Similar articles

Abstract: An efficient search method is desired for calligraphic characters due to the explosive growth of calligraphy works in digital libraries. However, traditional optical character recognition (OCR) and handwritten character recognition (HCR) technologies are not suitable for calligraphic character retrieval. In this paper, a novel shape descriptor called SC-HoG is proposed by integrating global and local features for more discriminability, where a gradient descent algorithm is used to learn the optimal combining parameter. Then two efficient methods, keypoint-based method and locality sensitive hashing (LSH) based method, are proposed to accelerate the retrieval by reducing the feature set and converting the feature set to a feature vector. Finally, a re-ranking method is described for practicability. The approach filters query-dissimilar characters using the LSH-based method to obtain candidates first, and then re-ranks the candidates using the keypoint- or sample-based method. Experimental results demonstrate that our approaches are effective and efficient for calligraphic character retrieval.

[1]Aslan, C., Tari, S., 2005. An Axis-Based Representation for Recognition. 10th IEEE Int. Conf. on Computer Vision, 2:1339-1346.

[2]Bai, X., Latecki, L.J., 2008. Path similarity skeleton graph matching. IEEE Trans. Pattern Anal. Mach. Intell., 30(7):1282-1292.

[3]Bai, X., Wang, B., Wang, X., Liu, W., Tu, Z., 2010a. Co-transduction for Shape Retrieval. Proc. 11th European Conf. on Computer Vision: Part III, p.328-341.

[4]Bai, X., Yang, X., Latecki, L.J., Liu, W., Tu, Z., 2010b. Learning context-sensitive shape similarity by graph transduction. IEEE Trans. Pattern Anal. Mach. Intell., 32(5):861-874.

[5]Belongie, S., Malik, J., Puzicha, J., 2000. Shape Context: a New Descriptor for Shape Matching and Object Recognition. NIPS, p.831-837.

[6]Bosch, A., Zisserman, A., Munoz, X., 2007. Representing Shape with a Spatial Pyramid Kernel. Proc. 6th ACM Int. Conf. on Image and Video Retrieval, p.401-408.

[7]Brandt, S., Laaksonen, J., Oja, E., 2002. Statistical shape features for content-based image retrieval. J. Math. Imag. Vis., 17(2):187-198.

[8]Chou, C.H., Wu, C.S., Han, C.C., 2005. An Interactive Grading and Learning System for Chinese Calligraphy. IEEE Int. Conf. on Electro Information Technology, p.1-6.

[9]Dalal, N., Triggs, B., Rhone-Alps, I., Montbonnot, F., 2005. Histograms of Oriented Gradients for Human Detection. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 1:886-893.

[10]Dong, W., Wang, Z., Charikar, M., Li, K., 2008. Efficiently Matching Sets of Features with Random Histograms. Proc. 16th ACM Int. Conf. on Multimedia, p.179-188.

[11]Fonseca, M.J., Jorge, J.A., 2003. NB-Tree: an Indexing Structure for Content-Based Retrieval in Large Databases. Proc. 8th Int. Conf. on Database Systems for Advanced Applications, p.267-274.

[12]Fornes, A., Escalera, S., Llados, J., Valveny, E., 2010. Symbol Classification Using Dynamic Aligned Shape Descriptor. Proc. 20th Int. Conf. on Pattern Recognition, p.1957-1960.

[13]Grauman, K., Darrell, T., 2005. The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features. 10th IEEE Int. Conf. on Computer Vision, 1:1458-1465.

[14]Jagadish, H.V., Ooi, B.C., Tan, K.L., Yu, C., Zhang, R., 2005. iDistance: an adaptive B⁺-tree based indexing method for nearest neighbor search. ACM Trans. Database Syst., 30(2):364-397.

[15]Kortgen, M., Park, G.J., Novotni, M., Klein, R., 2003. 3D Shape Matching with 3D Shape Contexts. 7th Central European Seminar on Computer Graphics, p.55-66.

[16]Ling, H.B., Jacobs, D.W., 2007. Shape classification using the inner-distance. IEEE Trans. Pattern Anal. Mach. Intell., 29(2):286-299.

[17]Lowe, D.G., 1999. Object Recognition from Local Scale-Invariant Features. Proc. 7th IEEE Int. Conf. on Computer Vision, 2:1150-1157.

[18]Lu, W., Zhuang, Y., Wu, J., 2009. Discovering calligraphy style relationships by supervised learning weighted random walk model. Multimedia Syst., 15(4):221-242.

[19]Luo, B., Robles-Kelly, A., Torsello, A., Wilson, R.C., Hancock, E.R., 2001. Discovering Shape Categories by Clustering Shock Trees. Proc. 9th Int. Conf. on Computer Analysis of Images and Patterns, p.152-160.

[20]Mori, G., Malik, J., 2003. Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 1:134-141.

[21]Mori, G., Belongie, S., Malik, J., 2005. Efficient shape matching using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell., 27(11):1832-1837.

[22]Mortensen, E.N., Deng, H., Shapiro, L., 2005. A SIFT Descriptor with Global Context. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 1:184-190.

[23]Sebastian, T.B., Klein, P.N., Kimia, B.B., Center, G.E.G.R., Schenectady, N.Y., 2004. Recognition of shapes by editing their shock graphs. IEEE Trans. Pattern Anal. Mach. Intell., 26(5):550-571.

[24]Suard, F., Rakotomamonjy, A., Bensrhair, A., 2006. Object Categorization Using Kernels Combining Graphs and Histograms of Gradients. Proc. ICIAR, p.23-34.

[25]Torsello, A., Hancock, E.R., 2004. A skeletal measure of 2D shape similarity. Comput. Vis. Image Underst., 95(1):1-29.

[26]Torsello, A., Robles-Kelly, A., Hancock, E.R., 2007. Discovering shape classes using tree edit-distance and pairwise clustering. Int. J. Comput. Vis., 72(3):259-285.

[27]van Eede, M., Macrini, D., Telea, A., Sminchisescu, C., Dickinson, S.S., 2006. Canonical Skeletons for Shape Matching. 18th Int. Conf. on Pattern Recognition, 2:64-69.

[28]Wang, S.Z., Lee, H.J., 2001. Dual-Binarization and Anisotropic Diffusion of Chinese Characters in Calligraphy Documents. Proc. 6th Int. Conf. on Document Analysis and Recognition, p.271-275.

[29]Wang, T.T., Lu, T., Liu, W.Y., 2010. Robust Shape Retrieval Through a Novel Statistical Descriptor. Proc. 11th Pacific Rim Conf. on Advances in Multimedia Information Processing: Part I, p.330-337.

[30]Weber, R., Schek, H.J., Blott, S., 1998. A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces. Proc. Int. Conf. on Very Large Data Bases, p.194-205.

[31]Wong, S.T.S., Leung, H., Ip, H.H.S., 2006. Brush Writing Style Classification from Individual Chinese Characters. Proc. 18th Int. Conf. on Pattern Recognition, p.884-887.

[32]Wong, S.T.S., Leung, H., Ip, H.H.S., 2008. Model-based analysis of Chinese calligraphy images. Comput. Vis. Image Underst., 109(1):69-85.

[33]Wu, Y.F., Zhuang, Y.T., Pan, Y.H., Wu, J.Q., 2006. Web Based Chinese Calligraphy Learning with 3-D Visualization Method. IEEE Int. Conf. on Multimedia and Expo, p.2073-2076.

[34]Xu, S., Lau, F.C.M., Cheung, W.K., Pan, Y., 2005. Automatic generation of artistic Chinese calligraphy. IEEE Intell. Syst. Appl., 20(3):32-39.

[35]Xu, S., Jiang, H., Lau, F.C.M., Pan, Y., 2007. An Intelligent System for Chinese Calligraphy. Proc. National Conf. on Artificial Intelligence, p.1578-1583.

[36]Yang, X., Koknar-Tezel, S., Latecki, L.J., 2009. Locally Constrained Diffusion Process on Locally Densified Distance Spaces with Applications to Shape Retrieval. IEEE Conf. on Computer Vision and Pattern Recognition, p.357-364.

[37]Yankov, D., Keogh, E., Wei, L., Xi, X.P., Hodges, W., 2008. Fast best-match shape searching in rotation-invariant metric spaces. IEEE Trans. Multimedia, 10(2):230-239.

[38]Yu, J.H., Peng, Q.S., 2005. Realistic synthesis of cao shu of Chinese calligraphy. Comput. Graph., 29(1):145-153.

[39]Yu, K., Wu, J., Zhuang, Y., 2008. Skeleton-Based Recognition of Chinese Calligraphic Character Image. Proc. 9th Pacific Rim Conf. on Multimedia: Advances in Multimedia Information Processing, p.228-237.

[40]Zhang, J., Liu, W.Y., 2009. A Pixel-Level Statistical Structural Descriptor for Shape Measure and Recognition. Proc. 10th Int. Conf. on Document Analysis and Recognition, p.386-390.

[41]Zhang, J.S., Yu, J.H., Mao, G.H., Ye, X.Z., 2006. Denoising of Chinese calligraphy tablet images based on run-length statistics and structure characteristic of character strokes. J. Zhejiang Univ.-Sci. A, 7(7):1178-1186.

[42]Zhang, X.F., Zhuang, Y.T., 2007. Visual Verification of Historical Chinese Calligraphy Works. Proc. 13th Int. Multimedia Modeling Conf., p.354-363.

[43]Zhang, X.F., Zhuang, Y.T., Wu, J.Q., Wu, F., 2007. Hierarchical approximate matching for retrieval of Chinese historical calligraphy character. J. Comput. Sci. Technol., 22(4):633-640.

[44]Zhang, Z., Wu, J., Yu, K., 2010. Chinese Calligraphy Specific Style Rendering System. Proc. 10th Annual Joint Conf. on Digital Libraries, p.99-108.

[45]Zhu, Q., Wang, L., Wu, Y., Shi, J., 2008. Contour Context Selection for Object Detection: a Set-to-Set Contour Matching Approach. Proc. 10th European Conf. on Computer Vision, p.774-787.

[46]Zhuang, Y., Zhang, X., Wu, J., Lu, X., 2004. Retrieval of Chinese Calligraphic Character Image. Proc. Pacific Rim Conf. on Multimedia, p.17-24.

[47]Zhuang, Y., Zhang, X., Lu, W., Wu, F., 2005. Web-based Chinese calligraphy retrieval and learning system. LNCS, 3583:186-196.

[48]Zhuang, Y., Zhuang, Y.T., Li, Q., Chen, L., 2007. Interactive high-dimensional index for large Chinese calligraphic character databases. ACM Trans. Asian Lang. Inform. Process., 6(2):54-85.

[49]Zhuang, Y., Lu, W., Wu, J., 2009. Latent style model: discovering writing styles for calligraphy works. J. Vis. Commun. Image Represent., 20(2):84-96.