- Digital Grinnell Repository
- Scholarship at Grinnell
- Faculty Scholarship
- A Discriminative Semi-Markov Model for Robust Scene Text Recognition
A Discriminative Semi-Markov Model for Robust Scene Text Recognition
Primary tabs
We present a semi-Markov model for recognizing scene text that integrates character and word segmen- tation with recognition.
| creator | Weinman, Jerod J. (Faculty/Staff) |
| creator | Erik |
| creator | Learned-Miller |
| creator | Allen |
| creator | Hanson |
| Title | A Discriminative Semi-Markov Model for Robust Scene Text Recognition |
| supporting host | Grinnell College. Computer Science |
| Index Date | 2008 |
| Publisher | Grinnell College |
| Genre | Essays |
| Digital Origin | born digital |
| Extent | 5 pages |
| Media Type | application/pdf |
| Language | English |
| Topic | Optical pattern recognition |
| Topic | Markov processes |
| Topic | Computer simulation |
| Topic | Text processing (Computer science) |
| Temporal | 21st century |
| Keyword | Scene text recognition |
| Classification | QA76 |
| Related Item | Faculty Scholarship |
| Related Item | Scholarship at Grinnell |
| Related Item | Digital Grinnell |
| Identifier (hdl) | http://hdl.handle.net/11084/10960 |
| Identifier (local) | grinnell:10960 |
| Access Condition | Copyright to this work is held by the author(s), in accordance with United States copyright law (USC 17). Readers of this work have certain rights as defined by the law, including but not limited to fair use (17 USC 107 et seq.). |
| Group Record | |
|---|---|
| creator | Weinman, Jerod. J. (Faculty/Staff) |
| creator | Learned-Miller, Erik |
| creator | Hanson, Allen |
| Title | A Discriminative Semi-Markov Model for Robust Scene Text Recognition |
| supporting host | Grinnell College. Computer Science |
| Index Date | 2008 |
| Publisher | Grinnell College |
| Genre | Essays |
| Digital Origin | born digital |
| Extent | 2 objects |
| description | We present a semi-Markov model for recognizing scene text that integrates character and word segmentation with recognition. Using wavelet features, it requires only approximate location of the text baseline and font size; no binarization or prior word segmentation is necessary. Our system is aided by a lexicon, yet it also allows non-lexicon words. To facilitate inference with a large lexicon, we use an approximate Viterbi beam search. Our system performs robustly on low-resolution images of signs containing text in fonts atypical of documents. |
| Language | English |
| Topic | Optical pattern recognition |
| Topic | Markov processes |
| Topic | Computer simulation |
| Topic | Text processing (Computer science) |
| Temporal | 21st century |
| Keyword | Scene text recognition |
| Classification | QA76 |
| Related Item | Faculty Scholarship |
| Related Item | Scholarship at Grinnell |
| Related Item | Digital Grinnell |
| Identifier (hdl) | http://hdl.handle.net/11084/6266 |
| Identifier (local) | grinnell:6266 |
| Access Condition | Copyright to this work is held by the author(s), in accordance with United States copyright law (USC 17). Readers of this work have certain rights as defined by the law, including but not limited to fair use (17 USC 107 et seq.). |