文字影像拼接的研究

本論文主要運用OpenCV影像程式庫來研發一個可以拼接全頁文字影像的運算方法。本研究的目標，是希望能夠將多張部份文字影像，不論其大小及拍攝角度，能自動拼接並合成清晰的文字影像。我們提出的演算法，能自動尋找影像中文字區塊的範圍，將影像轉正，並將所有影像拼接成單一清晰影像。我們希望提出的演算法，未來能夠運用在手機上，變成一個方便使用的文字影像掃描工具。

關鍵字

OpenCV ；拼接文字影像；影像轉正

並列摘要

In this these, we propose a text image stitching method based on OpenCV image processing library. The target of the research is to obtain a clear text image by stitching several partial text images which may be in different sizes or different skewed angles. We propose an algorithm to extract the text region for each text image, deskew the picture, and then stitch all images to get a single clear text image. We hope that the proposed method can be applied to build a convenient smartphone application to scan clear text images.

並列關鍵字

Text Image Stitching ； OpenCV ； Deskew

參考文獻

[1] ‘Office Lens’, 2018, [online] Available:

Google Scholar

https://play.google.com/store/apps/details?id=com.microsoft.office.officelens&hl=zh_TW

Google Scholar

[2] Yung-Yu Chuang ,‘Digital Visual Effects :Image Stitching’, 2017 , [online] Available: https://www.csie.ntu.edu.tw/~cyy/courses/vfx/17spring/lectures/

Google Scholar

[3] OpenCV, [online] Available: https://opencv.org/

Google Scholar

[4] G. Bradski, A. Kaebler, ‘Learning OpenCV 3’, 2017.

Google Scholar

國際替代計量

文字影像拼接的研究

全文下載

主題瀏覽