復雜自然環(huán)境下車牌識別算法研究
發(fā)布時間：2018-09-06 14:24
【摘要】：車牌識別技術是智能交通系統(tǒng)中的重要組成部分,是計算機視覺、圖像處理與模式識別在智能交通領域的重要研究課題之一。但在實際環(huán)境下采集到的車牌圖像,容易受到光照變化、尺度變化、目標干擾等諸多不利因素影響,因此在復雜多變的自然下識別車牌仍然是一個十分具有挑戰(zhàn)的課題。車牌識別技術主要解決車牌的定位、分割、識別三個問題。本文分別對這三個部分進行了研究,并提出了相應算法。本文提出了一種基于目標區(qū)域的車牌定位算法,采用逐步求精的定位策略。該算法適用于光照變化、尺度變化和目標干擾等復雜的自然環(huán)境。本文引入了Selective Search算法對輸入圖像進行目標區(qū)域提取,根據車牌特征篩選出車牌候選區(qū)域,并通過一個預訓練的支持向量機對候選區(qū)域進行判別,保留車牌區(qū)域。對獲得車牌區(qū)域進行非極大值(NMS)抑制剔除重合區(qū)域。最后精確定位到車牌位置。本文提出了一種基于連通區(qū)域的字符分割算法。該算法首先對輸入車牌進行預處理和傾斜校正,結合連通區(qū)域標記法和數(shù)學形態(tài)學處理法獲得字符區(qū)域。同時,本文對傳統(tǒng)的字符歸一化方法進行了改進,有效的解決了由字符歸一化造成的字符形變的問題。本文提出了一種基于卷積神經網絡的車牌字符識別算法,設計了兩個卷積網絡NET1和NET2,其中NET1用做識別漢字,NET2用做識別字母和數(shù)字。本文引入了 rectifier作為神經元的激活函數(shù),并使用mini-batch隨機梯度下降法訓練網絡,可以加速目標函數(shù)的收斂。采用卷積神經網絡可以從輸入的字符圖像中自動提取出圖像特征,并進行分類,從而獲得識別結果。在整個過程中,不需要手動選定圖像特征或對圖像作局部處理。實驗表明,本文算法可以有效的在復雜自然環(huán)境中定位車牌,分割字符和識別字符。并將本文算法與同類型算法做了比較,均有顯著的提升。
[Abstract]:License plate recognition technology is an important part of intelligent transportation system. It is one of the important research topics of computer vision, image processing and pattern recognition in the field of intelligent transportation. However, the license plate images collected in the actual environment are easily affected by many unfavorable factors, such as light change, scale change, target interference and so on, so it is still a challenge to recognize the license plate in the complex and changeable nature. License plate recognition technology mainly solves three problems of license plate location, segmentation and recognition. In this paper, the three parts are studied, and the corresponding algorithms are proposed. A license plate location algorithm based on target region is proposed in this paper. The algorithm is suitable for complex natural environment, such as illumination variation, scale change and target interference. In this paper, the Selective Search algorithm is introduced to extract the target region of the input image, and the candidate region is selected according to the license plate feature, and the candidate region is identified by a pre-trained support vector machine to preserve the license plate area. Non-maximum (NMS) suppression is used to eliminate the coincidence area of the obtained license plate. Finally, the location of the license plate is accurately located. In this paper, a character segmentation algorithm based on connected region is proposed. The algorithm firstly preprocesses and corrects the input license plate, and combines the connected region marking method and the mathematical morphology processing method to obtain the character region. At the same time, the traditional method of character normalization is improved, which effectively solves the problem of character deformation caused by character normalization. A license plate character recognition algorithm based on convolution neural network is presented in this paper. Two convolution networks NET1 and NET2, are designed in which NET1 is used to recognize Chinese characters and NET2 is used to recognize letters and numbers. In this paper, rectifier is introduced as the activation function of neurons, and the mini-batch stochastic gradient descent method is used to train the network, which can accelerate the convergence of the objective function. By using convolution neural network, the image features can be automatically extracted from the input character images and classified, and the recognition results can be obtained. In the whole process, there is no need to manually select image features or make partial image processing. Experimental results show that the proposed algorithm can effectively locate license plates, segment characters and recognize characters in complex environments. This algorithm is compared with the same type algorithm, and has a significant improvement.
【學位授予單位】：山東大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
本文編號：2226627
[Abstract]:License plate recognition technology is an important part of intelligent transportation system. It is one of the important research topics of computer vision, image processing and pattern recognition in the field of intelligent transportation. However, the license plate images collected in the actual environment are easily affected by many unfavorable factors, such as light change, scale change, target interference and so on, so it is still a challenge to recognize the license plate in the complex and changeable nature. License plate recognition technology mainly solves three problems of license plate location, segmentation and recognition. In this paper, the three parts are studied, and the corresponding algorithms are proposed. A license plate location algorithm based on target region is proposed in this paper. The algorithm is suitable for complex natural environment, such as illumination variation, scale change and target interference. In this paper, the Selective Search algorithm is introduced to extract the target region of the input image, and the candidate region is selected according to the license plate feature, and the candidate region is identified by a pre-trained support vector machine to preserve the license plate area. Non-maximum (NMS) suppression is used to eliminate the coincidence area of the obtained license plate. Finally, the location of the license plate is accurately located. In this paper, a character segmentation algorithm based on connected region is proposed. The algorithm firstly preprocesses and corrects the input license plate, and combines the connected region marking method and the mathematical morphology processing method to obtain the character region. At the same time, the traditional method of character normalization is improved, which effectively solves the problem of character deformation caused by character normalization. A license plate character recognition algorithm based on convolution neural network is presented in this paper. Two convolution networks NET1 and NET2, are designed in which NET1 is used to recognize Chinese characters and NET2 is used to recognize letters and numbers. In this paper, rectifier is introduced as the activation function of neurons, and the mini-batch stochastic gradient descent method is used to train the network, which can accelerate the convergence of the objective function. By using convolution neural network, the image features can be automatically extracted from the input character images and classified, and the recognition results can be obtained. In the whole process, there is no need to manually select image features or make partial image processing. Experimental results show that the proposed algorithm can effectively locate license plates, segment characters and recognize characters in complex environments. This algorithm is compared with the same type algorithm, and has a significant improvement.
【學位授予單位】：山東大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41
【參考文獻】
相關期刊論文 前10條
1 耿慶田;趙宏偉;;基于分形維數(shù)和隱馬爾科夫特征的車牌識別[J];光學精密工程;2013年12期
2 咼潤華;蘇婷婷;馬曉偉;;BP神經網絡聯(lián)合模板匹配的車牌識別系統(tǒng)[J];清華大學學報(自然科學版);2013年09期
3 王偉;馬永強;彭強;;SVM多類分類器在車牌字符識別中的應用[J];計算機工程與設計;2011年09期
4 綦宏志;孫長城;安興偉;許敏鵬;馬嵐;明東;萬柏坤;;基于SVM特征優(yōu)化的Farwell虛擬矩陣字符識別[J];天津大學學報;2011年09期
5 尚趙偉;國慶;馬尚君;袁博;楊建偉;;基于二進小波變換的多車牌定位算法[J];計算機工程;2011年03期
6 陳振學;常發(fā)亮;劉成云;;基于特征顯著性的多特征融合車牌定位算法[J];控制與決策;2010年12期
7 顧弘;趙光宙;齊冬蓮;孫峗;張建良;;車牌識別中先驗知識的嵌入及字符分割方法[J];中國圖象圖形學報;2010年05期
8 張坤艷;鐘宜亞;苗松池;王桂娟;;一種基于全局閾值二值化方法的BP神經網絡車牌字符識別系統(tǒng)[J];計算機工程與科學;2010年02期
9 閆雪梅;王曉華;夏興高;;基于PCA和BP神經網絡算法的車牌字符識別[J];激光與紅外;2007年05期
10 周開軍;陳三寶;徐江陵;;復雜背景下的車牌定位和字符分割研究[J];計算機工程;2007年04期
相關碩士學位論文 前1條
1 王慧;基于模板匹配的手寫體字符識別算法研究[D];北京交通大學;2012年
，本文編號：2226627
本文鏈接：http://www.lk138.cn/shoufeilunwen/xixikjs/2226627.html
最近更新
教材專著
