抗倾斜的中文文本图像文件识别技术
|
摘要
针对实际应用场景中如何在大批量图像文件中快速找到中文印刷体文本图像文件进行OCR (Optical Character Recognition)识别的问题,本文在笔画宽度变换算法(SWT)的基础上,设计了针对中文文本固有特点的启发式规则,并将水平投影技术与离散傅里叶变换相结合,提出了一种适合倾斜角度在–90至90°之间的中文印刷体文本图像文件识别技术.实验结果显示,在1606张测试集图像文件的识别中,本文算法针对文本图像文件整体识别F值(F-Measure)为0.95,平均识别耗时为0.65 s.
In view of how to quickly find Chinese printed text image files in bulk image file for Optical Character Recognition(OCR) recognition in practical application scenarios,this study designs heuristic rules for the inherent characteristics of Chinese text,based on the Stroke Width Transform algorithm(SWT),and combines horizontal projection technology with discrete Fourier transform,a Chinese printed text image file recognition technique suitable for tilt angles between –90 and 90° is proposed.The experimental results show that in 1606 test set image files,the overall recognition F-measure of the algorithm for text image files is 0.95,and the average recognition time is 0.65 s.
In view of how to quickly find Chinese printed text image files in bulk image file for Optical Character Recognition(OCR) recognition in practical application scenarios,this study designs heuristic rules for the inherent characteristics of Chinese text,based on the Stroke Width Transform algorithm(SWT),and combines horizontal projection technology with discrete Fourier transform,a Chinese printed text image file recognition technique suitable for tilt angles between –90 and 90° is proposed.The experimental results show that in 1606 test set image files,the overall recognition F-measure of the algorithm for text image files is 0.95,and the average recognition time is 0.65 s.
引文
1 Epshtein B, Ofek E, Wexler Y. Detecting text in natural scenes with stroke width transform. Proceedings of 2010IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA. 2010.2963-2970.[doi:10.1109/CVPR.2010.5540041]
2 Yao C, Bai X, Liu WY, et al. Detecting texts of arbitrary orientations in natural images. Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Providence, RI, USA. 2012. 1083-1090.[doi:10.1109/CVPR.2012.6247787]
3 Chen HZ, Tsai SS, Schroth G, et al. Robust text detection in natural images with edge-enhanced maximally stable extremal regions. Proceedings of the 2011 18th IEEE International Conference on Image Processing. Brussels,Belgium. 2011. 2609-2612.[doi:10.1109/ICIP.2011.6116200]
4 Matas J, Chum O, Urban M, et al. Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing,2004, 22(10):761-767.[doi:10.1016/j.imavis.2004.02.006]
5 Tang YB, Wu XQ. Scene text detection using superpixelbased stroke feature transform and deep learning based region classification. IEEE Transactions on Multimedia,2018, 20(9):2276-2288.[doi:10.1109/TMM.2018.2802644]
6 Zhou XY, Yao C, Wen H, et al. EAST:An efficient and accurate scene text detector. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu, HI, USA. 2017. 2642-2651.[doi:10.1109/CVPR.2017.283]
7 Yao C, Wu JN, Zhou XY, et al. Incidental scene text understanding:Recent progresses on ICDAR 2015 robust reading competition challenge 4. arXiv:1511.09207, 2015.
8 Tian Z, Huang WL, He T, et al. Detecting text in natural image with connectionist text proposal network. Proceedings of the 14th European Conference on Computer vision.Amsterdam, The Netherlands. 2016. 56-72.[doi:10.1007/978-3-319-46484-8_4]
9缪裕青,刘水清,万桢,等.自然场景图像中的中文文本检测算法.计算机工程与设计,2018, 39(3):804-807.[doi:10.16208/j.issn 1000-7024.2018.03.036]
10 Ren XH, Chen K, Yang XK, et al. A novel text structure feature extractor for Chinese scene text detection and recognition. Proceedings of the 2016 23rd International Conference on Pattern Recognition. Cancun, Mexico. 2016.3380-3385.[doi:10.1109/ICPR.2016.7900156]
11 Jiang XY, Lian J, Xia ZQ, et al. Fast Chinese character detection from complex scenes. Proceedings of the 2016 6th International Conference on Image Processing Theory, Tools and Applications. Oulu, Finland. 2016. 1-4.[doi:10.1109/IPTA.2016.7821001]
12 Sakila A, Vijayarani DS. Skew detection and correction in the document image. International Journal of Innovative Research in Science, Engineering and Technology, 2017,17457-17465.[doi:10.15680/IJIRSET.2016.0608274]
13 Singh R, Kaur R. Improved skew detection and correction approach using discrete Fourier algorithm. International Journal of Soft Computing and Engineering, 2013, 3(4):5-7.
14 Kaur M, Jindal S. An integrated skew detection and correction using fast Fourier transform and DCT.International Journal of Scientific&Technology Research,2013, 2(12):164-169.
15李秀勤.我国红头文件现状分析.合经作济与科技,2010,(11):60-61.[doi:10.13665/j.cnki.hzjjykj.2010.11.004]
16 Russakovsky O, Deng J, Su H, et al. Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 2015, 115(3):211-252.[doi:10.1007/s11263-015-0816-y]
2 Yao C, Bai X, Liu WY, et al. Detecting texts of arbitrary orientations in natural images. Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Providence, RI, USA. 2012. 1083-1090.[doi:10.1109/CVPR.2012.6247787]
3 Chen HZ, Tsai SS, Schroth G, et al. Robust text detection in natural images with edge-enhanced maximally stable extremal regions. Proceedings of the 2011 18th IEEE International Conference on Image Processing. Brussels,Belgium. 2011. 2609-2612.[doi:10.1109/ICIP.2011.6116200]
4 Matas J, Chum O, Urban M, et al. Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing,2004, 22(10):761-767.[doi:10.1016/j.imavis.2004.02.006]
5 Tang YB, Wu XQ. Scene text detection using superpixelbased stroke feature transform and deep learning based region classification. IEEE Transactions on Multimedia,2018, 20(9):2276-2288.[doi:10.1109/TMM.2018.2802644]
6 Zhou XY, Yao C, Wen H, et al. EAST:An efficient and accurate scene text detector. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu, HI, USA. 2017. 2642-2651.[doi:10.1109/CVPR.2017.283]
7 Yao C, Wu JN, Zhou XY, et al. Incidental scene text understanding:Recent progresses on ICDAR 2015 robust reading competition challenge 4. arXiv:1511.09207, 2015.
8 Tian Z, Huang WL, He T, et al. Detecting text in natural image with connectionist text proposal network. Proceedings of the 14th European Conference on Computer vision.Amsterdam, The Netherlands. 2016. 56-72.[doi:10.1007/978-3-319-46484-8_4]
9缪裕青,刘水清,万桢,等.自然场景图像中的中文文本检测算法.计算机工程与设计,2018, 39(3):804-807.[doi:10.16208/j.issn 1000-7024.2018.03.036]
10 Ren XH, Chen K, Yang XK, et al. A novel text structure feature extractor for Chinese scene text detection and recognition. Proceedings of the 2016 23rd International Conference on Pattern Recognition. Cancun, Mexico. 2016.3380-3385.[doi:10.1109/ICPR.2016.7900156]
11 Jiang XY, Lian J, Xia ZQ, et al. Fast Chinese character detection from complex scenes. Proceedings of the 2016 6th International Conference on Image Processing Theory, Tools and Applications. Oulu, Finland. 2016. 1-4.[doi:10.1109/IPTA.2016.7821001]
12 Sakila A, Vijayarani DS. Skew detection and correction in the document image. International Journal of Innovative Research in Science, Engineering and Technology, 2017,17457-17465.[doi:10.15680/IJIRSET.2016.0608274]
13 Singh R, Kaur R. Improved skew detection and correction approach using discrete Fourier algorithm. International Journal of Soft Computing and Engineering, 2013, 3(4):5-7.
14 Kaur M, Jindal S. An integrated skew detection and correction using fast Fourier transform and DCT.International Journal of Scientific&Technology Research,2013, 2(12):164-169.
15李秀勤.我国红头文件现状分析.合经作济与科技,2010,(11):60-61.[doi:10.13665/j.cnki.hzjjykj.2010.11.004]
16 Russakovsky O, Deng J, Su H, et al. Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 2015, 115(3):211-252.[doi:10.1007/s11263-015-0816-y]