CN112883213A - Picture archiving method and device and electronic equipment - Google Patents
Picture archiving method and device and electronic equipment Download PDFInfo
- Publication number
- CN112883213A CN112883213A CN201911207049.3A CN201911207049A CN112883213A CN 112883213 A CN112883213 A CN 112883213A CN 201911207049 A CN201911207049 A CN 201911207049A CN 112883213 A CN112883213 A CN 112883213A
- Authority
- CN
- China
- Prior art keywords
- picture
- similarity
- preset
- representative
- archive
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 14
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 230000036544 posture Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a picture archiving method, a picture archiving device and electronic equipment, wherein the method comprises the following steps: extracting a characteristic value of a picture to be archived; acquiring a first similarity with highest similarity between the characteristic value of the picture to be archived and the characteristic values of the representative pictures of the existing archives, wherein each archive in the existing archives comprises a plurality of representative pictures; judging whether the first similarity reaches a first preset similarity threshold value or not; if the first similarity does not reach the first preset similarity threshold, calculating a first average similarity of the first similarity and a second similarity; judging whether the first average similarity reaches a second preset similarity threshold value or not; if the first average similarity reaches the second preset similarity threshold, the picture to be archived is classified into the target archive. The method and the device can improve the recall rate and accuracy of the picture filing.
Description
Technical Field
The invention relates to the technical field of archive management, in particular to a picture archiving method and device and electronic equipment.
Background
Clustering and archiving the snap shots, and further analyzing valuable information capable of improving the security efficiency and effect of a certain area based on the archived information becomes an important research landing direction. The existing archiving method is as follows: when a new picture is accessed into the system, the characteristic value of the new picture is compared with the characteristic value of the representative picture of the existing file, the similarity is calculated, and the highest similarity exceeds a certain threshold value for filing. Each file generally only has one representative picture, which mainly comes from real-name information such as a certificate photo, or non-real-name pictures with better quality. Because the similarity between the characteristic value generated by the characteristic algorithm model and the characteristic value of the corresponding representative picture of the file cannot meet the threshold requirement under the influence of factors such as different light conditions, different shooting angles and the like, the face picture cannot be classified into the file, and even the face picture can be filed into an error file. Therefore, the existing filing method has the problems of low recall rate and low accuracy.
Disclosure of Invention
The embodiment of the invention provides a picture filing method and device and electronic equipment, which have the beneficial effects of improving the recall rate and accuracy rate of picture filing.
In a first aspect, an embodiment of the present invention provides a picture archiving method, including:
extracting a characteristic value of a picture to be archived;
acquiring a first similarity with highest similarity between the characteristic value of the picture to be archived and the characteristic values of the representative pictures of the existing archives, wherein each archive in the existing archives comprises a plurality of representative pictures;
judging whether the first similarity reaches a first preset similarity threshold value or not;
if the first similarity does not reach the first preset similarity threshold, calculating a first average similarity of the first similarity and a second similarity, wherein the second similarity is a similarity in which the similarity between the feature value of the picture to be archived and the feature values of the representative pictures of the target archive is ranked at the second, and the target archive is an archive corresponding to the first similarity;
judging whether the first average similarity reaches a second preset similarity threshold value or not;
if the first average similarity reaches the second preset similarity threshold, the picture to be archived is classified into the target archive;
wherein the first preset similarity threshold is greater than the second preset similarity threshold.
Optionally, before the extracting the feature value of the picture to be archived, the method further includes:
acquiring a characteristic value of an existing representative picture in a preset file;
acquiring a characteristic value of a picture to be added of the preset file, wherein the picture to be added is a filed picture of the preset file, and the filed picture is a filed picture except for the existing representative picture in the preset file;
and taking the picture to be added as an added representative picture of the preset archive according to the characteristic value of the existing representative picture and the characteristic value of the picture to be added so as to obtain a plurality of representative pictures of the preset archive.
Optionally, the step of taking the to-be-added picture as an additional representative picture of the preset archive according to the feature value of the existing representative picture and the feature value of the to-be-added picture to obtain a plurality of representative pictures of the preset archive includes:
when the preset file currently has an existing representative picture, calculating a third similarity between the characteristic value of the picture to be added and the characteristic value of the existing representative picture;
judging whether the third similarity is higher than a third preset similarity threshold and lower than a fourth preset similarity threshold;
if the third similarity is higher than the third preset similarity threshold and lower than the fourth similarity threshold, taking the picture to be added as an added representative picture of the preset file to obtain a plurality of representative pictures of the preset file;
wherein the third preset similarity threshold is smaller than the fourth similarity threshold.
Optionally, the step of taking the to-be-added picture as an additional representative picture of the preset archive according to the feature value of the existing representative picture and the feature value of the to-be-added picture to obtain a plurality of representative pictures of the preset archive includes:
when the preset archive has at least two existing representative pictures at present, respectively calculating a fourth similarity between the characteristic value of the picture to be added and the characteristic value of each existing representative picture, wherein the fourth similarity is the similarity between the characteristic value of the picture to be added and the characteristic value of any one of the at least two existing representative pictures;
judging whether each fourth similarity is lower than a fourth preset similarity threshold value;
calculating second average similarity of fourth similarities between the characteristic values of the picture to be added and the characteristic values of all the existing representative pictures;
judging whether the second average similarity is higher than a third preset similarity threshold value;
if each fourth similarity is lower than a fourth preset similarity threshold and the second similarity is higher than a third preset similarity threshold, determining the to-be-added picture as an added representative picture of the preset file to obtain a plurality of representative pictures of the preset file.
Optionally, before the step of obtaining the feature value of the to-be-added picture of the preset archive, the method further includes:
and screening out the filed pictures with the picture quality reaching a preset picture quality threshold value from the preset files to serve as the pictures to be added of the preset files.
Optionally, after the determining whether the first similarity reaches a first preset similarity threshold, the method further includes:
if the first similarity reaches the first preset similarity threshold, the picture to be archived is classified into a target archive corresponding to the first similarity.
In a second aspect, an embodiment of the present invention further provides a picture archiving apparatus, including:
the characteristic value extraction module is used for extracting the characteristic value of the picture to be archived;
the first similarity obtaining module is used for obtaining a first similarity with highest similarity between the characteristic value of the picture to be archived and the characteristic values of the representative pictures of the existing archives, and each archive in the existing archives comprises a plurality of representative pictures;
the first judging module is used for judging whether the first similarity reaches a first preset similarity threshold value;
a first average similarity calculation module, configured to calculate a first average similarity between the first similarity and a second similarity if the first similarity does not reach the first preset similarity threshold, where the second similarity is a similarity in which similarities between the feature value of the picture to be archived and feature values of respective representative pictures of a target archive are ranked second, and the target archive is an archive corresponding to the first similarity;
the second judgment module is used for judging whether the first average similarity reaches a second preset similarity threshold value;
and the first picture filing module is used for classifying the picture to be filed into the target file if the first average similarity reaches the second preset similarity threshold.
Optionally, the method further includes:
the first characteristic value acquisition unit is used for acquiring the characteristic value of the existing representative picture in the preset file;
the second characteristic acquisition unit is used for acquiring the characteristic value of the picture to be added of the preset archive, wherein the picture to be added is a filed picture of the preset archive, and the filed picture is a filed picture except the existing representative picture in the preset archive;
and the representative picture determining unit is used for taking the picture to be added as an added representative picture of the preset archive according to the characteristic value of the existing representative picture and the characteristic value of the picture to be added so as to obtain a plurality of representative pictures of the preset archive.
In a third aspect, an embodiment of the present invention further provides an electronic device, including: the image archiving method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the steps in the image archiving method provided by the embodiment of the invention.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the steps in the picture archiving method provided in the embodiment of the present invention.
In the embodiment of the invention, the characteristic value of the picture to be filed is extracted; acquiring a first similarity with highest similarity between the characteristic value of the picture to be archived and the characteristic values of the representative pictures of the existing archives, wherein each archive in the existing archives comprises a plurality of representative pictures; judging whether the first similarity reaches a first preset similarity threshold value or not; if the first similarity does not reach the first preset similarity threshold, calculating a first average similarity of the first similarity and a second similarity, wherein the second similarity is a similarity in which the similarity between the feature value of the picture to be archived and the feature values of the representative pictures of the target archive is ranked at the second, and the target archive is an archive corresponding to the first similarity; judging whether the first average similarity reaches a second preset similarity threshold value or not; if the first average similarity reaches the second preset similarity threshold, the picture to be archived is classified into the target archive; wherein the first preset similarity threshold is greater than the second preset similarity threshold. The method and the device provide more judgment bases for the picture filing judgment based on the fact that each file is provided with a plurality of representative pictures, and carry out multiple judgment on the pictures to be filed by setting multiple threshold conditions, so that the problem that each file contains a single representative picture, the picture similarity of the same person is not high enough due to factors such as light or different postures, the requirement of the filing similarity threshold (single threshold) is not met, and the file cannot be included or even the wrong file cannot be included is solved. Therefore, the beneficial effects of recall rate and accuracy rate of picture archiving are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a picture archiving method according to an embodiment of the present invention;
FIG. 2 is a flowchart of another picture archiving method according to an embodiment of the present invention;
FIG. 3 is a flowchart of another picture archiving method according to an embodiment of the present invention;
FIG. 4 is a flow chart of a method provided in the embodiment of step 301 in FIG. 3;
FIG. 5 is a flow chart of a method provided by the embodiment of step 403 in FIG. 4;
FIG. 6 is a flow chart of a method provided by the embodiment of step 403 in FIG. 4;
FIG. 7 is a schematic block diagram of a picture archiving apparatus according to an embodiment of the present invention;
FIG. 8 is a schematic block diagram of another picture archiving apparatus according to an embodiment of the present invention;
FIG. 9 is a schematic block diagram of another picture archiving apparatus according to an embodiment of the present invention;
FIG. 10 is a block diagram of the image setting module of FIG. 9;
FIG. 11 is a block diagram of the embodiment of the picture determination unit shown in FIG. 10;
FIG. 12 is a block diagram of the embodiment of the picture determination unit shown in FIG. 10;
fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1, fig. 1 is a flowchart of a picture archiving method according to an embodiment of the present invention, where the picture archiving method is used in a picture archiving system or an archive management system, and as shown in fig. 1, the method includes the following steps:
The picture to be archived can be a picture obtained by shooting and uploading through picture acquisition equipment (a monitor, a camera and the like), can also be a preset shot picture stored in a database, and can also be a picture to be archived provided by other departments (such as law enforcement departments, management departments and the like) or individuals. When a certain person picture needs to be filed, the picture to be filed comprises a face picture to be filed. The picture to be archived may be a picture, an image, a photograph, or the like, and may also be a frame picture obtained by decoding a video, or the like.
The characteristic value comprises a face characteristic value, and the characteristic value is a bit string with a certain length generated by processing a face picture by using a face characteristic algorithm model. The feature value of the picture to be archived can be a bit string with a certain length, which is generated by processing a face in the picture to be archived by using a face feature algorithm model.
Specifically, after receiving the picture to be archived, the characteristic value of the picture to be archived is extracted by using the characteristic algorithm model. And if the characteristic value of the face picture is extracted, extracting the characteristic value of the picture to be archived by using a face characteristic algorithm model.
As an embodiment, when other pictures need to be archived, for example, when a picture of a certain machine device needs to be archived, the picture to be archived may also be a picture of the device to be archived. For example, in a factory having a plurality of pieces of equipment, in order to monitor the operation condition of each piece of equipment, pictures of the corresponding piece of equipment are collected by different monitoring equipment or picture collecting equipment such as a camera, and filing monitoring management is performed for each piece of equipment, and at this time, pictures of each piece of equipment may be filed by the picture filing method. The feature value of the picture to be filed is the device feature value of the corresponding device image (for example, the feature value obtained through the attribute features such as the model, the shape and the like of the device).
And 102, acquiring a first similarity with the highest similarity between the characteristic value of the picture to be archived and the characteristic values of the representative pictures of the existing archive.
The existing archives are archives already existing in an archive system, a picture archiving system or an archive management system, the number of the existing archives can be one or more, and the number of the existing archives can be based on the actual number of the archives in the archive system. A file is correspondingly arranged for each person in the file system, and each file comprises more than one piece of information such as pictures of the person. Every archives all include a plurality of representative pictures in current archives, and every archives established promptly all is provided with a plurality of representative pictures. Pictures already present in the archive may be referred to as archived pictures.
The representative picture is a representative of each file and is used for judging whether the new picture should be included in the picture of the file. The representative pictures of the archives mainly come from real-name information such as certificate pictures and the like or non-real-name pictures with better quality.
It should be noted that, in this embodiment, the process of putting the picture into the corresponding person file by some method is called archiving.
In this embodiment, the similarity is a numerical value calculated based on the eigenvalue comparison and used for representing the probability that the pictures belong to the same person.
Specifically, after the feature value of the picture to be archived is extracted, the feature value of each representative picture of each existing archive is also extracted. And respectively calculating the similarity between the characteristic value of the picture to be archived and the characteristic value of each representative picture in each existing file, and sequencing the similarity based on the calculated similarity to obtain a similarity sequencing queue. And then selecting the similarity with the highest similarity from the similarity sorting queue as the first similarity.
And 103, judging whether the first similarity reaches a first preset similarity threshold value.
The first preset similarity threshold is a preset similarity threshold and is used for judging whether the picture to be archived can be archived. The first preset similarity threshold may be set as required, for example, to 0.90, 0.95, 0.99, or may be set to 1, etc. The greater the similarity, the more likely the face in the picture to be archived and the face in the representative picture are to be the same person.
Specifically, after the first similarity is obtained, the first similarity is compared with the first preset similarity threshold, and whether the first similarity is greater than or equal to the first preset similarity threshold is judged. If the first similarity is greater than or equal to the first preset similarity threshold, it indicates that the first similarity reaches the first preset similarity threshold. If the first similarity is smaller than the first preset similarity threshold, it indicates that the first similarity does not reach the first preset similarity threshold.
As another embodiment, the similarity between the feature value of the picture to be archived and the feature value of one of the representative pictures in the target archive may be compared with a first preset similarity threshold, and if the similarity is greater than or equal to the first preset similarity threshold, it indicates that the first preset similarity threshold is reached, and if the similarity is smaller than the first preset similarity threshold, it indicates that the first preset similarity threshold is not reached.
And 104, if the first similarity does not reach a first preset similarity threshold, calculating a first average similarity of the first similarity and the second similarity.
The second similarity is the similarity with the similarity ranked at the second in the feature value of the picture to be archived and the feature value of each representative picture of the target archive. The target file is a file corresponding to the first similarity. The first average similarity is equal to the average of the similarity between the feature value of the picture to be archived and the feature values of the two representative pictures with the highest similarity in the target archive.
Specifically, if the first similarity does not reach the first preset similarity threshold, it indicates that the picture to be archived may not belong to the picture of the target archive, that is, the person in the picture to be archived may not be the corresponding person in the target archive. The picture to be archived cannot be archived (it is determined that the archiving fails).
If the first similarity does not reach the first preset similarity threshold, it can be further described that the picture to be archived may have picture problems (for example, picture problems caused by different shooting angles, poor shooting environment (such as poor light, the face of the person blocked by other objects, etc.), poor picture quality (such as poor equipment, low pixels, etc.) and the like), so that the first similarity does not reach the first preset similarity threshold. And the picture to be archived cannot be archived (it is determined that the archiving fails).
In order to avoid unsuccessful image archiving failure caused by image problems, it is necessary to calculate the first average similarity between the feature value of the image to be archived and the feature values of the two representative images with the highest similarity between the feature values of the target archive. And judging whether the picture to be archived should be archived or not according to the first average similarity.
And 105, judging whether the first average similarity reaches a second preset similarity threshold value.
The first preset similarity threshold is larger than the second preset similarity threshold. The second preset similarity threshold is also a preset similarity threshold, and is used for judging whether the picture to be archived should be archived or not according to the first average similarity. The second preset similarity threshold may be set to 0.8, 0.85, 0.89, or the like, and the setting of the second preset similarity threshold is always smaller than the first preset similarity threshold.
Specifically, after the first average similarity is obtained through calculation, the first average similarity is compared with the second preset similarity threshold, if the first average similarity is greater than or equal to the second preset similarity threshold, it is determined that the first average similarity reaches the second preset similarity threshold, and if the first average similarity is smaller than the second preset similarity threshold, it is determined that the first average similarity does not reach the second preset similarity threshold.
And step 106, if the first average similarity reaches a second preset similarity threshold, classifying the picture to be archived into the target archive.
Specifically, if the first average similarity reaches the second preset similarity threshold, it indicates that the picture to be archived meets the requirement of the person picture in the target archive, that is, it indicates that the face in the picture to be archived is the face of a person stored in the target archive, that is, it indicates that the person is the same person. Therefore, the picture to be archived can be classified into the target archive so as to archive the picture to be archived, and the problem of archiving failure caused by the fact that the first similarity does not reach the first preset similarity threshold is solved.
As an embodiment, when there are a plurality of generation archiving pictures, the steps 101 to 106 may be repeatedly executed until all the pictures to be archived are judged to be finished, and the process may be ended.
In another embodiment of the present invention, if the first average similarity does not reach the second preset similarity threshold, a new file needs to be created for the picture to be archived. Specifically, when the first average similarity does not reach the second preset similarity threshold, it may be stated that a corresponding archive may not be established for the person in the picture to be archived in the archive system, so that the picture to be archived fails to be archived. Therefore, a new archive can be established for the picture to be archived, and the management of personnel corresponding to the picture to be archived is facilitated.
In another embodiment, if the first average similarity does not reach the second preset similarity threshold, the picture to be archived is stored in a storage (the storage may be a memory or a hard disk/a magnetic disk/a network disk, or may be another storage) for storing the picture which has failed to be archived. Therefore, the picture to be archived, which is not successfully archived temporarily, can be saved, and when the archiving is needed again, the picture to be archived is acquired from the memory, and the archiving determination of the picture to be archived is performed again in steps 101 to 106. If the picture to be archived is not needed to be archived again, the picture to be archived in the memory can be deleted, so that the storage space of the memory is released.
As another possible implementation, the picture archiving method can also be used in the fields of article classification, product classification and the like in the form of pictures.
In the embodiment of the invention, the characteristic value of the picture to be archived is extracted; acquiring a first similarity with the highest similarity between the characteristic value of the picture to be archived and the characteristic values of the representative pictures of the existing archives, wherein each archive in the existing archives comprises a plurality of representative pictures; judging whether the first similarity reaches a first preset similarity threshold value or not; if the first similarity does not reach a first preset similarity threshold, calculating a first average similarity of the first similarity and a second similarity, wherein the second similarity is a similarity of the feature value of the picture to be archived and the similarity of the feature values of the representative pictures of the target archive ranked at the second, and the target archive is an archive corresponding to the first similarity; judging whether the first average similarity reaches a second preset similarity threshold value or not; if the first average similarity reaches a second preset similarity threshold, the picture to be archived is classified into a target archive; the first preset similarity threshold is larger than the second preset similarity threshold. The method and the device provide more judgment bases for the picture filing judgment based on the fact that each file is provided with a plurality of representative pictures, and carry out multiple judgment on the pictures to be filed by setting multiple threshold conditions, so that the problem that each file contains a single representative picture, the picture similarity of the same person is not high enough due to factors such as light or different postures, the requirement of the filing similarity threshold (single threshold) is not met, and the file cannot be included or even the wrong file cannot be included is solved. Therefore, the beneficial effects of recall rate and accuracy rate of picture archiving are improved.
Referring to fig. 2, fig. 2 is a flowchart of another picture archiving method according to an embodiment of the present invention, and after step 103 in fig. 1, as shown in fig. 2, the method further includes:
Specifically, if the first similarity reaches a first preset similarity threshold, it is indicated that the face in the picture to be archived and the face in the target archive belong to the same person, that is, belong to the same person, and the picture to be archived is classified into the target archive, so as to archive the picture to be archived.
In the embodiment of the invention, the filing judgment of the picture to be filed is realized through the filing judgment strategy of the first similarity and the first preset similarity threshold, so that the picture to be filed can be filed only by comparing the first similarity with the first preset similarity threshold, and if the picture to be filed cannot be filed through the first similarity and the first preset similarity threshold, the picture to be filed can be judged to be filed through the first average similarity and the second preset similarity threshold, and the filing accuracy and recall rate are further improved.
Referring to fig. 3, fig. 3 is a flowchart of another picture archiving method according to an embodiment of the present invention, before step 101 of fig. 1, the method further includes:
The preset files can be established files or files being established in a file system, and the number of the preset files can be determined according to the number of the files in the file system. The archive may be referred to as a preset archive before the plurality of representative image settings are completed, and may be referred to as an existing archive after the plurality of representative picture settings are completed.
Specifically, when the archive is established, a plurality of representative pictures can be preset for each preset archive, so as to provide more judgment bases for the archiving judgment of the pictures to be archived. It should be noted that the number of the representative pictures of the preset archive may be set according to actual needs, for example, the number may be set to be 3, 4, or 5 to-be-tabulated pictures. When a plurality of representative pictures of the archive are set, all the representative pictures need to be ensured to be different, and meanwhile, the personnel in all the representative pictures need to be ensured to be the same person.
It should be noted that, the manner of presetting the representative pictures for the preset archive may be to automatically set the representative pictures of the preset archive according to the representative picture set first, the archived pictures already included in the preset archive, and a specific representative picture setting policy.
In another embodiment, the setting of the plurality of representative pictures for the preset archive may be performed by manually designating pictures belonging to a certain person at different shooting angles or different shooting postures, different shooting lights, and the like as the representative pictures of the archive when the archive is created by the archive creating worker, so as to set the plurality of representative pictures.
Referring to fig. 4, fig. 4 is a flow chart of a method provided in the embodiment of step 301 in fig. 3, as shown in fig. 4, step 301 includes:
The existing representative pictures are set during the initial filing, and the number of the existing representative pictures can be one or more than two. Specifically, a feature value (face feature value) of the existing representative picture is extracted through a feature algorithm model.
And 402, acquiring a characteristic value of a to-be-added picture of a preset archive.
The picture to be added is a filed picture of a preset file, and the filed picture is a filed picture except for the existing representative picture in the preset file. The archived pictures other than the existing representative pictures may be multiple pictures, that is, the archived pictures may be multiple pictures. The picture to be added is used as a candidate representative picture of a preset file, and the number of the pictures to be added can be multiple. Specifically, the filed picture is selected from the preset archive as the picture to be added, and the characteristic value of the picture to be added is extracted through a characteristic algorithm model.
It should be noted that the selection of the archived picture in the preset archive as the picture to be added is to ensure that the picture to be added and the pictures stored in the preset archive belong to the same person, and because the archived picture is an archived picture in the preset archive except for the existing representative picture, the process of repeatedly determining whether the existing representative picture can be used as the representative picture by using the existing representative picture as the picture to be added does not occur, and thus the workload of determining the newly added representative picture is reduced.
Specifically, as an embodiment, referring to fig. 5, fig. 5 is a flowchart of a method provided in step 403 in fig. 4. As shown in fig. 5, step 403 includes:
The third preset similarity threshold and the fourth preset similarity threshold are preset and used for judging whether the picture to be added can be used as the similarity threshold of the newly added representative picture of the preset archive or not. It should be noted that, when the third preset similarity threshold and the fourth preset similarity threshold are set, the third preset similarity threshold is always smaller than the fourth preset similarity threshold. The newly added representative picture is a picture meeting the requirements of the representative pictures of the preset files, and the newly added representative picture is different from the existing representative pictures in the preset files.
Specifically, the requirement that the third similarity is higher than the third preset similarity threshold is to ensure that the newly added representative picture and the people in the existing representative picture in the preset file are pictures of the same person. Moreover, the third similarity is required to be lower than a fourth preset similarity threshold value in order to ensure that the newly added representative picture has a certain difference from the existing representative picture of the preset file. If the newly added representative picture is too consistent with the existing representative picture in the preset archive, for example, if one person stands on a camera to take two identical pictures, the similarity of the two pictures is close to 1 (100%), then the two pictures are used for judging archiving and one picture is not used, and the aim of improving the archiving effect through a plurality of representative pictures of a single archive cannot be achieved.
When the third similarity is higher than a third preset similarity threshold and lower than a fourth similarity threshold, determining that the picture to be added is an additional representative picture of a preset file, so that the new representative picture can be added to the preset file, the picture to be filed can be conveniently filed and judged, and the filing accuracy and the recall rate of the picture to be filed are further improved.
As one embodiment, when there are a plurality of pictures to be added, sequentially calculating a third similarity between the feature value of the picture to be added and the feature value of the existing representative picture, and sequentially comparing and determining the corresponding third similarity with a third preset similarity threshold and a fourth preset similarity threshold until the number of representative pictures in the preset file reaches a specified number.
Referring to fig. 6, as another implementation, fig. 6 is a flowchart of a method provided in step 403 in fig. 4. As shown in fig. 6, step 403 includes:
And step 604, judging whether the second average similarity is higher than a third preset similarity threshold value.
The fourth similarity is a similarity between the feature value of the to-be-added picture and the feature value of any one of the at least two existing representative pictures.
Specifically, when each of the fourth similarities is required to be lower than the fourth preset similarity threshold, the to-be-added picture is ensured to be different from the current existing representative picture, that is, the obtained new representative picture is different from the current existing representative picture.
The second average similarity is required to be based on being higher than a third preset similarity threshold in order to ensure that the person in the picture to be augmented and the person in the currently existing representative picture belong to the same person.
And when each fourth similarity corresponding to the picture to be added is lower than a fourth preset similarity threshold and the second average similarity is higher than a third preset similarity threshold, determining the picture to be added as an added representative picture of the preset file to obtain a plurality of representative pictures of the preset file. Therefore, the newly added representative picture can be ensured to be different from the existing representative picture, and the personnel in the newly added representative picture and the personnel in the existing representative picture belong to the same person.
It should be noted that, when performing steps 601 to 605, the preset file may be executed on the basis of two representative pictures after completing steps 501 to 503. When steps 601 to 605 are executed, the execution may be directly performed when at least two existing representative pictures are initially set in the preset archive.
In the embodiment of the invention, a plurality of representative pictures can be set for the preset archive through the judgment relationship between the third similarity and the third preset similarity threshold and the fourth preset similarity threshold and through the judgment relationship between the second average similarity and the third preset similarity, so that more judgment bases can be provided when the pictures to be archived are subjected to archiving judgment, and the archiving accuracy and the recall rate of the pictures to be archived can be further improved.
Optionally, before the step of obtaining the feature value of the to-be-added picture of the preset archive, the method further includes:
and screening the filed pictures with the picture quality reaching a preset picture quality threshold value from the preset files to serve as the pictures to be added of the preset files.
The picture quality can be a numerical value of comprehensive attributes such as definition and integrity of the judged picture generated by using the picture quality algorithm model. The preset picture quality threshold is preset and is used for judging whether the picture meets the picture quality threshold of the picture quality requirement.
Specifically, the picture quality of each filed picture in the preset archive is calculated, the picture quality of each filed picture is compared with a preset picture quality threshold, and if the picture quality of the filed picture reaches the preset picture quality threshold, the filed picture is used as a picture to be added of the preset archive and is used as an alternative representative picture of the preset archive to be judged. When the number of the filed pictures meeting the picture quality requirement is large, the filed pictures meeting the picture quality are sequentially used as pictures to be added according to the picture quality sequence (from high to low) to determine the representative pictures of the preset archives, and the operation is stopped until the representative pictures of the preset archives are determined.
In the embodiment of the invention, the picture with the picture quality meeting the picture quality requirement is selected from the filed pictures of the preset archive to be used as the picture to be added of the preset archive, so that the picture quality of the representative picture of the preset archive is further improved, when the picture to be filed is subjected to filing judgment, a more accurate representative picture can be provided, and the filing accuracy and recall rate of the picture to be filed are further improved.
Referring to fig. 7, fig. 7 is a schematic diagram of a module structure of a picture archiving apparatus according to an embodiment of the present invention, and as shown in fig. 7, the picture archiving apparatus 70 includes:
and the characteristic value extraction module 71 is configured to extract a characteristic value of the picture to be archived.
The first similarity obtaining module 72 is configured to obtain a first similarity with a highest similarity between a feature value of a picture to be archived and feature values of representative pictures of existing archives, where each archive in the existing archives includes a plurality of representative pictures.
The first determining module 73 is configured to determine whether the first similarity reaches a first preset similarity threshold.
The first average similarity calculation module 74 is configured to calculate a first average similarity between the first similarity and a second similarity if the first similarity does not reach a first preset similarity threshold, where the second similarity is a similarity in which similarities between the feature value of the picture to be archived and feature values of respective representative pictures of the target archive are ranked on the second, and the target archive is an archive corresponding to the first similarity.
The second determining module 75 is configured to determine whether the first average similarity reaches a second preset similarity threshold.
The first picture archiving module 76 is configured to, if the first average similarity reaches the second preset similarity threshold, classify the picture to be archived into the target archive.
Referring to fig. 8, fig. 8 is a schematic diagram of a module structure of another picture archiving apparatus according to an embodiment of the present invention, and after the first determining module 73 in fig. 7, as shown in fig. 8, the picture archiving apparatus 70 further includes:
the second picture archiving module 77 is configured to, if the first similarity reaches a first preset similarity threshold, classify the picture to be archived into a target archive corresponding to the first similarity.
Referring to fig. 9, fig. 9 is a schematic diagram of a module structure of another picture archiving apparatus according to an embodiment of the present invention, before the feature value extracting module 71 in fig. 7, the picture archiving apparatus 70 further includes:
the representative picture setting module 78 is used for setting a plurality of representative pictures for the preset file in advance.
Referring to fig. 10, fig. 10 is a schematic diagram of a module structure provided in the embodiment of the representative picture setting module in fig. 9, and as shown in fig. 10, the representative picture setting module 78 includes:
the first characteristic value acquiring unit 781 is configured to acquire a characteristic value of an existing representative picture in a preset archive.
The second characteristic obtaining unit 782 is configured to obtain a characteristic value of a to-be-added picture of the preset archive, where the to-be-added picture is a filed picture of the preset archive, and the filed picture is a filed picture in the preset archive except for the existing representative picture.
The representative picture determining unit 783 is configured to use the to-be-added picture as an additional representative picture of the preset archive according to the feature value of the existing representative picture and the feature value of the to-be-added picture, so as to obtain a plurality of representative pictures of the preset archive.
Referring to fig. 11, fig. 11 is a schematic diagram of a module structure provided in the embodiment of the representative picture determining unit in fig. 10, and as shown in fig. 11, the representative picture determining unit 783 includes:
and a third similarity operator unit 7831, configured to calculate a third similarity between the feature value of the to-be-added picture and the feature value of the existing representative picture when the preset file currently has an existing representative picture.
The third similarity determination subunit 7832 is configured to determine whether the third similarity is higher than a third preset similarity threshold and lower than a fourth preset similarity threshold.
The first representative picture determining subunit 7833 is configured to, if the third similarity is higher than the third preset similarity threshold and lower than the fourth similarity threshold, use the to-be-added picture as an additional representative picture of the preset file to obtain a plurality of representative pictures of the preset file.
Wherein the third preset similarity threshold is smaller than the fourth similarity threshold.
Referring to fig. 12, fig. 12 is a schematic diagram of a module structure provided in the embodiment of the representative picture determining unit in fig. 10, and as shown in fig. 12, the representative picture determining unit 783 includes:
a fourth similarity operator unit 7834, configured to, when the preset archive currently has at least two existing representative pictures, respectively calculate a fourth similarity between the feature value of the picture to be added and the feature value of each existing representative picture, where the fourth similarity is a similarity between the feature value of the picture to be added and the feature value of any one of the at least two existing representative pictures;
a fourth similarity determination subunit 7835, configured to determine whether each fourth similarity is lower than a fourth preset similarity threshold;
the second average similarity operator unit 7836 calculates a second average similarity of fourth similarities between the feature values of the to-be-increased picture and the feature values of all the existing representative pictures;
a second average similarity determination subunit 7837, configured to determine whether the second average similarity is higher than a third preset similarity threshold;
the second representative picture determining subunit 7838 is configured to determine, if each fourth similarity is lower than a fourth preset similarity threshold and the second average similarity is higher than a third preset similarity threshold, the to-be-added picture as an additional representative picture of the preset file, so as to obtain a plurality of representative pictures of the preset file.
Optionally, on the basis of fig. 10, before the second feature obtaining unit 782, the picture archiving apparatus 70 further includes:
and the screening module is used for screening the filed pictures with the picture quality reaching the preset picture quality threshold value from the preset files as the pictures to be added of the preset files.
The image filing device provided by the embodiment of the present invention can implement each implementation manner in the above method embodiments and corresponding beneficial effects, and is not described herein again to avoid repetition.
Referring to fig. 13, fig. 13 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 80 includes: a memory 82, a processor 81 and a computer program stored on the memory 82 and operable on the processor 81, wherein the processor 81 executes the computer program to implement the steps of the picture archiving method provided by the above-mentioned embodiment, and the processor 81 executes the following steps:
and extracting the characteristic value of the picture to be archived.
And acquiring a first similarity with the highest similarity between the characteristic value of the picture to be archived and the characteristic values of the representative pictures of the existing archives, wherein each archive in the existing archives comprises a plurality of representative pictures.
And judging whether the first similarity reaches a first preset similarity threshold value.
If the first similarity does not reach a first preset similarity threshold, calculating a first average similarity of the feature values of the two representative pictures with the highest similarity between the feature value of the picture to be archived and the target archive, wherein the target archive is the archive corresponding to the first similarity.
And judging whether the first average similarity reaches a second preset similarity threshold value.
And if the first average similarity reaches a second preset similarity threshold, the picture to be archived is classified into the target archive.
The first preset similarity threshold is larger than the second preset similarity threshold.
Optionally, after the processor 81 performs the judgment on whether the first similarity reaches the first preset similarity threshold, the processor 81 further performs the following steps:
if the first similarity reaches a first preset similarity threshold, the picture to be archived is classified into a target archive corresponding to the first similarity.
Optionally, before the processor 81 executes the step of acquiring the picture to be archived, the processor 81 further executes the following steps:
a plurality of representative pictures are preset for a preset file.
Optionally, the step of setting a plurality of representative pictures for the preset archive in advance executed by the processor 81 includes:
and acquiring the characteristic value of the current representative picture in the preset file.
And acquiring the characteristic value of the picture to be added of the preset file, wherein the picture to be added is a filed picture of the preset file, and the filed picture is a filed picture except the existing representative picture in the preset file.
And taking the picture to be added as an added representative picture of the preset file according to the characteristic value of the existing representative picture and the characteristic value of the picture to be added so as to obtain a plurality of representative pictures of the preset file.
Optionally, the step, executed by the processor 81, of taking the to-be-added picture as an additional representative picture of the preset archive according to the feature value of the existing representative picture and the feature value of the to-be-added picture to obtain a plurality of representative pictures of the preset archive includes:
and when the preset file currently has an existing representative picture, calculating a third similarity between the characteristic value of the picture to be added and the characteristic value of the existing representative picture.
And judging whether the third similarity is higher than a third preset similarity threshold and lower than a fourth preset similarity threshold.
And if the third similarity is higher than a third preset similarity threshold and lower than a fourth similarity threshold, taking the picture to be added as an added representative picture of the preset file to obtain a plurality of representative pictures of the preset file.
Wherein the third preset similarity threshold is smaller than the fourth similarity threshold.
Optionally, the step, executed by the processor 81, of taking the to-be-added picture as an additional representative picture of the preset archive according to the feature value of the existing representative picture and the feature value of the to-be-added picture to obtain a plurality of representative pictures of the preset archive includes:
when the preset archive has at least two existing representative pictures at present, respectively calculating a fourth similarity between the characteristic value of the picture to be added and the characteristic value of each existing representative picture, wherein the fourth similarity is the similarity between the characteristic value of the picture to be added and the characteristic value of any one of the at least two existing representative pictures.
And judging whether each fourth similarity is lower than a fourth preset similarity threshold.
And calculating a second average similarity of fourth similarities between the characteristic values of the picture to be added and the characteristic values of all the existing representative pictures.
And judging whether the second average similarity is higher than a third preset similarity threshold value.
And if each fourth similarity is lower than a fourth preset similarity threshold and the second average similarity is higher than a third preset similarity threshold, determining the picture to be added as an additional representative picture of the preset file to obtain a plurality of representative pictures of the preset file.
Optionally, before the step of obtaining the feature value of the to-be-added picture of the preset archive, the processor 81 further performs the following steps:
and screening the filed pictures with the picture quality reaching a preset picture quality threshold value from the preset files to serve as the pictures to be added of the preset files.
It should be noted that the electronic device 80 may be an intelligent terminal, a mobile phone, a tablet computer, and the like of a department related to the archive.
The electronic device 80 provided in the embodiment of the present invention can implement each implementation manner in the above method embodiments and corresponding beneficial effects, and for avoiding repetition, details are not described here again.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor 81, the computer program implements each process of the image archiving method provided in the embodiment of the present invention, and can achieve the same technical effect, and in order to avoid repetition, the computer program is not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (10)
1. A picture archiving method, comprising:
extracting a characteristic value of a picture to be archived;
acquiring a first similarity with highest similarity between the characteristic value of the picture to be archived and the characteristic values of the representative pictures of the existing archives, wherein each archive in the existing archives comprises a plurality of representative pictures;
judging whether the first similarity reaches a first preset similarity threshold value or not;
if the first similarity does not reach the first preset similarity threshold, calculating a first average similarity of the first similarity and a second similarity, wherein the second similarity is a similarity in which the similarity between the feature value of the picture to be archived and the feature values of the representative pictures of the target archive is ranked at the second, and the target archive is an archive corresponding to the first similarity;
judging whether the first average similarity reaches a second preset similarity threshold value or not;
if the first average similarity reaches the second preset similarity threshold, the picture to be archived is classified into the target archive;
wherein the first preset similarity threshold is greater than the second preset similarity threshold.
2. The picture archiving method according to claim 1, wherein prior to said extracting the feature values of the picture to be archived, said method further comprises:
acquiring a characteristic value of an existing representative picture in a preset file;
acquiring a characteristic value of a picture to be added of the preset file, wherein the picture to be added is a filed picture of the preset file, and the filed picture is a filed picture except for the existing representative picture in the preset file;
and taking the picture to be added as an added representative picture of the preset archive according to the characteristic value of the existing representative picture and the characteristic value of the picture to be added so as to obtain a plurality of representative pictures of the preset archive.
3. The picture archiving method according to claim 2, wherein the step of using the to-be-added picture as an added representative picture of the preset archive according to the feature values of the existing representative picture and the feature values of the to-be-added picture to obtain a plurality of representative pictures of the preset archive comprises:
when the preset file currently has an existing representative picture, calculating a third similarity between the characteristic value of the picture to be added and the characteristic value of the existing representative picture;
judging whether the third similarity is higher than a third preset similarity threshold and lower than a fourth preset similarity threshold;
if the third similarity is higher than the third preset similarity threshold and lower than the fourth similarity threshold, taking the picture to be added as an added representative picture of the preset file to obtain a plurality of representative pictures of the preset file;
wherein the third preset similarity threshold is smaller than the fourth similarity threshold.
4. The picture archiving method according to claim 3, wherein the step of using the to-be-added picture as an added representative picture of the preset archive according to the feature values of the existing representative picture and the feature values of the to-be-added picture to obtain a plurality of representative pictures of the preset archive comprises:
when the preset archive has at least two existing representative pictures at present, respectively calculating a fourth similarity between the characteristic value of the picture to be added and the characteristic value of each existing representative picture, wherein the fourth similarity is the similarity between the characteristic value of the picture to be added and the characteristic value of any one of the at least two existing representative pictures;
judging whether each fourth similarity is lower than a fourth preset similarity threshold value;
calculating second average similarity of fourth similarities between the characteristic values of the picture to be added and the characteristic values of all the existing representative pictures;
judging whether the second average similarity is higher than a third preset similarity threshold value;
if each fourth similarity is lower than a fourth preset similarity threshold and the second similarity is higher than a third preset similarity threshold, determining the to-be-added picture as an added representative picture of the preset file to obtain a plurality of representative pictures of the preset file.
5. The picture archiving method according to claim 2, wherein before the step of obtaining the feature value of the picture to be added of the preset archive, the method further comprises:
and screening out the filed pictures with the picture quality reaching a preset picture quality threshold value from the preset files to serve as the pictures to be added of the preset files.
6. The picture archiving method according to claim 1, wherein after said determining whether said first similarity reaches a first preset similarity threshold, said method further comprises:
if the first similarity reaches the first preset similarity threshold, the picture to be archived is classified into the target archive.
7. A picture archiving apparatus, comprising:
the characteristic value extraction module is used for extracting the characteristic value of the picture to be archived;
the first similarity obtaining module is used for obtaining a first similarity with highest similarity between the characteristic value of the picture to be archived and the characteristic values of the representative pictures of the existing archives, and each archive in the existing archives comprises a plurality of representative pictures;
the first judging module is used for judging whether the first similarity reaches a first preset similarity threshold value;
a first average similarity calculation module, configured to calculate a first average similarity between the first similarity and a second similarity if the first similarity does not reach the first preset similarity threshold, where the second similarity is a similarity in which similarities between the feature value of the picture to be archived and feature values of respective representative pictures of a target archive are ranked second, and the target archive is an archive corresponding to the first similarity;
the second judgment module is used for judging whether the first average similarity reaches a second preset similarity threshold value;
and the first picture filing module is used for classifying the picture to be filed into the target file if the first average similarity reaches the second preset similarity threshold.
8. The picture archiving device according to claim 7, further comprising:
the first characteristic value acquisition unit is used for acquiring the characteristic value of the existing representative picture in the preset file;
the second characteristic acquisition unit is used for acquiring the characteristic value of the picture to be added of the preset archive, wherein the picture to be added is a filed picture of the preset archive, and the filed picture is a filed picture except the existing representative picture in the preset archive;
and the representative picture determining unit is used for taking the picture to be added as an added representative picture of the preset archive according to the characteristic value of the existing representative picture and the characteristic value of the picture to be added so as to obtain a plurality of representative pictures of the preset archive.
9. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, the processor implementing the steps in the picture archiving method according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps in the picture archiving method according to one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911207049.3A CN112883213B (en) | 2019-11-29 | 2019-11-29 | Picture archiving method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911207049.3A CN112883213B (en) | 2019-11-29 | 2019-11-29 | Picture archiving method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112883213A true CN112883213A (en) | 2021-06-01 |
| CN112883213B CN112883213B (en) | 2023-11-17 |
Family
ID=76039170
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911207049.3A Active CN112883213B (en) | 2019-11-29 | 2019-11-29 | Picture archiving method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112883213B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113326805A (en) * | 2021-06-24 | 2021-08-31 | 杭州海康威视数字技术股份有限公司 | Human body cover updating method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100257141A1 (en) * | 2009-04-02 | 2010-10-07 | Xerox Corporation | Apparatus and method for document collection and filtering |
| CN109815370A (en) * | 2018-12-28 | 2019-05-28 | 上海依图网络科技有限公司 | A kind of archiving method and device |
| WO2019192121A1 (en) * | 2018-04-04 | 2019-10-10 | 平安科技（深圳）有限公司 | Dual-channel neural network model training and human face comparison method, and terminal and medium |
| CN110378314A (en) * | 2019-05-31 | 2019-10-25 | 北京金山云网络技术有限公司 | A kind of human face region image archiving method, device, electronic equipment and storage medium |
-
2019
- 2019-11-29 CN CN201911207049.3A patent/CN112883213B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100257141A1 (en) * | 2009-04-02 | 2010-10-07 | Xerox Corporation | Apparatus and method for document collection and filtering |
| WO2019192121A1 (en) * | 2018-04-04 | 2019-10-10 | 平安科技（深圳）有限公司 | Dual-channel neural network model training and human face comparison method, and terminal and medium |
| CN109815370A (en) * | 2018-12-28 | 2019-05-28 | 上海依图网络科技有限公司 | A kind of archiving method and device |
| CN110378314A (en) * | 2019-05-31 | 2019-10-25 | 北京金山云网络技术有限公司 | A kind of human face region image archiving method, device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 孙永林;刘仲;: "基于动态区间映射的文档聚类算法", 计算机科学, no. 06 * |
| 江仙菊;: "以Digibook电子相册软件为例探索照片档案归档方法", 学理论, no. 08 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113326805A (en) * | 2021-06-24 | 2021-08-31 | 杭州海康威视数字技术股份有限公司 | Human body cover updating method and device, electronic equipment and storage medium |
| CN113326805B (en) * | 2021-06-24 | 2024-04-05 | 杭州海康威视数字技术股份有限公司 | Human body cover updating method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112883213B (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108733819B (en) | Personnel archive establishing method and device | |
| CN109284729B (en) | Method, device and medium for acquiring face recognition model training data based on video | |
| JP4553650B2 (en) | Image group representation method, descriptor derived by representation method, search method, apparatus, computer program, and storage medium | |
| US20160098636A1 (en) | Data processing apparatus, data processing method, and recording medium that stores computer program | |
| EP3358479A1 (en) | System, apparatus, method, program and recording medium for processing image | |
| US20130329059A1 (en) | Person detection system | |
| US8953039B2 (en) | System and method for auto-commissioning an intelligent video system | |
| CN111144332A (en) | Picture gathering method and device and electronic equipment | |
| JP2022518469A (en) | Information processing methods and devices, storage media | |
| CN111091106B (en) | Image clustering method and device, storage medium and electronic device | |
| CN111368867B (en) | File classifying method and system and computer readable storage medium | |
| CN110827432B (en) | Class attendance checking method and system based on face recognition | |
| CN113723157B (en) | Crop disease identification method and device, electronic equipment and storage medium | |
| CN112883213A (en) | Picture archiving method and device and electronic equipment | |
| KR20120051952A (en) | Method and apparatus for image searching using feature point | |
| CN110968719B (en) | Face clustering method and device | |
| CN112199555A (en) | Personnel gathering method and device and electronic equipment | |
| CN114863364B (en) | Security detection method and system based on intelligent video monitoring | |
| CN115937773A (en) | Intelligent image recognition system based on ai recognition | |
| CN112699810B (en) | Method and device for improving character recognition precision of indoor monitoring system | |
| CN111708906B (en) | Visiting retrieval method, device and equipment based on face recognition and storage medium | |
| CN115019360A (en) | Matching method and device, nonvolatile storage medium and computer equipment | |
| CN113591620A (en) | Early warning method, device and system based on integrated mobile acquisition equipment | |
| US20150208042A1 (en) | System and method for auto-commissioning an intelligent video system | |
| CN111563479B (en) | Concurrent person weight removing method, partner analyzing method and device and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |