【摘要】：自然場景圖像中的文本含有大量語義信息,是對圖像場景的重要補充。隨著智能手機、平板電腦和數(shù)碼相機的普及,人們越來越容易獲取高質(zhì)量的場景圖像。從自然場景圖像中提取文本信息不僅有助于人們更深層次地理解場景,而且在檢索、查詢以及視覺輔助系統(tǒng)中有重要用途。準(zhǔn)確提取自然場景中的文本信息的前提是精確定位文本區(qū)域,自然場景文本定位面臨著圖像背景復(fù)雜、字體多樣以及遮擋、模糊等難題,是一個極具挑戰(zhàn)性的研究課題。本文對自然場景文本定位的相關(guān)技術(shù)進(jìn)行探索,提出了一種新的基于最大穩(wěn)定極值區(qū)域的自然場景文本定位算法框架。本文的主要貢獻(xiàn)如下:(1)針對MSER檢測器檢測文本候選區(qū)域的重復(fù)檢測問題,提出了一種基于區(qū)域變化率的MSER重復(fù)嵌套區(qū)域刪除規(guī)則。首先對圖像進(jìn)行預(yù)處理,從各個顏色通道中提取出MSER,然后根據(jù)區(qū)域的變化率以及包含關(guān)系,刪除重復(fù)檢測的區(qū)域。(2)針對低分辨率或者有陰影的圖像,相鄰字符之間存在邊緣粘連的問題,本文用邊緣增強的MSER作為字符候選區(qū)域,并且在此基礎(chǔ)上設(shè)計了一種由粗到細(xì)的字符候選區(qū)域驗證規(guī)則。首先利用區(qū)域的形狀特征設(shè)計了驗證候選字符區(qū)域的啟發(fā)式規(guī)則,然后結(jié)合區(qū)域的筆畫寬度變換和支持向量機實現(xiàn)字符區(qū)域的確認(rèn)。(3)設(shè)計了一種基于字符區(qū)域特征相似性的文本行建立方法,將從多個通道中提取出的字符區(qū)域合并為能夠表達(dá)完整語義信息的文本行。為了驗證提出算法的性能,分別在ICDAR 2003、ICDAR 2013和SVT三個公開數(shù)據(jù)庫進(jìn)行了仿真實驗,得到了良好的實驗效果。
[Abstract]:The text in natural scene image contains a lot of semantic information, which is an important supplement to image scene. With the popularity of smartphones, tablets and digital cameras, it is more and more easy to obtain high-quality scene images. Extracting text information from natural scene images not only helps people to understand the scene more deeply, but also plays an important role in retrieval, query and visual assistance system. The premise of accurately extracting text information from natural scene is to accurately locate text area. Natural scene text location is faced with complex image background, diverse fonts, occlusion, blur and other problems, which is a very challenging research topic. In this paper, the related technologies of natural scene text location are explored, and a new natural scene text location algorithm framework based on maximum stable extremum region is proposed. The main contributions of this paper are as follows: (1) in order to solve the problem of repeated detection of text candidate regions detected by MSER detector, a MSER repeated nesting region deletion rule based on region change rate is proposed. Firstly, the image is preprocessed, and then the MSER, is extracted from each color channel, and then the repeated detection area is deleted according to the change rate of the region and the inclusion relationship. (2) aiming at the problem of edge adhesion between adjacent characters in low resolution or shadowed images, this paper uses edge enhanced MSER as character candidate region, and on this basis, designs a verification rule of character candidate region from thick to fine. Firstly, the heuristic rules for verifying the candidate character region are designed by using the shape features of the region, and then the recognition of the character region is realized by combining the stroke width transformation of the region and the support vector machine. (3) A text line establishment method based on the feature similarity of the character region is designed, which merges the character region extracted from multiple channels into a text line that can express the complete semantic information. In order to verify the performance of the proposed algorithm, three public databases, ICDAR 2013 and SVT, are simulated in ICDAR 2003, and good experimental results are obtained.
【學(xué)位授予單位】：西安科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 趙丹;;SVM核函數(shù)與選擇算法[J];數(shù)字技術(shù)與應(yīng)用;2014年09期

2 管士勇;陸利忠;閆鑌;童莉;;一種基于穩(wěn)定區(qū)域的圖像特征描述子[J];計算機工程;2012年18期

3 王國鋒;宋鵬飛;張?zhí)N靈;;智能交通系統(tǒng)發(fā)展與展望[J];公路;2012年05期

4 晉瑾;平西建;張濤;陳明貴;;圖像中的文本定位技術(shù)研究綜述[J];計算機應(yīng)用研究;2007年06期

5 ;Automatic character detection and segmentation in natural scene images[J];Journal of Zhejiang University Science A(Science in Engineer;2007年01期

相關(guān)碩士學(xué)位論文 前3條

1 黃攀;基于深度學(xué)習(xí)的自然場景文字識別[D];浙江大學(xué);2016年

2 吳慧;面向盲人視覺輔助系統(tǒng)的自然場景文本檢測[D];中南大學(xué);2014年

3 馬海清;基于邊緣和紋理的文本定位算法的研究[D];哈爾濱工業(yè)大學(xué);2007年

，

本文編號：2501713