TY  - CONF
AU  - Thanh Ha Do
AU  - Salvatore Tabbone
AU  - Oriol Ramos Terrades
A2  - ICPR
PY  - 2012//
TI  - Text/graphic separation using a sparse representation with multi-learned dictionaries
BT  - 21st International Conference on Pattern Recognition
KW  - Graphics Recognition
KW  - Layout Analysis
KW  - Document Understandin
N2  - In this paper, we propose a new approach to extract text regions from graphical documents. In our method, we first empirically construct two sequences of learned dictionaries for the text and graphical parts respectively. Then, we compute the sparse representations of all different sizes and non-overlapped document patches in these learned dictionaries. Based on these representations, each patch can be classified into the text or graphic category by comparing its reconstruction errors. Same-sized patches in one category are then merged together to define the corresponding text or graphic layers which are combined to createfinal text/graphic layer. Finally, in a post-processing step, text regions are further filtered out by using some learned thresholds.
UR  - http://hal.inria.fr/hal-00759554
L1  - http://refbase.cvc.uab.es/files/DTR2012a.pdf
N1  - DAG
ID  - Thanh Ha Do2012
ER  -