A novel feature extraction technique for the recognition of segmented handwritten characters
作者： M. Blumenstein , B. Verma , H. Basli
DOI: 10.1109/ICDAR.2003.1227647
关键词: Intelligent character recognition 、 Word recognition 、 Artificial neural network 、 Artificial intelligence 、 Computer science 、 Pattern recognition 、 Feature extraction 、 Speech recognition 、 Feature (machine learning) 、 Intelligent word recognition 、 Image segmentation 、 Segmentation
摘要: High accuracy character recognition techniques can provide useful information for segmentation-based handwritten word systems. This research describes neural network-based segmented that may be applied to the segmentation and components of an off-line system. Two architectures along with two different feature extraction were investigated. A novel technique is discussed compared others in literature. Recognition results above 80% are reported using characters automatically from CEDAR benchmark database as well standard alphanumerics.
sci-hub.se 参考文章(12)
M. Blumenstein, B. Verma, A new segmentation algorithm for handwritten word recognition international joint conference on neural network. ,vol. 4, pp. 2893- 2898 ,(1999) , 10.1109/IJCNN.1999.833544
F. Kimura, N. Kayahara, Y. Miyake, M. Shridhar, Machine and human recognition of segmented characters from handwritten words international conference on document analysis and recognition. ,vol. 2, pp. 866- 869 ,(1997) , 10.1109/ICDAR.1997.620635
James R. Parker, Practical Computer Vision Using C ,(1993)
M. Blumenstein, B. Verma, Neural-based solutions for the segmentation and recognition of difficult handwritten words from a benchmark database international conference on document analysis and recognition. pp. 281- 284 ,(1999) , 10.1109/ICDAR.1999.791779
C.Y. Suen, R. Legault, C. Nadal, M. Cheriet, L. Lam, Building a new generation of handwriting recognition systems Pattern Recognition Letters. ,vol. 14, pp. 303- 315 ,(1993) , 10.1016/0167-8655(93)90096-V
M. Shridhar, A. Badreldin, High accuracy character recognition algorithm using fourier and topological descriptors Pattern Recognition. ,vol. 17, pp. 515- 524 ,(1984) , 10.1016/0031-3203(84)90049-9
T. Y. Zhang, C. Y. Suen, A fast parallel algorithm for thinning digital patterns Communications of the ACM. ,vol. 27, pp. 236- 239 ,(1984) , 10.1145/357994.358023
J.J. Hull, A database for handwritten text recognition research IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 16, pp. 550- 554 ,(1994) , 10.1109/34.291440
Sung-Bae Cho, Neural-network classifiers for recognizing totally unconstrained handwritten numerals IEEE Transactions on Neural Networks. ,vol. 8, pp. 43- 53 ,(1997) , 10.1109/72.554190
S. Singh, M. Hewitt, Cursive digit and character recognition in CEDAR database international conference on pattern recognition. ,vol. 2, pp. 2569- 2572 ,(2000) , 10.1109/ICPR.2000.906138