| Title |
The SPARTACUS-Database: a Spanish Sentence Database for Offline Handwriting Recognition |
| Author(s) |
Salvador España, María José Castro, José Luis Hidalgo Departamento de Sistemas Informáticos y Computación, Universidad Politécnica de Valencia, Camino de Vera s/n, 46022 Valencia, Spain, {sespana,mcastro,jhidalgo}@dsic.upv.es |
| Session |
P1-W |
| Abstract |
In this paper we describe a database that consists of offline handwritten Spanish sentences from four different subtasks. The database includes 1,500 forms produced by the same number of writers. A total of around 100,000 word instances out of a vocabulary of around 3,300 words occur in the collection. This database is intended to be used for offline handwriting recognition tasks. However, this database is expected to be specially useful for recognition systems that may take advantage of language models of restricted-semantic tasks. The database also includes a few image-processing procedures for extraction of handwritten text images from the forms and segmentation of the images into lines and words. |
| Keyword(s) |
Handwriting recognition, offline handwriting recognition, databases, Spanish sentences, linguistic knowledge. |
| Language(s) | Spanish |
| Full Paper |