CN115510260A - Target image retrieval method and system - Google Patents
Target image retrieval method and system Download PDFInfo
- Publication number
- CN115510260A CN115510260A CN202211171625.5A CN202211171625A CN115510260A CN 115510260 A CN115510260 A CN 115510260A CN 202211171625 A CN202211171625 A CN 202211171625A CN 115510260 A CN115510260 A CN 115510260A
- Authority
- CN
- China
- Prior art keywords
- image
- target image
- target
- retrieval
- snap
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/535—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Library & Information Science (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to the technical field of information retrieval, in particular to a target image retrieval method and a target image retrieval system, which comprise the following steps: acquiring a target image, and extracting the identification characteristics of the target image; comparing the identification features of the target image with the identification features of the registered image and the non-registered image, and calculating the similarity; outputting all images with similarity greater than the same target threshold; screening a snap-shot image list from a snap-shot image database according to an output image; and comparing and outputting the snapshot images with the similarity higher than the similarity threshold of the retrieval condition. According to the invention, the registered target and the unregistered target are screened out by using the preset same target threshold, the snap-shot images meeting the conditions are obtained from the snap-shot image database according to the target retrieval conditions for comparison, so that a large amount of blind search of the database is avoided, and the database query process is replaced by algorithm comparison calculation aiming at the target, so that the recognition speed and efficiency are improved, the time consumption of search is reduced, and the target image retrieval is quicker.
Description
Technical Field
The invention relates to the technical field of information retrieval, in particular to a target image retrieval method and a target image retrieval system.
Background
Along with the gradual popularization of artificial intelligence deep learning, the accuracy and the performance of a face recognition algorithm are continuously improved, the face recognition technology is continuously advanced and matured in the development process, and the rich application scenes attract a wide market space, wherein one of the important applications is the comparison and retrieval of a target face picture. Target image retrieval, also called graph search, is an image retrieval technique based on target content, which takes a picture as a query object and returns an image record most similar to the query image content in a large number of image records.
The core process of the image searching algorithm is two: one is feature extraction, which is mainly responsible for extracting visual features from an image so as to obtain a high-dimensional feature vector, wherein the more similar images in the high-dimensional feature space are closer to each other; and the second is image retrieval which is mainly responsible for searching a plurality of image records closest to the characteristics of the query target image in a mass image characteristic set and returning a retrieval result. The difficulty in searching images with images is image retrieval, which is how to perform efficient searches from a vast data set. In the prior art, query search needs to be carried out from mass data stored in a database, which is undoubtedly quite time-consuming, so that the problems of low target image retrieval efficiency and slow response speed exist.
Disclosure of Invention
The invention provides a target image retrieval method and a target image retrieval system, which are used for overcoming the defects in the prior art, and the target image retrieval method and the system adopt a mode of comparing target images for many times, classify and update an image library, and can improve the efficiency and response speed of target image retrieval.
The invention provides a target image retrieval method, which comprises the following steps:
s1, acquiring a target image retrieval request and determining retrieval conditions;
s2, acquiring a corresponding target image according to the target image retrieval request, and extracting the identification characteristics of the target image;
s3, comparing the identification features of the target image with the identification features in the registered image database and the unregistered image database in sequence, and calculating to obtain the similarity of the identification features of the target image;
s4, outputting a registered image and a non-registered image with the similarity value larger than a preset same target threshold value;
s5, screening a snap-shot image list meeting the retrieval condition from a snap-shot image database according to the screened registered image and/or unregistered image based on the retrieval condition;
and S6, comparing the identification features of the target image with the identification features of the snap-shot images in the snap-shot image list in sequence to output snap-shot images with the similarity higher than the similarity threshold in the retrieval condition, and judging the next target image if no snap-shot images with the similarity higher than the similarity threshold in the retrieval condition exist.
According to the target image retrieval method provided by the invention, the retrieval conditions comprise a retrieval time period, a snapshot device list, a similarity threshold value and the most similar image number.
According to the target image retrieval method provided by the invention, in step S4, if there are no target image and corresponding registered image and/or unregistered image with a similarity value greater than a preset similarity threshold, the next target image is determined.
According to the present invention, before step S1, a target image retrieval method includes:
establishing a registered target image library and a non-registered target image library, respectively extracting the characteristics of each registered target image and each non-registered target image, and establishing a corresponding identification characteristic library;
and establishing an image feature recognition training set according to the mapping relation between the recognition features and the registered target images and the unregistered target images, and training an image recognition model based on the training set.
The invention provides a target image retrieval method, which comprises the following steps:
and sequentially comparing the identification characteristics of the target image with the identification characteristics of the snap-shot images in the snap-shot list through the trained image identification model, and outputting the snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition.
In another aspect, the present invention further provides a target image retrieval system, including:
the data module is used for acquiring a target image retrieval request and determining retrieval conditions;
the query module is used for acquiring a corresponding target image according to the target image retrieval request and extracting the identification characteristics of the target image;
the first feature comparison module is used for comparing the recognition features of the target image with the recognition features in the registered image database and the unregistered image database in sequence and calculating the similarity of the obtained recognition features; outputting a registered image and a non-registered image with the similarity value larger than a preset same target threshold value;
the screening module is used for screening a snap-shot image list from a snap-shot image database according to the output registered image and/or the non-registered image based on the retrieval condition;
the second characteristic comparison module is used for sequentially comparing the identification characteristics of the target image with the identification characteristics of the snap-shot images in the snap-shot image list and outputting the snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition; and if the snapshot image with the similarity higher than the similarity threshold in the retrieval condition does not exist, returning to the data module to judge the next target image.
The invention also provides an electronic device, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the target image retrieval method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the target image retrieval method as described in any of the above.
Compared with the prior art, the target image retrieval method and the target image retrieval system provided by the invention have the following beneficial effects:
1) In the real-time monitoring process, the snapshot image of the acquisition equipment is identified according to the target, which registered target or non-registered target corresponds to the snapshot image is judged in advance, a data basis is provided for subsequent image retrieval, comparison and judgment of a large number of snapshot images are avoided blindly, and comparison and analysis are carried out on the target.
2) The same target threshold corresponding to the algorithm is set, and the threshold is different from the threshold set in the retrieval condition, so that the retrieval process is prevented from depending on the retrieval threshold, too many or too few target objects are retrieved due to too small or too large setting of the retrieval threshold, and the calculation amount of identification feature comparison is influenced. According to the scheme, the threshold judgment of the same target is carried out from the angle of the algorithm, and the accuracy of target identification is improved.
3) In the process of screening the unregistered target, query search is not carried out in the unregistered target database or the captured image database according to the retrieval conditions, so that the problem that the database query is time-consuming when the number of the unregistered target database or the captured image database is extremely large is solved, the database query process is replaced by algorithm comparison calculation, and the speed of retrieval comparison is actually improved.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a target image retrieval method provided by the present invention;
fig. 2 is a schematic structural diagram of a target image retrieval system provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "including" and "having," and any variations thereof, in the description and claims of this application and the drawings described above, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or modules is not limited to only those steps or modules recited, but may alternatively include other steps or modules not recited, or that are inherent to such process, method, article, or apparatus.
It should be noted that the term "first \ second" referred to in the present invention is only used for distinguishing similar objects, and does not represent a specific ordering for the objects, and it should be understood that "first \ second" may be interchanged in a specific order or sequence, if allowed. It should be understood that "first \ second" distinguishing objects may be interchanged under appropriate circumstances such that the embodiments of the invention described herein may be practiced in sequences other than those described or illustrated herein.
In one embodiment, as shown in fig. 1, the present invention provides a target image retrieval method, including the steps of:
s1, acquiring a target image retrieval request and determining retrieval conditions;
s2, acquiring a corresponding target image according to the target image retrieval request, and extracting the identification characteristics of the target image;
s3, comparing the identification features of the target image with the identification features in the registered image database and the unregistered image database in sequence, and calculating to obtain the similarity of the identification features of the target image;
s4, outputting a registered image and a non-registered image with the similarity value larger than a preset same target threshold value;
s5, screening a snap-shot image list from a snap-shot image database according to the output registered image and the output unregistered image based on the retrieval condition;
and S6, comparing the identification features of the target image with the identification features of the snap-shot images in the snap-shot image list in sequence to output the snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition, and judging the next target image if no snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition exist.
According to the target image retrieval method provided by the invention, the retrieval conditions comprise a retrieval time period, a snapshot device list, a similarity threshold value and the most similar image number;
it should be noted that the same target threshold and the similarity threshold in the search condition are different values, the same target threshold is trained according to a used algorithm to determine whether the targets in each image are the same, if the similarity obtained by comparing the recognition features exceeds the same target threshold, the targets in the images are considered to be the same, otherwise, the targets in the images are considered to be different. This same target threshold requires algorithm testing, with different algorithms corresponding to different target thresholds.
It should be noted that registered personnel and non-registered personnel are a relative concept, the registered personnel include registered personnel, other staff and the like, the non-registered personnel include visitors and clients, the snapshot database is used for monitoring randomly shot snapshot images in a place, the snapshot images may be the registered personnel or the non-registered personnel, and the personnel belonging to which category are judged according to a preset similarity threshold;
sequentially comparing the identification features of the target image with the identification features of the snap-shot images in the snap-shot list to output snap-shot images with similarity higher than a similarity threshold in a retrieval condition;
according to the target image retrieval method provided by the invention, in step S4, if there is no target image with a similarity value greater than a preset same target threshold and corresponding registered image and/or unregistered image, the next target image is determined.
According to the present invention, before step S1, a target image retrieval method includes:
establishing a registered target image library and a non-registered target image library, respectively extracting the characteristics of each registered target image and each non-registered target image, and establishing a corresponding identification characteristic library;
and establishing an image feature recognition training set according to the mapping relation between the recognition features and the registered target images and the unregistered target images, and training an image recognition model based on the training set.
The invention provides a target image retrieval method, which comprises the following steps:
and sequentially comparing the identification characteristics of the target image with the identification characteristics of the snap-shot images in the snap-shot list through the trained image identification model, and outputting the snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition.
The image recognition efficiency can be further improved through a neural network including the image recognition model, and rapid image feature comparison can be realized through the neural network;
in the steps of the present invention, for the purpose of target retrieval, the comparison process of the identification features is performed three times: comparing the retrieval target with all registered targets for the first time to obtain the registered target which is the same as the retrieval target; comparing the retrieval target with all non-registered targets for the second time to obtain the non-registered target which is the same as the retrieval target; and thirdly, searching from the snapshot image database according to the retrieval conditions and by combining the screened registered target and the screened unregistered target, and acquiring snapshot image data meeting the conditions. In the retrieval process, only one database search is used, namely, a snap-shot image list meeting the retrieval condition is screened. Tests show that 10 ten thousand pieces of data require about 3 minutes for data reading, 20 ten thousand pieces of data require about 6 minutes for data reading, and 50 ten thousand pieces of data require about 15 minutes for data reading. Therefore, the larger the storage amount of the database, the longer the time taken to read the data, and the longest the time taken to replace the above operation with the algorithm is not more than 2 seconds. The target retrieval method provided by the patent reduces the query times of the database, replaces the query operation of the database by algorithm comparison, and can effectively improve the speed and efficiency of target image retrieval through actual verification.
On the other hand, as shown in fig. 2, the present invention further provides a target image retrieval system, where the target image retrieval system described below and the target image retrieval method described above may be referred to correspondingly, and specifically includes:
the data module is used for acquiring a target image retrieval request and determining retrieval conditions;
the query module is used for acquiring a corresponding target image according to the target image retrieval request and extracting the identification characteristics of the target image;
the first feature comparison module is used for comparing the recognition features of the target image with the recognition features in the registered image database and the unregistered image database in sequence and calculating the similarity of the obtained recognition features; and outputting a registered image and a non-registered image with the similarity value larger than the same target threshold value;
the screening module is used for screening a snap-shot image list meeting the retrieval condition from a snap-shot image database according to the output registered image and/or the output unregistered image;
the second characteristic comparison module is used for sequentially comparing the identification characteristics of the target image with the identification characteristics of the snap-shot images in the snap-shot list and outputting the snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition; and if the snapshot image with the similarity higher than the similarity threshold in the retrieval condition does not exist, returning to the data module to judge the next target image.
The invention also provides an electronic device, comprising a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the steps of the target image retrieval method.
In another aspect, the present invention further provides a schematic physical structure diagram of an electronic device, where the electronic device may include: the system comprises a processor (processor), a communication interface (communication interface), a memory (memory) and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus. The processor may call logic instructions in the memory 830 to perform a target image retrieval method provided by the above methods, comprising the steps of: s1, acquiring a target image retrieval request and determining retrieval conditions; s2, acquiring a corresponding target image according to the target image retrieval request, and extracting the identification characteristics of the target image; s3, comparing the identification features of the target image with the identification features in the registered image database and the unregistered image database in sequence, and calculating the similarity of the identification features of the target image; s4, outputting a registered image and a non-registered image with the similarity value larger than a preset same target threshold value; s5, screening a snap-shot image list meeting the retrieval condition from a snap-shot image database according to the output registered image and/or the output unregistered image based on the retrieval condition; and S6, comparing the identification features of the target image with the identification features of the snap-shot images in the snap-shot image list in sequence to output the snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition, and judging the next target image if no snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition exist.
In addition, the logic instructions in the memory may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform a target image retrieval method provided by the above methods, including the steps of: s1, acquiring a target image retrieval request and determining retrieval conditions; s2, acquiring a corresponding target image according to the target image retrieval request, and extracting the identification characteristics of the target image; s3, comparing the identification features of the target image with the identification features in the registered image database and the unregistered image database in sequence, and calculating to obtain the similarity of the identification features of the target image; s4, outputting a registered image and a non-registered image with the similarity value larger than a preset same target threshold value; s5, screening a snap-shot image list meeting the retrieval condition from a snap-shot image database based on the retrieval condition and according to the output registered image and/or non-registered image; and S6, comparing the identification features of the target image with the identification features of the snap-shot images in the snap-shot image list in sequence to output snap-shot images with the similarity higher than the similarity threshold in the retrieval condition, and judging the next target image if no snap-shot images with the similarity higher than the similarity threshold in the retrieval condition exist.
In still another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to execute a target image retrieval method provided by the above methods, including the steps of: s1, acquiring a target image retrieval request and determining retrieval conditions; s2, acquiring a corresponding target image according to the target image retrieval request, and extracting the identification characteristics of the target image; s3, comparing the identification features of the target image with the identification features in the registered image database and the unregistered image database in sequence, and calculating to obtain the similarity of the identification features of the target image; s4, outputting a target image with the similarity value larger than a preset same target threshold value and/or a corresponding registered image and a corresponding unregistered image; s5, screening a snap-shot image list meeting the retrieval condition from a snap-shot image database according to the output registered image and/or the output unregistered image based on the retrieval condition; and S6, comparing the identification features of the target image with the identification features of the snap-shot images in the snap-shot image list in sequence to output the snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition, and judging the next target image if no snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition exist.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A target image retrieval method, comprising:
s1, acquiring a target image retrieval request and determining retrieval conditions;
s2, acquiring a corresponding target image according to the target image retrieval request, and extracting the identification characteristics of the target image;
s3, comparing the identification features of the target image with the identification features in the registered image database and the unregistered image database in sequence, and calculating the similarity of the identification features of the target image;
s4, outputting a registered image and a non-registered image with the similarity value larger than a preset same target threshold value;
s5, screening a snap-shot image list from a snap-shot image database according to the output registered image and/or the output unregistered image based on the retrieval condition;
and S6, comparing the identification features of the target image with the identification features of the snap-shot images in the snap-shot list in sequence to output the snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition, and judging the next target image if no snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition exist.
2. The method according to claim 1, wherein the search condition includes a search time period, a list of capturing devices, a similarity threshold, and a number of most similar images.
3. The method as claimed in claim 1, wherein in step S4, if there is no target image with a similarity value greater than a preset same target threshold and corresponding registered image and/or unregistered image, determining the next target image.
4. A target image retrieval method according to any one of claims 1 to 3, comprising, before step S1:
establishing a registered target image library and a non-registered target image library, respectively extracting the characteristics of each registered target image and each non-registered target image, and establishing a corresponding identification characteristic library;
and establishing an image feature recognition training set according to the mapping relation between the recognition features and the registered target images and the unregistered target images, and training an image recognition model based on the training set.
5. The method for retrieving the target image according to claim 4, comprising:
and sequentially comparing the recognition features of the target image with the recognition features of the snap-shot images in the snap-shot list through the trained image recognition model, and outputting the snap-shot images with the similarity higher than a similarity threshold value.
6. A target image retrieval system, comprising:
the data module is used for acquiring a target image retrieval request and determining retrieval conditions;
the query module is used for acquiring a corresponding target image according to the target image retrieval request and extracting the identification characteristics of the target image;
the first feature comparison module is used for comparing the recognition features of the target image with the recognition features in the registered image database and the unregistered image database in sequence and calculating and acquiring the similarity of the recognition features; outputting a registered image and a non-registered image with the similarity value larger than a preset same target threshold value;
the screening module screens a snap-shot image list from a snap-shot image database according to the output registered images and/or non-registered images based on the retrieval conditions;
the second characteristic comparison module is used for sequentially comparing the identification characteristics of the target image with the identification characteristics of the snap-shot images in the snap-shot list and outputting the snap-shot images with the similarity higher than the similarity threshold value in the retrieval condition; and if the snapshot image with the similarity higher than the similarity threshold does not exist, returning to the data module to judge the next target image.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the target image retrieval method according to any of claims 1 to 5 are implemented when the processor executes the program.
8. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the target image retrieval method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211171625.5A CN115510260A (en) | 2022-09-26 | 2022-09-26 | Target image retrieval method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211171625.5A CN115510260A (en) | 2022-09-26 | 2022-09-26 | Target image retrieval method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115510260A true CN115510260A (en) | 2022-12-23 |
Family
ID=84506046
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211171625.5A Pending CN115510260A (en) | 2022-09-26 | 2022-09-26 | Target image retrieval method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115510260A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117218515A (en) * | 2023-09-19 | 2023-12-12 | 人民网股份有限公司 | Target detection method, device, computing equipment and storage medium |
| CN117290560A (en) * | 2023-11-23 | 2023-12-26 | 支付宝(杭州)信息技术有限公司 | Method and device for acquiring graph data in graph calculation task |
| CN117576425A (en) * | 2024-01-17 | 2024-02-20 | 南京掌控网络科技有限公司 | Method and system for detecting scurrying image |
-
2022
- 2022-09-26 CN CN202211171625.5A patent/CN115510260A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117218515A (en) * | 2023-09-19 | 2023-12-12 | 人民网股份有限公司 | Target detection method, device, computing equipment and storage medium |
| CN117218515B (en) * | 2023-09-19 | 2024-05-03 | 人民网股份有限公司 | Target detection method, device, computing equipment and storage medium |
| CN117290560A (en) * | 2023-11-23 | 2023-12-26 | 支付宝(杭州)信息技术有限公司 | Method and device for acquiring graph data in graph calculation task |
| CN117290560B (en) * | 2023-11-23 | 2024-02-23 | 支付宝(杭州)信息技术有限公司 | Method and device for acquiring graph data in graph calculation task |
| CN117576425A (en) * | 2024-01-17 | 2024-02-20 | 南京掌控网络科技有限公司 | Method and system for detecting scurrying image |
| CN117576425B (en) * | 2024-01-17 | 2024-04-16 | 南京掌控网络科技有限公司 | Method and system for detecting scurrying image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115510260A (en) | Target image retrieval method and system | |
| CN109710780B (en) | Archiving method and device | |
| CN107169106A (en) | Video retrieval method, device, storage medium and processor | |
| CN111160275B (en) | Pedestrian re-recognition model training method, device, computer equipment and storage medium | |
| CN111625687B (en) | Method and system for quickly searching people in media asset video library through human faces | |
| CN111814690B (en) | Target re-identification method, device and computer readable storage medium | |
| CN114139015A (en) | Video storage method, device, equipment and medium based on key event identification | |
| CN111488813B (en) | Video emotion marking method and device, electronic equipment and storage medium | |
| CN114329455B (en) | User abnormal behavior detection method and device based on heterogeneous graph embedding | |
| CN107203638B (en) | Monitoring video processing method, device and system | |
| CN112270204A (en) | Target identification method and device, storage medium and electronic equipment | |
| CN116206334A (en) | Wild animal identification method and device | |
| CN114140663A (en) | Multi-scale attention and learning network-based pest identification method and system | |
| CN112241470B (en) | Video classification method and system | |
| CN111708906B (en) | Visiting retrieval method, device and equipment based on face recognition and storage medium | |
| Song et al. | Text Siamese network for video textual keyframe detection | |
| CN116071569A (en) | Image selection method, computer equipment and storage device | |
| CN106557523A (en) | Presentation graphics system of selection and equipment and object images search method and equipment | |
| CN115761842A (en) | Automatic updating method and device for human face base | |
| CN116935253A (en) | Human face tampering detection method based on residual error network combined with space-time attention mechanism | |
| CN111414952B (en) | Noise sample recognition method, device, equipment and storage medium for pedestrian re-recognition | |
| CN114049608A (en) | Track monitoring method and device, computer equipment and storage medium | |
| CN112766139A (en) | Target identification method and device, storage medium and electronic equipment | |
| CN113129054B (en) | User identification method and device | |
| CN112422505A (en) | Network malicious traffic identification method based on high-dimensional extended key feature vector |
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 |