本文選題：深度學(xué)習(xí)　切入點：卷積神經(jīng)網(wǎng)絡(luò)　出處：《江西理工大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著交通管理技術(shù)的逐步發(fā)展和完善,車牌識別技術(shù)如今已普遍使用在道路監(jiān)控和道路指揮系統(tǒng)中,如高速路收費站、路口車流行人監(jiān)控、小區(qū)以及停車場自動收費放行系統(tǒng)等。同時它也是智能交通系統(tǒng)的重要組成部分,為解決道路擁堵的狀況提供了新的方案,能夠幫助決策者快速高效的制定執(zhí)行計劃,節(jié)約了勞動成本。車輛牌照是汽車獨有認證標志,因而對車牌相關(guān)技術(shù)的學(xué)習(xí)和探討能帶來重大社會價值。本文介紹了車牌識別的歷史和背景,并深入了解了車牌識別技術(shù)在國內(nèi)外的發(fā)展現(xiàn)狀,介紹近幾年一直很流行的機器學(xué)習(xí)算法及其在圖像檢測識別等方面的應(yīng)用�？朔F(xiàn)有算法的一些局限性,并結(jié)合機器學(xué)習(xí)的相關(guān)算法,提出一種機器學(xué)習(xí)和圖像處理技術(shù)相結(jié)合的車牌識別系統(tǒng),利用深度學(xué)習(xí)和圖像處理技術(shù)來實現(xiàn)。本文車牌識別著重從車輛位置的檢測、車牌位置的確定這兩方面來介紹。文中對各個部分的常見算法進行了總結(jié),并對相關(guān)算法進行了改進,利用深度學(xué)習(xí)和圖像處理的知識進行優(yōu)化。主要工作如下:⑴介紹數(shù)字圖像處理相關(guān)技術(shù),對圖像中三種顏色空間以及它們之間相互轉(zhuǎn)換進行了簡要的描述和分析,介紹了數(shù)學(xué)形態(tài)學(xué)原理及其在圖像濾波去噪方面的作用,針對文中要使用的卷積神經(jīng)網(wǎng)絡(luò)和角點密度聚類,描述了這兩種算法的基本概念,實現(xiàn)方式。⑵為了解決傳統(tǒng)車輛檢測存在的問題,提高車輛檢測的準確率,提出將區(qū)域卷積神經(jīng)網(wǎng)絡(luò)算法應(yīng)用到車輛檢測中。該方案依照圖像顏色層次相關(guān)特征,產(chǎn)生潛在車輛待選區(qū)域。建立相應(yīng)卷積神經(jīng)網(wǎng)絡(luò)模型,提取每個候選區(qū)域局部特征。對卷積神經(jīng)網(wǎng)絡(luò)模型做出改良,修改原輸入圖像大小,其網(wǎng)絡(luò)參數(shù)也做出相應(yīng)調(diào)整。選定正負樣本進行SVM分類器訓(xùn)練,采取SVM分類器進行車輛候選區(qū)域分類,最后判斷車輛信息。通過實驗數(shù)據(jù)論證,本文改進的卷積模型在車輛檢測測試中獲得較優(yōu)異的效果。⑶為了解決傳統(tǒng)車牌定位算法性能不夠理想的情況,提出一種角點密度統(tǒng)計方法對車牌進行定位。第一步,依據(jù)車牌自身的顏色特性,將整幅圖像從RGB彩色空間變換為HSL彩色空間,對獲取的HSL圖像進行閾值化處理,然后采用一系列形態(tài)學(xué)方法完成圖像濾波,剔除無用信息。接著,對濾波后圖像使用角點檢測算法,獲取角點數(shù)量、坐標信息。最后采取DBSCAN角點密度判定準則確定車牌位置。實驗結(jié)果表明,此算法定位精度也較高,定位時間較快,能滿足實時性需求。
[Abstract]:With the development and improvement of traffic management technology, license plate recognition technology has been widely used in road monitoring and road command system, such as highway toll stations, traffic and pedestrian traffic monitoring, It is also an important part of the Intelligent Transportation system, which provides a new solution to the congestion of roads, and can help decision makers to make implementation plans quickly and efficiently. This paper introduces the history and background of license plate recognition, which can bring great social value to the study and discussion of license plate related technology. And deeply understand the development of license plate recognition technology at home and abroad, introduce the machine learning algorithm and its application in image detection and recognition, which has been very popular in recent years, overcome some limitations of existing algorithms. Combined with the related algorithms of machine learning, a license plate recognition system combining machine learning and image processing technology is proposed, which uses depth learning and image processing technology to realize the license plate recognition. In this paper, the common algorithms of each part are summarized, and the related algorithms are improved. Using the knowledge of depth learning and image processing to optimize. The main work is as follows: 1 introduces the digital image processing technology, describes and analyzes the three color spaces in the image and the conversion between them. This paper introduces the principle of mathematical morphology and its role in image filtering and denoising, and describes the basic concepts of these two algorithms for the convolution neural network and corner density clustering used in this paper. In order to solve the problems existing in traditional vehicle detection and improve the accuracy of vehicle detection, a regional convolution neural network algorithm is proposed for vehicle detection. The corresponding convolution neural network model is established to extract the local features of each candidate region. The convolution neural network model is modified to modify the original input image size. The network parameters are adjusted accordingly. The positive and negative samples are selected for SVM classifier training, and the SVM classifier is used to classify vehicle candidate regions. Finally, the vehicle information is judged. In order to solve the problem that the performance of the traditional license plate location algorithm is not ideal, a corner density statistical method is proposed to locate the vehicle license plate. According to the color characteristics of license plate, the whole image is transformed from RGB color space to HSL color space, and the obtained HSL image is thresholded. Then, a series of morphological methods are used to filter the image and eliminate the useless information. Corner detection algorithm is used for filtered images to obtain corner number and coordinate information. Finally, DBSCAN corner density criterion is adopted to determine the location of license plate. The experimental results show that the algorithm has higher accuracy and faster localization time. It can meet the real-time requirement.
【學(xué)位授予單位】：江西理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：U495;TP391.41

【參考文獻】

相關(guān)期刊論文 前10條

1 孫陽;王云龍;何文鐸;;低清晰度車牌識別技術(shù)的研究與應(yīng)用[J];華中科技大學(xué)學(xué)報(自然科學(xué)版);2016年S1期

2 趙卓峰;丁維龍;張帥;;海量車牌識別數(shù)據(jù)集上基于時空劃分的旅行時間計算方法[J];電子學(xué)報;2016年05期

3 吳鵬;徐洪玲;李雯霖;宋文龍;張佳薇;;基于區(qū)域檢測的多尺度Harris角點檢測算法[J];哈爾濱工程大學(xué)學(xué)報;2016年07期

4 章為川;孔祥楠;宋文;;圖像的角點檢測研究綜述[J];電子學(xué)報;2015年11期

5 肖志濤;王紅;張芳;耿磊;吳駿;李月龍;李峰;;復(fù)雜自然環(huán)境下感興趣區(qū)域檢測[J];中國圖象圖形學(xué)報;2015年05期

6 蔡英鳳;王海;陳龍;江浩斌;;采用視覺顯著性和深度卷積網(wǎng)絡(luò)的魯棒視覺車輛識別算法[J];江蘇大學(xué)學(xué)報(自然科學(xué)版);2015年03期

7 劉建偉;劉媛;羅雄麟;;深度學(xué)習(xí)研究進展[J];計算機應(yīng)用研究;2014年07期

8 李tt;李帥;王家明;黃凱;;物聯(lián)網(wǎng)時代車牌識別技術(shù)在智能小區(qū)中的應(yīng)用[J];中國科技信息;2013年13期

9 朱夢哲;陳志華;趙鐘;尤越;;基于OpenCV的車牌定位和校正方法[J];計算機應(yīng)用;2013年S1期

10 陳汗青;萬艷玲;王國剛;;數(shù)字圖像處理技術(shù)研究進展[J];工業(yè)控制計算機;2013年01期

相關(guān)會議論文 前1條

1 陳喜群;楊新苗;史其信;;城市道路車牌識別系統(tǒng)在交通管理中的應(yīng)用[A];2008第四屆中國智能交通年會論文集[C];2008年

相關(guān)碩士學(xué)位論文 前1條

1 高雪成;實時監(jiān)控與數(shù)據(jù)采集系統(tǒng)中的圖像處理與應(yīng)用研究[D];東北大學(xué);2011年

，

本文編號：1628196