CN114495082B - Weak light compensation new energy license plate recognition system based on LabVIEW - Google Patents
Weak light compensation new energy license plate recognition system based on LabVIEW Download PDFInfo
- Publication number
- CN114495082B CN114495082B CN202210036559.4A CN202210036559A CN114495082B CN 114495082 B CN114495082 B CN 114495082B CN 202210036559 A CN202210036559 A CN 202210036559A CN 114495082 B CN114495082 B CN 114495082B
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- labview
- recognition
- new energy
- 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.)
- Active
Links
- 238000005286 illumination Methods 0.000 claims abstract description 54
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 14
- 230000006698 induction Effects 0.000 claims abstract description 13
- 230000011218 segmentation Effects 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 238000004891 communication Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims 1
- 238000012015 optical character recognition Methods 0.000 abstract 2
- 230000000694 effects Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000033228 biological regulation Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Facsimile Image Signal Circuits (AREA)
- Color Image Communication Systems (AREA)
Abstract
The invention discloses a LabVIEW-based weak illumination compensation new energy license plate recognition system, wherein a hardware part comprises a ground induction coil, a camera, an I2C VEML7700 ambient light sensor, lighting equipment, an Arduino UNO electronic prototype platform and a computer; the software part comprises an illumination automatic compensation module and a license plate recognition processing module. The system can collect the ambient illumination intensity in real time and perform weak illumination compensation by matching with an Arduino lower computer, license plate positioning is realized by applying HSL characteristic color extraction and mathematical morphology, license plate character segmentation is realized based on a threshold method, an optimal threshold value is automatically determined through a global dynamic threshold algorithm, and license plate character recognition is realized through an Optical Character Recognition (OCR) function module. The system can rapidly and accurately realize the identification of the new energy automobile license plate under low ambient light intensity, and can be used in the places such as intelligent traffic management systems, parking lots, new energy automobile charging stations and the like.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic management, and particularly relates to a LabVIEW-based weak illumination compensation new energy license plate recognition system.
Background
With the increasing number of new energy automobiles in China, the demand for intelligent traffic management systems is continuously increasing. The new energy automobile license plate ground color adopts gradual change green, is difficult to directly utilize color characteristics to carry out license plate positioning, is difficult to accurately judge when the vehicle breaks rules and regulations, and divides the responsibility of breaking rules and regulations.
The license plate positioning method based on edge detection realizes license plate positioning by extracting the texture features of the license plate, but for new energy license plates with gradual change green bottoms, the method is easily influenced by green backgrounds around the license plates. The license plate character segmentation is used for segmenting characters from a license plate image through digital image processing. The current license plate character segmentation method is a license plate character segmentation method based on a threshold method, the method realizes license plate character segmentation by setting a reasonable threshold value to carry out image binarization, is suitable for situations with large chromatic aberration between license plate characters and backgrounds, and is difficult to meet the real-time requirement of license plate recognition because the threshold value is manually set. License plate character recognition is the last processing step of license plate recognition, and along with the development of a neural network, a license plate character recognition method based on a convolutional neural network becomes the most commonly used license plate character recognition method, and the recognition accuracy of the method is high, but the algorithm design complexity is high.
Disclosure of Invention
The invention aims to overcome the limitation of new energy automobile license plate recognition, and designs a LabVIEW-based weak illumination compensation new energy automobile license plate recognition system, so that license plate image processing can be accurately and conveniently carried out to realize new energy automobile license plate recognition.
The system of the invention comprises a hardware part and a software part.
The hardware part consists of a ground induction coil, a camera, an I2C VEML7700 ambient light sensor, lighting equipment, an Arduino UNO electronic prototype platform and a computer;
The software part of the system consists of an illumination automatic compensation module and a license plate recognition processing module.
The automatic illumination compensation steps are as follows:
And step 1, an illumination automatic compensation module acquires the ambient illumination intensity in real time through an I2C VEML7700 ambient light sensor, and uploads the ambient illumination intensity data to an Arduino lower computer through I2C communication.
And 2, converting the ambient light intensity data into decimal double-precision data by the Arduino lower computer, and uploading the ambient light intensity data to the LabVIEW upper computer for real-time display through serial port communication.
And 3, when the new energy automobile passes through the ground induction coil, the ground induction coil generates a trigger signal.
Step 4, after receiving a trigger signal generated by the ground induction coil, the LabVIEW upper computer compares the ambient illumination intensity with the minimum illumination intensity allowed by identification:
1) If the ambient illumination intensity is greater than the minimum illumination intensity allowed by recognition, transmitting the license plate image acquired by the camera to a license plate recognition processing module;
2) If the ambient illumination intensity is smaller than the minimum illumination intensity allowed by recognition, the LabVIEW upper computer sends a control signal to the Arduino lower computer to switch on the illumination equipment for illumination compensation, and the license plate image acquired by the camera is transmitted to the license plate recognition processing module.
In the license plate recognition processing module, RGB format license plate images acquired by a camera are converted through space: the license plate images in R (red), G (green) and B (blue) formats in the RGB color space are converted into the HSL color space through HSL positive conversion, namely H (hue), S (saturation) and L (brightness).
And carrying out color analysis on the new energy license plate image under weak illumination intensity to obtain the value range of each component of the new energy license plate characteristic color HSL. And implementing HSL characteristic color extraction by using IMAQ Color Threshold function modules in LabVIEW.
After the HSL characteristic color is extracted, expansion operation and reference adjustment are adopted, so that the boundary of the license plate base color area is expanded, and the optimal standard license plate outline is identified.
And carrying out template matching on the license plate image subjected to mathematical morphology processing by using IMAQ MATCH PATTERN function modules in LabVIEW. The green areas of the non-license plates in the license plate images can be filtered through template matching, and the position information of the license plate areas in the license plate images can be obtained.
And dividing the license plate region from the license plate image according to the position information of the license plate region, so as to realize license plate positioning.
And converting the extracted color plane into a two-dimensional pixel Array by applying IMAQ IMAGE To Array function modules in LabVIEW and multiplying the two-dimensional pixel Array by corresponding weights.
And combining three two-dimensional pixel numbers through IMAQ ARRAY To Image function modules in LabVIEW, and converting the three two-dimensional pixel numbers into a gray Image To realize Image graying.
Image graying algorithm: f=0.299r+0.578g+0.114 b,
F is the gray value of a pixel point in the gray image after the image is gray; r, G and B are values of respective color components of pixel points in the RGB image.
Performing image binarization processing on the license plate image to realize character segmentation:
T is the image binarization optimal threshold value,
Wherein A is the pixel average value of the gray image; c is the pixel variance of the gray scale image; r 1 is the proportion of the total number of the character pixel points; r 2 is the proportion of the total number of non-character pixels.
And setting the gray value of the pixel point with the gray value larger than the threshold value in the license plate gray image to 0, and setting the gray value of other pixel points to 255, so that the license plate image is a black-and-white image with white characters and black matrixes on visual effect.
And selecting a template character set as a matching template of the OCR function module, performing template matching on the license plate image subjected to license plate positioning and license plate character segmentation, and outputting a character template with the highest matching degree as a license plate character recognition result to realize license plate character recognition.
And (3) implementing license plate character recognition by using an OCR function module in the LabVIEW, and displaying a recognition result in a LabVIEW upper computer.
The beneficial effects of the invention are as follows:
the system judges the ambient illumination intensity at the moment of image acquisition to realize weak illumination compensation. In the license plate recognition process, gradual change green-bottom license plate positioning is realized by combining HSL characteristic color extraction and mathematical morphology processing, an optimal threshold value of image binarization processing is automatically determined by adopting a global dynamic threshold algorithm, license plate character segmentation is realized, and license plate character recognition is realized by applying an OCR function module in LabVIEW. The system can rapidly and accurately realize the identification of the new energy automobile license plate under low illumination intensity, and can be used in places such as intelligent traffic management systems, parking lots, new energy automobile charging stations and the like.
Drawings
FIG. 1 is a block diagram of a system of the present invention;
FIG. 2 is a LabVIEW program diagram of the automatic illumination compensation module of the system;
FIG. 3 is a sample of a license plate of a new energy automobile provided by an embodiment of the invention;
FIG. 4 is a graph of HSL feature color extraction effects implemented in an embodiment of the present invention;
FIG. 5 is a program diagram of a license plate positioning LabVIEW of the system of the invention;
FIG. 6 is a diagram of license plate positioning effect achieved by the embodiment of the invention;
FIG. 7 is a system image greyscale LabVIEW program diagram according to an embodiment of the present invention;
FIG. 8 is a system threshold algorithm LabVIEW program diagram according to an embodiment of the present invention;
Fig. 9 is a license plate recognition effect diagram according to an embodiment of the present invention.
Detailed Description
The following describes the embodiments of the present invention further with reference to the drawings.
The system of the invention comprises a hardware part and a software part.
The hardware part consists of a ground induction coil, a camera, an I2C VEML7700 ambient light sensor, lighting equipment, an Arduino UNO electronic prototype platform and a computer, and is specifically shown in figure 1;
The software part of the system consists of an illumination automatic compensation module and a license plate recognition processing module.
The automatic illumination compensation steps are as follows:
Step 1, an illumination automatic compensation module collects ambient illumination intensity in real time through an I2C VEML7700 ambient light sensor, and uploads ambient illumination intensity data to an Arduino lower computer through I2C communication, and a LabVIEW program diagram of the system illumination automatic compensation module is shown in fig. 2.
And 2, converting the ambient light intensity data into decimal double-precision data by the Arduino lower computer, and uploading the ambient light intensity data to the LabVIEW upper computer for real-time display through serial port communication.
And 3, when the new energy automobile (see the license plate shown in fig. 3) passes through the ground induction coil, the ground induction coil generates a trigger signal.
Step 4, after receiving a trigger signal generated by the ground induction coil, the LabVIEW upper computer compares the ambient illumination intensity with the minimum illumination intensity allowed by identification:
1) If the ambient illumination intensity is greater than the minimum illumination intensity allowed by recognition, transmitting the license plate image acquired by the camera to a license plate recognition processing module;
2) If the ambient illumination intensity is smaller than the minimum illumination intensity allowed by recognition, the LabVIEW upper computer sends a control signal to the Arduino lower computer to switch on the illumination equipment for illumination compensation, and the license plate image acquired by the camera is transmitted to the license plate recognition processing module.
In the license plate recognition processing module, RGB format license plate images acquired by a camera are converted through space: the license plate images in R (red), G (green) and B (blue) formats in the RGB color space are converted into the HSL color space through HSL positive conversion, namely H (hue), S (saturation) and L (brightness).
And carrying out color analysis on the new energy license plate image under weak illumination intensity to obtain the value range of each component of the new energy license plate characteristic color HSL. And extracting the HSL characteristic color by applying IMAQ Color Threshold function modules in LabVIEW, wherein the extraction effect is shown in figure 4.
After the HSL characteristic color is extracted, expansion operation and reference adjustment are adopted, so that the boundary of the license plate base color area is expanded, and the optimal standard license plate outline is identified.
And carrying out template matching on the license plate image subjected to mathematical morphology processing by using IMAQ MATCH PATTERN function modules in LabVIEW. The green areas of non-license plates in the license plate images can be filtered through template matching, and the position information of the license plate areas in the license plate images is obtained, and the positioning program is shown in fig. 5.
According to the position information of the license plate region, the license plate region is segmented from the license plate image, so that license plate positioning is realized, and the effect is shown in fig. 6.
And converting the extracted color plane into a two-dimensional pixel Array by applying IMAQ IMAGE To Array function modules in LabVIEW and multiplying the two-dimensional pixel Array by corresponding weights.
And combining three two-dimensional pixel numbers through IMAQ ARRAY To Image function modules in LabVIEW, and converting the three two-dimensional pixel numbers into a gray Image To realize Image graying.
Image graying algorithm: f=0.299r+0.578g+0.114 b,
F is the gray value of a pixel point in the gray image after the image is gray; r, G and B are values of respective color components of pixel points in the RGB image. The gray scale processing procedure is shown in fig. 7.
Performing image binarization processing on the license plate image to realize character segmentation:
T is the image binarization optimal threshold value,
Wherein A is the pixel average value of the gray image; c is the pixel variance of the gray scale image; r 1 is the proportion of the total number of the character pixel points; r 2 is the proportion of the total number of non-character pixels, and the threshold processing procedure is shown in fig. 8.
And setting the gray value of the pixel point with the gray value larger than the threshold value in the license plate gray image to 0, and setting the gray value of other pixel points to 255, so that the license plate image is a black-and-white image with white characters and black matrixes on visual effect.
And selecting a template character set as a matching template of the OCR function module, performing template matching on the license plate image subjected to license plate positioning and license plate character segmentation, and outputting a character template with the highest matching degree as a license plate character recognition result to realize license plate character recognition.
And (3) implementing license plate character recognition by using an OCR function module in the LabVIEW, and displaying a recognition result in a LabVIEW upper computer, wherein the figure 9 is shown.
The foregoing description of the preferred embodiments of the present invention has been presented only in terms of those specific and detailed descriptions, and is not, therefore, to be construed as limiting the scope of the invention. It should be noted that modifications, improvements and substitutions can be made by those skilled in the art without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (1)
1. The LabVIEW-based weak illumination compensation new energy license plate recognition system is characterized by comprising a hardware part and a software part; the hardware part consists of a ground induction coil, a camera, an I2C VEML7700 ambient light sensor, lighting equipment, an Arduino UNO electronic prototype platform and a computer; the software part consists of an illumination automatic compensation module and a license plate recognition processing module;
The automatic illumination compensation steps are as follows:
The method comprises the steps that 1, an illumination automatic compensation module collects ambient illumination intensity in real time through an I2C VEML7700 ambient light sensor, and uploads ambient illumination intensity data to an Arduino lower computer through I2C communication;
Step 2, converting the ambient light intensity data into decimal double-precision data by the Arduino lower computer, and uploading the ambient light intensity data to the LabVIEW upper computer for real-time display through serial port communication;
step 3, when the new energy automobile passes through the ground induction coil, the ground induction coil generates a trigger signal;
step 4, after receiving a trigger signal generated by the ground induction coil, the LabVIEW upper computer compares the ambient illumination intensity with the minimum illumination intensity allowed by identification:
1) If the ambient illumination intensity is greater than the minimum illumination intensity allowed by recognition, transmitting the license plate image acquired by the camera to a license plate recognition processing module;
2) If the ambient illumination intensity is smaller than the minimum illumination intensity allowed by recognition, the LabVIEW upper computer sends a control signal to the Arduino lower computer to switch on the illumination equipment for illumination compensation, and the license plate image acquired by the camera is transmitted to the license plate recognition processing module;
In the license plate recognition processing module, RGB format license plate images acquired by a camera are converted through space: converting the license plate images in R (red), G (green) and B (blue) formats in the RGB color space into an HSL color space through HSL positive conversion, namely H (hue), S (saturation) and L (brightness);
performing color analysis on the new energy license plate image under weak illumination intensity to obtain the value range of each component of the new energy license plate characteristic color HSL; implementing HSL characteristic color extraction by using IMAQ Color Threshold function modules in LabVIEW;
After the HSL characteristic color is extracted, expansion operation and reference adjustment are adopted, so that the boundary of the license plate base color area is expanded, and the optimal standard license plate outline is marked;
carrying out template matching on the license plate image subjected to mathematical morphology processing by applying IMAQ MATCH PATTERN function modules in LabVIEW; filtering a green area of a non-license plate in the license plate image through template matching, and obtaining position information of the license plate area in the license plate image;
Dividing the license plate region from the license plate image according to the position information of the license plate region, so as to realize license plate positioning;
Converting the extracted color plane into a two-dimensional pixel Array by using IMAQ IMAGE To Array function modules in LabVIEW and multiplying the two-dimensional pixel Array by corresponding weights;
The three two-dimensional pixel numbers are combined and converted into a gray Image through IMAQ ARRAY To Image function modules in LabVIEW, so that Image graying is realized;
image graying algorithm: f=0.299r+0.578g+0.114 b,
F is the gray value of a pixel point in the gray image after the image is gray; r, G and B are values of each color component of the pixel point in the RGB image;
performing image binarization processing on the license plate image to realize character segmentation:
T is the image binarization optimal threshold value,
Wherein A is the pixel average value of the gray image; c is the pixel variance of the gray scale image; r 1 is the proportion of the total number of the character pixel points; r 2 is the proportion of the total number of non-character pixel points;
Setting the gray value of the pixel point with the gray value larger than the threshold value in the license plate gray image to be 0, and setting the gray value of other pixel points to be 255, so that the license plate image is presented as a black-and-white image with white characters and black matrixes on the visual effect;
selecting a template character set as a matching template of the OCR function module, performing template matching on the license plate image subjected to license plate positioning and license plate character segmentation, and outputting a character template with the highest matching degree as a license plate character recognition result to realize license plate character recognition;
And (3) implementing license plate character recognition by using an OCR function module in the LabVIEW, and displaying a recognition result in a LabVIEW upper computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210036559.4A CN114495082B (en) | 2022-01-13 | 2022-01-13 | Weak light compensation new energy license plate recognition system based on LabVIEW |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210036559.4A CN114495082B (en) | 2022-01-13 | 2022-01-13 | Weak light compensation new energy license plate recognition system based on LabVIEW |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114495082A CN114495082A (en) | 2022-05-13 |
| CN114495082B true CN114495082B (en) | 2024-05-03 |
Family
ID=81511958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210036559.4A Active CN114495082B (en) | 2022-01-13 | 2022-01-13 | Weak light compensation new energy license plate recognition system based on LabVIEW |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114495082B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118097650A (en) * | 2024-04-22 | 2024-05-28 | 民航成都电子技术有限责任公司 | Airport crossing license plate recognition method, device, medium and electronic equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358795A (en) * | 2017-07-17 | 2017-11-17 | 陈剑桃 | A kind of effective Vehicle License Plate Recognition System |
| WO2020130799A1 (en) * | 2018-12-21 | 2020-06-25 | Mimos Berhad | A system and method for licence plate detection |
-
2022
- 2022-01-13 CN CN202210036559.4A patent/CN114495082B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358795A (en) * | 2017-07-17 | 2017-11-17 | 陈剑桃 | A kind of effective Vehicle License Plate Recognition System |
| WO2020130799A1 (en) * | 2018-12-21 | 2020-06-25 | Mimos Berhad | A system and method for licence plate detection |
Non-Patent Citations (2)
| Title |
|---|
| 一种基于相似度的汽车车牌号码自动识别系统;郑宇, 肖南峰;交通与计算机;20041030(05);全文 * |
| 基于LabVIEW图像法车牌智能识别系统;王党树;王新霞;;计算机测量与控制;20150825(08);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114495082A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108108761B (en) | Rapid traffic signal lamp detection method based on deep feature learning | |
| CN104715239B (en) | A kind of vehicle color identification method based on defogging processing and weight piecemeal | |
| CN108364010B (en) | License plate recognition method, device, equipment and computer readable storage medium | |
| CN106651872B (en) | Pavement crack identification method and system based on Prewitt operator | |
| CN110648307A (en) | Method for checking state of transformer substation pressure plate by using image comparison technology | |
| CN112149543B (en) | Building dust recognition system and method based on computer vision | |
| CN109584258B (en) | Grassland boundary identification method and intelligent mowing device applying same | |
| CN106919910B (en) | Traffic sign identification method based on HOG-CTH combined features | |
| CN103761529A (en) | Open fire detection method and system based on multicolor models and rectangular features | |
| CN104408424A (en) | Multiple signal lamp recognition method based on image processing | |
| CN114495082B (en) | Weak light compensation new energy license plate recognition system based on LabVIEW | |
| Wonghabut et al. | Traffic light color identification for automatic traffic light violation detection system | |
| JP2007164737A (en) | Color-identifying method | |
| CN114926661B (en) | Textile surface color data processing and identifying method and system | |
| CN110610485A (en) | Ultra-high voltage transmission line channel hidden danger early warning method based on SSIM algorithm | |
| CN106558044B (en) | Method for measuring resolution of image module | |
| CN112348018A (en) | Digital display type instrument reading identification method based on inspection robot | |
| CN111401364A (en) | License plate positioning algorithm based on combination of color features and template matching | |
| CN113989771A (en) | Traffic signal lamp identification method based on digital image processing | |
| CN107977959B (en) | Respirator state identification method suitable for electric power robot | |
| CN111612797B (en) | Rice image information processing system | |
| CN111260603B (en) | Method and device for identifying blade tips of wind generating set | |
| CN114821078B (en) | License plate recognition method and device, electronic equipment and storage medium | |
| KR102118783B1 (en) | Preprocessing method for color filtering robust against illumination environment and the system thereof | |
| CN105184296A (en) | Image processing method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |