A Quick Response Code Beautification Method Based on Saliency Weighted Random Optimization
YANG Junfeng①② LIN Yaping①② OU bo① JIANG Junqiang①② LI Qiang①②
①(Collage of Information Science and Engineering, Hunan University, Changsha 410082, China) ②(Hunan Key Laboratory of Dependable System and Networks, Changsha 410082, China)
摘要 随着移动终端和移动互联网的发展，快速响应(QR)码被广泛运用于移动信息交互。但是，标准的 QR 码是由均匀分布的黑色与白色模块组成，外观类似噪声信号，缺乏视觉美感，限制了QR码的应用。针对此问题，该文提出一种提高QR码视觉效果的美化方法。该方法将给定的彩色图像进行显著性检测和半色调处理，得到相应的显著性矩阵和半色调图像，然后根据半色调图像上的网点分布，对QR码的模块分布进行优化。为了提高优化效率，该文提出一种显著性加权随机优化算法，将优化后的QR码和半色调图像进行融合，得到与半色调图像最相似的半色调QR码。在图像渲染阶段，该文提出一种基于二分搜索的色彩调整算法，得到具有色彩信息和视觉美感的彩色QR码。实验分析表明，该方法生成的QR码不仅保留了与标准QR码一样的抗遮挡、快速解码等特性，还有效地提升了视觉效果，具有很好的视觉吸引力。
Abstract：With the development of smart phones and mobile internet, Quick Response (QR) codes are widely applied to mobile information interaction. However, the appearance of the standard QR code is similar to the noise signal. It is lack of visual aesthetics, easy to damage the overall aesthetic of the publicity materials so that the promotional effect will be affected. To solve this problem, this paper proposes a beautification approach for embedding a color image in a QR code. At first, the method processes the given color image with saliency detection and halftoning techniques to acquire the corresponding saliency image and halftone image. Then, the modules distribution of QR code is optimized by according to the halftone image. In order to improve the optimization efficiency, a saliency weighted random sampling algorithm is proposed. Finally, a binary search based color adjustment algorithm is proposed in color rendering. Experimental results show that the color QR code generated by the proposed method can be correctly decoded. At the same time, it improves the visual appearance, increases the visual aesthetics, and possesses more visual appeal.
杨俊丰, 林亚平, 欧博, 蒋军强, 李强. 基于显著性加权随机优化的快速响应码美化方法[J]. 电子与信息学报, 2018, 40(2): 289-297.
YANG Junfeng, LIN Yaping, OU bo, JIANG Junqiang, LI Qiang. A Quick Response Code Beautification Method Based on Saliency Weighted Random Optimization. JEIT, 2018, 40(2): 289-297.
LIN Yishan, LUO Shengjie, and CHEN Bingyu. Artistic QR code embellishment[J]. Computer Graphics Forum, 2013, 32(7): 137-146. doi: 10.1111/cgf.12221.
[2]
LI Li, QIU Jinxia, LU Jianfeng, et al. An aesthetic QR code solution based on error correction mechanism[J]. Journal of Systems and Software, 2015, 116(C): 85-94. doi: 10.1016/j.jss. 2015.07.009.
[3]
NEVO A. Visualead[OL]. http://www.visualead.com/, 2013.
[4]
LIN Y H, CHANG Y P, and WU J L. Appearance-based QR code beautifier[J]. IEEE Transactions on Multimedia, 2013, 15(8): 2198-2207. doi: 10.1109/TMM.2013.2271745.
[5]
ONO S, MORINAGA K, and NAKAYAMA S. Animated two-dimensional barcode generation using optimization algorithms[J]. Scis, 2009, 2008: 1232-1237. doi: 10.14864/ softscis.2008.0.1232.0.
[6]
ONO S, MORINAGA K, and NAKAYAMA S. Barcode design by evolutionary computation[J]. Artificial Life and Robotics, 2008, 13(1): 238-241. doi: 10.1007/s10015-008- 0587-4.
[7]
ONO S, MORINAGA K, and NAKAYAMA S. Two- dimensional barcode decoration based on real-coded genetic algorithm[C]. 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence). IEEE, 2008: 1068-1073.
[8]
Denso Wave Inc. Logoq[OL]. http://www.qrcode.com/en/ codes/logoq.html, 2013.
[9]
GARATEGUY G J, ARCE G R, LAU D L, et al. QR images: Optimized image embedding in QR codes[J]. IEEE Transactions on Image Processing, 2014, 23(7): 2842-2853. doi: 10.1109/TIP.2014.2321501.
[10]
ZHANG Y, DENG S, LIU Z, et al. Aesthetic QR codes based on two-stage image blending[C]. International Conference on Multimedia Modeling. Springer International Publishing, Sydney, Australia, 2015: 183-194. doi: 10.1007/978-3-319- 14442-9_16.
[11]
LIN S S, HU M C, LEE C H, et al. Efficient QR code beautification with high quality visual content[J]. IEEE Transactions on Multimedia, 2015, 17(9): 1515-1524. doi: 10.1109/TMM.2015.2437711.
[12]
KURIBAYASHI M and MORII M. Enrichment of visual appearance of aesthetic QR code[C]. International Workshop on Digital Watermarking. Tokyo, Japan, 2015: 220-231. doi: 10.1007/978-3-319-31960-5_18.
LUO Huilan, WAN Chengtao, and KONG Fansheng. Salient region detection algorithm via KL dvergence and multi-scale merging[J]. Journal of Electronics & Information Technology, 2016, 38(7): 1594-1601 doi: 10.11999/JEIT151145.
XU Wei and TANG Zhenmin. Integrating phase congruency and two-dimensional principal component analysis for visual saliency prediction[J]. Journal of Electronics & Information Technology, 2015, 37(9): 2089-2096. doi: 10.11999/ JEIT141478.
TANG Hongmei, WU Shijing, GUO Yingchun et al. Saliency detection based on adaptive threshold segmentation and local background clues[J]. Journal of Electronics & Information Technology, 2017, 39(7): 1592-1598. doi: 10.11999/JEIT 160984.
JIANG Yuwen, TAN Leyi, and WANG Shoujue. Saliency detected model based on selective edges prior[J]. Journal of Electronics & Information Technology, 2015, 37(1): 130-136. doi: 10.11999/JEIT140119.
[17]
HOU X and ZHANG L. Saliency detection: A spectral residual approach[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Minneapolis, Minnesota, USA, 2007: 1-8.
[18]
LIU Y F and GUO J M. Dot-diffused halftoning with improved homogeneity[J]. IEEE Transactions on Image Processing, 2015, 24(11): 4581-4591. doi: 10.1109/TIP.2015. 2470599.
[19]
WANG Z, ARCE G R, and CRESCENZO G D. Halftone visual cryptography via error diffusion[J]. IEEE Transactions on Information Forensics and Security, 2009, 4(3): 383-396. doi: 10.1109/TIFS.2009.2024721.
[20]
WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612. doi: 10.1109/TIP.2003.819861.
