Compact and Accurate Scene Text Detectoropen access
- Authors
- Jeon, Minjun; Jeong, Young-Seob
- Issue Date
- Mar-2020
- Publisher
- MDPI
- Keywords
- efficient scene text detection; convolutional neural network; inverted residual block
- Citation
- Applied Sciences-basel, v.10, no.6
- Journal Title
- Applied Sciences-basel
- Volume
- 10
- Number
- 6
- URI
- https://scholarworks.bwise.kr/sch/handle/2021.sw.sch/3021
- DOI
- 10.3390/app10062096
- ISSN
- 2076-3417
- Abstract
- Scene text detection is the task of detecting word boxes in given images. The accuracy of text detection has been greatly elevated using deep learning models, especially convolutional neural networks. Previous studies commonly aimed at developing more accurate models, but their models became computationally heavy and worse in efficiency. In this paper, we propose a new efficient model for text detection. The proposed model, namely Compact and Accurate Scene Text detector (CAST), consists of MobileNetV2 as a backbone and balanced decoder. Unlike previous studies that used standard convolutional layers as a decoder, we carefully design a balanced decoder. Through experiments with three well-known datasets, we then demonstrated that the balanced decoder and the proposed CAST are efficient and effective. The CAST was about 1.1x worse in terms of the F1 score, but 30 similar to 115x better in terms of floating-point operations per second (FLOPS).
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - SCH Media Labs > Department of Big Data Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.