CN107123093A - A kind of processing method and processing device of vehicle image - Google Patents
A kind of processing method and processing device of vehicle image Download PDFInfo
- Publication number
- CN107123093A CN107123093A CN201611117133.2A CN201611117133A CN107123093A CN 107123093 A CN107123093 A CN 107123093A CN 201611117133 A CN201611117133 A CN 201611117133A CN 107123093 A CN107123093 A CN 107123093A
- Authority
- CN
- China
- Prior art keywords
- image
- brightness
- tomographic
- vehicle
- tomographic image
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- 238000006243 chemical reaction Methods 0.000 claims abstract description 24
- 230000004048 modification Effects 0.000 claims description 6
- 238000012986 modification Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 abstract description 9
- 230000008859 change Effects 0.000 description 6
- 239000003086 colorant Substances 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000004438 eyesight Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30236—Traffic on road, railway or crossing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention provides a kind of processing method and processing device of vehicle image, is related to the image processing techniques during railway automation management, wherein the treating method comprises following steps:The first image of a HLS color spaces is converted into the source vehicle image got;The brightness value of brightness tomographic image where changing described first image is a preset value, generates the second image of a HLS color spaces;Second image is changed into the 3rd image of a rgb color space;Binary conversion treatment is carried out to the 3rd image and obtains an intermediate image, and identify the character information in the intermediate image, the invention provides the processing unit of a correspondence processing method, in a word, the present invention can dexterously overcome prior art due to sunlight shade causes to block to source vehicle image and the problem of correctly can not identifying character information therein.
Description
Technical field
The present invention relates to the image processing techniques during railway automation management, more particularly to a kind of vehicle image
Processing method and processing device.
Background technology
In current railway administration, it is related to and the train by website is taken pictures to obtain the vehicle figure in often section compartment
Picture, then identifies the character in the vehicle image using software, so as to realize to the automatic identification and pipe by train information
The purpose of reason.
But find in actual applications, occur the character on accessed vehicle image by it in some environments
The situation that its barrier is blocked, for example the shadow of other foreign objects can be projected on the character in the sun, such as Fig. 1, so that
When processing is identified to the image, it is impossible to the correct character identified thereon.See Fig. 2, give different vehicle image and entering
Design sketch after row binary conversion treatment, as illustrated, image 1 is the vehicle image to not blocked by the shade of other objects
Carry out the design sketch after binary conversion treatment, it can be seen that correct license number letter can be clearly showed that out on the image 1 after processing
Breath;On the contrary, image 2 is to there is the vehicle image that the shade by other objects is blocked to carry out the design sketch after binary conversion treatment,
It can be seen that, clearly complete it can not show correct vehicle number information on the image 2 after processing.
Based on above-mentioned situation, how to overcome in vehicle image because extraneous shade causes what vehicle number information can not be recognized correctly
Situation, is the problem of current those skilled in the art need solution.
The content of the invention
The shortcoming of prior art in view of the above, it is an object of the invention to provide a kind of processing method of vehicle image
And device, for solving in existing vehicle image because extraneous shade causes the problem of vehicle number information can not be recognized correctly.
In order to achieve the above objects and other related objects, the present invention provides following technical scheme:
A kind of processing method of vehicle image, comprises the following steps:One HLS is converted into the source vehicle image got
First image of color space;The brightness value of brightness tomographic image where changing described first image is a preset value, generates HLS colors
One second image of color space;Second image is changed into one the 3rd image of rgb color space;3rd image is entered
Row binary conversion treatment obtains an intermediate image, and identifies the character information in the intermediate image.
In a preferred embodiment, the brightness value of brightness tomographic image is preset for one where the modification described first image
Value, the second image of one HLS color spaces of generation includes:By described first image layering obtain brightness tomographic image therein,
One form and aspect tomographic image and a saturation degree tomographic image;The brightness value for changing the brightness tomographic image is revised as a preset value, obtains one
New brightness tomographic image;The new brightness tomographic image is recombined with the form and aspect tomographic image and the saturation degree tomographic image
One second image of HLS color spaces.
In a preferred embodiment, the source vehicle image is the image of following any color space:RGB, HLS and
HSV。
In a preferred embodiment, the preset value is 60-150.
In a preferred embodiment, the preset value is 100-130.
In addition present invention also offers a kind of processing unit of vehicle image, including:First image conversion module, for pair
The source vehicle image got is converted into one first image of HLS color spaces;Second image conversion module, for changing
The brightness value of brightness tomographic image where stating the first image is a preset value, generates one second image of HLS color spaces;3rd figure
As modular converter, one the 3rd image for second image to be changed into rgb color space;Image recognition processing module, is used
An intermediate image is obtained in carrying out binary conversion treatment to the 3rd image, and identifies that the character in the intermediate image is believed
Breath.
In a preferred embodiment, second image conversion module includes:Image layered unit, for by described
One image layered obtains brightness tomographic image therein, a form and aspect tomographic image and a saturation degree tomographic image;Unit is changed in brightness, is used
A preset value is revised as in the brightness value for changing the brightness tomographic image, a new brightness tomographic image is obtained;Image composing unit,
The new brightness tomographic image and the form and aspect tomographic image and the saturation degree tomographic image are recombined into a HLS color spaces
Second image.
In a preferred embodiment, the source vehicle image is the image of following any color space:RGB, HLS and
HSV。
In a preferred embodiment, the preset value is 60-150.
In a preferred embodiment, the preset value is 100-130.
As described above, the invention has the advantages that:The present invention is converted to HLS figures by using color space
Picture, then changes the brightness value of wherein brightness layer, a new HLS images is regenerated with this, finally again by the new HLS images
RGB image is converted into, and then correctly identifies character information therein, prior art is cleverly overcome due to sunlight shade pair
The problem of source vehicle image causes to block and correctly can not identify character information therein.
Brief description of the drawings
Fig. 1 is shown as the source vehicle image for having sunlight shadow occlusion in the prior art.
Fig. 2 is shown as design sketch in the prior art to different vehicle image after binary conversion treatment is carried out.
A kind of flow chart of the processing method for vehicle image that Fig. 3 provides for the present invention.
Fig. 4 is the acquisition flow chart of the second image in the present invention.
A kind of schematic diagram of the processing unit for vehicle image that Fig. 5 provides for the present invention.
Fig. 6 is the structured flowchart of the second image conversion module in Fig. 5.
Drawing reference numeral explanation
100 processing units
110 first image conversion modules
120 second image conversion modules
121 image layered units
Unit is changed in 122 brightness
123 image composing units
130 the 3rd image conversion modules
140 image recognition processing modules
S1~S4 steps
Embodiment
Illustrate embodiments of the present invention below by way of specific instantiation, those skilled in the art can be by this specification
Disclosed content understands other advantages and effect of the present invention easily.The present invention can also pass through specific realities different in addition
The mode of applying is embodied or practiced, the various details in this specification can also based on different viewpoints with application, without departing from
Various modifications or alterations are carried out under the spirit of the present invention.It should be noted that, in the case where not conflicting, following examples and implementation
Feature in example can be mutually combined.
It should be noted that the diagram provided in following examples only illustrates the basic structure of the present invention in a schematic way
Think, then in schema only display with relevant component in the present invention rather than according to component count, shape and the size during actual implement
Draw, it is actual when implementing, and kenel, quantity and the ratio of each component can be a kind of random change, and its assembly layout kenel
It is likely more complexity.
Name Resolution:
HLS color spaces, i.e. HLS color modes, wherein, HLS is Hue colourities, Lightness brightness, Saturation
The abbreviation of saturation degree, HLS color spaces are a kind of color standards of industrial quarters, are by tone (H), saturation degree (S), brightness
(L) change of three Color Channels and their superpositions each other obtain miscellaneous color, and HSL is to represent
Tone, saturation degree, the color of three passages of brightness, this standard almost includes all colours that human eyesight can perceive,
It is at present with one of most wide color system.
Rgb color space, i.e. rgb color pattern, it is a kind of color standard of industrial quarters, is by red (R), green
(G), the change of blue (B) three Color Channels and their superpositions each other obtain miscellaneous color, and RGB is
It is the color for representing three passages of red, green, blue, this standard almost includes all colours that human eyesight can perceive, is
At present with one of most wide color system.
HSV color spaces, i.e. HSV colour models, HSV identify Hue, Saturation, Value respectively, and it is according to face
The intuitive nature of color.
Embodiment 1
See Fig. 3, present embodiments provide a kind of processing method of vehicle image, step is realized to the processing method below
It is described in detail.
Step S1, the first image of a HLS color spaces is converted into the source vehicle image got.
Wherein, the source vehicle image refers to obtain the train image that equipment is photographed by image scene, specifically, should
Source vehicle image can be the image of a rgb color space or be the image of a HSV color spaces, can also be HLS colors
The image in space.
S2, the brightness value of brightness tomographic image is a preset value where modification described first image, generates a HLS color spaces
The second image.
In step s 2, repaiied by the brightness value to brightness tomographic image where the first image for HLS color spaces
Change, the image of a HLS color spaces, i.e. the second image are regenerated with this, basis is provided for subsequent step processing.
Specifically, Fig. 4 is seen, the second image can be obtained by following process step:
S21, brightness tomographic image therein, a form and aspect tomographic image and saturation degree layer are obtained by described first image layering
Image.
Wherein, it is here to obtain brightness tomographic image to the purpose that the first image is layered, and the form and aspect gone out with layered
Tomographic image and saturation degree tomographic image are then to provide basis to subsequently regenerate the image of a new HLS color spaces.
S22, the brightness value for changing the brightness tomographic image is revised as a preset value, obtains a new brightness tomographic image.
S23, one is recombined by the new brightness tomographic image and the form and aspect tomographic image and the saturation degree tomographic image
Second image of HLS color spaces.
Wherein, the second image is obtained after brightness processed can overcome the problem of character is blocked by shadow in image
.
Step S3, second image is changed into the 3rd image of a rgb color space.
Step S4, carries out binary conversion treatment to the 3rd image and obtains an intermediate image, and identify the middle graph
Character information as in.
Two steps of above-mentioned steps S3 and S4 and the existing process step to normal picture are consistent, due to above-mentioned steps
S1 and S2 processing obtains the second image and goes for normal picture and abnormal image, so as to overcome word in the prior art
Accord with the situation of recognition failures.
Embodiment 2
If source vehicle image is inherently the image of a HLS color spaces, then can directly use above-described embodiment 1
In step S2-S4 solve the technical problems to be solved by the invention, reach the effect of character in correct identification image.
Implement 3
The present embodiment additionally provides a kind of processing unit of vehicle image, due to the processing unit solve problem principle with
Above-described embodiment 1 is similar with the method in embodiment 2, therefore, and the implementation process and implementation principle of processing unit may refer to
Implementation process and the implementation principle description of preceding method, repeat part and repeat no more.
Such as Fig. 5, the present embodiment provides a kind of processing unit of vehicle image, and the processing unit 100 includes:First image turns
Change the mold block 110, the first image for being converted into a HLS color spaces to the source vehicle image got;Second image turns
Block 120 is changed the mold, the brightness value of brightness tomographic image is a preset value where for changing described first image, generates a HLS colors
Second image in space;3rd image conversion module 130, for changing second image the 3rd of a rgb color space into
Image;Image recognition processing module 140, obtains an intermediate image, and know for carrying out binary conversion treatment to the 3rd image
The character information not gone out in the intermediate image.
Wherein, second image conversion module 120 can further include:Image layered unit 121, for by institute
State first and image layered obtain brightness tomographic image therein, a form and aspect tomographic image and a saturation degree tomographic image;Brightness amendment
Member 122, the brightness value for changing the brightness tomographic image is revised as a preset value, obtains a new brightness tomographic image;Image
Synthesis unit 123, one is recombined by the new brightness tomographic image and the form and aspect tomographic image and the saturation degree tomographic image
Second image of HLS color spaces.
Specifically, the source vehicle image is the image of following any color space:RGB, HLS and HSV.
Specifically, the preset value is 60-150, and more preferably, the preset value can be 100-130.
In summary, the present invention is converted to HLS images by using color space, then changes the bright of wherein brightness layer
Angle value, a new HLS images are regenerated with this, and the new HLS images finally are converted into RGB image, and then correct knowledge again
Do not go out character information therein, cleverly overcome prior art because sunlight shade causes to block to source vehicle image and can not
The problem of correctly identifying character information therein.So, the present invention effectively overcomes various shortcoming of the prior art and had
High industrial utilization.
The above-described embodiments merely illustrate the principles and effects of the present invention, not for the limitation present invention.It is any ripe
Know the personage of this technology all can carry out modifications and changes under the spirit and scope without prejudice to the present invention to above-described embodiment.Cause
This, those of ordinary skill in the art is complete without departing from disclosed spirit and institute under technological thought such as
Into all equivalent modifications or change, should by the present invention claim be covered.
Claims (10)
1. a kind of processing method of vehicle image, it is characterised in that including:
One first image of HLS color spaces is converted into the source vehicle image got;
The brightness value of brightness tomographic image where changing described first image is a preset value, the one second of generation HLS color spaces
Image;
Second image is changed into one the 3rd image of rgb color space;
Binary conversion treatment is carried out to the 3rd image and obtains an intermediate image, and identifies that the character in the intermediate image is believed
Breath.
2. the processing method of vehicle image according to claim 1, it is characterised in that:The modification described first image institute
Include the step of the brightness value of brightness tomographic image is a preset value, second image for generating HLS color spaces:
Described first image layering is obtained into brightness tomographic image therein, a form and aspect tomographic image and a saturation degree tomographic image;
The brightness value for changing the brightness tomographic image is revised as a preset value, obtains new brightness tomographic image;
The new brightness tomographic image and the form and aspect tomographic image and the saturation degree tomographic image are recombined into HLS color spaces
One second image.
3. the processing method of vehicle image according to claim 1, it is characterised in that:The source vehicle image is following
The image of one color space:RGB, HLS and HSV.
4. according to the processing method of any described vehicle images of claim 1-3, it is characterised in that:The preset value is 60-
150。
5. the processing method of vehicle image according to claim 4, it is characterised in that:The preset value is 100-130.
6. a kind of processing unit of vehicle image, it is characterised in that including:
First image conversion module, one first image for being converted into HLS color spaces to the source vehicle image got;
Second image conversion module, the brightness value of brightness tomographic image is a preset value where for changing described first image, raw
Into one second image of HLS color spaces;
3rd image conversion module, one the 3rd image for second image to be changed into rgb color space;
Image recognition processing module, obtains an intermediate image, and identify for carrying out binary conversion treatment to the 3rd image
Character information in the intermediate image.
7. the processing unit of vehicle image according to claim 6, it is characterised in that:The second image conversion module bag
Include:
Image layered unit, for by described first image layering obtain brightness tomographic image therein, a form and aspect tomographic image and
One saturation degree tomographic image;
Unit is changed in brightness, and the brightness value for changing the brightness tomographic image is revised as a preset value, obtains a new brightness
Tomographic image;
Image composing unit, the new brightness tomographic image is closed again with the form and aspect tomographic image and the saturation degree tomographic image
Into one second image of HLS color spaces.
8. the processing unit of vehicle image according to claim 6, it is characterised in that:The source vehicle image is following
The image of one color space:RGB, HLS and HSV.
9. according to the processing unit of any described vehicle images of claim 6-8, it is characterised in that:The preset value is 60-
150。
10. the processing unit of vehicle image according to claim 9, it is characterised in that:The preset value is 100-130.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611117133.2A CN107123093A (en) | 2016-12-07 | 2016-12-07 | A kind of processing method and processing device of vehicle image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611117133.2A CN107123093A (en) | 2016-12-07 | 2016-12-07 | A kind of processing method and processing device of vehicle image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107123093A true CN107123093A (en) | 2017-09-01 |
Family
ID=59717170
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611117133.2A Pending CN107123093A (en) | 2016-12-07 | 2016-12-07 | A kind of processing method and processing device of vehicle image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107123093A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020077530A1 (en) * | 2018-10-16 | 2020-04-23 | Fresenius Medical Care Deutschland Gmbh | Device and method for recognizing one or more characters |
CN113327012A (en) * | 2021-04-28 | 2021-08-31 | 东南大学 | Urban public transport index calculation method based on RGB color space and Monte Carlo method |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1787010A (en) * | 2005-11-24 | 2006-06-14 | 北京金山软件有限公司 | Method for dynamic changing picture element colour and method for changing image colour |
CN102063710A (en) * | 2009-11-13 | 2011-05-18 | 烟台海岸带可持续发展研究所 | Method for realizing fusion and enhancement of remote sensing image |
CN102186400A (en) * | 2008-10-17 | 2011-09-14 | 奥林巴斯株式会社 | Imaging device and imaging system |
CN102509095A (en) * | 2011-11-02 | 2012-06-20 | 青岛海信网络科技股份有限公司 | Number plate image preprocessing method |
CN104182947A (en) * | 2014-09-10 | 2014-12-03 | 安科智慧城市技术(中国)有限公司 | Low-illumination image enhancement method and system |
CN105096273A (en) * | 2015-08-20 | 2015-11-25 | 北京邮电大学 | Automatic adjustment method of color image brightness |
CN105741235A (en) * | 2016-02-29 | 2016-07-06 | 西北工业大学 | Visual rivalry improving method of complementary color three-dimensional image for improving color fidelity |
-
2016
- 2016-12-07 CN CN201611117133.2A patent/CN107123093A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1787010A (en) * | 2005-11-24 | 2006-06-14 | 北京金山软件有限公司 | Method for dynamic changing picture element colour and method for changing image colour |
CN102186400A (en) * | 2008-10-17 | 2011-09-14 | 奥林巴斯株式会社 | Imaging device and imaging system |
CN102063710A (en) * | 2009-11-13 | 2011-05-18 | 烟台海岸带可持续发展研究所 | Method for realizing fusion and enhancement of remote sensing image |
CN102509095A (en) * | 2011-11-02 | 2012-06-20 | 青岛海信网络科技股份有限公司 | Number plate image preprocessing method |
CN104182947A (en) * | 2014-09-10 | 2014-12-03 | 安科智慧城市技术(中国)有限公司 | Low-illumination image enhancement method and system |
CN105096273A (en) * | 2015-08-20 | 2015-11-25 | 北京邮电大学 | Automatic adjustment method of color image brightness |
CN105741235A (en) * | 2016-02-29 | 2016-07-06 | 西北工业大学 | Visual rivalry improving method of complementary color three-dimensional image for improving color fidelity |
Non-Patent Citations (2)
Title |
---|
王想 等: "图像和视频亮度的自动调整", 《电子学报》 * |
赵海燕 等: "基于车牌颜色变化剧烈特征的彩色车牌定位新方法", 《内蒙古民族大学学报(自然科学版)》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020077530A1 (en) * | 2018-10-16 | 2020-04-23 | Fresenius Medical Care Deutschland Gmbh | Device and method for recognizing one or more characters |
CN113327012A (en) * | 2021-04-28 | 2021-08-31 | 东南大学 | Urban public transport index calculation method based on RGB color space and Monte Carlo method |
CN113327012B (en) * | 2021-04-28 | 2022-03-11 | 东南大学 | Urban public transport index calculation method based on RGB color space and Monte Carlo method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103606182B (en) | Method and device for image rendering | |
CN110796595B (en) | Tone mapping method and device and electronic equipment | |
CN103593830B (en) | A kind of low illumination level video image enhancement | |
CN105118027B (en) | A kind of defogging method of image | |
CN106303483B (en) | A kind of image processing method and device | |
CN106228581B (en) | Pixel format is converted to the method and system of NV12 by GPU by ARGB | |
CN106504212A (en) | A kind of improved HSI spatial informations low-luminance color algorithm for image enhancement | |
CN101742339A (en) | Method for enhancing color image | |
CN105791783B (en) | Camera imaging color adjustment method and system | |
CN107396079B (en) | White balance adjustment method and device | |
CN111161683B (en) | Image processing method, image processor and display device | |
CN108337496A (en) | White balancing treatment method, processing unit, processing equipment and storage medium | |
CN107123093A (en) | A kind of processing method and processing device of vehicle image | |
CN104683780B (en) | The auto white balance method of a kind of video monitoring camera and device | |
CN106507079B (en) | A kind of color rendition method and device | |
CN104504661A (en) | Method for processing image to be in black and white effect | |
CN104144332B (en) | Image color adjusting method and electronic device using the same | |
CN101895771B (en) | Luminance and chrominance separately-acquiring and hybrid-correction method of LED display screen | |
CN105825531A (en) | Method and device for dyeing game object | |
CN102572448A (en) | Device and method for shooting color image based on red, white and blue (RWB) three-color light | |
CN108648144A (en) | A kind of FPM high-resolution colour picture method for reconstructing based on deep learning algorithm | |
Nakajima et al. | A novel color image processing scheme in HSI color space with negative image processing | |
KR101958263B1 (en) | The control method for VR contents and UI templates | |
US10175468B2 (en) | Method for generating a contrast image of an object structure and apparatuses relating thereto | |
CN106791741A (en) | Multi-screen marching 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170901 |