CN109285165B - Gray scale automatic segmentation and analysis method of gray scale test card - Google Patents
Gray scale automatic segmentation and analysis method of gray scale test card Download PDFInfo
- Publication number
- CN109285165B CN109285165B CN201811102822.5A CN201811102822A CN109285165B CN 109285165 B CN109285165 B CN 109285165B CN 201811102822 A CN201811102822 A CN 201811102822A CN 109285165 B CN109285165 B CN 109285165B
- Authority
- CN
- China
- Prior art keywords
- gray scale
- image
- gray
- scale test
- shot
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 51
- 230000011218 segmentation Effects 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 230000007797 corrosion Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 230000008961 swelling Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 238000013441 quality evaluation Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 description 2
- 239000003550 marker Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a gray scale automatic segmentation and analysis method of a gray scale test card, which utilizes the self attribute of the gray scale test card to automatically distinguish the type of the gray scale test card, realizes the segmentation of gray scale blocks with different gray scale values of a 20-order gray scale test card and a 36-order gray scale test card, fully automates the gray scale dynamic range analysis process in an objective image quality evaluation system, improves the processing efficiency and enables the overall gray scale evaluation to be more efficient and accurate.
Description
Technical Field
The invention relates to an objective image quality evaluation method, in particular to a gray scale automatic segmentation and analysis method of a gray scale test card.
Background
The gray scale test chart is a frequently used test object when objective image quality evaluation is carried out. When the gray scale division and dynamic range analysis of the gray scale test chart are performed, the gray scale and dynamic range of the gray scale test chart in the image objective evaluation system need to be divided and analyzed.
The existing gray scale segmentation and dynamic range analysis method firstly needs to calibrate an area to be evaluated manually or automatically under the condition of a marker, secondly can finely tune and extract a gray scale test card area, and finally calculates a dynamic range and related parameters.
The existing method is convenient and simple in the whole operation process when drawing the graphic card analysis, and the obtained result is ideal as long as the evaluation area is accurately selected, but the defect is that the fine adjustment of the gray scale test card is too complex, and a large amount of manual processing time is needed for positioning the position of the graphic card under the distortion when the geometric distortion occurs, and the processing efficiency is extremely low.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a method for automatically distinguishing the type of a gray-scale test chart by utilizing the attributes of the gray-scale test chart and realizing the segmentation of gray-scale blocks with different gray-scale values of the test chart.
In order to achieve the purpose, the technical scheme of the invention is as follows:
the gray scale automatic segmentation and analysis method of the gray scale test card is characterized by comprising the following steps
S1: shooting a gray scale test card by using the equipment to be evaluated, storing a shot image and transmitting the shot image to the processing unit;
s2: the processing unit carries out Lab conversion on the shot image, counts the average energy of ab space, considers that the gray scale test card shot by the equipment to be evaluated in S1 is a 36-order gray scale test chart when the average energy is more than or equal to N, and goes to step S3; when the gray scale test card is smaller than N, the gray scale test card shot by the equipment to be evaluated in S1 is considered to be a 20-order gray scale test graphic card, and the step is switched to S4;
s3: the method for calculating the position coordinates of each gray scale block of the 36-order gray scale test graphic card specifically comprises the following steps:
s31: adding RGB3 channels of the shot image to obtain a mean value image of the shot image;
s32: subtracting the mean image obtained in the step S31 from each channel image in the RGB3 channels of the shot image respectively to obtain three results, and adding the three results to obtain an image;
s33: binarizing the image obtained in the step S32 by using Otsu' S method, setting structural elements, performing open operation (corrosion and expansion), deleting areas which cannot contain the structural elements, disconnecting narrow connection, and finally obtaining specific coordinates of each color area in the shot image;
s34: obtaining the position coordinates of each gray scale block through the relative position relation between 36 gray scale blocks to be divided and each color area, and entering the step 5;
s4: the method for calculating the position coordinates of the gray scale blocks of the 20-order gray scale test graphic card specifically comprises the following steps:
s41: obtaining the gray value of the brightest area in the shot image, and determining whether the 20-order gray-scale test chart shot by the equipment to be evaluated in S1 is a 20-order chart with the middle grid mark based on the prior knowledge of different gray values of color blocks in different gray-scale test charts; if so, performing the automatic segmentation algorithm in S42, otherwise, performing automatic segmentation if the algorithm is not matched, and failing to perform the algorithm;
s42: converting the shot image into a gray scale image, and then copying and reducing to obtain a reduced image so as to accelerate the subsequent segmentation calculation speed;
s43: performing rotation correction on the gray-scale image and the reduced image to ensure that the grid region appears at a specific part of the reduced image;
s44: performing Fourier transform on a specific part of the reduced graph line by line to obtain an area with high-frequency detail information in the specific part, performing binarization on the specific part by using Otsu method, performing morphological processing of swelling corrosion, and finally obtaining specific position coordinates of a grid area on the reduced graph;
s45: obtaining the position coordinates of all the gray scale blocks through the relative position relation between 20 gray scale blocks to be divided and the grid area;
s46: mapping the coordinates of each gray scale block obtained from the reduced image back to the coordinates on the original gray scale image for gray scale division, and entering step S5;
s5: and performing noise evaluation and dynamic range estimation by using each gray-scale block image obtained by segmentation.
Preferably, the value of N in step S2 ranges from 5 ^7 to 8 ^ 9.
Preferably, the structural element in step S33 is a planar disc with radius R, 2< R < 10.
Preferably, a specific portion in the steps S43 and S44 is an upper half of the reduced size map.
According to the technical scheme, the gray scale dynamic range analysis process in the objective image quality evaluation system is completely automated by fully utilizing the attributes of the gray scale test chart. Therefore, the method has the obvious characteristics of improving the processing efficiency and enabling the overall gray scale evaluation to be more efficient and accurate.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
In the following detailed description of the embodiments of the present invention, in order to clearly illustrate the structure of the present invention and to facilitate explanation, the structure shown in the drawings is not drawn to a general scale and is partially enlarged, deformed and simplified, so that the present invention should not be construed as limited thereto.
In the following detailed description of the invention, reference is made to FIG. 1. As shown in the figure, the first and second,
the gray scale automatic segmentation and analysis method of the gray scale test card is characterized by comprising the following steps
S1: and shooting the gray scale test card by using the equipment to be evaluated, storing the shot image and transmitting the shot image to the processing unit.
S2: the processing unit carries out Lab conversion on the shot image, counts the average energy of ab space, considers that the gray scale test card shot by the equipment to be evaluated in S1 is a 36-order gray scale test chart when the average energy is more than or equal to N, and goes to step S3; when the gray scale test card is smaller than N, the gray scale test card shot by the device to be evaluated in S1 is considered to be a 20-level gray scale test chart, and the process goes to step S4.
The value of N can be adjusted properly according to the size of the video frame, and the value range is 5 x (10^7) to 8 x (10^ 9). In this embodiment, a 3024 x 4032 sized video frame is used, and N-8 x (10^8) is used.
S3: the method for calculating the position coordinates of each gray scale block of the 36-order gray scale test graphic card specifically comprises the following steps:
s31: adding RGB3 channels of the shot image to obtain a mean value image of the shot image;
s32: subtracting the mean image obtained in the step S31 from each channel image in the RGB3 channels of the shot image respectively to obtain three results, and adding the three results to obtain an image;
s33: binarizing the image obtained in the step S32 by using Otsu' S method, setting structural elements, performing open operation (corrosion and expansion), deleting areas which cannot contain the structural elements, disconnecting narrow connection, and finally obtaining specific coordinates of each color area in the shot image;
the structural elements are planar disks with radius R, 2< R < 10. In the present embodiment, R is 5.
S34: the positional coordinates of each gray block are obtained from the relative positional relationship of the 36 gray blocks to be divided and each color area, and the process proceeds to step S5.
S4: the method for calculating the position coordinates of the gray scale blocks of the 20-order gray scale test graphic card specifically comprises the following steps:
s41: obtaining the gray value of the brightest area in the shot image, and determining whether the 20-order gray-scale test chart shot by the equipment to be evaluated in S1 is a 20-order chart with the middle grid mark based on the prior knowledge of different gray values of color blocks in different gray-scale test charts; if so, performing the automatic segmentation algorithm in S42, otherwise, performing automatic segmentation if the algorithm is not matched, and failing to perform the algorithm;
s42: converting the shot image into a gray scale image, and then copying and reducing to obtain a reduced image so as to accelerate the subsequent segmentation calculation speed;
s43: performing rotation correction on the gray-scale image and the reduced image to ensure that the grid region appears at a specific part of the reduced image;
s44: performing Fourier transform on a specific part of the reduced graph line by line to obtain an area with high-frequency detail information in the specific part, performing binarization on the specific part by using Otsu method, performing morphological processing of swelling corrosion, and finally obtaining specific position coordinates of a grid area on the reduced graph;
in this embodiment, the selected specific portion in steps S43 and S44 is the top half of the reduced size drawing.
S45: obtaining the position coordinates of all the gray scale blocks through the relative position relation between 20 gray scale blocks to be divided and the grid area;
s46: the coordinates of each gray-scale block obtained on the reduced image are mapped back to the coordinates on the original gray-scale image for gray-scale division, and the process proceeds to step S5.
S5: and performing noise evaluation and dynamic range estimation by using each gray-scale block image obtained by segmentation.
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 (4)
1. The gray scale automatic segmentation and analysis method of the gray scale test card is characterized by comprising the following steps
S1: shooting a gray scale test card by using the equipment to be evaluated, storing a shot image and transmitting the shot image to the processing unit;
s2: the processing unit carries out Lab conversion on the shot image, counts the average energy of ab space, considers that the gray scale test card shot by the equipment to be evaluated in S1 is a 36-order gray scale test chart when the average energy is more than or equal to N, and goes to step S3; when the gray scale test card is smaller than N, the gray scale test card shot by the equipment to be evaluated in S1 is considered to be a 20-order gray scale test graphic card, and the step is switched to S4;
s3: the method for calculating the position coordinates of each gray scale block of the 36-order gray scale test graphic card specifically comprises the following steps:
s31: adding RGB3 channels of the shot image to obtain a mean value image of the shot image;
s32: subtracting the mean image obtained in the step S31 from each channel image in the RGB3 channels of the shot image respectively to obtain three results, and adding the three results to obtain an image;
s33: binarizing the image obtained in the step S32 by using Otsu' S method, setting structural elements for open operation, deleting areas which cannot contain the structural elements, disconnecting narrow connections, and finally obtaining specific coordinates of each color area in the shot image;
s34: obtaining the position coordinates of each gray scale block through the relative position relation between 36 gray scale blocks to be divided and each color area, and entering the step 5;
s4: the method for calculating the position coordinates of the gray scale blocks of the 20-order gray scale test graphic card specifically comprises the following steps:
s41: obtaining the gray value of the brightest area in the shot image, and determining whether the 20-order gray-scale test chart shot by the equipment to be evaluated in S1 is a 20-order chart with the middle grid mark based on the prior knowledge of different gray values of color blocks in different gray-scale test charts; if so, performing the automatic segmentation algorithm in S42, otherwise, performing automatic segmentation if the algorithm is not matched, and failing to perform the algorithm;
s42: converting the shot image into a gray scale image, and then copying and reducing to obtain a reduced image so as to accelerate the subsequent segmentation calculation speed;
s43: performing rotation correction on the gray-scale image and the reduced image to ensure that the grid region appears at a specific part of the reduced image;
s44: performing Fourier transform on a specific part of the reduced graph line by line to obtain an area with high-frequency detail information in the specific part, performing binarization on the specific part by using Otsu method, performing morphological processing of swelling corrosion, and finally obtaining specific position coordinates of a grid area on the reduced graph;
s45: obtaining the position coordinates of all the gray scale blocks through the relative position relation between 20 gray scale blocks to be divided and the grid area;
s46: mapping the coordinates of each gray scale block obtained from the reduced image back to the coordinates on the original gray scale image for gray scale division, and entering step S5;
s5: and performing noise evaluation and dynamic range estimation by using each gray-scale block image obtained by segmentation.
2. The method of claim 1, wherein N in step S2 ranges from 5 ^7 to 8 ^ 9.
3. The method of claim 1, wherein the structural element in step S33 is a planar disk with radius R, 2< R < 10.
4. The method as claimed in claim 1, wherein a specific portion in the steps S43 and S44 is an upper half of the reduced size map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811102822.5A CN109285165B (en) | 2018-09-20 | 2018-09-20 | Gray scale automatic segmentation and analysis method of gray scale test card |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811102822.5A CN109285165B (en) | 2018-09-20 | 2018-09-20 | Gray scale automatic segmentation and analysis method of gray scale test card |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109285165A CN109285165A (en) | 2019-01-29 |
| CN109285165B true CN109285165B (en) | 2021-11-23 |
Family
ID=65181199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811102822.5A Active CN109285165B (en) | 2018-09-20 | 2018-09-20 | Gray scale automatic segmentation and analysis method of gray scale test card |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109285165B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112945867B (en) * | 2021-02-03 | 2023-07-07 | 中国测试技术研究院 | Reflective gray-scale test card measuring system and method |
| CN113269841A (en) * | 2021-05-18 | 2021-08-17 | 江西晶浩光学有限公司 | Gray scale testing method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101207832A (en) * | 2006-12-19 | 2008-06-25 | Tcl数码科技（深圳）有限责任公司 | Method for checking digital camera color reduction |
| CN206413117U (en) * | 2016-10-18 | 2017-08-15 | 深圳月牙科技有限公司 | Image measurement colour table |
| CN108055532A (en) * | 2017-12-27 | 2018-05-18 | 上海传英信息技术有限公司 | Automate the method and apparatus of matching test card |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6678414B1 (en) * | 2000-02-17 | 2004-01-13 | Xerox Corporation | Loose-gray-scale template matching |
-
2018
- 2018-09-20 CN CN201811102822.5A patent/CN109285165B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101207832A (en) * | 2006-12-19 | 2008-06-25 | Tcl数码科技（深圳）有限责任公司 | Method for checking digital camera color reduction |
| CN206413117U (en) * | 2016-10-18 | 2017-08-15 | 深圳月牙科技有限公司 | Image measurement colour table |
| CN108055532A (en) * | 2017-12-27 | 2018-05-18 | 上海传英信息技术有限公司 | Automate the method and apparatus of matching test card |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109285165A (en) | 2019-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112115895B (en) | Pointer type instrument reading identification method, pointer type instrument reading identification device, computer equipment and storage medium | |
| CN110400290B (en) | Method and device for detecting chromatic aberration of solar cell and storage medium | |
| CN107679535B (en) | Automatic reading identification system and method for pointer type water meter based on template matching | |
| CN108550159B (en) | Flue gas concentration identification method based on image three-color segmentation | |
| CN108846397B (en) | Automatic detection method for cable semi-conducting layer based on image processing | |
| CN109285165B (en) | Gray scale automatic segmentation and analysis method of gray scale test card | |
| CN105095896A (en) | Image distortion correction method based on look-up table | |
| CN110853005A (en) | Immunohistochemical membrane staining section diagnosis method and device | |
| CN101114340A (en) | VLSI realizing system and method of histogram equalization image processing | |
| CN106790898B (en) | A kind of mobile phone screen bad point automatic testing method and system based on significance analysis | |
| CN110246138A (en) | A kind of method of digital cores image pore throat segmentation | |
| CN109766818A (en) | Pupil center's localization method and system, computer equipment and readable storage medium storing program for executing | |
| CN109359604B (en) | Method for identifying instrument under shadow interference facing inspection robot | |
| CN105447879A (en) | Method and apparatus for detecting breast muscle in breast image | |
| CN111598109A (en) | Intelligent identification method for reading of pointer instrument of transformer substation | |
| CN112734729A (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
| WO2022088856A1 (en) | Fundus image recognition method and apparatus, and device | |
| TW201512649A (en) | Method of chip detects inspecting, system therefor, and computer program product thereof | |
| CN116740579B (en) | Intelligent collection method for territorial space planning data | |
| CN108764343A (en) | A kind of localization method of tracking target frame in track algorithm | |
| CN109978859B (en) | Image display adaptation quality evaluation method based on visible distortion pooling | |
| CN110097533B (en) | Method for accurately testing overall dimension and position of light spot | |
| CN110849444A (en) | Video water level measuring method based on machine vision | |
| CN110579184A (en) | Product appearance online detection device and use method thereof | |
| CN109448012A (en) | A kind of method for detecting image edge 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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Liao Zhiliang Inventor after: Tao Liang Inventor after: Wang Daoning Inventor after: Zhang Yadong Inventor after: Guo Baozhu Inventor before: Guo Baozhu Inventor before: Wang Daoning Inventor before: Zhang Yadong |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A grayscale automatic segmentation and analysis method for grayscale test cards Effective date of registration: 20230726 Granted publication date: 20211123 Pledgee: Dalian Branch of Shanghai Pudong Development Bank Co.,Ltd. Pledgor: YICHENG GAOKE (DALIAN) TECHNOLOGY Co.,Ltd. Registration number: Y2023980049989 |