Use Case and High-Level Description

Text detector based on PixelLink architecture with MobileNetV2, depth_multiplier=1.4 as a backbone for indoor/outdoor scenes.



Metric Value
F-measure (Harmonic mean of precision and recall on ICDAR2015) 79.43%
GFlops 23.305
MParams 4.328
Source framework TensorFlow*


Image, name: input, shape: 1, 3, 768, 1280 in the format B, C, H, W, where:

  • B - batch size
  • C - number of channels
  • H - image height
  • W - image width

Expected color order: BGR.


  1. name: model/link\_logits\_/add, shape: 1, 16, 192, 320 - logits related to linkage between pixels and their neighbors.
  2. name: model/segm\_logits/add, shape: 1, 2, 192, 320 - logits related to text/no-text classification for each pixel.

Refer to PixelLink and demos for details.

Legal Information

[*] Other names and brands may be claimed as the property of others.