Open Access

ARTICLE

Menu Text Recognition of Few-shot Learning

Xiaoyu^1,2, Tian Zhenzhen², Xin Zihao², Liu Suolan², Chen Fuhua³, Wang Hongyuan^2,*

1 School of Computer Science and Artificial Intelligencea, Changzhou, 213164, China
2 Changzhou University, Changzhou, Jiangsu, 213164, China
3 West Liberty University, 208 University Drive, West Liberty, 26074, USA

* Corresponding Author: Wang Hongyuan. Email:

Journal of New Media 2022, 4(3), 137-143. https://doi.org/10.32604/jnm.2022.027890

Received 27 January 2022; Accepted 15 April 2022; Issue published 13 June 2022

Abstract

Recent advances in OCR show that end-to-end (E2E) training pipelines including detection and identification can achieve the best results. However, many existing methods usually focus on case insensitive English characters. In this paper, we apply an E2E approach, the multiplex multilingual mask TextSpotter, which performs script recognition at the word level and uses different recognition headers to process different scripts while maintaining uniform loss, thus optimizing script recognition and multiple recognition headers simultaneously. Experiments show that this method is superior to the single-head model with similar number of parameters in end-to-end identification tasks.

---

Keywords

---