|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| Toru Wakahara, Kazumi Odaka, "Adaptive Normalization of Handwritten Characters Using Global/Local Affine Transformation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 12, pp. 1332-1341, December, 1998. | |||
| BibTex | x | ||
| @article{ 10.1109/34.735806, author = {Toru Wakahara and Kazumi Odaka}, title = {Adaptive Normalization of Handwritten Characters Using Global/Local Affine Transformation}, journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {20}, number = {12}, issn = {0162-8828}, year = {1998}, pages = {1332-1341}, doi = {http://doi.ieeecomputersociety.org/10.1109/34.735806}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - JOUR JO - IEEE Transactions on Pattern Analysis and Machine Intelligence TI - Adaptive Normalization of Handwritten Characters Using Global/Local Affine Transformation IS - 12 SN - 0162-8828 SP1332 EP1341 EPD - 1332-1341 A1 - Toru Wakahara, A1 - Kazumi Odaka, PY - 1998 KW - Adaptive normalization KW - deformation model KW - global and local affine transformation KW - weighted least-squares criterion KW - distortion-tolerant shape matching. VL - 20 JA - IEEE Transactions on Pattern Analysis and Machine Intelligence ER - | |||
Abstract—Conventional normalization methods for handwritten characters have limitations as preprocessing operations because they are category-independent. This paper introduces an adaptive or category-dependent normalization method that normalizes an input pattern against each reference pattern using global/local affine transformation (GAT/LAT) in a hierarchical manner as a general deformation model. Also, the normalization criterion is clearly defined as minimization of the mean of nearest-neighbor interpoint distances between each reference pattern and a normalized input pattern. According to the above-mentioned criterion, optimal GAT/LAT is determined by iterative application of weighted least-squares fitting techniques. Experiments using input patterns of 3,171 character categories, including Kanji, Kana, and alphanumerics, written by 36 people in the cursive style against square-style reference patterns show not only that the proposed method can absorb a fairly large amount of handwriting fluctuation within the same category, but also that discrimination ability is greatly improved by the suppression of excessive normalization against similarly shaped but different categories. Furthermore, comparative results obtained by the conventional shape normalization method for preprocessing are presented to show the superiority of the proposed category-dependent GAT/LAT normalization over category-independent normalization.
[1] G. Nagy and N. Tuong, "Normalization Techniques for Handprinted Numerals," Comm. ACM, vol. 13, pp. 475-481, 1970.
[2] R.G. Casey, "Moment Normalization of Handprinted Characters," IBM J. Res. Develop., vol. 14, pp. 548-557, 1970.
[3] S.-W. Lee and J.-S. Park, "Nonlinear Shape Normalization Methods for the Recognition of Large-Set Handwritten Characters," Pattern Recognition, vol. 27, pp. 895-902, 1994.
[4] Y. Yamashita, K. Higuchi, Y. Yamada, and Y. Haga, "Classification of Handprinted Kanji Characters by the Structured Segment Matching Method," Pattern Recognition Letters, vol. 1, pp. 475-479, 1983.
[5] H. Yamada, K. Yamamoto, and T. Saito, "A Nonlinear Normalization Method for Handprinted Kanji Character RecognitionLine Density Equalization," Pattern Recognition, vol. 23, pp. 1,023-1,029, 1990.
[6] J. Tsukumo and H. Tanaka, "Classification of Handprinted Chinese Characters Using Nonlinear Normalization Methods," Proc. Ninth Int'l Conf. Pattern Recognition, Nov. 1988, pp. 168-171.
[7] P. Simard, Y. LeCun, and J. Denker, "Efficient Pattern Recognition Using a New Transformation Distance," Neural Information Processing Systems, vol. 5, pp. 50-59. Morgan Kaufmann, 1993.
[8] T. Wakahara, "Shape Matching Using LAT and Its Application to Handwritten Numeral Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, pp. 618-629, 1994.
[9] Mathematical Society of Japan, Encyclopedic Dictionary of Mathematics.Cambridge, Mass.: MIT Press, 1977.
[10] T. Wakahara, A. Suzuki, N. Nakajima, S. Miyahara, and K. Odaka, "Stroke-Number and Stroke-Order Free On-Line Kanji Character Recognition as One-to-One Stroke Correspondence Problem," IEICE Trans. Information and Systems, vol. E79-D, pp. 529-534, 1996.