proposals for Scene Images with Fully Convolutional Networks

  title={Improving Text Proposals for Scene Images with Fully Convolutional Networks},
  author={Dena Bazazian and Raul Gomez and Anguelos Nicolaou and L. G. I. Bigorda and Dimosthenis Karatzas and Andrew D. Bagdanov},
Text Proposals have emerged as a class-dependent version of object proposals - efficient approaches to reduce the search space of possible text object locations in an image. Combined with strong word classifiers, text proposals currently yield top state of the art results in end-to-end scene text recognition. In this paper we propose an improvement over the original Text Proposals algorithm of Gomez and Karatzas (2016), combining it with Fully Convolutional Networks to improve the ranking of… Expand
Weakly Supervised Text Attention Network for Generating Text Proposals in Scene Images
Fully Convolutional Networks for Text Understanding in Scene Images
W-A net: Leveraging Atrous and Deformable Convolutions for Efficient Text Detection
  • Sukhad Anand, Zoya Khan
  • Computer Science
  • 2020 Digital Image Computing: Techniques and Applications (DICTA)
  • 2020
Word Spotting in Scene Images Based on Character Recognition
Selective Style Transfer for Text
Arbitrary-Oriented Scene Text Detection via Rotation Proposals
Reading Text in the Wild from Compressed Images


Multi-oriented Text Detection with Fully Convolutional Networks
Object proposals for text extraction in the wild
Reading Text in the Wild with Convolutional Neural Networks
Character proposal network for robust text extraction
Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
End-to-end text recognition with convolutional neural networks
Enhancing energy minimization framework for scene text recognition with top-down cues
Robust Scene Text Detection with Convolution Neural Network Induced MSER Trees
End-to-end scene text recognition
Symmetry-based text line detection in natural scenes
  • Zheng Zhang, W. Shen, C. Yao, X. Bai
  • Computer Science
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015