1. NCCU Academic Hub
  2. 學術產出
  3. 資訊學院
  4. 期刊論文
  5. Item

學術產出-期刊論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 An Integrated Approach for Multilingual Scene Text Detection
作者 廖文宏;吳怡潔
貢獻者 資科系
關鍵詞 Multilingual scene text detection, Maximally stable extremal region (MSER), Support vector machine (SVM)
日期 2016-02
上傳時間 29-六月-2017 09:45:45 (UTC+8)
摘要 Text messages in an image usually contain useful information related to the scene, such as location, name, direction or warning. As such, robust and efficient scene text detection has gained increasing attention in the area of computer vision recently. However, most existing scene text detection methods are devised to process Latin-based languages. For the few researches that reported the investigation of Chinese text, the detection rate was inferior to the result for English. In this research, we propose a multilingual scene text detection algorithm for both Chinese and English. The method comprises of four stages: 1. Preprocessing by bilateral filter to make the text region more stable. 2. Extracting candidate text edge and region using Canny edge detector and Maximally Stable Extremal Region (MSER) respectively. Then combine these two features to achieve more robust results. 3. Linking candidate characters: considering both horizontal and vertical direction, character candidates are clustered into text candidates using geometrical constraints. 4. Classifying candidate texts using support vector machine (SVM), to separate text and non-text areas. Experimental results show that the proposed method detects both Chinese and English texts, and achieve satisfactory performance compared to those approaches designed only for English detection.
關聯 International Journal of Computer Information Systems and Industrial Management Applications, 8, 33-41
資料類型 article
dc.contributor 資科系
dc.creator (作者) 廖文宏;吳怡潔zh_TW
dc.date (日期) 2016-02
dc.date.accessioned 29-六月-2017 09:45:45 (UTC+8)-
dc.date.available 29-六月-2017 09:45:45 (UTC+8)-
dc.date.issued (上傳時間) 29-六月-2017 09:45:45 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/110586-
dc.description.abstract (摘要) Text messages in an image usually contain useful information related to the scene, such as location, name, direction or warning. As such, robust and efficient scene text detection has gained increasing attention in the area of computer vision recently. However, most existing scene text detection methods are devised to process Latin-based languages. For the few researches that reported the investigation of Chinese text, the detection rate was inferior to the result for English. In this research, we propose a multilingual scene text detection algorithm for both Chinese and English. The method comprises of four stages: 1. Preprocessing by bilateral filter to make the text region more stable. 2. Extracting candidate text edge and region using Canny edge detector and Maximally Stable Extremal Region (MSER) respectively. Then combine these two features to achieve more robust results. 3. Linking candidate characters: considering both horizontal and vertical direction, character candidates are clustered into text candidates using geometrical constraints. 4. Classifying candidate texts using support vector machine (SVM), to separate text and non-text areas. Experimental results show that the proposed method detects both Chinese and English texts, and achieve satisfactory performance compared to those approaches designed only for English detection.
dc.format.extent 1483242 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) International Journal of Computer Information Systems and Industrial Management Applications, 8, 33-41
dc.subject (關鍵詞) Multilingual scene text detection, Maximally stable extremal region (MSER), Support vector machine (SVM)
dc.title (題名) An Integrated Approach for Multilingual Scene Text Detection
dc.type (資料類型) article