本文關(guān)鍵詞： 模糊車(chē)牌識(shí)別 圖像模糊度評(píng)價(jià) 模糊字符識(shí)別 字典學(xué)習(xí) 稀疏表示　出處：《南京郵電大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：作為智能交通系統(tǒng)的重要組成部分之一,車(chē)牌識(shí)別在人們的日常生活中發(fā)揮著不可替代的作用。但是由于監(jiān)控?cái)z像機(jī)自身存在缺陷、惡劣天氣的影響以及車(chē)輛與攝像機(jī)之間的相對(duì)運(yùn)動(dòng)等因素,部分采集到的車(chē)牌圖像通常會(huì)變得模糊,因此就有必要建立能夠識(shí)別模糊車(chē)牌圖像的應(yīng)用系統(tǒng)。本文通過(guò)對(duì)模糊車(chē)牌圖像的特征進(jìn)行詳細(xì)分析,以及對(duì)車(chē)牌識(shí)別、圖像模糊度評(píng)價(jià)、模糊圖像識(shí)別等技術(shù)進(jìn)行深入研究,實(shí)現(xiàn)了對(duì)模糊車(chē)牌識(shí)別系統(tǒng)的建立。本文的主要工作及研究成果包括以下三個(gè)方面:1、總結(jié)了常見(jiàn)的車(chē)牌圖像定位、字符分割以及預(yù)處理方法,并結(jié)合需要識(shí)別的模糊車(chē)牌圖像的特點(diǎn),提出了適用于模糊車(chē)牌圖像的定位、字符分割以及預(yù)處理方法,然后基于以上方法創(chuàng)建了模糊字符圖像庫(kù)。2、實(shí)現(xiàn)了對(duì)模糊車(chē)牌圖像模糊度的評(píng)價(jià)。模糊度評(píng)價(jià)的目的是將嚴(yán)重模糊的車(chē)牌圖像以及比較模糊的車(chē)牌圖像區(qū)分開(kāi),從而只針對(duì)比較模糊的車(chē)牌圖像設(shè)計(jì)識(shí)別模型。首先,結(jié)合人眼對(duì)模糊車(chē)牌后五位字符的識(shí)別能力建立了一個(gè)模糊度主觀評(píng)價(jià)模型,并基于該模型創(chuàng)建了一個(gè)帶有模糊度等級(jí)標(biāo)簽的模糊車(chē)牌圖像數(shù)據(jù)庫(kù);其次,在所創(chuàng)建的模糊車(chē)牌圖像數(shù)據(jù)庫(kù)的基礎(chǔ)上,利用投影字典對(duì)學(xué)習(xí)模型以及邏輯回歸模型建立了一個(gè)模糊度客觀評(píng)價(jià)模型。實(shí)驗(yàn)結(jié)果表明,所建立的客觀評(píng)價(jià)模型取得的評(píng)價(jià)結(jié)果與主觀評(píng)價(jià)模型取得效果具有較好的一致性。3、將稀疏表示分類(lèi)模型以及盲去模糊模型緊密聯(lián)合起來(lái),建立了一個(gè)模糊車(chē)牌字符識(shí)別模型。所建立的模型將圖像去模糊以及圖像識(shí)別耦合在一個(gè)能量方程中,使得去模糊以及識(shí)別相互影響、相互促進(jìn),最終同時(shí)實(shí)現(xiàn)了對(duì)模糊字符圖像的恢復(fù)和識(shí)別。實(shí)驗(yàn)結(jié)果表明,所建立的模型具有良好的去模糊以及識(shí)別效果。
[Abstract]:As an important part of intelligent transportation system, license plate recognition plays an irreplaceable role in people's daily life. Because of the bad weather and the relative motion between the vehicle and the camera, some of the license plate images are usually blurred. Therefore, it is necessary to establish an application system that can recognize the fuzzy license plate image. Through the detailed analysis of the characteristics of the fuzzy license plate image, and the in-depth research on the license plate recognition, image ambiguity evaluation, fuzzy image recognition, etc. The main work and research results of this paper include the following three aspects: 1. The common license plate image location, character segmentation and preprocessing methods are summarized. Combined with the characteristics of fuzzy license plate image which needs to be recognized, the method of location, character segmentation and preprocessing for fuzzy license plate image is proposed. Then, based on the above methods, the fuzzy character image database .2is established to evaluate the ambiguity of the fuzzy license plate image. The purpose of the ambiguity evaluation is to distinguish the seriously blurred license plate image from the relatively fuzzy license plate image. So only the fuzzy license plate image recognition model is designed. Firstly, a subjective evaluation model of fuzzy degree is established by combining the recognition ability of the human eye to the five characters behind the fuzzy license plate. Based on the model, a fuzzy license plate image database with fuzzy grade label is created. Secondly, the fuzzy license plate image database is created based on the fuzzy license plate image database. An objective evaluation model of fuzzy degree is established for learning model and logical regression model by using projection dictionary. The experimental results show that, The evaluation results obtained by the established objective evaluation model are in good agreement with the results obtained by the subjective evaluation model. The sparse representation classification model and the blind de-fuzzy model are closely combined. In this paper, a fuzzy license plate character recognition model is established, which combines image de-blurring and image recognition into an energy equation, which makes de-blurring and recognition interact and promote each other. Finally, the restoration and recognition of fuzzy character images are realized at the same time. The experimental results show that the proposed model has a good effect of de-blurring and recognition.
【學(xué)位授予單位】：南京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 牛博雅;黃琳琳;胡健;;自然場(chǎng)景下的車(chē)牌檢測(cè)與識(shí)別算法[J];信號(hào)處理;2016年07期

2 殷羽;鄭宏;高婷婷;劉操;;基于聯(lián)合HOG特征的車(chē)牌識(shí)別算法[J];計(jì)算機(jī)工程與設(shè)計(jì);2015年02期

3 王永杰;裴明濤;賈云得;;多信息融合的快速車(chē)牌定位[J];中國(guó)圖象圖形學(xué)報(bào);2014年03期

4 耿慶田;趙宏偉;;基于分形維數(shù)和隱馬爾科夫特征的車(chē)牌識(shí)別[J];光學(xué)精密工程;2013年12期

5 桑慶兵;齊會(huì)新;吳小俊;李朝鋒;;基于DCT系數(shù)無(wú)參考模糊圖像質(zhì)量評(píng)價(jià)方法[J];儀器儀表學(xué)報(bào);2013年11期

6 咼潤(rùn)華;蘇婷婷;馬曉偉;;BP神經(jīng)網(wǎng)絡(luò)聯(lián)合模板匹配的車(chē)牌識(shí)別系統(tǒng)[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年09期

7 馬爽;樊養(yǎng)余;雷濤;吳鵬;;一種基于多特征提取的實(shí)用車(chē)牌識(shí)別方法[J];計(jì)算機(jī)應(yīng)用研究;2013年11期

8 呂文強(qiáng);楊健;;一種有效的提高車(chē)牌首字符識(shí)別率的方法[J];計(jì)算機(jī)科學(xué);2013年S1期

9 陳瑋;曹志廣;李劍平;;改進(jìn)的模板匹配方法在車(chē)牌識(shí)別中的應(yīng)用[J];計(jì)算機(jī)工程與設(shè)計(jì);2013年05期

10 張濤;梁德群;王新年;;基于稀疏表示的圖像模糊度評(píng)價(jià)方法[J];計(jì)算機(jī)工程;2013年04期

，

本文編號(hào)：1552444