A Line-Oriented Approach to Word Spotting in Handwritten Documents
| Autor: | Joshua Alspector, Aleksander Kolcz, G. Viorel Popescu, Robert Carlson, Marijke F. Augusteijn |
|---|---|
| Rok vydání: | 2000 |
| Předmět: |
Dynamic time warping
Computer science business.industry Speech recognition Template matching Spotting computer.software_genre Artificial Intelligence Handwriting recognition Pattern recognition (psychology) Word recognition Computer Vision and Pattern Recognition Pattern matching Artificial intelligence business computer Cursive Natural language processing |
| Zdroj: | Pattern Analysis & Applications. 3:153-168 |
| ISSN: | 1433-755X 1433-7541 |
| DOI: | 10.1007/s100440070020 |
| Popis: | The problem of word spotting in handwritten archives is approached by matching global shape features. A set of visual templates is used to define the keyword class of interest, and initiate a search for words exhibiting high shape similarity to the model set. Major problems of segmenting cursive script into individual words are avoided by applying line-oriented processing to the document pages. The use of profile-oriented features facilitates the application of dynamic programming techniques to pattern matching, and allows us to achieve high levels of recognition performance. Results of experiments with old Spanish manuscripts show a high recognition rate of the proposed approach. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink