Efficient shape matching for Chinese calligraphic character retrieval

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]  Sibel Tari,et al.  An axis-based representation for recognition , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[2]  E. Hancock,et al.  A Skeletal Measure of 2D Shape Similarity , 2001 .

[3]  Linda G. Shapiro,et al.  A SIFT descriptor with global context , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Yueting Zhuang,et al.  Visual Verification of Historical Chinese Calligraphy Works , 2007, MMM.

[5]  Chin-Chuan Han,et al.  An interactive grading and learning system for chinese calligraphy , 2005, 2005 IEEE International Conference on Electro Information Technology.

[6]  Li Wei,et al.  Fast Best-Match Shape Searching in Rotation-Invariant Metric Spaces , 2007, IEEE Transactions on Multimedia.

[7]  Jun-song Zhang,et al.  Denoising of Chinese calligraphy tablet images based on run-length statistics and structure characteristic of character strokes , 2006 .

[8]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Trevor Darrell,et al.  The pyramid match kernel: discriminative classification with sets of image features , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[10]  Edwin R. Hancock,et al.  Discovering Shape Classes using Tree Edit-Distance and Pairwise Clustering , 2007, International Journal of Computer Vision.

[11]  Marcel Körtgen,et al.  3D Shape Matching with 3D Shape Contexts , 2003 .

[12]  Yueting Zhuang,et al.  Skeleton-Based Recognition of Chinese Calligraphic Character Image , 2008, PCM.

[13]  Hsi-Jian Lee,et al.  Dual-binarization and anisotropic diffusion of Chinese characters in calligraphy documents , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[14]  Sergio Escalera,et al.  Symbol Classification Using Dynamic Aligned Shape Descriptor , 2010, 2010 20th International Conference on Pattern Recognition.

[15]  Yueting Zhuang,et al.  Interactive high-dimensional index for large Chinese calligraphic character databases , 2007, TALIP.

[16]  Beng Chin Ooi,et al.  iDistance: An adaptive B+-tree based indexing method for nearest neighbor search , 2005, TODS.

[17]  Jitendra Malik,et al.  Shape Context: A New Descriptor for Shape Matching and Object Recognition , 2000, NIPS.

[18]  Zhe Wang,et al.  Efficiently matching sets of features with random histograms , 2008, ACM Multimedia.

[19]  Yueting Zhuang,et al.  Web based Chinese Calligraphy Learning with 3-D Visualization Method , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[20]  Bo Wang,et al.  Co-transduction for Shape Retrieval , 2010, ECCV.

[21]  Jing Zhang,et al.  A Pixel-level Statistical Structural Descriptor for Shape Measure and Recognition , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[22]  Kai Yu,et al.  Chinese calligraphy specific style rendering system , 2010, JCDL '10.

[23]  Jitendra Malik,et al.  Recognizing objects in adversarial clutter: breaking a visual CAPTCHA , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[24]  Horace Ho-Shing Ip,et al.  Brush Writing Style Classification from Individual Chinese Characters , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[25]  Joaquim A. Jorge,et al.  NB-Tree : An Indexing Structure for Content-Based Retrieval in Large Databases , 2003 .

[26]  Yueting Zhuang,et al.  Retrieval of Chinese Calligraphic Character Image , 2004, PCM.

[27]  Yueting Zhuang,et al.  Discovering calligraphy style relationships by Supervised Learning Weighted Random Walk Model , 2009, Multimedia Systems.

[28]  Longin Jan Latecki,et al.  Path Similarity Skeleton Graph Matching , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Hans-Jörg Schek,et al.  A Quantitative Analysis and Performance Study for Similarity-Search Methods in High-Dimensional Spaces , 1998, VLDB.

[30]  Andrew Zisserman,et al.  Representing shape with a spatial pyramid kernel , 2007, CIVR '07.

[31]  Yueting Zhuang,et al.  Web-Based Chinese Calligraphy Retrieval and Learning System , 2005, ICWL.

[32]  Yueting Zhuang,et al.  Hierarchical Approximate Matching for Retrieval of Chinese Historical Calligraphy Character , 2007, Journal of Computer Science and Technology.

[33]  Yunhe Pan,et al.  Automatic generation of artistic chinese calligraphy , 2004, IEEE Intelligent Systems.

[34]  Jitendra Malik,et al.  Efficient shape matching using shape contexts , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Haibin Ling,et al.  Shape Classification Using the Inner-Distance , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Edwin R. Hancock,et al.  Discovering Shape Categories by Clustering Shock Trees , 2001, CAIP.

[37]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[38]  Sven J. Dickinson,et al.  Canonical Skeletons for Shape Matching , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[39]  Zhuowen Tu,et al.  Learning Context-Sensitive Shape Similarity by Graph Transduction , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[40]  Longin Jan Latecki,et al.  Locally constrained diffusion process on locally densified distance spaces with applications to shape retrieval , 2009, CVPR.

[41]  Hao Jiang,et al.  An Intelligent System for Chinese Calligraphy , 2007, AAAI.

[42]  Tong Lu,et al.  Robust Shape Retrieval through a Novel Statistical Descriptor , 2010, PCM.

[43]  Philip N. Klein,et al.  Recognition of shapes by editing their shock graphs , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Erkki Oja,et al.  Statistical Shape Features for Content-Based Image Retrieval , 2004, Journal of Mathematical Imaging and Vision.

[45]  Jianbo Shi,et al.  Contour Context Selection for Object Detection: A Set-to-Set Contour Matching Approach , 2008, ECCV.

[46]  Alain Rakotomamonjy,et al.  Object Categorization Using Kernels Combining Graphs and Histograms of Gradients , 2006, ICIAR.

[47]  Qunsheng Peng,et al.  Realistic synthesis of cao shu of Chinese calligraphy , 2005, Comput. Graph..

[48]  Yueting Zhuang,et al.  Latent Style Model: Discovering writing styles for calligraphy works , 2009, J. Vis. Commun. Image Represent..

[49]  Horace Ho-Shing Ip,et al.  Model-based analysis of Chinese calligraphy images , 2005, International Conference on Information Visualisation.