本文選題：車牌定位 + 形狀回歸�。� 參考：《浙江大學(xué)》2017年碩士論文

【摘要】：車牌識(shí)別系統(tǒng)是現(xiàn)代智能交通系統(tǒng)的重要組成部分之一,被廣泛應(yīng)用于出入控制、車流監(jiān)控、電子收費(fèi)等多個(gè)場(chǎng)合,提高了交通管理自動(dòng)化程度。車輛識(shí)別系統(tǒng)通過分析和處理復(fù)雜背景下的車輛圖像,檢測(cè)、定位車牌,識(shí)別汽車牌照的字符,從而快速識(shí)別車輛身份。其中車牌精確定位步驟是車牌角度矯正和準(zhǔn)確字符分割的重要基礎(chǔ)。傳統(tǒng)的車牌定位方法利用車牌幾何、顏色和紋理特征,處理步驟復(fù)雜,適用場(chǎng)景有限,在低照度、透視變換、低質(zhì)模糊等場(chǎng)景下的準(zhǔn)確率有待提高。為了構(gòu)建更加通用準(zhǔn)確的車牌精確定位算法,本文受人臉關(guān)鍵點(diǎn)檢測(cè)方法的啟發(fā),采用形狀回歸方法,將車牌的精確定位轉(zhuǎn)化為求取車牌四角坐標(biāo)。借助大量標(biāo)注后的車牌數(shù)據(jù),學(xué)習(xí)車牌的角點(diǎn)特征,建立多個(gè)階段的回歸方程,通過每一階段的反饋調(diào)整,逐漸接近真實(shí)的車牌位置。通過在真實(shí)復(fù)雜的車牌數(shù)據(jù)集里進(jìn)行實(shí)驗(yàn),我們證明基于形狀回歸的車牌定位算法有著更快的定位速度,和更低的位置偏移,對(duì)車牌的拍攝環(huán)境、拍攝角度和距離依賴較小,具備更高的通用性。同時(shí),基于形狀回歸的車牌定位算法能夠提高車牌識(shí)別的準(zhǔn)確率。
[Abstract]:License plate recognition system is one of the important parts of modern intelligent transportation system. It is widely used in many occasions such as access control, vehicle flow monitoring, electronic charge and so on, which improves the degree of automation of traffic management. The vehicle recognition system can quickly identify the vehicle identity by analyzing and processing the vehicle image under the complex background, detecting, locating the license plate and recognizing the characters of the vehicle license plate. The accurate location of license plate is an important basis for the correction of license plate angle and accurate character segmentation. The traditional license plate location method uses the license plate geometry, color and texture features, the processing steps are complex, the applicable scene is limited, and the accuracy of low illumination, perspective transformation and low quality fuzzy scene needs to be improved. In order to construct a more general and accurate license plate accurate location algorithm, this paper, inspired by the face key point detection method, uses the shape regression method to transform the accurate license plate location into obtaining the license plate quadrangle coordinates. With the help of a large number of tagged license plate data, learning the corner feature of license plate, the regression equation of multiple stages is established, and through the feedback adjustment of each stage, the real license plate position is gradually approached. Through experiments in the real and complex license plate data set, we prove that the shape regression based license plate localization algorithm has faster localization speed and lower position offset, and has less dependence on the shooting environment, shooting angle and distance of the license plate. It has higher generality. At the same time, the algorithm based on shape regression can improve the accuracy of license plate recognition.
【學(xué)位授予單位】：浙江大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：U495;TP391.41

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 董欣;車牌精確定位算法探究[D];浙江大學(xué);2017年

，

本文編號(hào)：1961650