Improving Scene Text Recognition With A Combinative Image Augmentation Approach

  • Nguyen, N.-L.; 
  • Lam, G.-H.; 
  • Vo, H.-T.; 
  • Do, T.-H.; 
  • Tran, A.-T.; 
  • ... Cho, Sungrae
Citations

SCOPUS

2

초록

Scene text recognition plays an important role in various intelligent systems today such as robotic process automation and self-driving cars. These systems require knowledge of the surrounding scenery, where the words in the scene hold a lot of valuable information. For instance, scene text recognitions can serve the development of smart tourism, smart museums, and self-propelled robots. To increase the practical applicability of the solution, the recognition model needs to meet efficiently both accuracies and processing time. However, before constructing the model, most existing scene text recognition frameworks underrate the importance of a reliable and well-served augmentation stage, all the images in the dataset are often applied with common augmentation functions. In this paper, we present a combinative augmentation framework that takes random augmentation functions from different types into combinations for each individual image. In addition, the framework also randomizes the number of functions taken and every specific parameter for a particular function on the image. Thus, all these tweaks help to greatly increase the pattern diversity in images and pose an improvement in the model evaluation. Evaluated on both seen and unseen test datasets, the framework increased the accuracy by an average of 5,02% on the NRTR model and 2.36% on the VietOCR model. © 2022 IEEE.

키워드

Combinative augmentation; Deep learning; Scene text recognition
제목
Improving Scene Text Recognition With A Combinative Image Augmentation Approach
저자
Nguyen, N.-L.; Lam, G.-H.; Vo, H.-T.; Do, T.-H.; Tran, A.-T.; Cho, Sungrae
DOI
10.1109/ICTC55196.2022.9952873
발행일
2022-10
유형
Conference Paper
저널명
International Conference on ICT Convergence
권
2022-October
페이지
1051 ~ 1055