Abstract：A covariance modeling method and a Bayesian method on Riemannian manifold are presented for classification of halftone image. According to the Fourier spectrum characteristic of halftone image,a feature extraction based on template matrices is presented to form a covariance matrix by combining with the spectrum of halftone image. An algorithm for covariance matrix extraction of halftone image is proposed by introducing a decision rule of effective image and partitioning technology. A Bayesian rule based on neighbor characteristic of tested samples and kernel density estimation is presented on Riemannian manifolds of symmetric positive definite matrices. In experiments,the problem of selection on threshold parameter is studied by statistical methods,the comparisons of the proposed method with 5 similar methods are conducted,and the influences of two parameters on classification performance and time cost of feature modeling are discussed. The experimental results show that the classification error of the proposed method is below 4% and computation time of modeling is under 100ms if parameters Q=32 or 64 and L=10~15. Furthermore,the proposed method is superior to other 5 methods.
[1] Ulichney R. Digital Halftoning and the Physical Reconstruction Function. Ph.D Dissertation. Cambridge, USA: Massachusetts Institute of Technology, 1986 [2] Ulichney R A. Dithering with Blue Noise. Proceedings of the IEEE, 1988, 76(1): 56-79 [3] Knuth D E. Digital Halftones by Dot Diffusion. ACM Trans on Graphics, 1987, 6(4): 245-273 [4] Mese M, Vaidyanathan P P. Lookup Table Method for Inverse Halftoning. IEEE Trans on Images Processing, 2001, 10(10): 1566-1578 [5] Huang W B, Su A W Y, Kuo Y H. Neural Network Based Method for Image Halftoning and Inverse Halftoning. Expert Systems with Applications, 2008, 34(4): 2491-2501 [6] Fung Y H, Chan Y H. A POCS-Based Restoration Algorithm for Restoring Halftoned Color-Quantized Images. IEEE Trans on Images Processing, 2006, 15(7): 1985-1992 [7] Mese M, Vaidyanathan P. Tree-Structured Method for LUT Inverse Halftoning and for Image Halftone. IEEE Trans on Images Processing, 2002, 11(6): 644-655 [8] Chung K L, Wu S T. Inverse Halftoning Algorithm Using Edge-Based Lookup Table Approach. IEEE Trans on Images Processing, 2005, 14(10): 1583-1589 [9] Suetake N, Tanaka G, Uchino E. Lookup Table and Gaussian Filter-Based Inverse Halftoning Method Excellent in Gray-Scale Reproducibility of Details and Flat Regions. Optical Review, 2009, 16(6): 594-600 [10] Freitas P G, Farias M C Q, de Araujo A P F. Fast Inverse Halftoning Algorithm for Ordered Dithered Images // Proc of the 24th SIBGRAPI Conference on Graphics, Patterns and Images. Maceio, Brazil, 2011: 250-257 [11] Saika Y, Okamoto K, Matsubara F. Probabilistic Modeling to Inverse Halftoning Based on Super Resolution // Proc of the International Conference on Control Automation and Systems. Gyeonggi-do, Republic of Korea, 2010: 162-167 [12] Stevenson R L. Inverse Halftoning via MAP Estimation. IEEE Trans on Image Processing, 1997, 6(4): 574-583 [13] Unal G B, Cetin A E. Restoration of Error-Diffused Images Using Projection onto Convex Sets. IEEE Trans on Images Processing, 2001, 10(12): 1836-1841 [14] Mese M, Vaidyanathan P P. Optimized Halftoning Using Dot Diffusion and Methods for Inverse Halftoning. IEEE Trans on Images Processing, 2000, 9(4): 691-709 [15] Chang Paochi, Yu Chesheng. Neural Net classification and LMS Reconstruction to Halftone Images // Proc of the SPIE Visual Communications and Image Processing. San Jose, USA, 1998: 592-602 [16] Kong Yueping, Zeng Ping, Zhang Yuepeng. Classification and Recognition Algorithm for the Halftone Image. Journal of Xidian University, 2011, 38(5): 52-58 (in Chinese) (孔月萍,曾 平,张跃鹏.一种半调图像分类识别算法.西安电子科技大学学报, 2011, 38(5): 52-58) [17] Kong Yueping. A Study of Inverse Halftoning and Quality Assessment Schemes. Ph.D Dissertation. Xi′an, China: Xidian University, 2008 (in Chinese) (孔月萍.图像逆半调及其质量评价技术研究.博士学位论文:西安:西安电子科技大学, 2008 [18] Liu Yunfu, Guo Jingming, Lee J D. Inverse Halftoning Based on the Bayesian Theorem. IEEE Trans on Image Processing, 2011, 20(4): 1077-1084 [19] Liu Yunfu, Guo Jingming, Lee J D. Halftone Image Classification Using LMS Algorithm and Naive Bayes. IEEE Trans on Image Processing, 2011, 20(10): 2837-2847 [20] Wu Yi, Cheng Jian, Wang Jun, et al. Real-Time Probabilistic Covariance Tracking with Efficient Model Update. IEEE Trans on Image Processing, 2012, 21(5): 2824-2837 [21] Qin Huafeng, Qin Lan, Xue Lian, et al. A Kernel Gabor-Based Weighted Region Covariance Matrix for Face Recognition. Sensors, 2012, 12(6): 7410-7422 [22] Harandi M T, Sanderson C, Wiliem A, et al. Kernel Analysis over Riemannian Manifolds for Visual Recognition of Actions, Pedestrians and Textures // Proc of the IEEE Workshop on the Applications of Computer Vision. Washington, USA, 2012: 433-439 [23] Tuzel O, Porikli F, Meer P. Region Covariance: A Fast Descriptor for Detection and Classification // Proc of the 9th European Conference on Computer Vision. Berlin, Germany, 2006, II: 589-600 [24]Pang Yanwei, Yuan Yuan, Li Xuelong. Gabor-Based Region Covariance Matrices for Face Recognition. IEEE Trans on Circuits and Systems for Video Technology, 2008, 18(7): 989-993 [25] Subbarao R, Meer P. Nonlinear Mean Shift Over Riemannian Manifolds. International Journal of Computer Vision, 2009, 84(1): 1-20 [26] Lang S. Differential and Riemannian Manifolds. Berlin, Germany: Springer-Verlag, 1995 [27] Chen Yongming, Lin Ping, He Yong, et al. Classification of Broadleaf Weed Images Using Gabor Wavelets and Lie Group Structure of Region Covariance on Riemannian Manifolds. Biosystems Engineering, 2011, 109(3): 220-227 [28] Tuzel O, Porikli F, Meer P. Pedestrian Detection via Classification on Riemannian Manifolds. IEEE Trans on Pattern Analysis and Machine Intelligence, 2008, 30(10): 1713-1727 [29] Pelletier B. Kernel Density Estimation on Riemannian Manifolds. Statistics and Probability Letters, 2005, 73(3): 297-304
2013, Vol. 26 
