CN112926447A - Electric power material automatic discrimination method based on image feature recognition - Google Patents
Electric power material automatic discrimination method based on image feature recognition Download PDFInfo
- Publication number
- CN112926447A CN112926447A CN202110206650.1A CN202110206650A CN112926447A CN 112926447 A CN112926447 A CN 112926447A CN 202110206650 A CN202110206650 A CN 202110206650A CN 112926447 A CN112926447 A CN 112926447A
- Authority
- CN
- China
- Prior art keywords
- image
- electric power
- matching
- return value
- sift
- 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
- 239000000463 material Substances 0.000 title claims abstract description 101
- 238000012850 discrimination method Methods 0.000 title description 2
- 238000000034 method Methods 0.000 claims abstract description 65
- 239000010421 standard material Substances 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 238000013479 data entry Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims 2
- 239000002994 raw material Substances 0.000 claims 2
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 description 8
- 238000004088 simulation Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000013095 identification testing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an automatic electric power material distinguishing method based on image feature recognition, which comprises the steps of establishing a standard material database based on an SIFT algorithm and storing an appearance image of a material; extracting an executable program of SIFT (scale invariant feature transform) features of the image by using a software programming technology to complete image matching; and according to the matching result, identifying the field information in the standard material database item to which the material belongs, and outputting the field information to an input interface of a user to finish material classification identification. The invention implements automatic classification recognition of the electric power materials based on information technology means and SIFT algorithm, is applied to actual production work, and can greatly improve the efficiency and accuracy of the classification recognition of the electric power materials.
Description
Technical Field
The invention relates to the technical field of image feature recognition, in particular to an automatic electric power material distinguishing method based on image feature recognition.
Background
At present, the variety of materials managed by the electric power material management department is various, and although there is "electric power material classification and coding guide rule" which can be referred to in the implementation of the electric power material informatization management process, due to the variety and the complex classification level, it is not easy to specify the attribute and the coding of a specific material in the actual work development process.
When a typical material management department records basic material information, the material classification operation efficiency is extremely low, and the material classification operation is also frequently mistaken, which causes great trouble to subsequent material transfer and information change.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides an automatic electric power material distinguishing method based on image feature recognition, which can solve the problems of low material classifying efficiency and high possibility of errors caused by manual judgment.
In order to solve the technical problems, the invention provides the following technical scheme: establishing a standard material database based on an SIFT algorithm and storing material appearance images; extracting an executable program of SIFT (scale invariant feature transform) features of the image by using a software programming technology to complete image matching; and according to the matching result, identifying the field information in the standard material database item to which the material belongs, and outputting the field information to an input interface of a user to finish material classification identification.
As a preferable scheme of the method for automatically distinguishing electric power materials based on image feature recognition of the present invention, the method comprises: the standard material database is established based on a relational database, and the data table field comprises material names, material classification codes and 3-5 material appearance images.
As a preferable scheme of the method for automatically distinguishing electric power materials based on image feature recognition of the present invention, the method comprises: the executable program for extracting the SIFT features of the image comprises the step of calling an OpenCV library for extraction in a console of a Visual Studio2010, and the executable program is named GetSIFT.
As a preferable scheme of the method for automatically distinguishing electric power materials based on image feature recognition of the present invention, the method comprises: the image matching is completed by calling the executable program GetSIFT. exe and combining with a Euclidean distance matching method, each feature point in one image is defined, and the distance d1 of the feature point closest to the feature point and the distance d2 of the next closest feature point are found in the other image; if d1/d2 is less than 0.6, image matching is accepted, and the matching rate is calculated; if the matching rate is more than 50%, the matching is successful, the return value of the method is TRUE, otherwise, the return value of the method is FALSE.
As a preferable scheme of the method for automatically distinguishing electric power materials based on image feature recognition of the present invention, the method comprises: and in the actual integrated application, when a user needs to confirm input of a material classification, uploading an actual material picture, calling a system to finish an image matching strategy, if the method return value is TRUE, matching is successful, outputting the material name, the material classification name and the material classification code field information of the data entry corresponding to the standard material database on an interface, and if all the data entries of the standard material database are traversed and not matched, outputting the matched entry by the interface, and asking for manual input.
As a preferable scheme of the method for automatically distinguishing electric power materials based on image feature recognition of the present invention, the method comprises: extracting the SIFT features of the image comprises the steps of carrying out initialization processing on an input image, and establishing a Gaussian pyramid and a DOG pyramid; carrying out scale space extreme point detection and accurate positioning on the pyramid; and calculating the scale, the main direction and the descriptors of the key points, and generating SIFT feature vectors according to the calculation result.
As a preferable scheme of the method for automatically distinguishing electric power materials based on image feature recognition of the present invention, the method comprises: uploading a material image to be detected, traversing all data entries in the standard material database, and judging whether data information is included; if yes, extracting a standard material image, calling an SIFT algorithm to judge a return value, if not, displaying that no matching item is found on an output interface, and manually inputting; and if the return value is TRUE, directly outputting the goods name, the goods classification name and the goods classification code, and if the return value is FALSE, traversing again.
As a preferable scheme of the method for automatically distinguishing electric power materials based on image feature recognition of the present invention, the method comprises: if the SIFT match algorithm is directly called by the uploaded material image to be detected, the return value is judged; and if the return value is TRUE, directly outputting the goods name, the goods classification name and the goods classification code, and if the return value is FALSE, traversing again.
The invention has the beneficial effects that: the invention implements automatic classification recognition of the electric power materials based on information technology means and SIFT algorithm, is applied to actual production work, and can greatly improve the efficiency and accuracy of the classification recognition of the electric power materials.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flowchart of an automatic electric power material distinguishing method based on image feature recognition according to a first embodiment of the present invention;
fig. 2 is a schematic view of a SIFT feature extraction flow of the method for automatically distinguishing electric power materials based on image feature recognition according to the first embodiment of the present invention;
fig. 3 is a schematic flow chart of a matching algorithm of the method for automatically distinguishing electric power materials based on image feature recognition according to the first embodiment of the present invention;
fig. 4 is a schematic diagram illustrating an integrated application flow of the method for automatically discriminating electric power materials based on image feature recognition according to the first embodiment of the present invention;
fig. 5 is a diagram illustrating an accuracy comparison curve of an automatic power material determination method based on image feature recognition according to a second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1 to 4, a first embodiment of the present invention provides an automatic power material determination method based on image feature recognition, which specifically includes:
s1: and establishing a standard material database based on a SIFT algorithm (scale invariant feature transform, a descriptor for graphic processing) and storing material appearance images. Referring to fig. 2, it should be noted that, establishing the standard material database includes:
and establishing a data table based on the relational database, wherein the data table field comprises a material name, a material classification code and 3-5 material appearance images.
Specifically, the executable program for extracting the SIFT features of the image comprises the following steps:
calling an OpenCV library in a console of Visual Studio2010 for extraction, wherein an executable program is named GetSIFT.exe and extracts SIFT features of one image;
initializing an input image, and establishing a Gaussian pyramid and a DOG pyramid;
carrying out scale space extreme point detection and accurate positioning on the pyramid;
and calculating the scale, the main direction and the descriptors of the key points, and generating SIFT feature vectors according to the calculation result.
S2: and (3) extracting an executable program of SIFT (scale invariant feature transform) features of the image by using a software programming technology to complete image matching. Referring to fig. 3, this step is to be described that completing image matching includes:
invoking an executable program GetSIFT.exe, combining with a Euclidean distance matching method to complete, defining each feature point in one image, and finding the distance d1 of the feature point closest to the feature point and the distance d2 of the next closest feature point in the other image;
if d1/d2 is less than 0.6, image matching is accepted, and the matching rate is calculated;
if the matching rate is more than 50%, the matching is successful, the return value of the method is TRUE, otherwise, the return value of the method is FALSE.
S3: and according to the matching result, identifying field information in the standard material database item to which the material belongs, and outputting the field information to an input interface of a user to finish material classification identification. Referring to fig. 4, it is further to be noted that the implementation of material classification and identification includes integrated application:
in practical integrated application, when a user needs to confirm input of a material classification, an actual material picture is uploaded, an image matching strategy is completed through system calling, if the method return value is TRUE, matching is successful, the material name, the material classification name and the material classification code field information of a data entry corresponding to a standard material database are output on an interface, if all data entries of the standard material database are traversed and not matched, the interface outputs that a matching item is not found, and manual input is required.
Specifically, still include:
uploading a material image to be detected, traversing all data entries in a standard material database, and judging whether data information is included;
if yes, extracting a standard material image, calling an SIFT algorithm to judge a return value, if not, displaying that no matching item is found on an output interface, and manually inputting;
if the return value is TRUE, directly outputting the material name, the material classification name and the material classification code, and if the return value is FALSE, traversing again;
if the SIFT algorithm is directly called by uploading the material image to be detected, judging a return value;
if the return value is TRUE, the material name, the material classification name and the material classification code are directly output, and if the return value is FALSE, the traversal is carried out again.
Generally speaking, in the embodiment, based on the SIFT algorithm principle, a standard material database is established through a software information technology and a material appearance image is stored, an executable program for extracting the SFIT features of an image and a method for completing image matching are respectively realized based on a software programming technology, in practical integration application, when a user needs to confirm input of classification of a material, a practical material picture is uploaded, and field information in a standard material database item to which the material belongs is identified and output to an input interface of the user based on the executable program for extracting the SFIT features of the image and the method for completing image matching, so that the application for assisting in quickly performing material classification identification is achieved, and the problems that manual judgment of low material classification efficiency and high possibility of errors are solved.
Preferably, the method is based on the SIFT algorithm principle, combines the establishment of a standard database and a template image, achieves accurate identification of electric power materials by comparing SIFT characteristics, is realized based on Matlab, releases dll dynamic link library, and can be flexibly suitable for integrated application of different scenes.
Example 2
Referring to fig. 5, a second embodiment of the present invention is different from the first embodiment in that the test verification of the automatic electric power material distinguishing method based on image feature recognition is provided, which specifically includes:
in order to better verify and explain the technical effects adopted in the method of the invention, the embodiment selects the traditional deep learning image identification method and the method of the invention to carry out comparison test, compares the test results by means of scientific demonstration, and verifies the real effect of the method of the invention.
In order to verify that the method has higher discrimination accuracy and efficiency compared with the traditional method, the traditional technical scheme and the method are adopted to respectively carry out real-time measurement and comparison on the material image to be detected in the simulation platform.
And (3) testing environment: running an image to be detected on a simulation platform to simulate a detection scene, adopting an image of electric power material equipment from 3 months to 9 months of a certain power supply bureau in the south of 2019 as a test sample, respectively carrying out identification test by utilizing a neural network algorithm of a traditional method and obtaining test result data; by adopting the method, the automatic test equipment is started, MATLB is used for realizing the simulation programming of the method, the simulation data are obtained according to the experimental result, 1000 groups of data are tested by the two methods, the time for obtaining each group of data is calculated, and the error calculation is carried out by comparing with the actual predicted value input by the simulation.
Referring to fig. 5, it can be seen intuitively that the trend of the solid line (the method of the present invention) is more stable than the trend of the dotted line (the traditional method), and the dotted line is steep (i.e. unstable, suddenly high and suddenly low), under the same detection and comparison conditions of the test sample, the curve value output by the method of the present invention is far higher than the curve value output by the traditional method, and the authenticity of the technical effect adopted by the method of the present invention is verified.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (8)
1. An electric power material automatic distinguishing method based on image feature recognition is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
establishing a standard material database based on an SIFT algorithm and storing material appearance images;
extracting an executable program of SIFT (scale invariant feature transform) features of the image by using a software programming technology to complete image matching;
and according to the matching result, identifying the field information in the standard material database item to which the material belongs, and outputting the field information to an input interface of a user to finish material classification identification.
2. The method for automatically distinguishing electric power materials based on image feature recognition according to claim 1, wherein: establishing the standard supplies database includes establishing a standard supplies database,
and establishing a data table based on a relational database, wherein the data table field comprises a material name, a material classification code and 3-5 material appearance images.
3. The method for automatically discriminating electric power materials based on image feature recognition according to claim 1 or 2, wherein: the executable program for extracting the SIFT features of the image comprises,
an OpenCV library is called in a console of the VisualStaudio 2010 for extraction, and the executable program is named GetSIFT.
4. The method for automatically distinguishing electric power materials based on image feature recognition according to claim 3, wherein: the completion of the image matching includes the completion of,
calling the executable program GetSIFT.exe and combining with a Euclidean distance matching method to complete, defining each feature point in one image, and finding the distance d1 between the feature point closest to the feature point and the distance d2 between the next closest feature point in the other image;
if d1/d2 is less than 0.6, image matching is accepted, and the matching rate is calculated;
if the matching rate is more than 50%, the matching is successful, the return value of the method is TRUE, otherwise, the return value of the method is FALSE.
5. The method for automatically distinguishing electric power materials based on image feature recognition according to claim 4, wherein: completing the material classification identification comprises integrating the application,
in practical integrated application, when a user needs to confirm input of a material classification, an actual material picture is uploaded, an image matching strategy is completed through system calling, if the method return value is TRUE, matching is successful, the material name, the material classification name and the material classification code field information of the data entry corresponding to the standard material database are output on an interface, and if all the data entries of the standard material database are traversed and not matched, the interface outputs that a matching item is not found, and manual input is requested.
6. The method for automatically discriminating electric power materials based on image feature recognition according to claim 1 or 5, wherein: the extracting of the SIFT features of the image comprises,
initializing an input image, and establishing a Gaussian pyramid and a DOG pyramid;
carrying out scale space extreme point detection and accurate positioning on the pyramid;
and calculating the scale, the main direction and the descriptors of the key points, and generating SIFT feature vectors according to the calculation result.
7. The method for automatically distinguishing electric power materials based on image feature recognition according to claim 6, wherein: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
uploading a material image to be detected, traversing all data entries in the standard material database, and judging whether data information is included;
if yes, extracting a standard material image, calling an SIFT algorithm to judge a return value, if not, displaying that no matching item is found on an output interface, and manually inputting;
and if the return value is TRUE, directly outputting the goods name, the goods classification name and the goods classification code, and if the return value is FALSE, traversing again.
8. The method for automatically distinguishing electric power materials based on image feature recognition according to claim 7, wherein: also comprises the following steps of (1) preparing,
if the SIFT match algorithm is directly called by the uploaded material image to be detected, the return value is judged;
and if the return value is TRUE, directly outputting the goods name, the goods classification name and the goods classification code, and if the return value is FALSE, traversing again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110206650.1A CN112926447A (en) | 2021-02-24 | 2021-02-24 | Electric power material automatic discrimination method based on image feature recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110206650.1A CN112926447A (en) | 2021-02-24 | 2021-02-24 | Electric power material automatic discrimination method based on image feature recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112926447A true CN112926447A (en) | 2021-06-08 |
Family
ID=76171565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110206650.1A Pending CN112926447A (en) | 2021-02-24 | 2021-02-24 | Electric power material automatic discrimination method based on image feature recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112926447A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069144A (en) * | 2015-08-20 | 2015-11-18 | 华南理工大学 | Similar image search method |
| CN105550381A (en) * | 2016-03-17 | 2016-05-04 | 北京工业大学 | Efficient image retrieval method based on improved SIFT (scale invariant feature transform) feature |
| CN109685075A (en) * | 2018-11-27 | 2019-04-26 | 山东鲁能软件技术有限公司 | A kind of power equipment recognition methods based on image, apparatus and system |
-
2021
- 2021-02-24 CN CN202110206650.1A patent/CN112926447A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069144A (en) * | 2015-08-20 | 2015-11-18 | 华南理工大学 | Similar image search method |
| CN105550381A (en) * | 2016-03-17 | 2016-05-04 | 北京工业大学 | Efficient image retrieval method based on improved SIFT (scale invariant feature transform) feature |
| CN109685075A (en) * | 2018-11-27 | 2019-04-26 | 山东鲁能软件技术有限公司 | A kind of power equipment recognition methods based on image, apparatus and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110717534B (en) | Target classification and positioning method based on network supervision | |
| KR20190116199A (en) | Video data processing method, device and readable storage medium | |
| CN109446885B (en) | Text-based component identification method, system, device and storage medium | |
| US20150269149A1 (en) | Storing and searching fingerprints derived from media content based on a classification of the media content | |
| CN114078008A (en) | Abnormal behavior detection method, device, equipment and computer readable storage medium | |
| CN111553176A (en) | Wireless transmission checking method and system suitable for wiring of transformer substation cubicle | |
| CN107077617B (en) | Fingerprint extraction method and device | |
| CN116932499B (en) | Method for modifying labels of DWG format files in batches | |
| CN113255752A (en) | Solid material consistency sorting method based on feature clustering | |
| CN112926447A (en) | Electric power material automatic discrimination method based on image feature recognition | |
| CN115620083B (en) | Model training method, face image quality evaluation method, equipment and medium | |
| CN112818068A (en) | Big data and multidimensional feature-based data tracing method and system | |
| CN115310606A (en) | Deep learning model depolarization method and device based on data set sensitive attribute reconstruction | |
| CN114116456A (en) | Test case generation method, system and computer readable storage medium | |
| CN111310536A (en) | Machine continuous learning method for neural network object classification and monitoring camera equipment thereof | |
| CN112818160B (en) | Furniture retrieval method and device based on furniture style | |
| KR102632771B1 (en) | System and method for extracting data of catalog image | |
| CN116257488B (en) | Geotechnical engineering investigation big data archiving method, device, electronic equipment and medium | |
| CN116883794B (en) | Spatial structure cognitive ability evaluation method and system based on graph attention network | |
| CN117994822B (en) | Cross-mode pedestrian re-identification method based on auxiliary mode enhancement and multi-scale feature fusion | |
| CN111221995B (en) | Sequence matching method based on big data and set theory | |
| CN111062419B (en) | Compression and recovery method for deep learning data set | |
| CN112597833A (en) | Processing method and electronic equipment | |
| JP2778562B2 (en) | Figure retrieval device | |
| CN117829737A (en) | Material information verification 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 |