本文選題：文本檢測 + 文種辨識�。� 參考：《延邊大學》2017年碩士論文

【摘要】：文字在人類思想情感以及文化傳承中是十分重要的符號工具,在社會生產(chǎn)生活的各個方面都體現(xiàn)出了文字的重要性與不可替代性。在現(xiàn)代城市環(huán)境中,文字是普遍存在的元素,如海報、道路標志、牌匾燈箱等,其中不乏大量的文字信息。在自然圖像中,文字所表達的語義信息是理解圖像內(nèi)容時一個很重要的參考信息。自然圖像中的文種辨識是基于內(nèi)容的圖像檢索和多語種系統(tǒng)開發(fā)領域的一個重要方向。在自然圖像場景中文字的檢測及其文種的辨識有相當大的難度:不同自然場景中的文字含有不同的特性,例如顏色不同、數(shù)量不一、大小與間隔不同等;而且在自然圖像中,文字的背景往往很復雜,同時存在著諸如噪聲、傾斜和透視變換等各種問題。這些都對自然圖像中的文字檢測和文種辨識工作帶來了極大的困難。如何有效地對包含有多種語言文字的自然圖像進行處理成為自然場景分析與理解中亟待解決的難題。本學位論文提出了一種基于視覺顯著性和邊緣密集度的文本區(qū)域檢測方法以及基于圖像特征和機器學習方法的文種辨識方法。首先,提出了基于視覺顯著性和邊緣密集度的文本區(qū)域檢測方法。該文本區(qū)域檢測方法通過多尺度譜殘差方法來檢測視覺顯著性區(qū)域,接著在視覺顯著性區(qū)域內(nèi)使用Sobel算子來對圖像進行檢測邊緣,通過計算圖像的邊緣密集度,再使用數(shù)學形態(tài)學方法對圖像邊緣進行預處理,最終通過自然圖像中文字排列的先驗知識來檢測文本區(qū)域。其次,提出了基于基本圖像特征與機器學習方法的文種辨識方法。該方法對阿拉伯數(shù)字、英文、俄文、日文假名、簡體中文和朝鮮文構(gòu)建了文字樣本圖像并提取其骨架,利用該骨架的基本圖像特征構(gòu)造相應文種的特征集,并根據(jù)不同文種的結(jié)構(gòu)特征,結(jié)合分類方法的特性,將文種辨識分為兩個階段.·粗分類階段和細分類階段。在粗分類階段,使用支持向量機將文字劃分為兩大類,第一類中包含阿拉伯數(shù)字、英文、俄文和日文假名,第二類中包含簡體中文和朝鮮文。在辨識階段,使用支持向量機對第一類文字進行文種辨識,使用BP神經(jīng)網(wǎng)絡對第二類文字進行辨識。實驗結(jié)果表明,本文提出的基于視覺顯著性與文字邊緣密集度的文本檢測方法得到了 73%的檢測率,基于基本圖像特征與機器學習方法的文種辨識方法得到了 73.33%的辨識率,解決了自然圖像中的文本檢測與文種辨識問題,同時也驗證了本學位論文所提出方法的正確性與可行性。
[Abstract]:Writing is a very important symbolic tool in human thoughts and emotions as well as cultural heritage. It embodies the importance and irreplaceable character in all aspects of social production and life. In modern urban environment, characters are common elements, such as posters, road signs, plaques and lampboxes, among which there is a lot of text information. In natural images, the semantic information expressed by text is an important reference information in understanding image content. Language recognition in natural images is an important direction in the field of content-based image retrieval and multilingual system development. Text detection and text recognition in natural image scenes are quite difficult: text in different natural scenes contains different characteristics, such as different colors, different quantities, different sizes and intervals, and in natural images, The background of text is often very complex, and there are many problems such as noise, tilt and perspective transformation. All these bring great difficulties to text detection and language recognition in natural images. How to effectively process the natural images containing many languages and characters has become a difficult problem to be solved in the analysis and understanding of natural scenes. In this dissertation, a text region detection method based on visual salience and edge intensity, and a text recognition method based on image features and machine learning methods are proposed. Firstly, a text region detection method based on visual salience and edge intensity is proposed. The text region detection method uses multi-scale spectral residuals method to detect the visual significant region, then uses Sobel operator to detect the edge of the image in the visual salience region, and calculates the edge density of the image. Then the edge of the image is preprocessed by mathematical morphology, and the text region is detected by the prior knowledge of the text arrangement in the natural image. Secondly, a language identification method based on basic image features and machine learning is proposed. In this method, the Arabic numerals, English, Russian, Japanese pseudonyms, simplified Chinese and Korean characters were constructed and their skeleton was extracted, and the feature sets of the corresponding languages were constructed by using the basic image features of the skeleton. According to the structural characteristics of different languages and the characteristics of classification methods, the text identification is divided into two stages: coarse classification stage and fine classification stage. In the rough classification stage, the support vector machine is used to divide the characters into two categories. The first includes Arabic numerals, English, Russian and Japanese pseudonyms, and the second includes simplified Chinese and Korean. In the phase of identification, support vector machine (SVM) is used to identify the first kind of characters and BP neural network is used to identify the second kind of characters. The experimental results show that the proposed text detection method based on visual salience and text edge density has a 73% detection rate, and a text recognition rate of 73.33% based on basic image features and machine learning methods. The problems of text detection and text identification in natural images are solved, and the correctness and feasibility of the methods proposed in this dissertation are also verified.
【學位授予單位】：延邊大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前10條

1 張國和;黃凱;張斌;符歡歡;趙季中;;最大穩(wěn)定極值區(qū)域與筆畫寬度變換的自然場景文本提取方法[J];西安交通大學學報;2017年01期

2 楊玲玲;葉東毅;;一種基于圖像矩和紋理特征的自然場景文本檢測算法[J];小型微型計算機系統(tǒng);2016年06期

3 唐有寶;卜巍;鄔向前;;多層次MSER自然場景文本檢測[J];浙江大學學報(工學版);2016年06期

4 許肖;顧磊;;結(jié)合顯著性檢測和中心分割算法的文本檢測方法[J];計算機科學;2016年04期

5 尹芳;鄭亮;陳田田;;基于Adaboost算法的場景中文文本定位[J];計算機工程與應用;2017年04期

6 買買提依明·哈斯木;吾守爾·斯拉木;維尼拉·木沙江;努爾麥麥提·尤魯瓦斯;;基于統(tǒng)計專用字符的維、哈、柯文文種識別研究[J];中文信息學報;2015年02期

7 劉亞亞;于鳳芹;陳瑩;;基于連通區(qū)域和統(tǒng)計特征的圖像文本定位[J];計算機工程與應用;2016年05期

8 閔華清;鄭華強;羅榮華;;自然場景圖像中基于視覺顯著性的文本區(qū)域檢測[J];華南理工大學學報(自然科學版);2012年08期

9 崔榮一;金世珍;;朝鮮文字信息結(jié)構(gòu)的研究[J];中文信息學報;2011年05期

10 郭龍;平西建;周林;童莉;;基本圖像特征用于文本圖像文種識別[J];應用科學學報;2011年01期

相關(guān)碩士學位論文 前3條

1 樸明姬;自然圖像中文字語種辨識方法的研究[D];延邊大學;2014年

2 金貞;漢字特征提取及識別技術(shù)的研究[D];上海交通大學;2010年

3 項思俊;基于SVM的脫機手寫體漢字識別方法的研究[D];合肥工業(yè)大學;2009年

，

本文編號：2047957