Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Fink, Gernot A. | - |
dc.contributor.author | Hammerla, Nils Y. | - |
dc.contributor.author | Plötz, Thomas | - |
dc.contributor.author | Vajda, Szilárd | - |
dc.date.accessioned | 2011-01-12T16:02:51Z | - |
dc.date.available | 2011-01-12T16:02:51Z | - |
dc.date.issued | 2011-01-12 | - |
dc.identifier.uri | http://hdl.handle.net/2003/27556 | - |
dc.identifier.uri | http://dx.doi.org/10.17877/DE290R-8202 | - |
dc.description.abstract | Statistical modelling techniques for automatic reading systems substantially rely on the availability of compact and meaningful feature representations. State-of-the-art feature extraction for offline handwriting recognition is usually based on heuristic approaches that describe either basic geometric properties or statistical distributions of raw pixel values. Working well on average, still fundamental insights into the nature of handwriting are desired. In this paper we present a novel approach for the automatic extraction of appearance-based representations of offline handwriting data. Given the framework of deep belief networks -- Restricted Boltzmann Machines -- a two-stage method for feature learning and optimization is developed. Given two standard corpora of both Arabic and Roman handwriting data it is demonstrated across script boundaries, that automatically learned features achieve recognition results comparable to state-of-the-art handcrafted features. Given these promising results the potential of feature learning for future reading systems is discussed. | en |
dc.language.iso | en | - |
dc.relation.ispartof | First International Workshop on Frontiers in Arabic Handwritng Recognition, 2010 | en |
dc.subject | Arabic/Roman handwriting recognition | en |
dc.subject | automatic feature extraction | en |
dc.subject | Hidden Markov Models | en |
dc.subject | non-linear regularized NCA | en |
dc.subject | Restricted Boltzmann Machines | en |
dc.subject.ddc | 004 | - |
dc.title | Towards Feature Learning for HMM-based Offline Handwriting Recognition | en |
dc.type | Text | - |
dc.type.publicationtype | conferenceObject | - |
dcterms.accessRights | open access | - |
Appears in Collections: | 2010 - First International Workshop on Frontiers in Arabic Handwriting Recognition |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Hammerla.pdf | DNB | 162.71 kB | Adobe PDF | View/Open |
This item is protected by original copyright |
This item is protected by original copyright
rightsstatements.org