Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Hesuo Zhang"'
Online and offline handwritten Chinese text recognition (HTCR) has been studied for decades. Early methods adopted oversegmentation-based strategies but suffered from low speed, insufficient accuracy, and high cost of character segmentation annotatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27da6a59e23b04c27e1bd771e5861528
Autor:
Yichao Huang, Yaqiang Wu, Hui Li, Weihong Ma, Shuang Yan, Hesuo Zhang, Guangshun Yao, Lianwen Jin
Publikováno v:
Document Analysis and Recognition – ICDAR 2021 ISBN: 9783030865481
ICDAR (1)
ICDAR (1)
In this paper, we fill the research gap by adopting state-of-the-art computer vision techniques for the data extraction stage in a data mining system. As shown in Fig. 1, this stage contains two subtasks, namely, plot element detection and data conve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3bcc6e05ce2f5a58b25ccc1b6cc74841
https://doi.org/10.1007/978-3-030-86549-8_37
https://doi.org/10.1007/978-3-030-86549-8_37
Publikováno v:
Document Analysis and Recognition – ICDAR 2021 ISBN: 9783030863333
ICDAR (3)
ICDAR (3)
Chart document understanding is a challenging task in document analysis because of the complex format and specific semantics it contains. In this paper, we first define the chart panel analysis problem and propose a complete framework that can be per
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::73871197161e6efe5b3cf93a87821167
https://doi.org/10.1007/978-3-030-86334-0_45
https://doi.org/10.1007/978-3-030-86334-0_45
Publikováno v:
ICFHR
In this paper, we propose an end-to-end trainable framework for restoring historical documents content that follows the correct reading order. In this framework, two branches named character branch and layout branch are added behind the feature extra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9f83de3175e1bd8007c0a648d0a675d2
http://arxiv.org/abs/2007.06890
http://arxiv.org/abs/2007.06890
Publikováno v:
Pattern Recognition. 108:107559
In this paper, we introduce a large-scale dataset, called SCUT-HCCDoc, to address challenging detection and recognition problems of handwritten Chinese text (HCT) in the camera-captured documents. Despite extensive studies of optical character recogn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5f59788d703e2ffdaf372955aa1e5791
https://doi.org/10.1016/j.patcog.2020.107559
https://doi.org/10.1016/j.patcog.2020.107559
This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. T
Autor:
Alberto Del Bimbo, Rita Cucchiara, Stan Sclaroff, Giovanni Maria Farinella, Tao Mei, Marco Bertini, Hugo Jair Escalante, Roberto Vezzani
This 8-volumes set constitutes the refereed of the 25th International Conference on Pattern Recognition Workshops, ICPR 2020, held virtually in Milan, Italy and rescheduled to January 10 - 11, 2021 due to Covid-19 pandemic. The 416 full papers presen