chullhwan-song / Reading-Paper

151 stars 26 forks source link

PixelLink: Detecting Scene Text via Instance Segmentation #71

Open chullhwan-song opened 5 years ago

chullhwan-song commented 5 years ago

https://arxiv.org/abs/1801.01315

chullhwan-song commented 5 years ago

abstract

동기

Detecting Text via Instance Segmentation

Linking Pixels Together

Given predictions on pixels and links, two different thresholds can be applied on them separately. 
Positive pixels are then grouped together using positive links, resulting in a collection of CCs, 
each representing a detected text instance. 
Thus instance segmentation is achieved. It is worth noting that, given two neighboring
 positive pixels,  their link are predicted by both of them, and they should be connected 
when one or both of the two link predictions are positive. 
This linking process can be implemented using disjoint-set data structure.

Extraction of Bounding Boxes

Post Filtering after Segmentation

전체 프로세스 Fig

image

전체 network 구조

image

Loss Function

image

실험

image