Detecting Text Baselines in Historical Documents With Baseline Primitives

Previous deep learning based approaches to text baseline detection in historical documents usually take it as a semantic segmentation task. These methods adopt a fully convolutional neural network to predict baseline pixels first and then group them into lines by heuristic post-processing steps, whi...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Wei Jia, Chixiang Ma, Lei Sun, Qiang Huo
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2021-01-01
Edice:	IEEE Access
Témata:	Handwritten documents historical documents text baseline detection baseline primitive
On-line přístup:	https://ieeexplore.ieee.org/document/9468639/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!