Research on TV Logo Detection Based on Compressive Sensing

doi:10.3969/j.issn.1671-1122.2015.05.012

Abstract

Abstract:

TV logo is embedded in complex background, and usually has hollow and translucent characteristics. There are many defects in the conventional TV logo detection techniques such as the complexities of image features extraction and matching algorithm as well as the characteristic dimension curse, so this paper proposes a method based on compressive sensing to quickly and efficiently identify the TV logo. This method directly processes raw pixels, not only avoiding the difficulty of features extraction, but also having good robustness for hollow and translucent logos. Experiment shows that when identifying TV logo in a single frame, the average recognition time is within 35ms, while recognition accuracy rate can reach more than 98%.

Key words: compressive sensing, TV logo, video detection

CLC Number:

TP309

XU Jie, HE Min, BAO Xiu-guo. Research on TV Logo Detection Based on Compressive Sensing[J]. Netinfo Security, 2015, 15(5): 77-81.

Figures/Tables 6

References 22

[1]	Sizintsev M, Derpanis K G, Hogue A.Histogram-based search: a comparative study[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2008. Anchorage, AK: IEEE Computer Society Press, 2008: 1-8.
[2]	Wang J, Duan L, Li Z.A robust method for TV logo tracking in video streams[C]// Proceedings of the IEEE International Conference on Multimedia and Expo 2006. Toronto, Ont: IEEE Computer Society Press, 2006: 1041-1044.
[3]	Maldonado-Bascon S, Lafuente-Arroyo S, Gil-Jimenez P.Road-sign detection and recognition based on support vector machines[J]. Journal of IEEE Transactions on Intelligent Transportation Systems, 2007,8(2): 264-278.
[4]	Mikolajczyk K, Schmid C.A performance evaluation of local descriptors[J]. Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(20): 1615-1630.
[5]	Donoho D L.Compressed sensing[J]. Journal of IEEE Transactions on Information Theory, 2006, 52(4): 1289-1306.
[6]	Candes E J, Romberg J, Tao T.Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information[J]. Journal of IEEE Transactions on Information Theory, 2006, 52(2): 489-509.
[7]	Candes E J, Romberg J, Tao T.Stable signal recovery from incomplete and inaccurate measurements[J]. Journal of Communications on Pure and Applied Mathematics, 2006, 59(8): 1207-1223.
[8]	Duarte M F, Davenport M A, Takhar D.Single-pixel imaging via compressive sampling[J]. Journal of IEEE Signal Processing Magazine, 2008, 25(2): 83-91.
[9]	Xu J, Ma J, Zhang D.Compressive video sensing based on user attention model[C]//Proceedings of the Picture Coding Symposium 2010. Nagoya: IEEE Computer Society Press, 2010: 90-93.
[10]	Xu J, Ma J, Zhang D.Improved total variation minimization method for compressive sensing by intra prediction[J]. Journal of Signal Processing,2012, 92(11): 2614-2623.
[11]	Taubock G, Hlawatsch F.A compressed sensing technique for OFDM channel estimation in mobile environments: Exploiting channel sparsity for reducing pilots[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing 2008. Las Vegas, NV: IEEE Computer Society Press, 2008: 2885-2888.
[12]	Ma Jianwei, Xu Jie, Bao Yuequan.Compressive sensing and its application: from sparse to low-rank regularized optimization[J]. Journal of Signal Processing, 2012, 28(5): 609-623.
[13]	Chartrand R, Nonconvex compressed sensing and error correction[C]//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing 2007. Honolulu, HI: IEEE Computer Society Press, 2007: 889-892.
[14]	Wright J, Yang A Y, Ganesh A.Robust face recognition via sparse representation[J]. Journal of IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227.
[15]	Nagesh P, Li B.A compressive sensing approach for expression-invariant face recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2009. Miami, FL: IEEE Computer Society Press, 2009: 1518-1525.
[16]	Yang A Y, Sastry S S, Ganesh A.Fast ℓ 1-minimization algorithms and an application in robust face recognition: A review[C]//Proceedings of the IEEE International Conference on Image Processing 2010. Hong Kong: IEEE Computer Society Press, 2010: 1849-1852.
[17]	Donoho D L, Elad M, Temlyakov V N.Stable recovery of sparse overcomplete representations in the presence of noise[J]. Journal of IEEE Transactions on Information Theory, 2006, 52(1): 6-18.
[18]	Chen S S B, Donoho D L, Saunders M A. Atomic decomposition by basis pursuit[J]. Journal of SIAM Journal on Scientific Computing,1998, 20(1): 33-61.
[19]	Van Den Berg E, Friedlander M P. Probing the Pareto frontier for basis pursuit solutions[J]. Journal of SIAM Journal on Scientific Computing, 2008, 31(2): 890-912.
[20]	Beeran Kutty S, Saaidin S, Yunus M.Evaluation of canny and sobel operator for logo edge detection[C]//2014 International Symposium on Technology Management and Emerging Technologies (ISTMET). 2014:153-156.
[21]	Zhang X, Zhang D, Liu F.Spatial HOG based TV logo detection[C]//The Fifth International Conference on Internet Multimedia Computing and Service. 2013:76-81.
[22]	Lowe D G.Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision, 2004, (60): 91-110.