Symmetric Inkball Alignment with Loopy Models

Alignment tasks generally seek to establish a spatial correspondence between two versions of a text, for example between a set of manuscript images and their transcript. This paper examines a different form of alignment problem, namely pixel-scale alignment between two renditions of a handwritten word or phrase. Using loopy inkball graph models, the proposed technique finds spatial correspondences between two text images such that similar parts map to each other. The method has applications to word spotting and signature verification, and can provide analytical tools for the study of handwriting variation.

[1]  Edward M. Riseman,et al.  Word spotting: a new approach to indexing handwriting , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Ching Y. Suen,et al.  Matching of complex patterns by energy minimization , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[3]  R. Manmatha,et al.  Holistic word recognition for handwritten historical documents , 2004, First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings..

[4]  Y. K. Wong,et al.  Offline signature verification with generated training samples , 2002 .

[5]  Daniel P. Huttenlocher,et al.  Distance Transforms of Sampled Functions , 2012, Theory Comput..

[6]  Miguel Angel Ferrer-Ballester,et al.  A Behavioral Handwriting Model for Static and Dynamic Signature Synthesis , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Tal Hassner,et al.  OCR-Free Transcript Alignment , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[8]  Nicholas R. Howe.  Inkball models for character localization and out-of-vocabulary word spotting , 2015, 2015 13th International Conference on Document Analysis and Recognition (ICDAR).

[9]  Gregory F. Cooper,et al.  The Computational Complexity of Probabilistic Inference Using Bayesian Belief Networks , 1990, Artif. Intell..

[10]  Anders Brun,et al.  Neural Ctrl-F: Segmentation-Free Query-by-String Word Spotting in Handwritten Manuscript Collections , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[11]  Sebastian Sudholt,et al.  Learning Deep Representations for Word Spotting under Weak Supervision , 2017, 2018 13th IAPR International Workshop on Document Analysis Systems (DAS).

[12]  Xiaoyu Song,et al.  Signature alignment based on GMM for on-line signature verification , 2017, Pattern Recognit..

[13]  Michael Isard,et al.  Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief Propagation , 2011, International Journal of Computer Vision.

[14]  Erik G. Learned-Miller,et al.  Data driven image models through continuous joint alignment , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Kaspar Riesen,et al.  Graph-Based Offline Signature Verification , 2019, ArXiv.

[16]  H. C. Longuet-Higgins,et al.  An algorithm for associating the features of two images , 1991, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[17]  Nicholas R. Howe,et al.  Part-Structured Inkball Models for One-Shot Handwritten Word Spotting , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[18]  Anders Brun,et al.  Semantic and Verbatim Word Spotting Using Deep Neural Networks , 2016, 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[19]  Javier Garrido Salas,et al.  BiosecurID: a multimodal biometric database , 2009, Pattern Analysis and Applications.