Text Detection based on Edge Enhanced Contrast Extremal Region and Tensor Voting in Natural Scene Images
3
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In this paper, a robust text detection method based on edge enhanced contrasting extremal region (CER) is proposed using stroke width transform (SWT) and tensor voting. First, the edge enhanced CER extracts a number of covariant regions, which is a stable connected component from input images. Next, SWT is created by the distance map, which is used to eliminate non-text regions. Then, these candidate text regions are verified based on tensor voting, which uses the input center point in the previous step to compute curve salience values. Finally, the connected component grouping is applied to a cluster closed to characters. The proposed method is evaluated with the ICDAR2003 and ICDAR2013 text detection competition datasets and the experiment results show high accuracy compared to previous methods.
Abstract
In this paper, a robust text detection method based on edge enhanced contrasting extremal region (CER) is proposed using stroke width transform (SWT) and tensor voting. First, the edge enhanced CER extracts a number of covariant regions, which is a stable connected component from input images. Next, SWT is created by the distance map, which is used to eliminate non-text regions. Then, these candidate text regions are verified based on tensor voting, which uses the input center point in the previous step to compute curve salience values. Finally, the connected component grouping is applied to a cluster closed to characters. The proposed method is evaluated with the ICDAR2003 and ICDAR2013 text detection competition datasets and the experiment results show high accuracy compared to previous methods.
참고문헌 (25)
- G. Zhou, "Detecting multi lingual text in natural scene", International Symposium on Access Spaces, pp.116~120 (2011)
- S. A. Angadi, "A texture based methodology for text region extraction from low resolution natural scene images", Advance Computing Conference, pp.121~128 (2010)
- Xiaoqing Liu, "Multiscale Edge-Based Text Extraction from Complex Images", ICME (2006)
- Qixiang Ye, "Text detection and restoration in natural scene images", Journal of Visual Communication and Image Representation, 18, pp.504~513 (2007)
- 최현수, "텐서보팅과 마르코프 랜덤 필드를 이용한 자연 영상의 텍스트 이진화", 스마트미디어저널, 4(4), pp.18~23 (2015), (사)한국스마트미디어학회
- R. Jiang, "Using connected components features to detect and segment text", Journal of Image and Graphics (2006)
- L. Neumann, "On combining multiple segmentations in scene text recognition", ICDAR, pp.523~527 (2013)
- Li, Yao, "Scene text detection via stroke width", ICPR, pp.681~684 (2012)
- B. Epshtein, "Detecting text in natural scenes with stroke width transform", IEEE Conference on Computer Vision and Pattern Recognition, pp.2963~2970 (2010)
- Alvaro Gonzalez, "Text location in complex images", ICPR, pp.617~620 (2012)
- W. Huang, "Robust scene text detection with convolution neural network induced MSER trees", ECCV, pp.497~511 (2014)
- M. Jaderberg, "Deep features for text spotting", ECCV, pp.512~528 (2014)
- Cunzhao Shi, "Scene text detection using graph model built upon maximally stable extremal regions", Pattern Recognition Letters, 34, pp.107~116 (2013)
- L. Neumann, "Real-time scene text localization and recognition", CVPR, pp.3538~3545 (2012)
- Chen Huizhong, "Robust Text Detection in Natural Images with Edge-Enhanced Maximally Stable Extremal Regions", ICIP (2011)
- Toan Dinh Nguyen, "Tensor Voting Based Text Localization in Natural Scene Images", IEEE Signal Processing Letters, 17, pp.639~642 (2010)
- Mikolajczyk, K., "A comparison of affine region detectors", International. J. Computer Vision, 65(1), pp.43~72 (2005)
- G. Medioni, "A computational framework for segmentation and grouping" (2000), Elsevier
- S. Aja-Fernndez, "Tensors in image processing and computer vision" (2009), Springer Publishing Co
- T. D. Nguyen, "Color image segmentation using tensor voting based color clustering", Pattern Recogn. Letters, pp.605~614 (2012)
- Rodrigo Minetto, "Snooper Text : A text detection system for automatic indexing of urban scenes", Computer Vision and Image Understanding, 122, pp.92~104 (2014)
- Yao Li, "Characterness : An Indicator of Text in the Wild", IEEE Transactions on Image Processing, 23(4), pp.1666~1677 (2014)
- Xiaobing Wang, "Natural scene text detection with multi-layer segmentation and higher order conditional random field based analysis", Pattern Recognition Letters, pp.41~47 (2015)
- D. Karatzas, "Icdar2013robust reading competition", ICDAR, pp.1484~1493 (2013)
- Lei Sun, "A robust approach for text detection from natural scene images", Pattern Recognition Letters, pp.2906~2920 (2015)