CN112839173A - Shooting subject type identification method and system - Google Patents

Shooting subject type identification method and system Download PDF

Info

Publication number
CN112839173A
CN112839173A CN202011640187.3A CN202011640187A CN112839173A CN 112839173 A CN112839173 A CN 112839173A CN 202011640187 A CN202011640187 A CN 202011640187A CN 112839173 A CN112839173 A CN 112839173A
Authority
CN
China
Prior art keywords
shooting
area
subject type
judging whether
face
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
Application number
CN202011640187.3A
Other languages
Chinese (zh)
Other versions
CN112839173B (en
Inventor
黄安昊
李琪
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Instant Play Technology Co ltd
Original Assignee
Shenzhen Instant Play Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Instant Play Technology Co ltd filed Critical Shenzhen Instant Play Technology Co ltd
Priority to CN202011640187.3A priority Critical patent/CN112839173B/en
Publication of CN112839173A publication Critical patent/CN112839173A/en
Application granted granted Critical
Publication of CN112839173B publication Critical patent/CN112839173B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/63—Control of cameras or camera modules by using electronic viewfinders
    • H04N23/631—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters
    • H04N23/632—Graphical user interfaces [GUI] specially adapted for controlling image capture or setting capture parameters for displaying or modifying preview images prior to image capturing, e.g. variety of image resolutions or capturing parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/61—Control of cameras or camera modules based on recognised objects
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Image Analysis (AREA)
  • Studio Devices (AREA)
  • Image Processing (AREA)

Abstract

The invention provides a shooting subject type identification method and system, and relates to the technical field of image identification. The invention analyzes the image from three dimensions of shooting mode, shooting position and image area ratio, identifies the shooting subject type of the image, and divides the shooting subject type into three types of character, background and character + background, realizes the overall identification of the shooting subject type of the image, and provides support for the generation of subsequent preview pictures.

Description

Shooting subject type identification method and system
Technical Field
The invention relates to the technical field of cloud mobile phones, in particular to a shooting subject type identification method and system.
Background
When generating a preview image of an image, it is often necessary to determine the type of a subject in the image, select different zoom strategies for different types of subjects, and finally generate the preview image.
However, in the existing method for identifying the type of the subject, the central area of the image is usually used as the position of the type of the subject, and then the object at the position of the subject is identified to determine the type of the subject.
However, in actual shooting, the composition of the shot is not the subject installed at the center, and the above method only considers the object in the local area, cannot identify the type of the subject from the whole image, and easily omits information in other areas.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a shooting subject type identification method and a shooting subject type identification system, which solve the problem that the shooting subject type cannot be identified from the whole image by the existing method.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
in a first aspect, a photographic subject type identification method is provided, including:
judging whether the shooting mode in the shooting information is a portrait or not based on the shooting information, and if so, enabling a first judgment item v1(P) is 1, otherwise, let v1(P)＝0；
Judging whether the shooting place is a hot shooting area or not based on the shooting information, and if so, ordering a second judgment item v2(P) is 0, otherwise, let v2(P)＝1；
Judging whether the number of the face areas is more than 0, if so, judging whether the portrait area ratio is more than a first ratio threshold value, and if so, enabling a third judgment item v3(P) is 1, otherwise, let v3(P)＝0；
Calculating whether the determination value V (P) is greater than the determination threshold value V0If yes, identifying the type of the shooting subject as a figure;
wherein V (P) k1*v1(P)+k2*v2(P)+k3*v3(P), and k1～k3Is the weight of each decision term.
Further, the method further comprises:
calculating whether the determination value V (P) is greater than the determination threshold value V0If not, the shooting subject type is identified as the person + the background.
Further, the method further comprises:
and judging whether the number of the face areas is greater than 0, if not, judging whether the shooting place is a hot shooting area, and if so, identifying the type of the shooting subject as a background.
Further, the weight k of each decision term1～k3Are all 1, and the threshold value V is determined0Is 1.5.
Further, the determining whether the shooting location is a hot shooting area includes:
acquiring a shooting place from the shooting information;
determining whether a shooting place is in a hot shooting area; the hot shooting area comprises a scenic region and an area in which the ratio of the image with the shooting subject type as the background in the area to the total number of images in the database exceeds a second ratio threshold.
Further, the calculation method for judging the area of the portrait includes:
respectively identifying a face area and a human body area in the image;
acquiring an identification frame corresponding to the human body region and an identification frame corresponding to the face region to obtain a human body region set Rb ═ { Rb1,rb2,...,rbn}，rbnDenotes the nth human body region and the set of facial regions Rf ═ Rf1,rf2,...,rfn}，rfnRepresents the nth face region;
calculating the human body area occupation range Sb＝rb1∪rb2∪...∪rbn；
Deletion of S in RfbThe corrected face region set Rf 'is obtained for the face regions within the range'1,rf’2,...,rf’m}；
The facial region in Rf' is compared with SbPerforming intersection operation to obtain a superposition area set Z;
calculating face region occupation range Sf＝rf’1+rf’2+...+rf’m；
Obtaining the portrait area Sp＝Sb+Sf-Z。
Further, the face region or the human body region includes coordinates of the recognition frame and an occupied area of the recognition frame.
In a second aspect, a photographic subject type identification system is provided, the system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method when executing the computer program:
judging whether the shooting mode in the shooting information is a portrait or not based on the shooting information, and if so, enabling a first judgment item v1(P) is 1, otherwise, let v1(P)＝0；
Judging whether the shooting place is a hot shooting area or not based on the shooting information, and if so, ordering a second judgment item v2(P) is 0, otherwise, let v2(P)＝1；
Judging whether the number of the face areas is more than 0, if so, judging whether the portrait area ratio is more than a first ratio threshold value, and if so, enabling a third judgment item v3(P) is 1, otherwise, let v3(P)＝0；
Calculating whether the determination value V (P) is greater than the determination threshold value V0If yes, identifying the type of the shooting subject as a figure;
wherein V (P) k1*v1(P)+k2*v2(P)+k3*v3(P), and k1～k3Is the weight of each decision term.
Further, the method further comprises:
calculating whether the determination value V (P) is greater than the determination threshold value V0If not, the shooting subject type is identified as the person + the background.
Further, the method further comprises:
and judging whether the number of the face areas is greater than 0, if not, judging whether the shooting place is a hot shooting area, and if so, identifying the type of the shooting subject as a background.
Further, the weight k of each decision term1～k3Are all 1, and the threshold value V is determined0Is 1.5.
Further, the determining whether the shooting location is a hot shooting area includes:
acquiring a shooting place from the shooting information;
determining whether a shooting place is in a hot shooting area; the hot shooting area comprises a scenic region and an area in which the ratio of the image with the shooting subject type as the background in the area to the total number of images in the database exceeds a second ratio threshold.
Further, the calculation method for judging the area of the portrait includes:
respectively identifying a face area and a human body area in the image;
acquiring an identification frame corresponding to the human body region and an identification frame corresponding to the face region to obtain a human body region set Rb ═ { Rb1,rb2,...,rbn}，rbnDenotes the nth human body region and the set of facial regions Rf ═ Rf1,rf2,...,rfn}，rfnRepresents the nth face region;
calculating the human body area occupation range Sb＝rb1∪rb2∪...∪rbn；
Deletion of S in RfbThe corrected face region set Rf 'is obtained for the face regions within the range'1,rf’2,...,rf’m}；
The facial region in Rf' is compared with SbPerforming intersection operation to obtain a superposition area set Z;
calculating face region occupation range Sf＝rf’1+rf’2+...+rf’m；
Obtaining the portrait area Sp＝Sb+Sf-Z。
Further, the face region or the human body region includes coordinates of the recognition frame and an occupied area of the recognition frame.
(III) advantageous effects
The invention provides a shooting subject type identification method and system. Compared with the prior art, the method has the following beneficial effects:
according to the invention, the image is analyzed from three dimensions of the shooting mode, the shooting position and the image area ratio, the image information is fully utilized, the shooting subject type of the image is identified and is divided into three types of the character, the background and the character + background, the shooting subject type of the image is identified on the whole, the accuracy of the shooting subject type identification is improved, and support is provided for the generation of a subsequent preview image.
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 flow chart of an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are a part of the embodiments of the present invention, but 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.
The embodiment of the application provides a shooting subject type identification method and system, and solves the problem that the shooting subject type cannot be identified from the whole image in the existing method.
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Example 1:
as shown in fig. 1, the present invention provides a photographic subject type identification method, including:
judging whether the shooting mode in the shooting information is a portrait or not based on the shooting information, and if so, enabling a first judgment item v1(P) is 1, otherwise, let v1(P)＝0；
Judging whether the shooting place is hot or not based on the shooting informationShooting the area by the door, if so, making a second judgment item v2(P) is 0, otherwise, let v2(P)＝1；
It is determined whether the number of face regions is greater than 0,
if yes, judging whether the portrait area ratio is larger than the first ratio threshold value, if yes, enabling a third judgment item v3(P) is 1, otherwise, let v3(P)＝0；
If not, judging whether the shooting place is a hot shooting area or not, and if so, identifying the type of the shooting subject as a background.
Calculating whether the determination value V (P) is greater than the determination threshold value V0If yes, identifying the type of the shooting subject as a figure; if not, the shooting subject type is identified as the person + the background.
Wherein V (P) k1*v1(P)+k2*v2(P)+k3*v3(P), and k1～k3Is the weight of each decision term.
The beneficial effect of this embodiment does:
the image is analyzed from three dimensions of shooting mode, shooting position and portrait area ratio, the shooting subject type of the image is identified and is divided into three types of characters, background and character + background, the shooting subject type of the image is identified on the whole, and support is provided for the generation of a subsequent preview image.
The following describes the implementation process of the embodiment of the present invention in detail:
in consideration of three types of photographing scenes most common to users, the types of photographing subjects are classified into a character, a background, and a character + background. The method for analyzing the three dimensions of the shooting mode, the shooting position and the human image area ratio in the embodiment specifically comprises steps from S21 to S24:
s21, based on the shooting information, judging whether the shooting mode in the shooting information is a portrait, if so, making a first judgment item v1(P) is 1, otherwise, let v1(P)＝0；
S22, based on the shooting information, judging whether the shooting location is a hot shooting area, if yes, making a second judgment item v2(P) ═ 0, otherwise,let v2(P)＝1；
The judging whether the shooting place is a hot shooting area or not comprises the following steps:
firstly, acquiring a shooting place from shooting information; then determining whether the shooting place is in a hot shooting area; the hot shooting area comprises a scenic region and an area in which the ratio of the image with the shooting subject type as the background in the area to the total number of images in the database exceeds a second ratio threshold.
For example, the database is constructed in advance from various types of images labeled with the type of the subject and the shooting position. Each unit area is divided into a shooting area, and according to the shooting position, 100 corresponding images are known in the database in total in a certain shooting area, wherein the shooting subject type of 80 images is the environment, and the second percentage threshold value is set to be 70%, then the shooting area can be set as a hot shooting area.
S23, judging whether the number of the face areas is larger than 0, if so, judging whether the portrait area ratio is larger than a first ratio threshold value, for example, the first ratio threshold value can be set to 34%, if so, making a third judgment item v3(P) is 1, otherwise, let v3(P)＝0；
And judging whether the number of the face areas is greater than 0, if not, judging whether the shooting place is a hot shooting area, and if so, identifying the type of the shooting subject as a background.
When calculating the portrait area ratio, the problem that there may be overlapping between the human recognition frames and the problem that the face region and the human recognition frame are repeatedly calculated need to be considered, so the calculation method of the portrait area ratio includes K1 to K7:
k1, respectively identifying a face area and a human body area in the image;
k2, obtaining a recognition frame corresponding to the human body region and a recognition frame corresponding to the face region, and obtaining a human body region set Rb ═ { Rb1,rb2,...,rbn}，rbnDenotes the nth human body region and the set of facial regions Rf ═ Rf1,rf2,...,rfn}，rfnRepresents the nth face region;
k3 calculating human bodyArea occupation range Sb＝rb1∪rb2∪...∪rbn；
K4 deletion of Rf at SbThe corrected face region set Rf 'is obtained for the face regions within the range'1,rf’2,...,rf’m}；
K5, matching the facial region in Rf' with SbPerforming intersection operation to obtain a superposition area set Z;
k6, calculating face area occupation range Sf＝rf’1+rf’2+...+rf’m；
K7 obtaining portrait area Sp＝Sb+Sf-Z。
For example, if 3 faces and 2 persons are recognized, Rb ═ Rb1,rb2}，Rf＝{rf1,rf2,rf3}；rb1Representing a first body region, rf1The first face area is shown, and the rest is analogized, and the face and the human body area comprise the coordinates of the identification frame and the occupied area information of the identification frame. The occupied area of the body region, i.e. the total area S occupied by the body regionb＝rb1∪rb2(ii) a Then determining whether rf is needed based on the coordinates1,rf2,rf3In the presence of a complete site at SbIf any, the face region is deleted to obtain Rf ═ { Rf'1,rf’2}; let the facial region in Rf' and SbPerforming intersection calculation to obtain a superposition region set Z, wherein the set Z contains rf'1And SbOf and rf'2And SbThe overlapping area of (a); if Z is not null, it indicates that the face region overlaps the body region and needs to be removed, and therefore, the portrait area Sp＝Sb+Sf-Z。
S24, calculating whether the judgment value V (P) is larger than the judgment threshold value V0If yes, shooting the type of the subject as a figure; if not, the shooting subject type is identified as the person + the background. Wherein V (P) k1*v1(P)+k2*v2(P)+k3*v3(P), and k1～k3Is the weight of each decision term.
For example, the weight k of each decision term1～k3All set to 1, the determination threshold V0 is set to 1.5, that is, at least two of the three determination items need to be satisfied to determine that the type of the subject is a person, otherwise, the type of the subject is a person + background.
Example 2
The invention also provides a photographic subject type identification system, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the following steps:
judging whether the shooting mode in the shooting information is a portrait or not based on the shooting information, if so, making the first judgment item v1(P) equal to 1, and otherwise, making the v1(P) equal to 0;
judging whether the shooting place is a hot shooting area or not based on the shooting information, if so, making the second judgment item v2(P) equal to 0, and otherwise, making v2(P) equal to 1;
judging whether the number of the face regions is greater than 0, if so, judging whether the portrait area ratio is greater than a first ratio threshold, if so, making the third judgment item v3(P) be 1, otherwise, making v3(P) be 0;
calculating whether the judgment value V (P) is larger than a judgment threshold value V0, and if so, identifying the type of the shooting subject as a person;
where v (P) ═ k1 × v1(P) + k2 × v2(P) + k3 × v3(P), and k1 to k3 are the weights of the respective determination terms.
Further, the method further comprises:
and calculating whether the judgment value V (P) is larger than a judgment threshold value V0, and if not, identifying the type of the shooting subject as a person + background.
Further, the method further comprises:
and judging whether the number of the face areas is greater than 0, if not, judging whether the shooting place is a hot shooting area, and if so, identifying the type of the shooting subject as a background.
Further, the weights k1 to k3 of the respective determination terms are all 1, and the determination threshold V0 is 1.5.
Further, the determining whether the shooting location is a hot shooting area includes:
acquiring a shooting place from the shooting information;
determining whether a shooting place is in a hot shooting area; the hot shooting area comprises a scenic region and an area in which the ratio of the image with the shooting subject type as the background in the area to the total number of images in the database exceeds a second ratio threshold.
Further, the calculation method for judging the area of the portrait includes:
respectively identifying a face area and a human body area in the image;
acquiring an identification frame corresponding to the human body region and an identification frame corresponding to the face region to obtain a human body region set Rb ═ { Rb1,rb2,...,rbn}，rbnDenotes the nth human body region and the set of facial regions Rf ═ Rf1,rf2,...,rfn}，rfnRepresents the nth face region;
calculating the human body area occupation range Sb＝rb1∪rb2∪...∪rbn；
Deletion of S in RfbThe corrected face region set Rf 'is obtained for the face regions within the range'1,rf’2,...,rf’m}；
The facial region in Rf' is compared with SbPerforming intersection operation to obtain a superposition area set Z;
calculating face region occupation range Sf＝rf’1+rf’2+...+rf’m；
Obtaining the portrait area Sp＝Sb+Sf-Z。
Further, the face region or the human body region includes coordinates of the recognition frame and an occupied area of the recognition frame.
It can be understood that the system for identifying the type of the photographic subject provided by the embodiment of the present invention corresponds to the method for identifying the type of the photographic subject, and the explanation, examples, and beneficial effects of the relevant contents thereof may refer to the corresponding contents in the method for identifying the type of the photographic subject, which are not described herein again.
In summary, compared with the prior art, the invention has the following beneficial effects:
the image is analyzed from three dimensions of shooting mode, shooting position and portrait area ratio, the shooting subject type of the image is identified and is divided into three types of characters, background and character + background, the shooting subject type of the image is identified on the whole, and support is provided for the generation of a subsequent preview image.
It should be noted that, through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform. With this understanding, the above technical solutions may be embodied in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes 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 embodiments or some parts of the embodiments. In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
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 photographic subject type identification method, characterized by comprising:
judging whether the shooting mode in the shooting information is a portrait or not based on the shooting information, and if so, enabling a first judgment item v1(P) is 1, otherwise, let v1(P)＝0；
Judging whether the shooting place is a hot shooting area or not based on the shooting information, and if so, ordering a second judgment item v2(P) is 0, otherwise, let v2(P)＝1；
Judging whether the number of the face areas is more than 0, if so, judging whether the portrait area ratio is more than a first ratio threshold value, and if so, enabling a third judgment item v3(P) is 1, otherwise, let v3(P)＝0；
Calculating whether the determination value V (P) is greater than the determination threshold value V0If yes, identifying the type of the shooting subject as a figure;
wherein V (P) k1*v1(P)+k2*v2(P)+k3*v3(P), and k1～k3Is the weight of each decision term.
2. The photographic subject type identification method according to claim 1, characterized by further comprising:
calculating whether the determination value V (P) is greater than the determination threshold value V0If not, the shooting subject type is identified as the person + the background.
3. The photographic subject type identification method according to claim 1, characterized by further comprising:
and judging whether the number of the face areas is greater than 0, if not, judging whether the shooting place is a hot shooting area, and if so, identifying the type of the shooting subject as a background.
4. The photographic subject type identification method according to claim 1, wherein the weight k of each decision term1～k3Are all 1, and the threshold value V is determined0Is 1.5.
5. The photographic subject type identification method according to claim 1, wherein the judging whether the photographic place is a hot photographic area comprises:
acquiring a shooting place from the shooting information;
determining whether a shooting place is in a hot shooting area; the hot shooting area comprises a scenic region and an area in which the ratio of the image with the shooting subject type as the background in the area to the total number of images in the database exceeds a second ratio threshold.
6. The photographic subject type identification method according to claim 1, wherein the calculation method of judging the portrait area includes:
respectively identifying a face area and a human body area in the image;
acquiring an identification frame corresponding to the human body region and an identification frame corresponding to the face region to obtain a human body region set Rb ═ { Rb1,rb2,...,rbn}，rbnDenotes the nth human body region and the set of facial regions Rf ═ Rf1,rf2,...,rfn}，rfnRepresents the nth face region;
calculating the human body area occupation range Sb＝rb1∪rb2∪...∪rbn；
Deletion of S in RfbThe corrected face region set Rf 'is obtained for the face regions within the range'1,rf’2,...,rf’m}；
The facial region in Rf' is compared with SbPerforming intersection operation to obtain a superposition area set Z;
calculating face region occupation range Sf＝rf’1+rf’2+...+rf’m；
Obtaining the portrait area Sp＝Sb+Sf-Z。
7. The photographic subject type identification method according to claim 6, wherein the face area or the body area each contains coordinates of an identification frame and an occupation area of the identification frame.
8. A photographic subject type identification system, the system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any of claims 1-7 when executing the computer program.
CN202011640187.3A 2020-12-31 2020-12-31 Shooting subject type identification method and system Active CN112839173B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011640187.3A CN112839173B (en) 2020-12-31 2020-12-31 Shooting subject type identification method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011640187.3A CN112839173B (en) 2020-12-31 2020-12-31 Shooting subject type identification method and system

Publications (2)

Publication Number Publication Date
CN112839173A true CN112839173A (en) 2021-05-25
CN112839173B CN112839173B (en) 2022-05-20

Family

ID=75926835

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011640187.3A Active CN112839173B (en) 2020-12-31 2020-12-31 Shooting subject type identification method and system

Country Status (1)

Country Link
CN (1) CN112839173B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016213574A (en) * 2015-04-30 2016-12-15 キヤノン株式会社 Image processing apparatus and control method of image processing apparatus
CN107128492A (en) * 2017-05-05 2017-09-05 成都通甲优博科技有限责任公司 A kind of unmanned plane tracking, device and unmanned plane detected based on the number of people
CN109033991A (en) * 2018-07-02 2018-12-18 北京搜狗科技发展有限公司 A kind of image-recognizing method and device
CN109784124A (en) * 2017-11-10 2019-05-21 北京嘀嘀无限科技发展有限公司 A kind of determination method of vivo identification, decision-making system and computer installation
CN111669492A (en) * 2019-03-06 2020-09-15 青岛海信移动通信技术股份有限公司 Method for processing shot digital image by terminal and terminal

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016213574A (en) * 2015-04-30 2016-12-15 キヤノン株式会社 Image processing apparatus and control method of image processing apparatus
CN107128492A (en) * 2017-05-05 2017-09-05 成都通甲优博科技有限责任公司 A kind of unmanned plane tracking, device and unmanned plane detected based on the number of people
CN109784124A (en) * 2017-11-10 2019-05-21 北京嘀嘀无限科技发展有限公司 A kind of determination method of vivo identification, decision-making system and computer installation
CN109033991A (en) * 2018-07-02 2018-12-18 北京搜狗科技发展有限公司 A kind of image-recognizing method and device
CN111669492A (en) * 2019-03-06 2020-09-15 青岛海信移动通信技术股份有限公司 Method for processing shot digital image by terminal and terminal

Also Published As

Publication number Publication date
CN112839173B (en) 2022-05-20

Similar Documents

Publication Publication Date Title
CN108733819B (en) Personnel archive establishing method and device
TWI773189B (en) Method of detecting object based on artificial intelligence, device, equipment and computer-readable storage medium
US9477685B1 (en) Finding untagged images of a social network member
CN108776834B (en) System reinforcement learning method and device, electronic equipment and computer storage medium
KR20200098875A (en) System and method for providing 3D face recognition
US20070174272A1 (en) Facial Recognition in Groups
JP2000306095A (en) Image collation/retrieval system
TW202026948A (en) Methods and devices for biological testing and storage medium thereof
CN111814620A (en) Face image quality evaluation model establishing method, optimization method, medium and device
Surikov et al. Floor plan recognition and vectorization using combination unet, faster-rcnn, statistical component analysis and ramer-douglas-peucker
JP2014164656A (en) Image processing method and program
Takahashi et al. Estimation of the attractiveness of food photography focusing on main ingredients
CN111144215A (en) Image processing method, image processing device, electronic equipment and storage medium
US11615292B2 (en) Projecting images to a generative model based on gradient-free latent vector determination
CN111723707A (en) Method and device for estimating fixation point based on visual saliency
Kim et al. Stabilized adaptive sampling control for reliable real-time learning-based surveillance systems
Nikita Quantitative sex estimation based on cranial traits using R functions
CN111860253A (en) Multitask attribute identification method, multitask attribute identification device, multitask attribute identification medium and multitask attribute identification equipment for driving scene
CN110321935A (en) Business event relationship determines method and device, computer readable storage medium
Chamoso et al. Social computing for image matching
CN112766164A (en) Face recognition model training method, device and equipment and readable storage medium
CN112839173B (en) Shooting subject type identification method and system
JP7276483B2 (en) LEARNING DEVICE, CLASSIFIER, LEARNING METHOD AND LEARNING PROGRAM
CN111274447A (en) Target expression generation method, device, medium and electronic equipment based on video
CN115798005A (en) Reference photo processing method and device, processor 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