TY  - JOUR
AU  - Marçal Rusiñol
AU  - David Aldavert
AU  - Ricardo Toledo
AU  - Josep Llados
PY  - 2015//
TI  - Efficient segmentation-free keyword spotting in historical document collections
T2  - PR
JO  - Pattern Recognition
SP  - 545–555
VL  - 48
IS  - 2
KW  - Historical documents
KW  - Keyword spotting
KW  - Segmentation-free
KW  - Dense SIFT features
KW  - Latent semantic analysis
KW  - Product quantization
N2  - In this paper we present an efficient segmentation-free word spotting method, applied in the context of historical document collections, that follows the query-by-example paradigm. We use a patch-based framework where local patches are described by a bag-of-visual-words model powered by SIFT descriptors. By projecting the patch descriptors to a topic space with the latent semantic analysis technique and compressing the descriptors with the product quantization method, we are able to efficiently index the document information both in terms of memory and time. The proposed method is evaluated using four different collections of historical documents achieving good performances on both handwritten and typewritten scenarios. The yielded performances outperform the recent state-of-the-art keyword spotting approaches.
UR  - http://dx.doi.org/10.1016/j.patcog.2014.08.021
N1  - DAG; ADAS; 600.076; 600.077; 600.061; 601.223; 602.006; 600.055
ID  - Marçal Rusiñol2015
ER  -