CN114266741A - Material analysis and detection method based on image recognition technology - Google Patents
Material analysis and detection method based on image recognition technology Download PDFInfo
- Publication number
- CN114266741A CN114266741A CN202111534072.0A CN202111534072A CN114266741A CN 114266741 A CN114266741 A CN 114266741A CN 202111534072 A CN202111534072 A CN 202111534072A CN 114266741 A CN114266741 A CN 114266741A
- Authority
- CN
- China
- Prior art keywords
- spectral
- detected
- spectrogram
- image
- inspection
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 239000000463 material Substances 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 title claims abstract description 23
- 238000005516 engineering process Methods 0.000 title claims abstract description 15
- 230000003595 spectral effect Effects 0.000 claims abstract description 88
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000001228 spectrum Methods 0.000 claims abstract description 10
- 238000007689 inspection Methods 0.000 claims description 53
- 238000004364 calculation method Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000010892 electric spark Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 4
- 150000002500 ions Chemical class 0.000 description 4
- 230000004438 eyesight Effects 0.000 description 2
- 230000002269 spontaneous effect Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The application relates to the technical field of material analysis, and discloses a material analysis detection method based on an image recognition technology. This application compares in the current spectrum that adopts artificial mode to the part material of adoption and analyzes, has reduced the growth degree of difficulty and the cycle of professional skill talent, and whole analytic process no longer relies on the professional skill level of measurement personnel, and the rate of accuracy of analysis result is higher to through spectral image's automatic acquisition and analysis, still reduced measurement personnel's intensity of labour.
Description
Technical Field
The application relates to the technical field of material analysis, in particular to a material analysis and detection method based on an image recognition technology.
Background
The spectroscopic analysis technique is a spontaneous transition from a high energy state to a low energy state according to each of the atoms or ions of an element, and from its spectral diagram, it can be visually observed that a spectral line of a certain wavelength corresponding thereto appears. Among the many lines emitted by the atoms or ions of each element, there are always some lines specific to the wavelength (colour) and intensity (intensity), which constitute the characteristic lines of the element. On the contrary, each spectral line in the spectrogram necessarily corresponds to a spontaneous transition of an atom or ion of a certain element. Therefore, the presence or absence of an element in a sample can be determined based on the presence or absence of a characteristic spectral line of an atom or ion of the element in the spectrum.
The existing operation method is that a part to be measured is usually placed at an electrode, a pedal switch is stepped on by feet to carry out electric spark excitation, the spectrum is observed through an eyepiece, and when different wave bands need to be observed, a knob is rotated to adjust images of the different wave bands in the eyepiece. Therefore, the above prior art mainly has the following disadvantages: (1) the situation of overuse of eyes can exist in long-time spectral observation, and certain damage is caused to the eyesight of practitioners; (2) the requirement on the professional skill level of a practitioner is high, relevant practitioner training is required, and the skill level of the practitioner grows for an extremely slow period; (3) the eyepiece can only be observed by a single person, and whether the observer has misjudgment or not can not be ensured; (4) the aviation parts are numerous, and the problems of material grade mixing of front and rear parts, part false detection, part missing detection and the like can occur.
Disclosure of Invention
In order to overcome the problems and the defects in the prior art, the application provides an automatic material spectrum analysis method, which does not depend on the professional skill level of an operator, has high accuracy of an analysis result, and does not damage the eyesight of the operator.
In order to achieve the above object, the technical solution of the present application is as follows:
a material analysis and detection method based on an image recognition technology specifically comprises the following steps:
acquiring information of the part to be detected: before detection, firstly scanning an identification label of a part to be detected, acquiring the detection number of the part to be detected and the label of the part, and finally determining a compared standard spectrogram;
a spectral image acquisition step: placing a part to be detected on a detection platform of a spectral mirror, starting a switch, firstly exciting the spectral mirror to generate sparks by a computer host, then controlling a servo motor to rotate, driving a knob of the spectral mirror to rotate to a specified position by the servo motor, controlling an industrial camera to take a picture by the computer host, converting a collected spectral image into a digital image containing a coordinate relation, then sequentially splicing a plurality of collected spectral images by using a coordinate system to form an inspection spectrogram of the part to be detected, and finally displaying the inspection spectrogram in a display;
comparing the spectral images and judging results: and comparing the inspection spectrogram of the current part to be detected with the standard spectral image, calculating the similarity of the images, and then judging the result.
Further, the steps of comparing the spectral images and determining the result are as follows:
an image digitalizing step: converting the RGB color value of each pixel point on the inspection spectrum image of the part to be detected into the gray value of the pixel point, and establishing a gray value matrix according to the gray value of the pixel point
Calculating the arithmetic mean value of the gray value of each row of the matrix, and combining the gray value mean values of each row to obtain the characteristic value vector of the inspection spectral image of the part to be detected
C＝[g1，g2，g3，…，gn]Formula (2);
wherein, gnThe nth characteristic value represents the inspection spectral image of the part to be detected;
matching image similarity: calculating the difference d between the n characteristic value of the inspection spectrogram and the n characteristic value of the standard spectrogram of the part to be detectedn
dn＝gn-g’nFormula (3);
wherein, gnDenotes an n-th characteristic value, g'nAn nth characteristic value representing a standard spectral image;
comparing the inspection spectrogram of the part to be detected with the standard spectrogram, and calculating the gray value difference L 'between the inspection spectrogram of the part to be detected and the standard spectrogram according to a Euclidean distance formula'
Comparing for many times, and taking an arithmetic mean value of all the gray value differences obtained by calculation as a final value L of the gray value difference between the inspection spectrogram of the part to be detected and the standard spectrogram;
normalizing the final value L of the gray value difference between the inspection spectrogram of the part to be detected and the standard spectrogram according to the following expression
L/(255 × sqrt (n)) (5);
where N represents the width of the image.
Finally, the similarity S between the inspection spectrogram of the part to be detected and the standard spectrogram is obtained through the following calculation expression
100% -V formula (6).
Further, the calculation expression for converting the RGB color value of each pixel point into the gray value of the pixel point is as follows:
wherein R represents red, G represents green, and B represents blue.
Furthermore, when the display displays the spectral image, the standard spectral image and the inspection spectral image of the part to be detected are displayed together, so that whether the part is qualified or not can be conveniently and manually confirmed.
A material analysis and detection device based on an image recognition technology comprises a spectral lens, an industrial camera, a servo motor, a label recognizer, a display and a computer host, wherein the computer host is respectively connected with the spectral lens, the industrial camera, the servo motor, the label recognizer and the display and is a control terminal of the whole device and used for triggering the spectral lens, the industrial camera, the servo motor and the label recognizer to work, receiving data transmitted by the industrial camera and the label recognizer and processing the data, and realizing man-machine information interaction with an operator through the display; the spectral viewer is used for generating electric sparks and spectral images; the industrial camera is arranged on an eyepiece of the spectoscope and used for collecting a spectral image of a part to be measured; the output end of the servo motor is connected with a knob of the spectometer lens and used for driving the knob to rotate; the label recognizer is used for scanning and recognizing the recognition label of the part to be detected.
Further, the industry camera passes through the camera mount pad setting on the spectral lens, the camera mount pad includes camera lens adapter ring and camera support, and the one end of camera lens adapter ring is connected with the camera lens of industry camera, and the other end is connected with the eyepiece of spectral lens, the camera support is formed by connecting two half supports to closing, and two half supports enclose to close to form one after connecting and enclose the portion of closing, and the camera lens of industry camera and the eyepiece of spectral lens are located enclose in the portion of closing, two half supports pass through fastening bolt fixed connection.
The beneficial effect of this application:
(1) this application compares in the current spectrum that adopts artificial mode to the part material of adoption and analyzes, has reduced the growth degree of difficulty and the cycle of professional skill talent, and whole analytic process no longer relies on the professional skill level of measurement personnel, and the rate of accuracy of analysis result is higher to through spectral image's automatic acquisition and analysis, still reduced measurement personnel's intensity of labour.
(2) When the spectrum of the part material is analyzed, the spectrum image can be watched by only one person, but can be projected on a display screen for all people to watch, people can discuss and exchange at the same time, the rapid culture of talents is realized, and the damage and fatigue of the direct observation electric spark spectrum to eyes are reduced.
(3) The data of the detection process can be associated and matched with the product information, the detailed digital record of the detection process is realized, and the displayable, storable and traceable effects of the detection process image are realized.
(4) According to the method, in the comparison process of the spectral images, the mechanical error is eliminated by taking an alignment measure on the spectral images, the overall material analysis result is more accurate, and the error is smaller.
Drawings
FIG. 1 is a flow chart of the method of the present application;
FIG. 2 is a schematic view of the structure of the detecting device of the present application;
fig. 3 is a schematic view of an industrial camera mounting structure according to the present application.
In the drawings:
1. a music reading mirror; 2. an industrial camera; 3. a servo motor; 4. a label identifier; 5. a display; 6. a computer host; 7. a camera mount; 71. a lens adapter ring; 72. a camera support.
Detailed Description
The present application will be described in further detail with reference to examples, but the embodiments of the present application are not limited thereto.
Example 1
The embodiment discloses a material analysis and detection method based on an image recognition technology, which specifically comprises the following steps:
acquiring information of the part to be detected: before detection, firstly, a label recognizer is used for scanning an identification label of a part to be detected to obtain the detection number of the part to be detected and the label number of the part, then the label recognizer transmits the part information to a computer host, the computer host searches for matching in a stored database according to the part information, and finally a compared standard spectrogram is determined;
a spectral image acquisition step: placing a part to be detected on a detection platform of a spectral mirror, starting a switch, firstly exciting the spectral mirror to generate sparks by a computer host, then controlling a servo motor to rotate, driving a knob of the spectral mirror to rotate to a specified position by the servo motor, controlling an industrial camera to take a picture by the computer host, converting a collected spectral image into a digital image containing a coordinate relation, then sequentially splicing a plurality of collected spectral images by using a coordinate system to form an inspection spectrogram of the part to be detected, and finally displaying the inspection spectrogram in a display;
comparing the spectral images and judging results: and the computer host compares the inspection spectrogram of the current part to be detected with the standard spectral image, calculates the similarity of the images, outputs a judgment result and transmits the result to the display for display.
Example 2
In this embodiment, in the step of collecting spectral images, splicing the collected multiple spectral images in sequence by using a coordinate system specifically means that the rightmost edge of a first image is spliced with the left edge of a second image, the height of a new image is consistent with that of the original two images, and the width of the new image is the sum of the two images.
Further, the steps of comparing the spectral images and determining the result specifically comprise the following steps:
an image digitalizing step: firstly, converting the RGB color value of each pixel point on the inspection spectrum image of the part to be detected into the gray value of the pixel point through the following calculation expression
100% -V formula (6).
Wherein RGB refers to three primary colors optically, R represents red, G represents green, B represents blue, and the value of each color is 0-255.
Then, the gray value matrix is established according to the gray value of the calculated pixel points
And finally, calculating the arithmetic mean value of the gray value of each row of the matrix, and combining the mean values of the gray value of each row to obtain the following characteristic value vector of the inspection spectral image of the part to be detected
C＝[g1，g2，g3，…，gn]Formula (2);
wherein, gnAn nth characteristic value representing an inspection spectral image of the part to be tested;
matching image similarity: firstly, calculating the difference d between the n-th characteristic value of the inspection spectral image and the standard spectral image of the part to be detected according to the following calculation expressionn
dn＝gn-g’nFormula (3);
wherein, gnN-th characteristic value, g'nAn nth characteristic value representing a standard spectral image;
then, comparing the inspection spectrogram of the part to be detected with the standard spectrogram, calculating the gray value difference L' between the inspection spectrogram of the part to be detected and the standard spectrogram according to the Euclidean distance formula, wherein the larger the distance between the two vectors is, the smaller the similarity is
Comparing for many times, and taking an arithmetic mean value of all the gray value differences obtained by calculation as a gray value difference final value L of the inspection spectrogram and the standard spectrogram of the part to be detected;
because the distance value is larger due to the larger image width, the value of L needs to be normalized, so that the images with different widths can be placed under a reference standard surface for comparison, and the normalization formula is as follows
L/(255 × sqrt (n)) (5);
wherein N represents the width of the image;
finally, the similarity S between the inspection spectrogram of the part to be detected and the standard spectrogram is obtained through the following calculation expression
100% -V formula (6);
when the similarity reaches more than 95%, the material of the current part to be detected and the material represented by the standard spectrogram are considered to be the same material; when the similarity is between 80% and 95%, manual intervention is needed for judgment and determination; and when the similarity is less than 80%, determining that the material of the current part to be detected and the material represented by the standard spectrogram are not the same material, and the two materials are different.
In this embodiment, because some mechanical errors can appear in the motor in the actual use process, when leading to the inspection spectral image of collection and standard spectral image to compare, the deviation can appear in the actual result, so this embodiment adopts many times to compare through the mode of image alignment, has eliminated above-mentioned mechanical error, and concrete process is as follows:
firstly, acquiring the contrast range (X) of a standard spectrogram1，X2) During detection, the range of the distance between the two images is determined by taking the range of the standard spectrogram as the standard, and the actual range of the inspection spectrogram of the part to be detected, which is acquired during production and acquisition, is larger than the range of the standard spectrogram, so that a constant delta X is set to represent the allowable error range of the images and is used for improving the contrast area of the images, the contrast range of the inspection spectrogram of the part to be detected is expanded according to the constant delta X, and the contrast range of the inspection spectrogram of the part to be detected after the expansion is (X) the contrast range of the inspection spectrogram of the part to be detected1-Δx，X2+ Δ x), the actual range of the inspection spectrogram of the part to be measured is 2 Δ x more than the range of the standard spectrogram, so the whole comparison process is changed, and the comparison times are changed from the original onesTo 2 x times now, that is:
when the first comparison is carried out, the range of the inspection spectrogram of the part to be detected is (X)1-Δx，X2-Δx)；
When the comparison is carried out for the second time, the range of the inspection spectrogram of the part to be detected is (X)1-Δx+1，X2-Δx+1)；
…
When the 2 Deltax is compared, the inspection spectrogram of the part to be detected has the range of (X)1+Δx，X2+Δx)；
Wherein 1 represents a pixel point of the image;
therefore, in actual detection, the comparison range of the inspection spectrogram of the to-be-detected part and the comparison range of the standard spectrogram need to be compared each time, the gray value difference between the inspection spectrogram of the to-be-detected part and the standard spectrogram is obtained by calculation according to the euclidean distance formula, and finally 2 Δ x gray value differences are obtained, then the arithmetic mean value is taken as the final value of the gray value difference between the inspection spectrogram of the to-be-detected part and the standard spectrogram, and finally the arithmetic mean value is normalized to calculate the similarity between the inspection spectrogram of the to-be-detected part and the standard spectrogram.
Example 3
The embodiment discloses a material analysis detection device based on image recognition technology, refers to description attached drawing 2, mainly includes spectral observation mirror 1, industrial camera 2, servo motor 3, sign recognizer 4, display 5 and computer 6, computer 6 is connected with spectral observation mirror 1, industrial camera 2, servo motor 3, sign recognizer 4 and display 5 respectively, for the control terminal of whole device, spectral observation mirror 1 is a prior art, is the finished product equipment on sale on the market, and industrial camera 2 passes through camera mount pad 7 and sets up on the eyepiece of spectral observation mirror 1, and servo motor 3's output is connected with the knob on the spectral observation mirror 1, sign recognizer 4 is the RFID ware that reads.
Further, referring to the attached drawing 2 of the specification, the camera mounting base 7 includes a lens adapter ring 71 and a camera support 72, one end of the lens adapter ring 71 is connected with the lens of the industrial camera 2, the other end of the lens adapter ring is connected with the eyepiece of the spectoscope 1, the camera support 72 is formed by connecting two half-piece supports in a closing manner, the two half-piece supports are closed to form a closing portion after being connected in a closing manner, the lens of the industrial camera 2 and the eyepiece of the spectoscope 1 are located in the closing portion, and the two half-piece supports are fixedly connected through fastening bolts.
When detection is carried out, firstly, a label recognizer is used for scanning an identification label of a part to be detected, so that related information of the part to be detected, including the detection number and the label of the part, is obtained, then the information is transmitted to a computer host, a sample standard database is stored in the computer host, the sample standard database comprises standard data information such as the label of each type of material, a standard spectrogram and the like, the computer host searches and matches the material type of the corresponding part in the database according to the label of the part to be detected, and finally determines and obtains a compared standard spectrogram according to the material type of the part; then, placing a part to be detected on a detection platform of a spectral mirror, starting a switch, firstly exciting the spectral mirror to generate sparks by a computer host, forming a corresponding spectral image by the spectral mirror while generating the sparks, then controlling a servo motor to rotate by the computer host, driving a knob of the spectral mirror to rotate to a specified position by the servo motor, then controlling an industrial camera to take a picture by the computer host, converting the acquired spectral image into a digital image with a coordinate relation, splicing the acquired spectral images in sequence by using a coordinate system, finally forming an inspection spectrogram of the part to be detected, and displaying the inspection spectrogram in a display; and finally, comparing the inspection spectrogram of the current part to be detected with the standard spectral image by the computer host, finally outputting a judgment result, and transmitting the result to the display.
In this embodiment, the sample standard database is established by manually inputting relevant standard data of the material at the initial stage, and the database is automatically learned, analyzed and compared by the system in the later stage during the use process, so that continuous automatic optimization of the database is realized, the standard data of the material in the database is continuously iterated, and the detection accuracy is finally further improved.
In the description of the present application, it is to be understood that the terms "center", "longitudinal", "lateral", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience in describing the present application and for simplifying the description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed in a particular orientation, and be operated, and therefore should not be construed as limiting the scope of the present application.
The foregoing is directed to embodiments of the present invention, which are not limited thereto, and any simple modifications and equivalents thereof according to the technical spirit of the present invention may be made within the scope of the present invention.
Claims (6)
1. A material analysis and detection method based on an image recognition technology is characterized in that: the method specifically comprises the following steps:
acquiring information of the part to be detected: before detection, firstly scanning an identification label of a part to be detected, acquiring the detection number of the part to be detected and the label of the part, and finally determining a compared standard spectrogram;
a spectral image acquisition step: placing a part to be detected on a detection platform of a spectral mirror, starting a switch, firstly exciting the spectral mirror to generate sparks by a computer host, then controlling a servo motor to rotate, driving a knob of the spectral mirror to rotate to a specified position by the servo motor, controlling an industrial camera to take a picture by the computer host, converting a collected spectral image into a digital image containing a coordinate relation, then sequentially splicing a plurality of collected spectral images by using a coordinate system to form an inspection spectrogram of the part to be detected, and finally displaying the inspection spectrogram in a display;
comparing the spectral images and judging results: and comparing the inspection spectrogram of the current part to be detected with the standard spectral image, calculating the similarity of the images, and then judging the result.
2. The material analysis and detection method based on the image recognition technology as claimed in claim 1, wherein: the steps of comparing the spectral images and judging the result are as follows:
an image digitalizing step: converting the RGB color value of each pixel point on the inspection spectrum image of the part to be detected into the gray value of the pixel point, and establishing a gray value matrix according to the gray value of the pixel point
Calculating the arithmetic mean value of the gray value of each row of the matrix, and combining the gray value mean values of each row to obtain the characteristic value vector of the inspection spectral image of the part to be detected
C＝[g1，g2，g3，...，gn]Formula (2);
wherein, gnThe nth characteristic value represents the inspection spectral image of the part to be detected;
matching image similarity: calculating the difference d between the n characteristic value of the inspection spectrogram and the n characteristic value of the standard spectrogram of the part to be detectedn
dn＝gn-g′nFormula (3);
wherein, gnDenotes an n-th characteristic value, g'nAn nth characteristic value representing a standard spectral image;
comparing the inspection spectrogram of the part to be detected with the standard spectrogram, and calculating the gray value difference L 'between the inspection spectrogram of the part to be detected and the standard spectrogram according to a Euclidean distance formula'
Comparing for many times, and taking an arithmetic mean value of all the gray value differences obtained by calculation as a final value L of the gray value difference between the inspection spectrogram of the part to be detected and the standard spectrogram;
normalizing the final value L of the gray value difference between the inspection spectrogram of the part to be detected and the standard spectrogram according to the following expression
L/(255 × sqrt (n)) (5);
where N represents the width of the image.
Finally, the similarity S between the inspection spectrogram of the part to be detected and the standard spectrogram is obtained through the following calculation expression
100% -V formula (6).
3. The material analysis and detection method based on the image recognition technology as claimed in claim 2, wherein: the calculation expression for converting the RGB color value of each pixel point into the gray value of the pixel point is as follows:
wherein R represents red, G represents green, and B represents blue.
4. The material analysis and detection method based on the image recognition technology as claimed in claim 1, wherein: when the display displays the spectral image, the standard spectral image and the inspection spectral image of the part to be detected are displayed together, so that whether the part is qualified or not can be conveniently and manually confirmed.
5. The material analysis and detection method based on the image recognition technology as claimed in claim 1, wherein: the device for completing the method is a material analysis and detection device based on an image recognition technology, the device comprises a spectral lens, an industrial camera, a servo motor, a label recognizer, a display and a computer host, the computer host is respectively connected with the spectral lens, the industrial camera, the servo motor, the label recognizer and the display, and is a control terminal of the whole device and used for triggering the spectral lens, the industrial camera, the servo motor and the label recognizer to work, receiving data transmitted by the industrial camera and the label recognizer and processing the data, and realizing man-machine information interaction with an operator through the display; the spectral viewer is used for generating electric sparks and spectral images; the industrial camera is arranged on an eyepiece of the spectoscope and used for collecting a spectral image of a part to be measured; the output end of the servo motor is connected with a knob of the spectometer lens and used for driving the knob to rotate; the label recognizer is used for scanning and recognizing the recognition label of the part to be detected.
6. The material analysis and detection method based on the image recognition technology as claimed in claim 5, wherein: the industrial camera is arranged on the spectral finder through the camera mounting seat, the camera mounting seat comprises a lens adapter ring and a camera support, one end of the lens adapter ring is connected with a lens of the industrial camera, the other end of the lens adapter ring is connected with an ocular of the spectral finder, the camera support is formed by connecting two half supports in a closing mode, the two half supports are enclosed, a closing portion is formed after the closing connection, the lens of the industrial camera and the ocular of the spectral finder are located in the closing portion, and the two half supports are fixedly connected through fastening bolts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111534072.0A CN114266741A (en) | 2021-12-15 | 2021-12-15 | Material analysis and detection method based on image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111534072.0A CN114266741A (en) | 2021-12-15 | 2021-12-15 | Material analysis and detection method based on image recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114266741A true CN114266741A (en) | 2022-04-01 |
Family
ID=80827304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111534072.0A Pending CN114266741A (en) | 2021-12-15 | 2021-12-15 | Material analysis and detection method based on image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114266741A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117589779A (en) * | 2023-11-28 | 2024-02-23 | 苏州瑞德智慧精密科技股份有限公司 | Visual inspection system and hardware fitting forming equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107843566A (en) * | 2017-10-13 | 2018-03-27 | 上海工程技术大学 | A kind of textile component detection means and method |
| CN107870164A (en) * | 2017-10-16 | 2018-04-03 | 合肥学院 | A kind of material detection system and application method based on laser Induced Fluorescence Technology |
| US20200364835A1 (en) * | 2018-01-31 | 2020-11-19 | Nec Corporation | Image processing device, image processing method and storage medium |
-
2021
- 2021-12-15 CN CN202111534072.0A patent/CN114266741A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107843566A (en) * | 2017-10-13 | 2018-03-27 | 上海工程技术大学 | A kind of textile component detection means and method |
| CN107870164A (en) * | 2017-10-16 | 2018-04-03 | 合肥学院 | A kind of material detection system and application method based on laser Induced Fluorescence Technology |
| US20200364835A1 (en) * | 2018-01-31 | 2020-11-19 | Nec Corporation | Image processing device, image processing method and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| RECEP DEMIRCI: "Similarity relation matrix-based color edge detection", 《AEU - INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS》, 2 July 2007 (2007-07-02), pages 469 - 477 * |
| 固态二氧化碳: "RGB(RGI/RGV)颜色亮度计算公式", 《HTTPS://WWW.CNBLOGS.COM/DRYICE/P/12333381.HTML》, 25 September 2019 (2019-09-25), pages 1 * |
| 杨翊艺: "高光谱异常检测算法研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》, 15 May 2021 (2021-05-15), pages 028 - 101 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117589779A (en) * | 2023-11-28 | 2024-02-23 | 苏州瑞德智慧精密科技股份有限公司 | Visual inspection system and hardware fitting forming equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9076068B2 (en) | Method and apparatus for evaluating color in an image | |
| US7463757B2 (en) | Tooth locating within dental images | |
| US20070035554A1 (en) | Method of visualizing a color deviation | |
| CN102213618A (en) | Color measuring apparatus and color measuring method | |
| CN101267494A (en) | Color correction table generation method and compound color measuring separation method for digital video device | |
| CN104777172A (en) | Quick and intelligent defective optical lens detection device and method | |
| US11614362B1 (en) | Method of digital measuring color of fabrics based on digital camera | |
| JPH02112713A (en) | Method and device for identifying state of surface finishing of metal | |
| CN109596054A (en) | The size detection recognition methods of strip workpiece | |
| CN109984719A (en) | A kind of visual color access function detection method and system | |
| US5585872A (en) | Ophthalmic measuring apparatus for determining the shape of the cornea of an eye | |
| CN102414722A (en) | Display of effect coatings on electronic display devices | |
| CN113624458B (en) | Film uniformity detecting system based on double-path full-projection light | |
| CN114266741A (en) | Material analysis and detection method based on image recognition technology | |
| CN112488997B (en) | Method for detecting and evaluating color reproduction of ancient painting printed matter based on characteristic interpolation | |
| CN116297496B (en) | Multispectral intelligent defect detection method | |
| CN115876086B (en) | Detection method and detection system for high-density connector | |
| CN108593113A (en) | A kind of processing method and system of color identification | |
| CN115776560B (en) | Image stitching and repairing processing system and method based on naked eye 3D technology | |
| CN115638962A (en) | Optical performance measurement method of near-to-eye display equipment based on binocular camera | |
| CN116386498A (en) | Quantitative evaluation data set construction method, device and equipment | |
| CN115900578A (en) | Three-dimensional model visualization system based on pressure vessel design | |
| JP3759904B2 (en) | Skin color evaluation device | |
| CN110174351B (en) | Color measuring device and method | |
| CN112858331A (en) | VR screen detection method and detection system |
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 |