CN111563857A - Image identification method for special lead seal number of container - Google Patents
Image identification method for special lead seal number of container Download PDFInfo
- Publication number
- CN111563857A CN111563857A CN202010395571.5A CN202010395571A CN111563857A CN 111563857 A CN111563857 A CN 111563857A CN 202010395571 A CN202010395571 A CN 202010395571A CN 111563857 A CN111563857 A CN 111563857A
- Authority
- CN
- China
- Prior art keywords
- image
- color space
- lead seal
- information
- original 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013507 mapping Methods 0.000 claims description 26
- 230000003287 optical effect Effects 0.000 description 8
- 230000015556 catabolic process Effects 0.000 description 6
- 238000006731 degradation reaction Methods 0.000 description 6
- 238000003672 processing method Methods 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 238000002310 reflectometry Methods 0.000 description 4
- 239000000523 sample Substances 0.000 description 4
- 230000008447 perception Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
Images
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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image identification method of a special lead seal number for a container, which comprises the following steps: acquiring an original image and a degraded image of the original image added with ambient light ground color; acquiring the chromaticity difference Cdiff between the original image and the degraded image; and carrying out chromaticity compensation on the original image by using the chromaticity difference to obtain a compensated image. The invention can finish the work of automatically uploading the wharf system after the seal number is identified by the algorithm, and has high identification accuracy and high efficiency compared with manual operation.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to an image recognition method of a special lead seal number for a container.
Background
A lead seal is a device like a latch that is applied by a particular person after the cargo is loaded into the container and the door is properly closed. Once the lead seal is properly locked, it cannot be opened unless violently damaged, and the damaged lead seal cannot be reused. Each lead seal is provided with a unique number mark. As long as the appearance of the container is complete, the door of the container is correctly closed, and the lead seal is normally locked, the condition that the container is not opened privately in the transportation process can be proved, and the condition in the container is supervised and responsible by a container loader during container loading. The issuing of the lead seal is always manual issuing, and the number on the lead seal, namely the seal number, is identified and uploaded to a wharf system, so that the identification accuracy is low, the efficiency is low, and the image identification method of the special lead seal number for the container is provided.
Disclosure of Invention
Based on the technical problems in the background art, the invention provides an image identification method of a special lead seal number of a container.
The invention provides an image identification method of a special lead seal number for a container, which comprises the following steps:
s1: acquiring an original image and a degraded image of the original image added with ambient light ground color;
s2: acquiring the chromaticity difference Cdiff between the original image and the degraded image;
s3: and carrying out chromaticity compensation on the original image by using the chromaticity difference to obtain a compensated image.
Preferably, the specific steps of S1 are: converting the obtained original image from an RGB color space to an LCH color space, extracting color saturation C and brightness information of each pixel of the original image in the chromaticity information of the LCH color space, converting the degraded image from the RGB color space to the LCH color space, and extracting the color saturation Cflare of each pixel of the degraded image in the chromaticity information of the LCH color space.
Preferably, the specific steps of S1 are: converting the obtained original image from an RGB color space to an LCH color space, extracting color saturation C and brightness information of each pixel of the original image in the chromaticity information of the LCH color space, and mapping the brightness information; and converting the degraded image from the RGB color space to the LCH color space, and extracting the color saturation Cflare of each pixel of the degraded image in the chrominance information of the LCH color space.
Preferably, the Cdiff is the value of C minus cflar.
Preferably, in S3, the color saturation of the compensated image is a sum of the product of the compensation coefficients α and Cdiff and C.
Preferably, the compensation coefficient α is less than or equal to 1.
Preferably, in S3, the luminance information and the chrominance information of the compensated image are converted from the LCH color space to the luminance information and the chrominance information of the RGB space, so as to obtain a color image with compensated color saturation.
Preferably, the mapping process includes the specific steps of: and carrying out global nonlinear mapping on the brightness information.
Preferably, the mapping process includes the specific steps of: dividing the brightness information of the image into a low-frequency part base layer and a high-frequency part detail layer, and then carrying out global mapping processing on the base layer.
Preferably, the global mapping process employs a mapping algorithm that preserves perceptual differences in image brightness or a non-linear global mapping algorithm.
The beneficial effects of the invention are as follows:
1. can be through combining together with self-service cash dispenser, on the basis that cash dispenser has solved the issue problem, solved the scanning recognition problem to the lead sealing surface, can be with the back of seal number through algorithm identification, accomplish the work of automatic pier system of uploading, compare in manual operation, the discernment correct rate is high, efficient.
2. Based on the deep learning theory, the original image is subjected to chromaticity compensation according to the ambient light condition, for example, the color saturation is compensated or the color gamut range of the original image is expanded, so that the color vividness of the image displayed under the ambient light can be improved, and the display effect of the display device is greatly improved.
Drawings
Fig. 1 is a schematic flow chart of an image identification method of a special lead seal number for a container according to the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments.
Embodiment 1, referring to fig. 1, an image recognition method for a special lead seal number of a container includes the following steps:
converting the acquired original image from an RGB color space to an LCH color space;
extracting brightness information of each pixel of the original image in an LCH color space;
extracting chromaticity information of each pixel of the original image in an LCH color space for chromaticity compensation, for example, extracting color saturation in the chromaticity information for color saturation compensation, wherein the color saturation compensation of the original image is mainly determined by ambient light intensity which can be obtained by an optical sensor or an optical probe in real time; when the ambient light is strong, the original image displayed after the chromaticity compensation is enhanced, the image becomes more bright, and the hue H is kept unchanged;
the method comprises the steps of carrying out degradation processing on an original image to simulate the perception of human eyes on the quality of a display image on a display screen under ambient light, wherein the step of carrying out degradation processing on the image is to simulate the image of adding ambient light background color to the original image, the ambient light background color can be added to RGB three channels generally by the degradation processing, and the ambient light background color is generally determined by the ambient light intensity and the material reflectivity of the display equipment screen, so that the degraded image related to the ambient light intensity can be obtained;
converting the degraded image from an RGB color space to an LCH color space, wherein L represents a brightness value, C represents a color saturation value and H represents a hue angle value, extracting the color saturation of each pixel of the degraded image in the chrominance information of the LCH color space, the color saturation of the degraded image represents the color saturation after reduction caused by reflection of a display screen on ambient light, the color saturation is represented by Cflare, the color saturation of each pixel of the original image in the chrominance information of the LCH color space is also extracted, the color saturation is represented by C, the difference value Cdiff of the color saturation of each pixel of the original image and the degraded image is obtained, and the chrominance compensation can be calculated according to the difference value Cdiff to obtain the chrominance saturation of the original image, namely the color saturation of each pixel of the compensated image after the color saturation compensation; the specific calculation formula is as follows:
Cdiff＝C-Cflare
C*＝C+αCdiff
alpha is a compensation coefficient and is less than or equal to 1, and represents the degree of color saturation compensation, and under the condition that the alpha is not more than the color gamut boundary of the display device, the larger the alpha is, the larger the degree of color saturation compensation is, and the more vivid the color of the compensated image is; c denotes the color saturation of the compensated image;
after color saturation compensation is carried out to obtain a compensated image, the brightness and chrominance information of the compensated image is converted into the brightness and chrominance information of an RGB space from an LCH color space, thereby obtaining a color image with the color saturation compensated,
in the LCH color space, the brightness information of the original image can be kept unchanged, and the hue H in the chroma information of the original image is kept unchanged;
the method is applied to the image display process of the display equipment, the ambient light intensity of the display equipment can be measured in real time by equipment such as an optical sensor or an optical probe and is combined with the material reflectivity of a display screen of the display equipment to obtain the ambient light background color, then the input original image is added into the ambient light background color to obtain a degraded image, then the image processing method is carried out to obtain a compensated image, and finally the compensated image is displayed on the display screen of the display equipment.
Embodiment 2, referring to fig. 1, an image recognition method for a special lead seal number of a container includes the following steps:
converting the acquired original image from an RGB color space to an LCH color space;
extracting brightness information of each pixel of the original image in an LCH color space, and mapping the brightness information to improve the overall contrast of the image, wherein the specific mapping processing method comprises the following steps: global nonlinear mapping is carried out on the brightness information, so that the contrast of a low-gray region of the image is remarkably improved, and the details of the dark tone are smoothly expanded;
extracting chromaticity information of each pixel of the original image in an LCH color space for chromaticity compensation, for example, extracting color saturation in the chromaticity information for color saturation compensation, wherein the color saturation compensation of the original image is mainly determined by ambient light intensity which can be obtained by an optical sensor or an optical probe in real time; when the ambient light is strong, the original image displayed after the chromaticity compensation is enhanced, the image becomes more bright, and the hue H is kept unchanged;
the method comprises the steps of carrying out degradation processing on an original image to simulate the perception of human eyes on the quality of a display image on a display screen under ambient light, wherein the step of carrying out degradation processing on the image is to simulate the image of adding ambient light background color to the original image, the ambient light background color can be added to RGB three channels generally by the degradation processing, and the ambient light background color is generally determined by the ambient light intensity and the material reflectivity of the display equipment screen, so that the degraded image related to the ambient light intensity can be obtained;
converting the degraded image from an RGB color space to an LCH color space, wherein L represents a brightness value, C represents a color saturation value and H represents a hue angle value, extracting the color saturation of each pixel of the degraded image in the chrominance information of the LCH color space, the color saturation of the degraded image represents the color saturation after reduction caused by reflection of a display screen on ambient light, the color saturation is represented by Cflare, the color saturation of each pixel of the original image in the chrominance information of the LCH color space is also extracted, the color saturation is represented by C, the difference value Cdiff of the color saturation of each pixel of the original image and the degraded image is obtained, and the chrominance compensation can be calculated according to the difference value Cdiff to obtain the chrominance saturation of the original image, namely the color saturation of each pixel of the compensated image after the color saturation compensation; the specific calculation formula is as follows:
Cdiff＝C-Cflare
C*＝C+αCdiff
alpha is a compensation coefficient and is less than or equal to 1, and represents the degree of color saturation compensation, and under the condition that the alpha is not more than the color gamut boundary of the display device, the larger the alpha is, the larger the degree of color saturation compensation is, and the more vivid the color of the compensated image is; c denotes the color saturation of the compensated image;
after color saturation compensation is carried out to obtain a compensated image, converting the brightness and chrominance information of the compensated image from an LCH color space into the brightness and chrominance information of an RGB space, thereby obtaining a color image with the color saturation compensated;
in the LCH color space, the luminance information is transformed from L to L by the global or local mapping process described above, and the hue H in the chrominance information of the original image remains unchanged;
the method is applied to the image display process of the display equipment, the ambient light intensity of the display equipment can be measured in real time by equipment such as an optical sensor or an optical probe and is combined with the material reflectivity of a display screen of the display equipment to obtain the ambient light background color, then the input original image is added into the ambient light background color to obtain a degraded image, then the image processing method is carried out to obtain a compensated image, and finally the compensated image is displayed on the display screen of the display equipment.
Example 3, with reference to fig. 1, differs from example 2 in that: the specific mapping processing method comprises the following steps: dividing the brightness information of the image into a low-frequency part basic layer and a high-frequency part detail layer, then carrying out global mapping processing on the basic layer, and adopting a mapping algorithm for reserving the image brightness perception difference.
Example 4, referring to fig. 1, compared with examples 2 and 3, the difference lies in: the specific mapping processing method comprises the following steps: dividing the brightness information of the image into a low-frequency part basic layer and a high-frequency part detail layer, then carrying out global mapping processing on the basic layer, and adopting a nonlinear global mapping algorithm.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (10)
1. The image identification method of the special lead seal number of the container is characterized by comprising the following steps:
s1: acquiring an original image and a degraded image of the original image added with ambient light ground color;
s2: acquiring the chromaticity difference Cdiff between the original image and the degraded image;
s3: and carrying out chromaticity compensation on the original image by using the chromaticity difference to obtain a compensated image.
2. The image identification method for the special lead seal number of the container according to claim 1, wherein the specific steps of S1 are as follows: converting the obtained original image from an RGB color space to an LCH color space, extracting color saturation C and brightness information of each pixel of the original image in the chromaticity information of the LCH color space, converting the degraded image from the RGB color space to the LCH color space, and extracting the color saturation Cflare of each pixel of the degraded image in the chromaticity information of the LCH color space.
3. The image identification method for the special lead seal number of the container according to claim 1, wherein the specific steps of S1 are as follows: converting the obtained original image from an RGB color space to an LCH color space, extracting color saturation C and brightness information of each pixel of the original image in the chromaticity information of the LCH color space, and mapping the brightness information; and converting the degraded image from the RGB color space to the LCH color space, and extracting the color saturation Cflare of each pixel of the degraded image in the chrominance information of the LCH color space.
4. The image identification method for the special lead seal number of the container according to claim 2 or 3, wherein the Cdiff is a value obtained by subtracting Cflare from C.
5. The image identification method for the special lead seal number of the container according to claim 4, wherein in the step S3, the color saturation of the compensated image is the sum of C and the product of the compensation coefficients α and Cdiff.
6. The image identification method for the special lead seal number of the container as claimed in claim 5, wherein the compensation coefficient α is less than or equal to 1.
7. The image recognition method of the special lead seal number for the container according to claim 1, wherein in S3, the luminance information and the chrominance information of the compensated image are converted from the LCH color space to the luminance information and the chrominance information of the RGB space, so as to obtain the color saturation compensated color image.
8. The image identification method of the special lead seal number for the container according to claim 3, wherein the mapping process comprises the following specific steps: and carrying out global nonlinear mapping on the brightness information.
9. The image identification method of the special lead seal number for the container according to claim 3, wherein the mapping process comprises the following specific steps: dividing the brightness information of the image into a low-frequency part base layer and a high-frequency part detail layer, and then carrying out global mapping processing on the base layer.
10. The image identification method for the special lead seal number of the container according to claim 9, wherein the global mapping process adopts a mapping algorithm which retains the perceived difference of image brightness or a non-linear global mapping algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010395571.5A CN111563857A (en) | 2020-05-12 | 2020-05-12 | Image identification method for special lead seal number of container |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010395571.5A CN111563857A (en) | 2020-05-12 | 2020-05-12 | Image identification method for special lead seal number of container |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111563857A true CN111563857A (en) | 2020-08-21 |
Family
ID=72071931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010395571.5A Pending CN111563857A (en) | 2020-05-12 | 2020-05-12 | Image identification method for special lead seal number of container |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111563857A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096910A (en) * | 2015-07-09 | 2015-11-25 | 西安诺瓦电子科技有限公司 | Image processing method |
| CN105100761A (en) * | 2015-07-09 | 2015-11-25 | 西安电子科技大学 | Image display method |
-
2020
- 2020-05-12 CN CN202010395571.5A patent/CN111563857A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096910A (en) * | 2015-07-09 | 2015-11-25 | 西安诺瓦电子科技有限公司 | Image processing method |
| CN105100761A (en) * | 2015-07-09 | 2015-11-25 | 西安电子科技大学 | Image display method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11145035B2 (en) | Method for rapidly dehazing underground pipeline image based on dark channel prior | |
| EP2959682B1 (en) | Display management for high dynamic range video | |
| EP3572928B1 (en) | Method for producing high dynamic range image from low dynamic range image | |
| US8050511B2 (en) | High dynamic range images from low dynamic range images | |
| Smith et al. | Apparent greyscale: A simple and fast conversion to perceptually accurate images and video | |
| EP1747665B1 (en) | Method for processing color image data | |
| US8483479B2 (en) | Light detection, color appearance models, and modifying dynamic range for image display | |
| US8731322B2 (en) | Image brightness controlling apparatus and method thereof | |
| US8325198B2 (en) | Color gamut mapping and brightness enhancement for mobile displays | |
| CN103493489B (en) | Image prediction based on primary colors hierarchy model | |
| CN101454820B (en) | Optimal backlighting determination apparatus and method | |
| CN105915755B (en) | The method encoded to image data and the method that image data is decoded | |
| CN109801233B (en) | Method for enhancing true color remote sensing image | |
| TWI443639B (en) | Image display device and method of driving the same | |
| CN101809647A (en) | Methods for selecting backlight illumination level and adjusting image characteristics | |
| KR100888429B1 (en) | Image brightness controlling apparatus and method thereof | |
| EP2347571A2 (en) | Contrast enhancement of images | |
| US20200105225A1 (en) | Ambient Saturation Adaptation | |
| Wang et al. | Hazy image decolorization with color contrast restoration | |
| CN109035175A (en) | Facial image Enhancement Method based on color correction and Pulse Coupled Neural Network | |
| CN102542526B (en) | Image decolorizing method | |
| US20130027371A1 (en) | Electronic device, method for adjusting color saturation, program therefor, and recording medium | |
| US8004538B2 (en) | Preferential tone scale for electronic displays | |
| CN111563857A (en) | Image identification method for special lead seal number of container | |
| CN109493289A (en) | One kind having brightness and saturation degree Double Nonlinear image enchancing method |
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 |
Application publication date: 20200821 |
|
| RJ01 | Rejection of invention patent application after publication |