Deep-Learning Approach for Text Detection Using Fully Convolutional Networks
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Text, as one of the most influential inventions of humanity, has played an important role in human life since ancient times. The rich and precise information embodied in text is very useful in a wide range of vision-based applications such as the text data extracted from images that can provide information for automatic annotation, indexing, language translation, and the assistance systems for impaired persons. Therefore, natural-scene text detection with active research topics regarding computer vision and document analysis is very important. Previous methods have poor performances due to numerous false-positive and true-negative regions. In this paper, a fully-convolutional-network (FCN)-based method that uses supervised architecture is used to localize textual regions. The model was trained directly using images wherein pixel values were used as inputs and binary ground truth was used as label. The method was evaluated using ICDAR-2013 dataset and proved to be comparable to other feature-based methods. It could expedite research on text detection using deep-learning based approach in the future.
Abstract
Text, as one of the most influential inventions of humanity, has played an important role in human life since ancient times. The rich and precise information embodied in text is very useful in a wide range of vision-based applications such as the text data extracted from images that can provide information for automatic annotation, indexing, language translation, and the assistance systems for impaired persons. Therefore, natural-scene text detection with active research topics regarding computer vision and document analysis is very important. Previous methods have poor performances due to numerous false-positive and true-negative regions. In this paper, a fully-convolutional-network (FCN)-based method that uses supervised architecture is used to localize textual regions. The model was trained directly using images wherein pixel values were used as inputs and binary ground truth was used as label. The method was evaluated using ICDAR-2013 dataset and proved to be comparable to other feature-based methods. It could expedite research on text detection using deep-learning based approach in the future.
참고문헌 (33)
- C. Yao, "Rotation-invariant features for multi-oriented text detection in natural images", PLoS One, 8(8) (2013)
- C. Yao, "A learned multi-scale representation for scene text recognition", CVPR (2014)
- "ICDAR 2013 robust reading competition"[URL]
- X. Chen, "Detecting and reading text in natural scenes", CVPR (2004)
- Y. Zhong, "Locating text in complex color images", Pattern Recognition, 28(10), pp.1523~1535 (1995)[DOI]
- K. I. Kim, "Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm", IEEE Trans. PAMI, 25(12), pp.1631~1639 (2003)[DOI]
- J. Gllavata, "Text detection in images based on unsupervised classification of high-frequency wavelet coefficients", ICPR (2004)
- B. Leibe, "Scale-invariant object categorization using a scale-adaptive mean-shift search", Pattern Recognition, pp.145~153 (2004)
- M. R. Lyu, "A comprehensive method for multilingual video text detection, localization, and extraction", IEEE Trans. CSVT, 15(2), pp.243~255 (2005)
- Y. Zhong, "Automatic caption localization in compressed video", IEEE Trans. PAMI, 22(4), pp.385~392 (2000)[DOI]
- P. Viola, "Fast and robust classification using asymmetric adaboost and a detector cascade", Proc. of NIPS (2001)
- V. Wu, "Finding text in images", ACM Int. Conf. Digital Libraries (1997)
- C. Wolf, "Extraction and recognition of artificial text in multimedia documents", Formal Pattern Analysis and Applications, 6(4), pp.309~326 (2004)
- K. Wang, "Word spotting in the wild", ECCV (2010)
- B. Epshtein, "Detecting text in natural scenes with stroke width transform", CVPR (2010)
- C. Yao, "Detecting texts of arbitrary orientations in natural images", CVPR (2012)
- C. Yi, "Text string detection from natural scenes by structure-based partition and grouping", IEEE Trans. Image Processing, 20(9), pp.2594~2605 (2011)[DOI]
- W. Huang, "Text localization in natural images using stroke feature transform and text covariance descriptors", ICCV (2013)
- A. Jain, "Automatic text location in images and video frames", Pattern Recognition, 31(12), pp.2055~2076 (1998)[DOI]
- L. Neumann, "A method for text localization and recognition in real-world images", ACCV (2010)
- J. Wright, "Robust face recognition via sparse representation", IEEE Trans. PAMI, 31(2), pp.210~227 (2009)[DOI]
- M. Elad, "Image denoising via sparse and redundant representations over learned dictionaries", IEEE Trans. Image Processing, 15(12), pp.3736~3745 (2006)[DOI]
- M. Zhao, "Text detection in images using sparse representation with discriminative dictionaries", Image and Vision Computing, 28(12), pp.1590~1599 (2010)[DOI]
- P. Shivakumara, "A laplacian approach to multi-oriented text detection in video", IEEE Trans. PAMI, 33(2), pp.412~419 (2011)[DOI]
- Y. Pan, "A hybrid approach to detect and localize texts in natural scene images", IEEE Trans. Image Processing, 20(3), pp.800~813 (2011)[DOI]
- J. Long, "Fully convolutional networks for semantic segmentation", CVPR (2015)
- W. Huang, "Robust scene text detection with convolution neural network induced mser trees", ECCV (2014)
- Z. Zhang, "Multi-oriented text detection with fully convolutional networks", CVPR (2016)
- S. Xie, "Holistically-Nested Edge Detection", ICCV (2015)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", ICLR (2015)
- X. C. Yin, "Multi-orientation scene text detection with adaptive clustering", IEEE Trans. on PAMI, 37(9), pp.1930~1937 (2015)[DOI]
- A. Zamberletti, "Text localization based on fast feature pyramids and multi-resolution maximally stable extremal regions", ACCV workshop (2014)
- Z. Zhang, "Symmetrybased text line detection in natural scenes", CVPR (2015)