透過您的圖書館登入
IP:216.73.216.192
  • 學位論文

自然場景跑馬燈偵測與完整文句重構

A study of detecting and reconstructing marquee texts in natural scenes

指導教授 : 范國清
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


現實生活中常常出現很多的資訊傳播媒介,諸如:廣告、電視牆、交通號誌或是跑馬燈,但是當人們面對這麼多傳播媒介的時候總是會不小心有遺漏的狀況出現,而在這之中可能會有很多資訊是對我們有所幫助的,因此,如何輔助人們在資訊快速傳播時,完整的重現以避免錯失接收資訊的機會。本研究針對現實環境中常常出現的跑馬燈作為分析的對象,跑馬燈通常應用於重複提供人們簡短而重要的訊息,但是跑馬燈的顯示範圍有限,往往無法在同一時間顯示完整的訊息,所以會一直不斷更新顯示的訊息。本論文提供一種基於視覺的方法,以幫助人們避免錯失訊息,主要目標是找出跑馬燈位置,並且顯示跑馬燈所顯示過的所有內容。 本研究透過分析跑馬燈影片的光流值,二值化以及文字區塊標記來擷取欲分析的影像資料,並利用本研究所提出來的過濾機制,將影片時間前後的單張影像中不同樣的文字過濾出來,當跑馬燈影片撥放完畢的時候,本研究會將影片中所出現過的文字做一個完整的重現,讓人們可以減少時間以及錯失接收到跑馬燈文字的狀況。

關鍵字

文字 文字偵測

並列摘要


Many devices such as advertisements, TV wall, traffic signals and marquee (scrolling text) are delivering multimedia contents in our daily lives. People may miss some important information when facing so many different multimedia contents. This thesis proposes a vision-based approach to assist users avoiding missing information that might be important to them. This study aims the marquee the messages it contains are constantly updating so that people miss part of the contents easily. The purpose of work is to display the full contents shown by a marquee. First, the system locates the marquee texts by analyzing the optical flow field. Meanwhile, the starting and ending time of scrolling texts can also be obtained. Second, text blocks are retrieved by the integration of temporal differencing, vertical projection, and histogram matching method. Finally, the content of the marquee is displayed by rearranging these text blocks. Experiments demonstrate that the proposed method can display most texts in the marquee regardless of the language or color of texts.

並列關鍵字

text detection Mareuee text

參考文獻


[9] C.M. Wang, K.C. Fan, C.T. Wang, “Estimating Optical Flow by Integrating Multi-Frame Information”, Journal of Information Science and Engineering 24, 1719-1731 (2008)
[1] A.K. Jain, B. Yu. ”Automatic Text Location in Images and Video Frames”. Pattern Recognition, 1998, pp. 2055-2076.
[2] Q. Ye, Q. Huang, W. Gao and D. Zhao. “Fast and robust text detection in images and video frames”. Image and Vision Computing, 2005, pp. 565-576.
[3] C. Liu, C. Wang and R. Dai. “Text Detection in Images Based on Unsupervised Classification of Edge-based Features”. ICDAR 2005, pp. 610-614.
[4] K. Jung, K. I. Kim, and A. K. Jain. Text information extraction in images and videos: A survey. Pattern Recognition, 37(5):977–997, 2004.

被引用紀錄


廖文晧(2014)。自然場景中手持裝置的跑馬燈偵測及文句重構〔碩士論文,國立中央大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0031-0412201512011631

延伸閱讀