Fast Convolutional OCR with the Scanning N-Tuple Grid

9 years 5 months ago
Fast Convolutional OCR with the Scanning N-Tuple Grid
This paper introduces a novel high speed convolutional character recognition system. Convolutional mode operation means that no prior localization or segmentation of characters is required, making this mode extremely robust. The method uses a 2-d n-tuple grid to sample the image, but decomposes the address calculations into two onedimensional scans. This simple innovation leads to a very fast system, and speeds in excess of 100,000 recognitions per second have been achieved for a 10-class character recognition problem, when operated in convolutional mode. Quantitative performance results show an error rate of 4.3% on the MNist dataset of isolated hand-written characters. Qualitative results are presented on museum archive card images, indicating that the method has great potential for the character recognition component in a document image analysis system for images of this type.
Simon M. Lucas, Kyu Tae Cho
Added 24 Jun 2010
Updated 24 Jun 2010
Type Conference
Year 2005
Authors Simon M. Lucas, Kyu Tae Cho
Comments (0)