TY  - STD
AU  - Francisco Cruz
AU  - Oriol Ramos Terrades
PY  - 2018//
TI  - A probabilistic framework for handwritten text line segmentation
KW  - Document Analysis
KW  - Text Line Segmentation
KW  - EM algorithm
KW  - Probabilistic Graphical Models
KW  - Parameter Learning
N2  - We successfully combine Expectation-Maximization algorithm and variationalapproaches for parameter learning and computing inference on Markov random fields. This is a general method that can be applied to many computervision tasks. In this paper, we apply it to handwritten text line segmentation.We conduct several experiments that demonstrate that our method deal withcommon issues of this task, such as complex document layout or non-latinscripts. The obtained results prove that our method achieve state-of-theart performance on different benchmark datasets without any particular finetuning step.
N1  - DAG; 600.097; 600.121
ID  - Francisco Cruz2018
ER  -