Image super-resolution approach for license-plate recognition

doi:10.7523/j.issn.1002-1175.2013.01.021

Abstract

Abstract:

An object-oriented image super-resolution approach is proposed, which imitates visual cognition of human beings. The reconstruction procedure needs only a single image of the license plate. In the training stage, the corresponding relationship between high and low image patches is built by combined sparse coding. After an object is detected, the low resolution object image is reconstructed by compressing sensing under assumption of sparse representation. Experimental results on license plate images show that the PSNR is improved by nearly 2 dB compared to conventional non-object oriented strategy, and 20% of misrecognized characters are correctly recognized after reconstruction.

Key words: object oriented, super-resolution, compressed sensing, sparse coding, neighbor feature

CLC Number:

TP391

YAO Zhen-Jie, YI Wei-Dong. Image super-resolution approach for license-plate recognition[J]. , 2013, 30(1): 137-143.

References

[1] Park S C, Park M K, Kang M G. Super-resolution image reconstruction: a technical overview[J]. IEEE Signal Processing Magazine, 2003, 20(3):21-36.

[2] Yao Z J, Yi W D. A high accuracy image fusion algorithm for multi-image sensors[J]. Computer Science, 2009, 36(10A):265-268(in Chinese). 姚振杰,易卫东. 多传感器高精度图像融合算法[J]. 计算机科学, 2009, 36(10A):265-268.

[3] Tsai R Y, Huang T S. Multiple frame image restoration and registration[C]//Advances in Computer Vision and Image Processing. Greenwich: JAI Press, 1984: 317-339.

[4] Zhao S B, Peng S L.Wavelet-domain HMT-based image superresolution[J]. Journal of Computer-Aided Design & Computer Graphics, 2003, 15(11): 1347-1352(in Chinese). 赵书斌, 彭思龙. 基于小波域HMT模型的图像超分辨率重构[J]. 计算机辅助设计与图形学学报, 2003,15(11):1347-1352.

[5] Stark H, Oskoui P. High-resolution image recovery from imageplane arrays, using convex projections[J]. Journal of Optical Society of America A, 1989, 6(11):1715-1726.

[6] Freeman W T, Pasztor E C. Learning low-level vision[C]//Proceedings of Seventh International Conference on Computer Vision. Corfu: IEEE, 1999: 1182-1189.

[7] Yang J C, Wright J, Huang T S, et al. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing, 2010, 19(11): 2861-2873.

[8] Kim K I, Kwon Y. Single-image super-resolution using sparse regression and natural image prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(6): 1127-1133.

[9] Glasner D, Bagon S, Irani M. Super-resolution from a single image[C]//12th International Conference on Computer Vision. Kyoto: IEEE, 2009: 349-356.

[10] Anagnostopoulos C, Anagnostopoulos I, Psoroulas I, et al. License plate recognition from still images and video sequences: a survey[J]. IEEE Transactions on Intelligent Transportation Systems, 2008, 9(3): 377-391.

[11] Hanton K, Sunde J, Butavicius M, et al. Super-resolution of infrared images: Does it improve operator object detection performance?[J]. Journal of Computing and Information Technology, 2010, 18(2): 141-150.

[12] Carlson E, Rasquinha R, Zhang K, et al. A sparse object coding scheme in area v4[J]. Current Biology, 2011,21(4): 288-293.

[13] Candés E, Romberg J, Tao T. Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information[J]. IEEE Transactions on Information Theory, 2006, 52(2): 489-509.

[14] Donoho D L. For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution[J]. Communications on Pure and Applied Mathematics, 2006, 59(6):797-829.

[15] Lee H, Battle A, Raina R, et al. Efficient sparse coding algorithms[C]//Advances in Neural Information Processing Systems (NIPS). 2007:801-808.

[16] Viola P, Jones M J. Rapid object detection using a boosted cascade of simple features[C]//IEEE CVPR. 2001.

[17] LeCun Y, Bottou L, Bengio Y, et al.Gradient-based learning applied to document recognition[C]//Proceedings of the IEEE.Nov 1998, 86(11):2278-2324.