首页 » 文章 » 文章详细信息
Mathematical Problems in Engineering Volume 2018 ,2018-10-25
Joint Method of Interference Suppression and Super-Resolution for Chinese Characters Image with Interference
Research Article
Bo Jiang 1 Wei Hu 1 Jian Liang 2 Shouxu Zhang 3 Xiaolei Ma 4 Yan Zhou 1 Jinping Niu 1 Xiaoxuan Chen 1
Show affiliations
DOI:10.1155/2018/4203121
Received 2018-04-25, accepted for publication 2018-10-02, Published 2018-10-02
PDF
摘要

As Chinese characters image often has insufficient photography illumination, or underlines under characters, or low resolution, a joint method of interference suppression and super-resolution for Chinese characters image with interference is proposed. In the stage of interference suppression preprocessing, the technology of image layer separation is used to decompose Chinese characters image into the illumination layer and reflectance layer at first, and reflectance layer that contains the essential property of input image is retained consequently. Then the reflectance layer is decomposed into four coefficient subimages by wavelet transform, and image smoothing via L0 gradient minimization with different scale factors is adopted to these different coefficient subimages. Subsequently, by a simple background processing and image filtering, the image preprocessing for Chinese characters image with interference is ultimately completed. In the stage of image super-resolution, due to acquisition limitation of a large number of high-resolution Chinese characters images, we adopt neighbor embedding super-resolution method for its advantage of greatly reducing the scale of training set. In the key feature vector of Chinese characters image, the weights of horizontal and vertical stroke features are strengthened; meanwhile, the other stroke features of Chinese characters are also considered. Ultimately, a super-resolution method more suitable for Chinese characters image is proposed. Experimental results show that our method of interference suppression has the superiority for Chinese characters images with aforementioned interference, and our optimized super-resolution method has better performance for test Chinese characters images than bicubic interpolation method and three classical super-resolution methods.

授权许可

Copyright © 2018 Bo Jiang et al. 2018
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

图表

Overall flow chart of the proposed method.

Preprocessing experiment I on Chinese characters image with dark background. (a) Original Chinese characters image with dark background. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment I on Chinese characters image with dark background. (a) Original Chinese characters image with dark background. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment I on Chinese characters image with dark background. (a) Original Chinese characters image with dark background. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment I on Chinese characters image with dark background. (a) Original Chinese characters image with dark background. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment II on Chinese characters image with dark background. (a) Original Chinese characters image with dark background. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment II on Chinese characters image with dark background. (a) Original Chinese characters image with dark background. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment II on Chinese characters image with dark background. (a) Original Chinese characters image with dark background. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment II on Chinese characters image with dark background. (a) Original Chinese characters image with dark background. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment I on Chinese characters image with underlines. (a) Original Chinese characters image with underlines. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment I on Chinese characters image with underlines. (a) Original Chinese characters image with underlines. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment I on Chinese characters image with underlines. (a) Original Chinese characters image with underlines. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment I on Chinese characters image with underlines. (a) Original Chinese characters image with underlines. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment II on Chinese characters image with underlines. (a) Original Chinese characters image with underlines. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment II on Chinese characters image with underlines. (a) Original Chinese characters image with underlines. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment II on Chinese characters image with underlines. (a) Original Chinese characters image with underlines. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Preprocessing experiment II on Chinese characters image with underlines. (a) Original Chinese characters image with underlines. (b) Retained reflectance layer using layer separation method [15]. (c) Reflectance layer after three operations of wavelet decomposition [16], image smoothing [17], and wavelet synthesis [16]. (d) Final preprocessing result when (c) after three operations of gray-scale conversion, background processing, and median filtering.

Super-resolution experiment I on Chinese characters image with dark background after interference suppression. (a) One Chinese character in Figure 2(d). (b) Result by bicubic interpolation. (c)-(f) Results by super-resolution methods of classical neighbor embedding [6], sparse representation [1, 9], transformed self-exemplars [14], and ours, respectively. (e)-(k) Magnification display of part region of (b)-(f), respectively.

Super-resolution experiment II on Chinese characters image with dark background after interference suppression. (a) One Chinese character in Figure 3(d). (b) Result by bicubic interpolation. (c)-(f) Results by super-resolution methods of classical neighbor embedding [6], sparse representation [1, 9], transformed self-exemplars [14], and ours, respectively. (e)-(k) Magnification display of part region of (b)-(f), respectively.

Super-resolution experiment I on Chinese characters image with underlines after interference suppression. (a) One Chinese character in Figure 4(d). (b) Result by bicubic interpolation. (c)-(f) Results by super-resolution methods of classical neighbor embedding [6], sparse representation [1, 9], transformed self-exemplars [14], and ours, respectively. (e)-(k) Magnification display of part region of (b)-(f), respectively.

Super-resolution experiment II on Chinese characters image with underlines after interference suppression. (a) One Chinese character in Figure 5(d). (b) Result by bicubic interpolation. (c)-(f) Results by super-resolution methods of classical neighbor embedding [6], sparse representation [1, 9], transformed self-exemplars [14], and ours, respectively. (e)-(k) Magnification display of part region of (b)-(f), respectively.

通讯作者

Xiaoxuan Chen.School of Information Science and Technology, Northwest University, Xi’an 710127, China, nwu.edu.cn.chenxx@nwu.edu.cn

推荐引用方式

Bo Jiang,Wei Hu,Jian Liang,Shouxu Zhang,Xiaolei Ma,Yan Zhou,Jinping Niu,Xiaoxuan Chen. Joint Method of Interference Suppression and Super-Resolution for Chinese Characters Image with Interference. Mathematical Problems in Engineering ,Vol.2018(2018)

您觉得这篇文章对您有帮助吗?
分享和收藏
0

是否收藏?

参考文献
[1] W. Shi, J. Caballero, F. Huszár, J. Totz. et al.Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. :1874-1883. DOI: 10.1109/TIP.2010.2050625.
[2] E. J. Candès, X. Li, Y. Ma, J. Wright. et al.(2011). Robust principal component analysis?. Journal of the ACM.58(3, article 11). DOI: 10.1109/TIP.2010.2050625.
[3] Y. Li, M. S. Brown. Single image layer separation using relative smoothness. :2752-2759. DOI: 10.1109/TIP.2010.2050625.
[4] H. Demirel, G. Anbarjafari. (2011). IMAGE resolution enhancement by using discrete and stationary wavelet decomposition. IEEE Transactions on Image Processing.20(5):1458-1460. DOI: 10.1109/TIP.2010.2050625.
[5] T. Katsuki, A. Torii, M. Inoue. (2012). Posterior-mean super-resolution with a causal Gaussian Markov random field prior. IEEE Transactions on Image Processing.21(7):3182-3193. DOI: 10.1109/TIP.2010.2050625.
[6] H. Chang, D.-Y. Yeung, Y. Xiong. Super-resolution through neighbor embedding. :275-282. DOI: 10.1109/TIP.2010.2050625.
[7] K. Jia, X. Wang, X. Tang. (2013). Image transformation based on learning dictionaries across image spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence.35(2):367-380. DOI: 10.1109/TIP.2010.2050625.
[8] T. Ogawa, M. Haseyama. (2011). Missing intensity interpolation using a kernel PCA-based POCS algorithm and its applications. IEEE Transactions on Image Processing.20(2):417-432. DOI: 10.1109/TIP.2010.2050625.
[9] L. Xu, C. Lu, Y. Xu, J. Jia. et al.(2011). Image smoothing via gradient minimization. ACM Transactions on Graphics.30(6, article 174). DOI: 10.1109/TIP.2010.2050625.
[10] J.-B. Huang, A. Singh, N. Ahuja. Single image super-resolution from transformed self-exemplars. :5197-5206. DOI: 10.1109/TIP.2010.2050625.
[11] Y. Tai, J. Yang, X. Liu. Image super-resolution via deep recursive residual network. :2790-2798. DOI: 10.1109/TIP.2010.2050625.
[12] D.-T. Huang, W.-Q. Huang, P.-T. Gu, P.-Z. Liu. et al.(2017). Image super-resolution reconstruction based on regularization technique and guided filter. Infrared Physics & Technology.83:103-113. DOI: 10.1109/TIP.2010.2050625.
[13] H. Zhang, Y. Zhang, H. Li, T. S. Huang. et al.(2012). Generative Bayesian image super resolution with natural image prior. IEEE Transactions on Image Processing.21(9):4054-4067. DOI: 10.1109/TIP.2010.2050625.
[14] R. C. Gonzalez, R. E. Woods. (2007). Digital Image Processing (Second Edition). Publishing House of Electronics Industry:349-408. DOI: 10.1109/TIP.2010.2050625.
[15] C. Dong, C. C. Loy, K. He, X. Tang. et al.(2014). Learning a deep convolutional network for image super-resolution. European Conference on Computer Vision:184-199. DOI: 10.1109/TIP.2010.2050625.
[16] X. Chen, C. Qi. (2014). Low-rank neighbor embedding for single image super-resolution. IEEE Signal Processing Letters.21(1):79-82. DOI: 10.1109/TIP.2010.2050625.
[17] J. Yang, J. Wright, T. S. Huang, Y. Ma. et al.(2010). Image super-resolution via sparse representation. IEEE Transactions on Image Processing.19(11):2861-2873. DOI: 10.1109/TIP.2010.2050625.
[18] J. Yang, J. Wright, T. Huang, Y. Ma. et al.Image super-resolution as sparse representation of raw image patches. :1-8. DOI: 10.1109/TIP.2010.2050625.
[19] J. Jiang, X. Ma, C. Chen, T. Lu. et al.(2017). Single Image Super-Resolution via Locally Regularized Anchored Neighborhood Regression and Nonlocal Means. IEEE Transactions on Multimedia.19(1):15-26. DOI: 10.1109/TIP.2010.2050625.
文献评价指标
浏览 48次
下载全文 7次
评分次数 0次
用户评分 0.0分
分享 0次