車牌識(shí)別外文翻譯

1、中英文翻譯A configurable method for multi-style license platerecognitionAutomatic license plate recognition (LPR) has been a practical technique in the past decades. Numerous applications, such as automatic toll collection, criminal pursuit and traffic law enforcement , have been benefited from it . Alth

2、ough some novel techniques, for example RFID (radio frequency identification), WSN (wireless sensor network), etc. , have been proposed for car ID identification, LPR on image data is still an indispensable technique in current intelligent transportation systems for its convenience and low cost. LPR

3、 is generally divided into three steps： license plate detection, character segmentation and character recognition. The detection step roughly classifies LP and non-LP regions, the segmentation step separates the symbols/characters from each other in one LP so that only accurate outline of each image

4、 block of characters is left for the recognition, and the recognition step finally converts greylevel image block into characters/symbols by predefined recognition models. Although LPR technique has a long research history, it is still driven forward by various arising demands, the most frequent one

5、 of which is the variation of LP styles, for example：(1) Appearance variation caused by the change of image capturing conditions.(2) Style variation from one nation to another.(3) Style variation when the government releases new LP format.We summed them up into four factors, namely rotation angle, l

6、ine number, character type and format, after comprehensive analyses of multi-style LP characteristics on real data. Generally speaking, any change of the above four factors can result in the change of LP style or appearance and then affect the detection, segmentation or recognition algorithms. If on

7、e LP has a large rotation angle, the segmentation and recognition algorithms for horizontal LP may not work. If there are more than one character lines in one LP, additional line separation algorithm is needed before a segmentation process. With the variation of character types when we apply the met

8、hod from one nation to another, the ability to re-define the recognition models is needed. What is more, the change of LP styles requires the method to adjust by itself so that the segmented and recognized character candidates can match best with an LP format.Several methods have been proposed for m

9、ulti-national LPs or multiformat LPs in the past years while few of them comprehensively address the style adaptation problem in terms of the abovementioned factors. Some of them only claim the ability of processing multinational LPs by redefining the detection and segmentation rules or recognition

10、models.In this paper, we propose a configurable LPR method which is adaptable from one style to another, particularly from one 1 / 13nation to another, by defining the four factors as parameters. Users can constrain the scope of a parameter and at the same time the method will adjust itself so that

11、the recognition can be faster and more accurate. Similar to existing LPR techniques, we also provide details of detection, segmentation and recognition algorithms. The difference is that we emphasize on the configurable framework for LPR and the extensibility of the proposed method for multistyle LP

12、s instead of the performance of each algorithm.In the past decades, many methods have been proposed for LPR that contains detection, segmentation and recognition algorithms. In the following paragraphs, these algorithms and LPR methods based on them are briefly reviewed.LP detection algorithms can b

13、e mainly classified into three classes according to the features used, namely edgebased algorithms, colorbased algorithms and texture-based algorithms. The most commonly used method for LP detection is certainly the combinations of edge detection and mathematical morphology . In these methods, gradi

14、ent (edges) is first extracted from the image and then a spatial analysis by morphology is applied to connect the edges into LP regions. Another way is counting edges on the image rows to find out regions of dense edges or to describe the dense edges in LP regions by a Hough transformation . Edge an

15、alysis is the most straightforward method with low computation complexity and good extensibility. Compared with edgebased algorithms, colorbased algorithms depend more on the application conditions. Since LPs in a nation often have several predefined colors, researchers have defined color models to

16、segment region of interests as the LP regions . This kind of method can be affected a lot by lighting conditions. To win both high recall and low false positive rates, texture classification has been used for LP detection. InRef. Kim et al. used an SVM to train texture classifiers to detect image bl

17、ock that contains LP pixels. In Ref. the authors used Gabor filters to extract texture features in multiscales and multiorientations to describe the texture properties of LP regions. In Ref. Zhang used X and Y derivative features, grey-value variance and Adaboost classifier to classify LP and non-LP

18、 regions in an image. In Refs, wavelet feature analysis is applied to identify LP regions. Despite the good performance of these methods the computation complexity will limit their usability. In addition, texture-based algorithms may be affected by multi-lingual factors.Multi-line LP segmentation al

19、gorithms can also be classified into three classes, namely algorithms based on projection, binarization and global optimization. In the projection algorithms, gradient or color projection on vertical orientation will be calculated at first. The "valleys“ on the projection result are regarded as

20、 the space between characters and used to segment characters from each other. Segmented regions are further processed by vertical projection to obtain precise bounding boxes of the LP characters. Since simple segmentation methods are easily affected by the rotation of LP, 3 / 13segmenting the skewed

21、 LP becomes a key issue to be solved. In the binarization algorithms, global or local methods are often used to obtain foreground from background and then region connection operation is used to obtain character regions. In the most recent work, local threshold determination and slide window techniqu

22、e are developed to improve the segmentation performance. In the global optimization algorithms, the goal is not to obtain good segmentation result for independent characters but to obtain a compromise of character spatial arrangement and single character recognition result. Hidden Markov chain has b

23、een used to formulate the dynamic segmentation of characters in LP. The advantage of the algorithm is that the global optimization will improve the robustness to noise. And the disadvantage is that precise format definition is necessary before a segmentation process.Character and symbol recognition

24、algorithms in LPR can be categorized into learning-based ones and template matching ones. For the former one, artificial neural network (ANN) is the mostly used method since it is proved to be able to obtain very good recognition result given a large training set. An important factor in training an

25、ANN recognition model for LP is to build reasonable network structure with good features. SVM-based method is also adopted in LPR to obtain good recognition performance with even few training samples. Recently, cascade classifier method is also used for LP recognition. Template matching is another w

26、idely used algorithm. Generally, researchers need to build template images by hand for the LP characters and symbols. They can assign larger weights for the important points, for example, the corner points, in the template to emphasize the different characteristics of the characters. Invariance of f

27、eature points is also considered in the template matching method to improve the robustness. The disadvantage is that it is difficult to define new template by the users who have no professional knowledge on pattern recognition, which will restrict the application of the algorithm.Based on the abovem

28、entioned algorithms, lots of LPR methods have been developed. However, these methods aremainly developed for specific nation or special LP formats. In Ref. the authors focus on recognizing Greek LPs by proposing new segmentation and recognition algorithms. The characters on LPs are alphanumerics wit

29、h several fixed formats. In Ref. Zhang et al. developed a learning-based method for LP detection and character recognition. Their method is mainly for LPs of Korean styles. In Ref. optical character recognition (OCR) technique are integrated into LPR to develop general LPR method, while the performa

30、nce of OCR may drop when facing LPs of poor image quality since it is difficult to discriminate real character from candidates without format supervision. This method can only select candidates of best recognition results as LP characters without recovery process. Wang et al. developed a method to r

31、ecognize LPR with various viewing angles. Skew factor is considered in their method. In Ref. the authors proposed an automatic LPR method which can treat the cases of changes of 5 / 13illumination, vehicle speed, routes and backgrounds, which was realized by developing new detection and segmentation

32、 algorithms with robustness to the illumination and image blurring. The performance of the method is encouraging while the authors do not present the recognition result in multination or multistyle conditions. In Ref. the authors propose an LPR method in multinational environment with character segm

33、entation and format independent recognition. Since no recognition information is used in character segmentation, false segmented characters from background noise may be produced. What is more, the recognition method is not a learning-based method, which will limit its extensibility. In Ref. Mecocci

34、et al. propose a generative recognition method. Generative models (GM) are proposed to produce many synthetic characters whose statistical variability is equivalent (for each class) to that showed by real samples. Thus a suitable statistical description of a large set of characters can be obtained b

35、y using only a limited set of images. As a result, the extension ability of character recognition is improved. This method mainly concerns the character recognition extensibility instead of whole LPR method.From the review we can see that LPR method in multistyle LPR with multinational application i

36、s not fully considered. Lots of existing LPR methods can work very well in a special application condition while the performance will drop sharply when they are extended from one condition to another, or from several styles to others.多類型車牌識(shí)別配置的方法自動(dòng)車牌識(shí)別（LPR）在過去的幾十年中的實(shí)用技術(shù)。許多應(yīng)用，如 自動(dòng)收費(fèi)，犯罪的追求和交通執(zhí)法，已從中受益。

37、雖然一些新技術(shù)， 如RFID （無線射頻識(shí)別），WSN （無線傳感器網(wǎng)絡(luò)），等，已提出了汽 車身份識(shí)別，車牌圖像數(shù)據(jù)仍因其方便、成本低，在目前的智能交通 系統(tǒng)不可缺少的技術(shù)。車牌識(shí)別系統(tǒng)一般分為三個(gè)步驟：車牌定位， 字符分割和字符識(shí)別。檢測(cè)步驟大致分類LP和非LP區(qū)域分割步驟， 將符號(hào)/字符從彼此在一個(gè)LP,只有準(zhǔn)確的輪廓，每個(gè)字符圖像塊左 為識(shí)別和識(shí)別步驟，最后將灰度圖像塊轉(zhuǎn)換成字符/符號(hào)通過預(yù)定義 的識(shí)別模型。雖然車牌識(shí)別技術(shù)有著很長(zhǎng)的研究歷史，它仍然是推動(dòng) 各種要求而產(chǎn)生的，最常見的一個(gè)是LP風(fēng)格的變化，例如：（1）通過圖像采集條件的變化引起的外觀變化。風(fēng)格的變化從一個(gè)國(guó)家到另一個(gè)。風(fēng)格

38、的變化時(shí)，政府發(fā)布新的LP格式。我們將其總結(jié)為四個(gè)因素，即旋轉(zhuǎn)角度，線數(shù)，性格類型和格式，在 對(duì)實(shí)際數(shù)據(jù)的多樣式的LP特征綜合分析。一般來說，上述四個(gè)因素 的任何變化都會(huì)導(dǎo)致LP的風(fēng)格或外表的變化進(jìn)而影響檢測(cè)，分割和 識(shí)別算法。如果LP有一個(gè)大的旋轉(zhuǎn)角度，水平LP分割和識(shí)別算法可 7 / 13能不工作。如果有一個(gè)以上的在一個(gè)LP的特征線，更多的線分離算 法分割處理前需要。及人的性格類型的變化時(shí)，我們采用的方法從一 個(gè)國(guó)家到另一個(gè)，有能力重新定義識(shí)別模型是必要的。更甚的是，LP 風(fēng)格的變化需要調(diào)整的方法本身，分割和識(shí)別候選字符可以匹配最好 用一個(gè)LP格式。已經(jīng)提出了幾種方法，近年來跨國(guó)LPS或L

39、PS多而很少全面解決上述 因素的風(fēng)格適應(yīng)問題。他們中的一些人只要求處理跨國(guó)LPS的能力通 過重新定義的檢測(cè)和分割規(guī)則或識(shí)別模型。在本文中，我們提出了一個(gè)可配置的車牌識(shí)別方法是從一個(gè)到另一個(gè) 適合的風(fēng)格，特別是從一個(gè)國(guó)家到另一個(gè)，通過定義四個(gè)因素作為參 數(shù)。用戶可以約束的參數(shù)范圍，同時(shí)該方法將自我調(diào)整，這樣可以更 快、更準(zhǔn)確的識(shí)別。類似于現(xiàn)有的車牌識(shí)別技術(shù)，我們還提供詳細(xì)的 檢測(cè)，分割和識(shí)別算法。不同的是，我們強(qiáng)調(diào)了車牌識(shí)別和可擴(kuò)展性 的方法而不是multistyle LPS各算法性能的可配置的框架。在過去的兒十年中，已經(jīng)提出了許多方法用于車牌識(shí)別包含檢測(cè)，分 割和識(shí)別算法。在下面的段落中，這些

40、算法和車牌識(shí)別方法的基礎(chǔ)上, 簡(jiǎn)要回顧。低壓檢測(cè)算法主要可按特征分為三類，即edgebased算法，基于顏色 特征的算法和基于紋理的算法。LP檢測(cè)最常用的方法是邊緣檢測(cè)和數(shù) 學(xué)形態(tài)學(xué)的組合。在這些方法中，梯度（邊）是第一個(gè)從圖像中提取 和隨后的形態(tài)空間分析應(yīng)用于邊緣連接到低壓區(qū)域。另一種方法是計(jì) 數(shù)的邊緣在圖像行發(fā)現(xiàn)密集的邊緣地區(qū)或描述密集的邊緣在LP地區(qū) 的Hough變換。邊緣分析是最簡(jiǎn)單的方法具有較低的計(jì)算復(fù)雜度和良 好的可擴(kuò)展性。及edgebased算法相比，基于顏色特征的算法更依賴 于應(yīng)用條件。由于LPS中的國(guó)家往往有幾個(gè)預(yù)定義的顏色，研究人員 已經(jīng)定義的顏色模型的分割區(qū)域的利益為低壓

41、區(qū)。這種方法可以通過 照明條件影響很大。贏得了較高的召回率和較低的誤報(bào)率，紋理分類 已被用于低壓檢測(cè)。在參考這種方法可以通過照明條件影響很大。贏 得了較高的召回率和較低的誤報(bào)率，紋理分類己被用于低壓檢測(cè)?；?姆等人在文獻(xiàn)。使用SVM分類器來檢測(cè)圖像塊的紋理包含LP像素。 在參考文獻(xiàn)作者使用Gabor濾波器提取紋理特征的多尺度、 multiorientations描述LP區(qū)域的紋理特性。在參考文獻(xiàn)采用張X 和Y的衍生功能，灰度值的方差和AdaBoost分類潛，對(duì)圖像中的LP 和非LP區(qū)域進(jìn)行分類，在文獻(xiàn)。小波特征分析方法識(shí)別低壓區(qū)。盡 管這些方法的計(jì)算復(fù)雜性限制了他們的可用性，性能良好。此外，基 于紋理的算法可以通過多語(yǔ)言因素的影響。多線的LP分割算法可分為三類，即算法的基礎(chǔ)上投影，二值化和 全局優(yōu)化。在投影算法，梯度或彩色投影在垂直方向?qū)⑾扔?jì)算?！肮取? / 13在投影結(jié)果作為特征和用于分割字符之間的空間。分割區(qū)域的垂直投 影的進(jìn)一步