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

Abstract

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 $32\times 128$), 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 $8\times$ faster and $96\%$ smaller than it full-precision version.

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
• An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition