Abstract
In text images, there are some frequently used characters repeating more than others. Likewise, some characters have common strokes. This characteristic is used in this paper for machine-printed text-image super resolution. After segmenting the input low-resolution image into text lines and characters, 1) the characters are clustered and the clusters with large number of members, corresponding to the frequent characters, are detected. 2) A text-specific multiple-image super resolution is applied to the members of each large cluster and the result is verified by the recognition confidence of an OCR system. 3) A training example set is then constructed by extracting patches from the low-resolution frequent characters and their verified super resolution. Using this example set, infrequent characters are super resolved through the neighbor embedding SR algorithm. By placing all the super-resolved characters on their corresponding positions in the high-resolution grid, the final high-resolution image is generated. Our method achieves significant improvements in visual image quality and OCR character accuracy compared to related SR methods.
Similar content being viewed by others
References
Abedi A, Kabir E (2016) Stroke width-based directional total variation regularisation for document image super resolution. IET Image Process 10:158–166
Andrew KDC, Webb R (2011) Statistical Pattern Recognition, 3rd ed.: wiley
Bergen JR, Anandan P, Hanna KJ and Hingorani R (1992) “Hierarchical model-based motion estimation,” in Computer Vision—ECCV’92, pp. 237–252
Chan T-M, Zhang J, Pu J, Huang H (2009) Neighbor embedding based super-resolution algorithm through edge detection and feature selection. Pattern Recogn Lett 30:494–502
Chang H, Yeung DY and Xiong Y (2004) “Super-resolution through neighbor embedding,” in Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 I.E. Computer Society Conference on, pp. I-I
Chen X and Qi C (2014) “Document image super-resolution using structural similarity and Markov random field”
Dai D, Wang Y, Chen Y and VL (2016) Gool, “Is image super-resolution helpful for other vision tasks?,” in 2016 I.E. Winter Conference on Applications of Computer Vision (WACV), pp. 1–9
Datsenko D and Elad M (2007) “Example-based single document image super-resolution: a global MAP approach with outlier rejection,” Multidimensional Systems and Signal Processing, vol. 18, pp. 103–121, 2007/09/01
Donaldson K, Myers GK (2005) Bayesian super-resolution of text in videowith a text-specific bimodal prior. IJDAR 7:159–167
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38:295–307
Farsiu S, Robinson MD, Elad M, Milanfar P (2004) Fast and robust multiframe super resolution. Image Proc IEEE Trans on 13:1327–1344
Farsiu S, Robinson D, Elad M, Milanfar P (2004) Advances and challenges in super-resolution. Int J Imaging Syst Technol 14:47–57
Glasner D, Bagon S and Irani M (2009) “Super-resolution from a single image,” in Computer Vision, 2009 I.E. 12th International Conference on, pp. 349–356
Haiping L, Kot AC, Shi YQ (2004) Distance-reciprocal distortion measure for binary document images. Signal Proc Lett IEEE 11:228–231
Lu Y (1993) “On the segmentation of touching characters,” in Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on, pp. 440–443
Luong H and Philips W (2008) “Robust reconstruction of low-resolution document images by exploiting repetitive character behaviour,” International Journal of Document Analysis and Recognition (IJDAR), vol. 11, pp. 39–51, 2008/10/01
Ma D and Agam G (2013) “A super resolution framework for low resolution document image OCR,” in IS&T/SPIE Electronic Imaging, pp. 86580P-86580P-9
Nasrollahi K, Moeslund TB (2014) Super-resolution: a comprehensive survey. Mach Vis Appl 25:1423–1468
Nayef N, Chazalon J, Gomez-Kramer P and Ogier JM (2014) “Efficient example-based super-resolution of single text images based on selective patch processing,” in Document Analysis Systems (DAS), 2014 11th IAPR International Workshop on, pp. 227–231
Peyrard C, Baccouche M, Mamalet F and Garcia C (2015) “ICDAR2015 Competition on Text Image Super-Resolution,” in Document Analysis and Recognition (ICDAR), 13th International Conference on, 2015, pp. 1201–1205
Smith R (2007) “An Overview of the Tesseract OCR Engine,” in ICDAR, pp. 629–633
Thouin PD, Chang C-I (2000) A method for restoration of low-resolution document images. Int J Doc Anal Recognit 2:200–210
Timofte R, De Smet V and Van Gool L (2014) “A+: Adjusted anchored neighborhood regression for fast super-resolution,” in Computer Vision--ACCV, ed: Springer, 2014, pp. 111–126
Walha R, Drira F, Lebourgeois F, Alimi AM, Garcia C (2016) Resolution enhancement of textual images: a survey of single image-based methods. IET Image Process 10:325–337
Walha R, Drira F, Lebourgeois F, Garcia C and Alimi AM (2015) “Resolution enhancement of textual images via multiple coupled dictionaries and adaptive sparse representation selection,” International Journal on Document Analysis and Recognition (IJDAR), pp. 1–21
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. Image Proc IEEE Trans on 13:600–612
Zeyde R, Elad M and Protter M (2012) “On single image scale-up using sparse-representations,” in Curves and Surfaces, ed: Springer, pp. 711–730
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Abedi, A., Kabir, E. Text image super resolution using within-scale repetition of characters and strokes. Multimed Tools Appl 76, 16415–16438 (2017). https://doi.org/10.1007/s11042-016-3919-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3919-8