A hybrid feature extraction framework for handwritten numeric fields recognition

Jung Hsien Chiang, Paul Gader

研究成果: Conference contribution

摘要

A hybrid feature extraction framework for handwritten numeric fields recognition is described. The numeric fields were extracted from binary images of credit card application forms. The images include identity numbers (ID) and phone numbers. The feature extraction framework utilizes a cascade of a Kohonen self-organizing feature map (SOM) and a set of non-linear filtering units. The goals of our feature extraction process are to provide reliable information to the recognition stage. The recognition stage uses the feature set as inputs to a multi-layer neural network. We present experimental results which demonstrate the ability to extract features automatically in handwritten digit recognition. Experiments were performed on a test data set from the CCL/ITRI Database which consists of over 90,390 handwritten numeric digits. Recognition rate of 98.6% is achieved on this database.

原文English
主出版物標題Track D
主出版物子標題Parallel and Connectionist Systems
發行者Institute of Electrical and Electronics Engineers Inc.
頁面436-440
頁數5
ISBN(列印)081867282X, 9780818672828
DOIs
出版狀態Published - 1996 一月 1
事件13th International Conference on Pattern Recognition, ICPR 1996 - Vienna, Austria
持續時間: 1996 八月 251996 八月 29

出版系列

名字Proceedings - International Conference on Pattern Recognition
4
ISSN(列印)1051-4651

Other

Other13th International Conference on Pattern Recognition, ICPR 1996
國家Austria
城市Vienna
期間96-08-2596-08-29

    指紋

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

引用此

Chiang, J. H., & Gader, P. (1996). A hybrid feature extraction framework for handwritten numeric fields recognition. 於 Track D: Parallel and Connectionist Systems (頁 436-440). [547604] (Proceedings - International Conference on Pattern Recognition; 卷 4). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.1996.547604