Warping-Based Approach to Offline Handwriting Recognition
An enormous amount of the historical record is currently trapped in non-indexed handwritten format. Even after being scanned into images, only a minute fraction of the existing records can be manually transcribed / indexed with reasonable amounts of time and cost. Although progress continues to be m...
Main Author: | |
---|---|
Format: | Others |
Published: |
BYU ScholarsArchive
2013
|
Subjects: | |
Online Access: | https://scholarsarchive.byu.edu/etd/3991 https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=4990&context=etd |
id |
ndltd-BGMYU2-oai-scholarsarchive.byu.edu-etd-4990 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-BGMYU2-oai-scholarsarchive.byu.edu-etd-49902021-09-01T05:02:23Z Warping-Based Approach to Offline Handwriting Recognition Kennard, Douglas J. An enormous amount of the historical record is currently trapped in non-indexed handwritten format. Even after being scanned into images, only a minute fraction of the existing records can be manually transcribed / indexed with reasonable amounts of time and cost. Although progress continues to be made with automatic handwriting recognition (HR), it is not yet good enough to replace manual transcription or indexing. Much of the recent HR work has focused on incremental improvements to methods based on Hidden Markov Models (HMMs) and other similar probabilistic approaches. In this dissertation we present a fundamentally new approach to HR based on 2-D geometric warping of word images. The results of our experimentation indicate that our approach is significantly more accurate than an existing whole-word approach used for word-spotting, and may also be better than HMM-based HR approaches. Since it is a completely new method, we also believe there is potential for improvement and future work that builds on this approach. In addition, we demonstrate that the approach can be used effectively in the related application domain of signature verification and forgery detection. 2013-04-03T07:00:00Z text application/pdf https://scholarsarchive.byu.edu/etd/3991 https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=4990&context=etd http://lib.byu.edu/about/copyright/ Theses and Dissertations BYU ScholarsArchive Handwriting Recognition Word Warping Word Morphing Signature Verification Forgery Detection Computer Sciences |
collection |
NDLTD |
format |
Others
|
sources |
NDLTD |
topic |
Handwriting Recognition Word Warping Word Morphing Signature Verification Forgery Detection Computer Sciences |
spellingShingle |
Handwriting Recognition Word Warping Word Morphing Signature Verification Forgery Detection Computer Sciences Kennard, Douglas J. Warping-Based Approach to Offline Handwriting Recognition |
description |
An enormous amount of the historical record is currently trapped in non-indexed handwritten format. Even after being scanned into images, only a minute fraction of the existing records can be manually transcribed / indexed with reasonable amounts of time and cost. Although progress continues to be made with automatic handwriting recognition (HR), it is not yet good enough to replace manual transcription or indexing. Much of the recent HR work has focused on incremental improvements to methods based on Hidden Markov Models (HMMs) and other similar probabilistic approaches. In this dissertation we present a fundamentally new approach to HR based on 2-D geometric warping of word images. The results of our experimentation indicate that our approach is significantly more accurate than an existing whole-word approach used for word-spotting, and may also be better than HMM-based HR approaches. Since it is a completely new method, we also believe there is potential for improvement and future work that builds on this approach. In addition, we demonstrate that the approach can be used effectively in the related application domain of signature verification and forgery detection. |
author |
Kennard, Douglas J. |
author_facet |
Kennard, Douglas J. |
author_sort |
Kennard, Douglas J. |
title |
Warping-Based Approach to Offline Handwriting Recognition |
title_short |
Warping-Based Approach to Offline Handwriting Recognition |
title_full |
Warping-Based Approach to Offline Handwriting Recognition |
title_fullStr |
Warping-Based Approach to Offline Handwriting Recognition |
title_full_unstemmed |
Warping-Based Approach to Offline Handwriting Recognition |
title_sort |
warping-based approach to offline handwriting recognition |
publisher |
BYU ScholarsArchive |
publishDate |
2013 |
url |
https://scholarsarchive.byu.edu/etd/3991 https://scholarsarchive.byu.edu/cgi/viewcontent.cgi?article=4990&context=etd |
work_keys_str_mv |
AT kennarddouglasj warpingbasedapproachtoofflinehandwritingrecognition |
_version_ |
1719473580977160192 |