Evaluating Performance and Accuracy Improvements for Attention-OCR

Adam Brzeski; Kamil Grinholc; Kamil Nowodworski; Adam Przybyłek

doi:10.1007/978-3-030-28957-7_1

Evaluating Performance and Accuracy Improvements for Attention-OCR

Abstract

In this paper we evaluated a set of potential improvements to the successful Attention-OCR architecture, designed to predict multiline text from unconstrained scenes in real-world images. We investigated the impact of several optimizations on model’s accuracy, including employing dynamic RNNs (Recurrent Neural Networks), scheduled sampling, BiLSTM (Bidirectional Long Short-Term Memory) and a modified attention model. BiLSTM was found to slightly increase the accuracy, while dynamic RNNs and a simpler attention model provided a significant training time reduction with only a slight decline in accuracy.

Citations

4

CrossRef
0

Web of Science
6

Scopus

Authors (4)

Cite as

Full text

full text is not available in portal

full content of the article see on external site open in new tab

Keywords

ATTENTION-OCR

Details

Category:: Conference activity
Type:: publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
Title of issue:: Computer Information Systems and Industrial Management strony 3 - 11
Language:: English
Publication year:: 2019
Bibliographic description:: Brzeski A., Grinholc K., Nowodworski K., Przybyłek A.: Evaluating Performance and Accuracy Improvements for Attention-OCR// Computer Information Systems and Industrial Management/ : , 2019, s.3-11
DOI:: Digital Object Identifier (open in new tab) 10.1007/978-3-030-28957-7_1
Verified by:: Gdańsk University of Technology