Sciweavers

205 search results - page 36 / 41
» Part-Based Recognition of Handwritten Characters
Sort
View
ICPR
2000
IEEE
14 years 11 months ago
Accuracy Improvement of Slant Estimation for Handwritten Words
Handwritten words are usually slant or Italicized due to the mechanism of handwriting and the personality. In order to improve the accuracy of character segmentation and recogniti...
Yimei Ding, Fumitaka Kimura, Yasuji Miyake, Malaya...
IJDAR
2008
121views more  IJDAR 2008»
13 years 9 months ago
Partial discriminative training for classification of overlapping classes in document analysis
For character recognition in document analysis, some classes are closely overlapped but are not necessarily to be separated before contextual information is exploited. For classifi...
Cheng-Lin Liu
ICDAR
2007
IEEE
14 years 4 months ago
Elastic Matching of Online Handwritten Tamil and Telugu Scripts Using Local Features
This paper describes character based elastic matching using local features for recognizing online handwritten data. Dynamic Time Warping (DTW) has been used with four different fe...
L. Prasanth, V. Babu, R. Sharma, G. V. Rao, Dinesh...
ICANN
2010
Springer
13 years 11 months ago
Accelerating Large-Scale Convolutional Neural Networks with Parallel Graphics Multiprocessors
Training convolutional neural networks (CNNs) on large sets of high-resolution images is too computationally intense to be performed on commodity CPUs. Such architectures however ...
Dominik Scherer, Hannes Schulz, Sven Behnke
AAAI
2008
14 years 4 days ago
Using a Geometric-Based Sketch Recognition Approach to Sketch Chinese Radicals
Unlike English, where unfamiliar words can be queried for its meaning by typing out its letters, the analogous operation in Chinese is far from trivial due to the nature of its wr...
Paul Taele, Tracy Hammond