TY  - JOUR
AU  - Josep Llados
AU  - Marçal Rusiñol
AU  - Alicia Fornes
AU  - David Fernandez
AU  - Anjan Dutta
PY  - 2012//
TI  - On the Influence of Word Representations for Handwritten Word Spotting in Historical  Documents
T2  - IJPRAI
JO  - International Journal of Pattern Recognition and Artificial Intelligence
SP  - 1263002-126027
VL  - 26
IS  - 5
KW  - Handwriting recognition
KW  - word spotting
KW  - historical documents
KW  - feature representation
KW  - shape descriptors   Read More: http://www.worldscientific.com/doi/abs/10.1142/S0218001412630025
N2  - 0,624 JCRWord spotting is the process of retrieving all instances of a queried keyword from a digital library of document images. In this paper we evaluate the performance of different word descriptors to assess the advantages and disadvantages of statistical and structural models in a framework of query-by-example word spotting in historical documents. We compare four word representation models, namely sequence alignment using DTW as a baseline reference, a bag of visual words approach as statistical model, a pseudo-structural model based on a Loci features representation, and a structural approach where words are represented by graphs. The four approaches have been tested with two collections of historical data: the George Washington database and the marriage records from the Barcelona Cathedral. We experimentally demonstrate that statistical representations generally give a better performance, however it cannot be neglected that large descriptors are difficult to be implemented in a retrieval scenario where word spotting requires the indexation of data with million word images.
L1  - http://refbase.cvc.uab.es/files/LRF2012.pdf
UR  - http://dx.doi.org/10.1142/S0218001412630025
N1  - DAG
ID  - Josep Llados2012
ER  -