By Topic

Neural network based segmentation of handwritten words

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $31
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Eastwood, B. ; R. Melbourne Inst. of Technol., Vic., Australia ; Jennings, A. ; Harvey, A.

Techniques for off-line recognition of handwritten words commonly require a form of character segmentation. We present an approach based on training of a neural network for segmentation. Using a large database of hand-segmented images we can successfully train the network to segment images. Results indicate that the approach is promising in situations where context cannot be employed as an aid to segmentation

Published in:

Image Processing and Its Applications, 1997., Sixth International Conference on  (Volume:2 )

Date of Conference:

14-17 Jul 1997