《基于BP神经网络的车型识别外文翻译.doc》由会员分享，可在线阅读，更多相关《基于BP神经网络的车型识别外文翻译.doc（19页珍藏版）》请在三一办公上搜索。
1、一、外 文 资 料License Plate Recognition Based On Prior KnowledgeAbstract - In this paper, a new algorithm based on improved BP (back propagation) neural network for Chinese vehicle license plate recognition (LPR) is described. The proposed approach provides a solution for the vehicle license plates (VLP)
2、 which were degraded severely. What it remarkably differs from the traditional methods is the application of prior knowledge of license plate to the procedure of location, segmentation and recognition. Color collocation is used to locate the license plate in the image. Dimensions of each character a
3、re constant, which is used to segment the character of VLPs. The Layout of the Chinese VLP is an important feature, which is used to construct a classifier for recognizing. The experimental results show that the improved algorithm is effective under the condition that the license plates were degrade
4、d severely.Index Terms - License plate recognition, prior knowledge, vehicle license plates, neural network.I. INTRODUCTIONVehicle License-Plate (VLP) recognition is a very interesting but difficult problem. It is important in a number of applications such as weight-and-speed-limit, red traffic infr
5、ingement, road surveys and park security 1. VLP recognition system consists of the plate location, the characters segmentation, and the characters recognition. These tasks become more sophisticated when dealing with plate images taken in various inclined angles or under various lighting, weather con
6、dition and cleanliness of the plate. Because this problem is usually used in real-time systems, it requires not only accuracy but also fast processing. Most existing VLP recognition methods 2, 3, 4, 5 reduce the complexity and increase the recognition rate by using some specific features of local VL
7、Ps and establishing some constrains on the position, distance from the camera to vehicles, and the inclined angles. In addition, neural network was used to increase the recognition rate 6, 7 but the traditional recognition methods seldom consider the prior knowledge of the local VLPs. In this paper,
8、 we proposed a new improved learning method of BP algorithm based on specific features of Chinese VLPs. The proposed algorithm overcomes the low speed convergence of BP neural network 8 and remarkable increases the recognition rate especially under the condition that the license plate images were de
9、grade severely.II. SPECIFIC FEATURES OF CHINESE VLPSA. DimensionsAccording to the guideline for vehicle inspection 9, all license plates must be rectangular and have the dimensions and have all 7 characters written in a single line. Under practical environments, the distance from the camera to vehic
10、les and the inclined angles are constant, so all characters of the license plate have a fixed width, and the distance between the medium axes of two adjoining characters is fixed and the ratio between width and height is nearly constant. Those features can be used to locate the plate and segment the
11、 individual character.B. Color collocation of the plateThere are four kinds of color collocation for the Chinese vehicle license plate .These color collocations are shown in table I. TABLE ICategory of license plateColor collocationsmall horse power plateblue background and white charactersmotor tru
12、ck plateyellow background and black charactersmilitary vehicle and police wagon plateblack background and the white charactersembassy vehicle platewhite background and black charactersMoreover, military vehicle and police wagon plates contain a red character which belongs to a specific character set
13、. This feature can be used to improve the recognition rate.C. Layout of the Chinese VLPSThe criterion of the vehicle license plate defines the characters layout of Chinese license plate. All standard license plates contain Chinese characters, numbers and letters which are shown in Fig.1. The first o
14、ne is a Chinese character which is an abbreviation of Chinese provinces. The second one is a letter ranging from A to Z except the letter I. The third and fourth ones are letters or numbers. The fifth to seventh ones are numbers ranging from 0 to 9 only. However the first or the seventh ones may be
15、red characters in special plates (as shown in Fig.1). After segmentation process the individual character is extracted. Taking advantage of the layout and color collocation prior knowledge, the individual character will enter one of the classes: abbreviations of Chinese provinces set, letters set, l
16、etters or numbers set, number set, special characters set.辽BA9083Chinese charactercharacterLetterLetter or numberNumber(a)Typical layout辽BB092警Chinese charactercharacterLetterLetter or numberSpecial redcharacter(b) Special characterFig.1 The layout of the Chinese license plateIII. THE PROPOSED ALGOR
17、ITHMThis algorithm consists of four modules: VLP location, character segmentation, character classification and character recognition. The main steps of the flowchart of LPR system are shown in Fig. 2. Firstly the license plate is located in an input image and characters are segmented. Then every in
18、dividual character image enters the classifier to decide which class it belongs to, and finally the BP network decides which character the character image represents.Image acquisitionPlate locationCharacters segmentation segmentationclassifierChinese characterLetterLetter or numberNumberSpecial char
19、acterCharacters recognitionFig.2 The flowchart of LPR systemA. Preprocessing the license plate1) VLP LocationThis process sufficiently utilizes the color feature such as color collocation, color centers and distribution in the plate region, which are described in section II. These color features can
20、 be used to eliminate the disturbance of the fake plates regions. The flowchart of the plate location is shown in Fig. 3.Characters edge detectionBinary image segmentingCandidate image detectionVehicle plate extractionFig.3 The flowchart of the plate location algorithmThe regions which structure and
21、 texture similar to the vehicle plate are extracted. The process is described as followed: (1) (2)Here, the Gaussian variance is set to be less than W/3 (W is the character stroke width), so gets its maximum value M at the center of the stroke. After convolution, binarization is performed according
22、to a threshold which equals T * M (T MaxFFor each character segmentsCalculate the medium point For each two consecutive medium pointsCalculate the distance Calculate the minimum distanceMerge the character segment k and the character segment k +1NF = NF - 1End of algorithm where Nf is the number of
23、character segments, MaxF is the number of the license plate, and i is the index of each character segment.The medium point of each segmented character is determined by: （3）where is the initial coordinates for the character segment, and is the final coordinate for the character segment. The distance
24、between two consecutive medium points is calculated by: （4）Fig.6 The segmentation resultsB. Using specific prior knowledge for recognition The layout of the Chinese VLP is an important feature (as described in the section II), which can be used to construct a classifier for recognizing. The recogniz
25、ing procedure adopted conjugate gradient descent fast learning method, which is an improved learning method of BP neural network10. Conjugate gradient descent, which employs a series of line searches in weight or parameter space. One picks the first descent direction and moves along that direction u
26、ntil the minimum in error is reached. The second descent direction is then computed: this direction the “conjugate direction” is the one along which the gradient does not change its direction will not “spoil” the contribution from the previous descent iterations. This algorithm adopted topology 625-
27、35-N as shown in Fig. 7. The size of input value is 625 (25*25 ) and initial weights are with random values, desired output values have the same feature with the input values.Fig. 7 The network topologyAs Fig. 7 shows, there is a three-layer network which contains working signal feed forward operati
28、on and reverse propagation of error processes. The target parameter is t and the length of network output vectors is n. Sigmoid is the nonlinear transfer function, weights are initialized with random values, and changed in a direction that will reduce the errors.The algorithm was trained with 1000 i
29、mages of different background and illumination most of which were degrade severely. After preprocessing process, the individual characters are stored. All characters used for training and testing have the same size (25*25 ).The integrated process for license plate recognition consists of the followi
30、ng steps:1) Feature extractingThe feature vectors from separated character images have direct effects on the recognition rate. Many methods can be used to extract feature of the image samples, e.g. statistics of data at vertical direction, edge and shape, framework and all pixels values. Based on ex
31、tensive experiments, all pixels values method is used to construct feature vectors. Each character was reshaped into a column of 625 rows feature vector. These feature vectors are divided into two categories which can be used for training process and testing process. 2) Training modelThe layout of t
32、he Chinese VLP is an important feature, which can be used to construct a classifier for training, so five categories are divided. The training process of numbers is shown in Fig. 8.Fig. 8 The architecture of a neural network for character recognitionAs Fig. 8 shows, firstly the classifier decides th
33、e class of the input feature vector, and then the feature vector enters the neural network correspondingly. After the training process the optimum parameters of the net are stored for recognition. The training and testing process is summarized in Fig. 9.Input character vector for recognition 特征向量Neu
34、ral networkTarget outputerror(a) Training processInput character vector for recognition 特征向量Neural networkoutput(b)Testing processFig.9 The recognition process3) Recognizing modelAfter training process there are five nets which were completely trained and the optimum parameters were stored. The untr
35、ained feature vectors are used to test the net, the performance of the recognition system is shown in Table III. The license plate recognition system is characterized by the recognition rate which is defined by equation (5). Recognition rate =(number of correctly read characters)/ (number of found c
36、haracters) (5)TABLE IIIClassRecognitionNumber99.5%Letter97.4%Chinese character96%Number and letter97.3%Special character98.2%IV. COMPARISON OF THE RECOGNITION RATE WITH OTHER METHODSIn order to evaluate the proposed algorithm, two groups of experiments were conducted. One group is to compare the pro
37、posed method with the BP based recognition method 11. The result is shown in table IV. The other group is to compare the proposed method with the method based on SVM 12.The result is shown in table V. The same training and test data set are used. The comparison results show that the proposed method
38、performs better than the BP neural network and SVM counterpart.TABLE IVMethodChinese characterNumberLetterOur method96%99.5%97.4%BP945%97.6%89.8%TABLE VMethodChinese characterNumberLetterOur method96%99.5%97.4%SVM937%99.5%95.7%V. CONCLUSIONIn this paper, we adopt a new improved learning method of BP
39、 algorithm based on specific features of Chinese VLPs. Color collocation and dimension are used in the preprocessing procedure, which makes location and segmentation more accurate. The Layout of the Chinese VLP is an important feature, which is used to construct a classifier for recognizing and make
40、s the system performs well on scratch and inclined plate images. Experimental results show that the proposed method reduces the error rate and consumes less time. However, it still has a few errors when dealing with specially bad quality plates and characters similar to others. This often takes plac
41、e among these characters (especially letter and number):38 4A 8B D0. In order to improve the incorrect recognizing problem we try to add template-based model 13 at the end of the neural network.REFERENCES1 P. Davies, N. Emmottand N. Ayland,“ License Plate Recognition Technology for Toll Violation Enf
