traditionalchineseocrdataset

由YCChen著作·2021·被引用2次—Tothebestofourknowledge,publicdatasetsforTraditionalChinesetextrecognitionarelacking.Thispaperpresentsaframeworkfora ...,Inthispaper,weintroduceaverylargeChinesetextdatasetinthewild.Whileopticalcharacterrecognition(OCR)indocumentimagesiswellstudiedand ...,CnOCR:AwesomeChinese/EnglishOCRtoolkitsbasedonPyTorch/MXNet,Itcomeswith20+well-trainedmodelsfordifferentapplicat...

參考資訊如下
Traditional Chinese Synthetic Datasets Verified with ...

由 YC Chen 著作 · 2021 · 被引用 2 次 — To the best of our knowledge, public datasets for Traditional Chinese text recognition are lacking. This paper presents a framework for a ...

CTW Dataset

In this paper, we introduce a very large Chinese text dataset in the wild. While optical character recognition (OCR) in document images is well studied and ...

chinese-character

CnOCR: Awesome Chinese/English OCR toolkits based on PyTorch/MXNet, It comes with 20+ well-trained models for different application scenarios and can be ...

AI-FREE-TeamTraditional-Chinese-Handwriting

Original dataset was produced based on Tegaki, an open-source package. Total 13,065 different Chinese characters, with average of 50 samples for each character.

FudanVIbenchmarking-chinese-text

This repository contains datasets and baselines for benchmarking Chinese text recognition. Please see the corresponding paper for more details regarding the ...

5000-Images-Handwriting-OCR-Data-of

5000-Images-Handwriting-OCR-Data-of-Traditional-Chinese-Characters-Taiwan-China. Description. There are 5,000 images of handwriting data of traditional ...

Datatang adds 5000 Traditional Chinese characters to ...

2022年8月31日 — Beijing-based artificial intelligence (AI) company Datatang has updated its optical character recognition (OCR) database to include 5,000 ...

262 People

The handwriting ocr data can be used for traditional Chinese characters recognition application.The accuracy of line-level annotation and transcription is >= 97 ...

Handwritten Chinese Character (Hanzi) Datasets

This data set contains labeled PNG images of 7330 handwritten characters. This includes all of 6763 Chinese characters in the GB2312 encoding, as well as 171 ...

Large

由 YQ Li 著作 · 2022 · 被引用 7 次 — In this study, we developed an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters by using deep learning neural ...