期刊
JOURNAL OF ENGINEERING-JOE
卷 2020, 期 13, 页码 626-629出版社
WILEY
DOI: 10.1049/joe.2019.1208
关键词
feature extraction; handwritten character recognition; text analysis; text detection; history; art; natural languages; text detection; SE-seglink method; Chinese cursive character detection method; Chinese cursive script; distinctive calligraphy art; connected writing; text recognition; cursive image dataset; continuous strokes text; image feature extraction; traditional cultures; ICDAR2015 benchmark image dataset
资金
- National Natural Science Foundation of China [61562008, 61772091, 61802035]
- National Natural Science Foundation of Guangxi [2016GXNSFAA380209]
- Natural Science Foundation of Guangxi [2018GXNSFDA138005]
- Project of Science Research and Technology Development in Guangxi [AA18118047, AD18126015, AB16380272, 20175177]
- Sichuan Science and Technology Program [2018JY0448, 2019YFG0106, 2019YFS0067]
- Innovative Research Team Construction Plan in Universities of Sichuan Province [18TD0027]
- Soft Science Foundation of Chengdu [2017-RK00-00053-ZF]
- Scientific Research Foundation for Young Academic Leaders of Chengdu University of Information Technology [J201701]
- Scientific Research Foundation for Advanced Talents of Chengdu University of Information Technology [KYTZ201715, KYTZ201750]
- Guangdong Key Laboratory Project [2017B030314073]
- BAGUI Scholar Program of Guangxi Zhuang Autonomous Region of China
Chinese is a widely used language in the world. Chinese cursive script is one of the most distinctive calligraphy art and traditional cultures of China. However, for its connected writing, there is a lack of research on text recognition for cursive images. Here, the authors construct a small cursive image dataset named as Chinese Cursive and there are 523 images in this dataset. It contains continuous strokes text, recognises difficulty etc. Each cursive character is corresponded to a label. The authors proposed a cursive detection method named as SE-seglink for the dataset. The SE-seglink further enhances the image feature extraction. Compared to the existing methods, the SE-seglink performs better in recognising cursive scripts and improves the precision of text detection in cursive images. After multiple sets of comparative experiments, the effectiveness of the SE-seglink method was evaluated by the experiment on the benchmark image dataset ICDAR2015.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据