Sciweavers

566 search results - page 19 / 114
» OCR with No Shape Training
Sort
View
ICIP
2000
IEEE
14 years 9 months ago
A Novel Scheme for Image Rotation for Document Processing
Rotation of the binary image of a document page for correcting the skew in the case of OCR or signature verification systems entails disfigurement of the shape of the characters, ...
Kaushik Mahata, A. G. Ramakrishnan
ICML
2004
IEEE
14 years 8 months ago
Improving SVM accuracy by training on auxiliary data sources
The standard model of supervised learning assumes that training and test data are drawn from the same underlying distribution. This paper explores an application in which a second...
Pengcheng Wu, Thomas G. Dietterich
IJFCS
2006
77views more  IJFCS 2006»
13 years 7 months ago
Spike Trains in Spiking Neural P Systems
We continue here the study of the recently introduced spiking neural P systems, which mimic the way that neurons communicate with each other by means of short electrical impulses, ...
Gheorghe Paun, Mario J. Pérez-Jiméne...
NCA
2006
IEEE
13 years 7 months ago
Evolutionary training of hardware realizable multilayer perceptrons
The use of multilayer perceptrons (MLP) with threshold functions (binary step function activations) greatly reduces the complexity of the hardware implementation of neural networks...
Vassilis P. Plagianakos, George D. Magoulas, Micha...
CVPR
2011
IEEE
12 years 11 months ago
Learning People Detection Models from Few Training Samples
People detection is an important task for a wide range of applications in computer vision. State-of-the-art methods learn appearance based models requiring tedious collection and ...
Leonid Pishchulin, Christian Wojek, Arjun Jain, Th...