繁體中文場景資料集建置暨文字定位與辨識之評估;Designs of the Traditional Chinese Scene Text Dataset and Performance Evaluation for Text Detection and Recognition

NCU Institutional Repository > 資訊電機學院 > 資訊工程研究所 > 博碩士論文 > Item 987654321/88311

請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/88311

題名:	繁體中文場景資料集建置暨文字定位與辨識之評估;Designs of the Traditional Chinese Scene Text Dataset and Performance Evaluation for Text Detection and Recognition
作者:	董怡廷;Tong, Leslie
貢獻者:	資訊工程學系
關鍵詞:	深度學習;場景文字資料集;文字定位;文字辨識;Deep learning;scene text dataset;text detection;text recognition
日期:	2022-01-25
上傳時間:	2022-07-13 22:46:14 (UTC+8)
出版者:	國立中央大學
摘要:	場景文字包含非常豐富的影像相關訊息，擷取並辨識畫面中的文字內容能夠促成許多具潛力的應用，因此場景文字分析目前為電腦視覺領域所關注的研究議題之一。然而，現有場景文字資料集或相關競賽多集中於英文或其他語言的處理，台灣所使用的繁體中文尚未有較完整的資料。為了促進繁體中文字辨識領域的發展，本研究蒐集大量繁體中文街景圖片，包含20,188張街景影像，經後處理與標記後整合為繁體中文場景文字資料集。由於中文字的走向、大小、字體相當多元，為了讓標記資料趨於一致，我們訂定較符合包含中文場景文字的標記原則，其中的字串與字元都帶有位置與內容，並加上語言種類。資料集經錯誤檢查與整理後，應用於日前所舉辦的繁體中文場景文字辨識競賽。此競賽共分成三項任務，初階賽-文字定位、進階賽-繁體中文字元辨識，以及高階賽-複雜街景之中英數字辨識。本論文針對各階段競賽訂定評分原則，並展示競賽最終結果。比賽於2021年4月開始，2021年12月結束。每項競賽的參賽隊伍數與提交次數分別為，初階賽341組246次有效提交; 進階賽183組60次有效提交; 高階賽128組91次有效提交。;Texts in pictures contain rich information. Extracting and recognizing these texts in images, i.e., scene text detection and recognition, help to facilitate many interesting and potential applications. Therefore, scene text analytics have become one of the research topics in the filed of computer vision. Nevertheless, most existing datasets and competitions related to scene text detection and recognition focused on English or other languages. The Traditional Chinese used in Taiwan has not been paid too much attention in this field. In order to promote the research of Traditional Chinese scene text analytics, in this study, we collected a large volume of street-view images to form the dataset called "Traditional Chinese Street-View Texts" (TCSVT), containing $20,188$ images with careful annotations. The characters in this dataset have various forms and the strings have varying orientations, sizes, and fonts. We formulated a set of labeling principles for texts containing Chinese so that the annotations can be more standardized. The labels of text lines and characters include their locations, contents and the language types. This dataset was then adopted in the 2021 AICUP Traditional Chinese Scene Text Recognition Competition. This competition has three stages: 1) Text-line Localization, 2) Traditional Chinese Text-line Recognition and 3) Text Spotting and Recognition in Complex Streetscapes. We set up reasonable evaluation metrics of each task. The competition started in April 2021 and ended in December 2021. The numbers of teams partipating the three stages are $341$, $183$ and $128$, repectively. The numbers of valid submissions of the three tasks are $246$, $60$ and $91$ respectively.
顯示於類別:	[資訊工程研究所] 博碩士論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	64	檢視/開啟

在NCUIR中所有的資料項目都受到原著作權保護.

社群 sharing

資料載入中.....