Better Text Detection through Improved K-means-based Feature Learning by Kardo

@inproceedings{Aziz2017BetterTD,
  title={Better Text Detection through Improved K-means-based Feature Learning by Kardo},
  author={Othman Aziz},
  year={2017}
}
Better Text Detection through Improved K-means-based Feature Learning Kardo Othman Aziz, M.S. Rochester Institute of Technology, 2017 Supervisor: Dr. Richard Zanibbi In this thesis, we propose a different technique to initialize a Convolutional K-means. We propose Visual Similarity Sampling (VSS) to collect 8 × 8 sample patches from images for convolutional feature learning. The algorithm uses within-class and between-class cosine similarity/dissimilarity measure to collect samples from both… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-2 of 2 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 36 references

ICDAR 2015 competition on Robust Reading

2015 13th International Conference on Document Analysis and Recognition (ICDAR) • 2015
View 20 Excerpts
Highly Influenced

Patch-based image representation and restoration

Markus Juvonen
PhD thesis, University of Helsinki, • 2017
View 7 Excerpts
Highly Influenced

Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning

2011 International Conference on Document Analysis and Recognition • 2011
View 9 Excerpts
Highly Influenced

Discriminative Bayesian Dictionary Learning for Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2016
View 4 Excerpts
Highly Influenced

Whiteboard Video Summarization via Spatio-Temporal Conflict Minimization

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) • 2017
View 1 Excerpt

Canny Text Detector: Fast and Robust Scene Text Localization Algorithm

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016

Similar Papers

Loading similar papers…