A Binary Convolutional Encoder-decoder Network for Real-time Natural Scene Text Processing

12/12/2016
by   Zichuan Liu, et al.
0

In this paper, we develop a binary convolutional encoder-decoder network (B-CEDNet) for natural scene text processing (NSTP). It converts a text image to a class-distinguished salience map that reveals the categorical, spatial and morphological information of characters. The existing solutions are either memory consuming or run-time consuming that cannot be applied to real-time applications on resource-constrained devices such as advanced driver assistance systems. The developed network can process multiple regions containing characters by one-off forward operation, and is trained to have binary weights and binary feature maps, which lead to both remarkable inference run-time speedup and memory usage reduction. By training with over 200, 000 synthesis scene text images (size of 32×128), it can achieve 90% and 91% pixel-wise accuracy on ICDAR-03 and ICDAR-13 datasets. It only consumes 4.59ms inference run-time realized on GPU with a small network size of 2.14 MB, which is up to 8× faster and 96% smaller than it full-precision version.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset