CN111627218A - Method for recognizing license plate at night through image enhancement - Google Patents
Method for recognizing license plate at night through image enhancement Download PDFInfo
- Publication number
- CN111627218A CN111627218A CN202010488288.7A CN202010488288A CN111627218A CN 111627218 A CN111627218 A CN 111627218A CN 202010488288 A CN202010488288 A CN 202010488288A CN 111627218 A CN111627218 A CN 111627218A
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- night
- image enhancement
- steps
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000001914 filtration Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Character Input (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of image processing, in particular to a method for recognizing license plates at night through image enhancement. According to the character recognition method, the character recognition effect is enhanced through image enhancement and filtering, and meanwhile, the recognition accuracy is improved through a multi-sheet comparison mode.
Description
Technical Field
The invention relates to the field of image processing, in particular to a method for recognizing a license plate at night through image enhancement.
Background
At present, roads are generally provided with a plurality of cameras, and the cameras can help traffic polices to measure speed and play a great role in handling cases or tracking vehicles.
However, at present, direct photographing is adopted mostly, and then the license plate is identified manually, which wastes time and labor and can cause the situation of identification error. And simply directly adopt machine discernment, on the one hand machine discernment characters are not too high to the license plate image accuracy rate that the camera was shone out at present, and on the other hand to the not high condition of contrast at night, the degree of difficulty of machine discernment promotes a lot again.
Disclosure of Invention
The invention aims to: in order to solve the problems, the invention provides a method for recognizing a license plate at night through image enhancement.
Some embodiments of the invention are implemented as follows:
a method for night license plate recognition through image enhancement comprises the following steps:
s01: collecting a plurality of automobile license plate number images through a camera, and transmitting all the collected automobile license plate number images back to a server;
s02: the server splits each license plate number image into RGB (red, green and blue) three-color maps, and combines the RGB three-color maps after histogram normalization to obtain a corrected image;
s03: sharpening the corrected image to obtain a sharpened image;
s04: putting the sharpened image into a convolutional neural network for number and letter identification to obtain the probability of each letter on the originally acquired automobile license plate number image;
s05: and comparing the probabilities obtained by processing a plurality of different acquired automobile license plate number images to obtain the final license plate number, and recording the final license plate number into the system.
In one embodiment of the invention:
the photographing device in the step S01 is arranged beside the road, and a plurality of photographing lenses are arranged on the photographing device and face different angles;
in one embodiment of the invention:
any photographing lens is provided with a flash lamp device.
In one embodiment of the invention:
by controlling the switch of the flash lamp device, the photographing lenses at different angles respectively collect a plurality of automobile license plate images with flash and automobile license plate images without flash at respective angles.
Some embodiments of the invention are implemented as follows:
in step S03, the corrected image is also subjected to noise reduction by noise reduction filtering before sharpening.
Some embodiments of the invention are implemented as follows:
in step S05, the first word is set to be one of the province abbreviation and the special mark, and the second word is set to be one of the alphabet.
Some embodiments of the invention are implemented as follows:
the photographing device is also provided with a speed measuring device.
The technical scheme of the invention at least has the following beneficial effects:
the contrast is greatly improved by carrying out image enhancement on a plurality of automobile license plate images, and meanwhile, because the histogram is specified, the transformation function can be defined by self, so that different functions can be selected according to the photographing time to adapt to the contrast. When the contrast is greatly increased, the subsequent image processing is facilitated.
The probability of each letter can be obtained by sharpening and then performing character recognition through a convolutional neural network, but because the probability of wrong recognition or unrecognized character can occur, the probability of the final generation is obtained by comparing the probabilities of each picture in the form of multiple pictures at different angles, and the highest probability in the final probabilities is taken as the recognition result.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart illustrating a method for night license plate recognition through image enhancement according to some embodiments of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
It should be understood that "system", "device", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.
Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
Fig. 1 illustrates a method for night license plate recognition through image enhancement according to some embodiments of the present disclosure.
The images are collected by the camera 111 and then transmitted to the server 112 for image processing and then to the recording system 113.
The collected images are obtained by continuously shooting vehicles coming and going on the road through a camera and transmitting the shot images to a server.
The camera may be a variety of cameras.
The information transmission can adopt a wired network, a mobile network and the like.
The server comprises a Central Processing Unit (CPU) serving as a control core, a Graphics Processing Unit (GPU) used for neural network operation, a hard disk used for storing information, a memory used for operating space, a network transceiver (network card) and the like, and is responsible for image correction and enhancement and character recognition operation in image processing.
A method for night license plate recognition through image enhancement comprises the following steps:
s01: a plurality of automobile license plate number images are collected through the photographing device, and all the collected automobile license plate number images are transmitted back to the server.
Furthermore, the photographing device is arranged beside the road, a plurality of photographing lenses are arranged on the photographing device, and the plurality of photographing lenses face different angles. Any photographing lens is provided with a flash lamp device. By controlling the switch of the flash lamp device, the photographing lenses at different angles respectively collect a plurality of automobile license plate images with flash and automobile license plate images without flash at respective angles.
S02: the server splits each license plate number image into RGB (red, green and blue) three-color maps, and combines the RGB three-color maps after histogram normalization to obtain a corrected image;
the traditional jpg format image can be decomposed into R, G, B three-color matrix through RGB color space, each element in the matrix is the point which is located at the pixel, the image is decomposed, then the histogram specification is carried out on each image, the frequency is relatively averaged, the contrast of the image is changed, the contrast of the image is not changed into one color on the boundary like linear histogram correction, the image is distorted, and the new image is merged back through the matrix after the transformation, so that the contrast adjustment is completed.
S03: and sharpening the corrected image to obtain a sharpened image.
The image enhancement is performed by a sharpening operation, wherein the sharpening operation includes sharpening by high-pass filtering, i.e., a low-pass filtering operation, which can effectively suppress high-frequency components, and random noise is a sudden change with a high frequency, so that smoothing can suppress noise.
Further, before sharpening, the corrected image is denoised through denoising filtering, wherein the denoising filtering comprises an algorithm based on a spatial domain and an algorithm based on a frequency domain, the spatial domain filtering specifically comprises Gaussian filtering, median filtering and mean shift filtering, and the core point of the spatial domain filtering is image convolution operation. The two-frequency domain filtering adopts mathematical operation to transform the image from a space domain to a frequency domain, and the two-frequency domain filtering carries out filtering operation on the frequency spectrum of the image and then carries out inverse transformation back to the space domain, and specifically comprises Fourier transformation, discrete cosine transformation, wavelet transformation and the like.
S04: and (4) putting the sharpened image into a convolutional neural network for number and letter identification to obtain the probability of each letter on the originally acquired automobile license plate number image.
When the environment and procedure are verified to be error free, analysis of the image by the convolutional neural network can begin.
Splitting the image through a color space, carrying out region segmentation on each split image according to a position sequence, then carrying out feature extraction on each region, and sequentially arranging the extracted feature values to form a feature map; performing inner product operation on the convolution kernel and the characteristic graph and adding the inner product operation and the offset to obtain an area characteristic value, and then gradually operating all the characteristic values of the characteristic graph through sliding steps and splicing the characteristic values into an area characteristic graph so as to obtain a convolution layer; carrying out primary nonlinear mapping on the obtained convolutional layer through an activation function, and then pooling, thereby compressing data to obtain a pooling layer; and after the steps are sequentially circulated, compressing the characteristic diagram into an at least three-dimensional characteristic diagram, then elongating the characteristic diagram to obtain a characteristic vector, and performing full-connection operation on the characteristic vector to obtain a probability result.
S05: and comparing the probabilities obtained by processing a plurality of different acquired automobile license plate number images to obtain the final license plate number, and recording the final license plate number into the system.
After each shot automobile license plate number image is subjected to the operation, a feature vector, namely a classification, is finally obtained, the classifications of different images are compared, relatively overlapped parts are selected, and a final result is finally obtained, so that character recognition is completed.
The application has at least the following beneficial effects:
the contrast is greatly improved by carrying out image enhancement on a plurality of automobile license plate images, and meanwhile, because the histogram is specified, the transformation function can be defined by self, so that different functions can be selected according to the photographing time to adapt to the contrast. When the contrast is greatly increased, the subsequent image processing is facilitated.
The probability of each letter can be obtained by sharpening and then performing character recognition through a convolutional neural network, but because the probability of wrong recognition or unrecognized character can occur, the probability of the final generation is obtained by comparing the probabilities of each picture in the form of multiple pictures at different angles, and the highest probability in the final probabilities is taken as the recognition result.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.
Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present description may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereof. Accordingly, aspects of this description may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present description may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
Claims (7)
1. A method for recognizing a license plate at night through image enhancement is characterized by comprising the following steps:
s01: collecting a plurality of automobile license plate number images through a camera, and transmitting all the collected automobile license plate number images back to a server;
s02: the server splits each license plate number image into RGB (red, green and blue) three-color maps, and combines the RGB three-color maps after histogram normalization to obtain a corrected image;
s03: sharpening the corrected image to obtain a sharpened image;
s04: putting the sharpened image into a convolutional neural network for number and letter identification to obtain the probability of each letter on the originally acquired automobile license plate number image;
s05: and comparing the probabilities obtained by processing a plurality of different acquired automobile license plate number images to obtain the final license plate number, and recording the final license plate number into the system.
2. The method of claim 1, wherein the image enhancement is used for night license plate recognition, and the method comprises the following steps: the photographing device in the step S01 is disposed beside the road, and a plurality of photographing lenses are disposed on the photographing device, and face different angles.
3. The method of claim 2, wherein the image enhancement is used for night license plate recognition, and the method comprises the following steps: any photographing lens is provided with a flash lamp device.
4. The method of claim 3, wherein the image enhancement is used for night license plate recognition, and the method comprises the following steps: by controlling the switch of the flash lamp device, the photographing lenses at different angles respectively collect a plurality of automobile license plate images with flash and automobile license plate images without flash at respective angles.
5. The method of claim 1, wherein the image enhancement is used for night license plate recognition, and the method comprises the following steps: in step S03, the corrected image is also subjected to noise reduction by noise reduction filtering before sharpening.
6. The method of claim 1, wherein the image enhancement is used for night license plate recognition, and the method comprises the following steps: in step S05, the first word is set to be one of the province abbreviation and the special mark, and the second word is set to be one of the alphabet.
7. The method of claim 1, wherein the image enhancement is used for night license plate recognition, and the method comprises the following steps: the photographing device is also provided with a speed measuring device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010488288.7A CN111627218A (en) | 2020-06-02 | 2020-06-02 | Method for recognizing license plate at night through image enhancement |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010488288.7A CN111627218A (en) | 2020-06-02 | 2020-06-02 | Method for recognizing license plate at night through image enhancement |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111627218A true CN111627218A (en) | 2020-09-04 |
Family
ID=72272631
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010488288.7A Pending CN111627218A (en) | 2020-06-02 | 2020-06-02 | Method for recognizing license plate at night through image enhancement |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111627218A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101877050A (en) * | 2009-11-10 | 2010-11-03 | 青岛海信网络科技股份有限公司 | Automatic extracting method for characters on license plate |
CN106408950A (en) * | 2016-11-18 | 2017-02-15 | 北京停简单信息技术有限公司 | Parking lot entrance and exit license plate recognition system and method |
CN106909923A (en) * | 2017-02-20 | 2017-06-30 | 汪爱民 | A kind of vehicles peccancy processing system |
US20190066492A1 (en) * | 2017-08-22 | 2019-02-28 | Jos A. G. Nijhuis | License Plate Recognition |
CN110298278A (en) * | 2019-06-19 | 2019-10-01 | 中国计量大学 | A kind of underground parking garage Pedestrians and vehicles monitoring method based on artificial intelligence |
CN111079764A (en) * | 2019-12-06 | 2020-04-28 | 深圳久凌软件技术有限公司 | Low-illumination license plate image recognition method and device based on deep learning |
-
2020
- 2020-06-02 CN CN202010488288.7A patent/CN111627218A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101877050A (en) * | 2009-11-10 | 2010-11-03 | 青岛海信网络科技股份有限公司 | Automatic extracting method for characters on license plate |
CN106408950A (en) * | 2016-11-18 | 2017-02-15 | 北京停简单信息技术有限公司 | Parking lot entrance and exit license plate recognition system and method |
CN106909923A (en) * | 2017-02-20 | 2017-06-30 | 汪爱民 | A kind of vehicles peccancy processing system |
US20190066492A1 (en) * | 2017-08-22 | 2019-02-28 | Jos A. G. Nijhuis | License Plate Recognition |
CN110298278A (en) * | 2019-06-19 | 2019-10-01 | 中国计量大学 | A kind of underground parking garage Pedestrians and vehicles monitoring method based on artificial intelligence |
CN111079764A (en) * | 2019-12-06 | 2020-04-28 | 深圳久凌软件技术有限公司 | Low-illumination license plate image recognition method and device based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111709883B (en) | Image detection method, device and equipment | |
CN112686812B (en) | Bank card inclination correction detection method and device, readable storage medium and terminal | |
CN109492642B (en) | License plate recognition method, license plate recognition device, computer equipment and storage medium | |
CN108197644A (en) | A kind of image-recognizing method and device | |
CN110378254B (en) | Method and system for identifying vehicle damage image modification trace, electronic device and storage medium | |
CN112380978B (en) | Multi-face detection method, system and storage medium based on key point positioning | |
CN113657528B (en) | Image feature point extraction method and device, computer terminal and storage medium | |
CN117218029B (en) | Night dim light image intelligent processing method based on neural network | |
CN114140346A (en) | Image processing method and device | |
CN112101205A (en) | Training method and device based on multi-task network | |
CN111031241B (en) | Image processing method and device, terminal and computer readable storage medium | |
Elsharkawy et al. | New and efficient blind detection algorithm for digital image forgery using homomorphic image processing | |
WO2022199395A1 (en) | Facial liveness detection method, terminal device and computer-readable storage medium | |
CN114170565A (en) | Image comparison method and device based on unmanned aerial vehicle aerial photography and terminal equipment | |
CN111723805A (en) | Signal lamp foreground area identification method and related device | |
CN111627218A (en) | Method for recognizing license plate at night through image enhancement | |
Dhar et al. | Interval type-2 fuzzy set and human vision based multi-scale geometric analysis for text-graphics segmentation | |
CN110633705A (en) | Low-illumination imaging license plate recognition method and device | |
CN109241865B (en) | Vehicle detection segmentation algorithm under weak contrast traffic scene | |
Tahaoglu et al. | Robust copy-move forgery detection technique against image degradation and geometric distortion attacks | |
CN113111883B (en) | License plate detection method, electronic device and storage medium | |
CN116152079A (en) | Image processing method and image processing model training method | |
CN112669346B (en) | Pavement emergency determination method and device | |
CN115423765A (en) | Grain defect quantitative segmentation method based on template image | |
CN110796684B (en) | Target tracking method and related device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200904 |