CN103177102A - Method and device of image processing - Google Patents
Method and device of image processing Download PDFInfo
- Publication number
- CN103177102A CN103177102A CN2013100948620A CN201310094862A CN103177102A CN 103177102 A CN103177102 A CN 103177102A CN 2013100948620 A CN2013100948620 A CN 2013100948620A CN 201310094862 A CN201310094862 A CN 201310094862A CN 103177102 A CN103177102 A CN 103177102A
- Authority
- CN
- China
- Prior art keywords
- face
- people
- image
- similarity
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device of image processing. The method comprises the following steps: detecting human faces contained in each image in an image collection; respectively confirming the similarity of each detected human face and a preset target human face; and outputting the images in which the similarity of human faces and the target human face is not smaller than a preset value from the image collection. According to the method and the device of image processing, the human faces contained in the image are compared with the preset target human face to confirm and output the images containing the target human face, and the function that the images are classified according to the target human face is achieved.
Description
Technical field
The present invention relates to data processing field, more specifically, relate to a kind of image processing method and device.
Background technology
At present, along with popularizing of camera, the photo that people take is more and more.After shooting is completed, usually need comparison film to sort out management.
Photo carries some characteristic informations usually, such as comprising the information such as file type, file size, time.Generally can manage by these information comparison films, for example, can photo be sorted according to time sequencing, perhaps according to file type, photo be sorted.
Yet, when the user need to when photo is classified, can only realize by manual classification at present according to the feature in photo (for example people's face).
Summary of the invention
In view of this, the purpose of the embodiment of the present invention is to propose a kind of image processing method and device, has realized according to the feature in image classification of images.
In order to achieve the above object, the present invention proposes a kind of image processing method, comprises the following steps:
People's face that each image in the detected image set comprises;
Determine respectively the similarity of detected everyone face and default target people's face;
Output and the similarity of target people face are not less than the image under people's face of preset value from image collection.
The embodiment of the present invention compares by the people's face that will comprise in image and target people's face of presetting, determines and exports the image that comprises target people face, has realized the function of image being classified according to target people face.
Preferred as technique scheme, the people's face that will select from the detected people's face of image collection is defined as described default target people's face.This programme obtains the method for target people face for the user with providing convenience.
Preferred as technique scheme after the step of people's face that each image in described detected image set comprises, also comprises: will set up index between the image under detected people's face and described people's face.This programme can be realized fast finding by setting up index.
Preferred as technique scheme, the step that output and the similarity of target people face are not less than the image under people's face of preset value from image collection comprises: according to index, search the image under people's face that similarity with target people face is not less than preset value from image collection; The image that output finds.This method can the affiliated image of fast finding people face by index.
Preferred as technique scheme, it is described after output and the similarity of target people face are not less than image under people's face of preset value from image collection, also comprise: will be not less than copying image under people's face of preset value in the identical file folder, for the user provides convenience with the similarity of target people face in image collection.
The embodiment of the present invention also proposes a kind of image processing apparatus, comprising:
Detecting unit, the people's face that comprises for detection of each image in image collection;
Determining unit is used for determining respectively the similarity of detected everyone face and default target people's face;
Output unit is used for being not less than image under people's face of preset value from the similarity of image collection output and target people face.
Preferred as technique scheme, described device also comprises:
Default unit is used for being defined as from people's face that the detected people's face of image collection is selected described default target people's face.
Preferred as technique scheme, described device also comprises:
Set up indexing units, be used for and set up index between the image under detected people's face and described people's face.
Preferred as technique scheme, described output unit comprises:
Search module, be used for searching image under people's face that similarity with target people face is not less than preset value according to index from image collection;
Output module, the image that output finds.
Preferred as technique scheme, described device also comprises:
Copied cells is used for copying image under people's face that similarity with image collection and target people face is not less than preset value in the identical file folder.
The further feature of the embodiment of the present invention and advantage will be set forth in the following description, and, partly become apparent from instructions, perhaps understand by implementing the embodiment of the present invention.The purpose of the embodiment of the present invention and other advantages can realize and obtain by specifically noted structure in the instructions of writing, claims and accompanying drawing.
Below by drawings and Examples, the technical scheme of the embodiment of the present invention is described in further detail.
Description of drawings
Accompanying drawing is used to provide the further understanding to the embodiment of the present invention, and consists of the part of instructions, does not consist of the restriction to the embodiment of the present invention.In the accompanying drawings:
Fig. 1 is the process flow diagram of the image processing method of embodiment of the present invention proposition;
Fig. 2 is the process flow diagram of the image processing method of passing through of proposing of the embodiment of the present invention index realization of setting up people's face and image;
Fig. 3 be the embodiment of the present invention propose will identify the process flow diagram that image outputs to the image processing method of new folder;
Fig. 4 is the primary structure schematic diagram of the image processing apparatus of embodiment of the present invention proposition;
Fig. 5 is the concrete structure schematic diagram of the image processing apparatus of embodiment of the present invention proposition.
Embodiment
Below in conjunction with accompanying drawing, preferred embodiment is described, should be appreciated that preferred embodiment described herein only is used for the description and interpretation embodiment of the present invention, is not intended to limit the present invention embodiment.
Be illustrated in figure 1 as the main flow process of a kind of image processing method of embodiment of the present invention proposition, comprise the following steps:
Step S101: people's face that each image in the detected image set comprises.
Step S102: the similarity of determining respectively detected everyone face and default target people's face.
Wherein, default target people's face can be that the user obtains in advance, can be also people's face that the user selects in detected people's face from step S101.
Step S103: output and the similarity of target people face are not less than the image under people's face of preset value from image collection.
The embodiment of the present invention compares by the people's face that will comprise in image and target people's face of presetting, determines and exports the image that comprises target people face, can realize the function of image being classified according to target people face.
Introduce in detail implementation procedure below by two exemplary embodiments.
Passing through of being illustrated in figure 2 as that the embodiment of the present invention proposes set up the image processing method of the index realization of people's face and image.Particularly, comprise the following steps:
Step S201: people's face that each image in the detected image set comprises.
Wherein, image collection can be the image folder under user's specified path, can be also the image folder of depositing image that automatically detects, can be for example with camera that computer is connected in the file of depositing photo.
The people's face that comprises in detected image is that people's face detects, and can use following technology:
The assigned address of image can be converted into feature, and then the good sorter of training in advance will determine this part yes or no people face.Sorter is classified to the optional position of image and the part of arbitrary dimension (normally square or rectangular), judges yes or no people face.Image ratio with blank and static background is easier to process, if image only comprises a front face, as long as removed after background with regard to surplus human face only.More outstanding people's face detection algorithm is the cascade classifier algorithm of Viola-Jones at present.This algorithm uses the cascade classifier strategy based on the Haar feature, can have fast and effectively find the facial image of many attitude and size.
Step S202: the image under detected people's face and people's face is set up index.
For example detect that in image collection, image 1 comprises people's face 1, people's face 2, people's face 3, comprise people's face 1, people's face 2 in image 2.Set up index for people's face 1 and image 1, image 2, for people's face 2 and image 1, image 2 are set up index, for people's face 3 and image 1 are set up index.
Step S203: show detected people's face.
Step S204: receive the user to the selection instruction of detected people's face.
This selection instruction can be one or more in detected people's face, that is to say, has indicated one or more people's faces of selecting in this selection instruction.
Step S205: with people's face of selecting in selection instruction as target people face.
Step S206: for detected everyone face, calculate the similarity of this people's face and target people face.
Use face recognition algorithms, PCA (Principal Component Analysis for example, principal component analysis (PCA)) or SIFT (Scale-invariant feature transform, yardstick invariant features conversion) calculate the similarity between each people's face that detects and target people face.
Step S207: whether judge similarity more than or equal to preset value, if, execution in step S208; If not, ignore.
Preset value is for example 0.8, and this parameter can be adjusted.During more than or equal to preset value, illustrate that this people's face and target people face are same targets when similarity.
Step S208: search the image under this people's face according to index from image collection.
Step S209: the image that output finds.
In this embodiment, search image corresponding to people's face by setting up under people's face and people's face the index relative between image, can realize fast finding.
What be illustrated in figure 3 as embodiment of the present invention proposition will identify the image processing method that image outputs to new folder.Particularly, comprise the following steps:
Step S301: people's face that each image in the detected image set comprises.
Step S302: the image under detected people's face and people's face is set up index.
For example detect that in image collection, image 1 comprises people's face 1, people's face 2, people's face 3, comprise people's face 1, people's face 2 in image 2.Set up index for people's face 1 and image 1, image 2, for people's face 2 and image 1, image 2 are set up index, for people's face 3 and image 1 are set up index.
Step S303: show detected people's face.
Step S304: receive the user for the selection instruction of detected people's face.
This selection instruction can be one or more in detected people's face, that is to say, has indicated one or more people's faces of selecting in this selection instruction.
Step S305: with people's face of selecting in selection instruction as target people face.
Step S306: for detected everyone face, calculate the similarity of this people's face and target people face.
Use face recognition algorithms, PCA (Principal Component Analysis for example, principal component analysis (PCA)) or SIFT (Scale-invariant feature transform, yardstick invariant features conversion) calculate the similarity between each people's face that detects and target people face.
Step S307: whether judge the similarity that calculates more than or equal to preset value, if, execution in step S308; If not, ignore.
Preset value is for example 0.8, and this parameter can be adjusted.During more than or equal to preset value, illustrate that this people's face and target people face are same targets when similarity.
Step S308: search the image under this people's face according to index from image collection.
Step S309: judge whether to receive the instruction at the specified location in user new folder, if, execution in step S310, if not, execution in step S311.
Step S310: at the assigned address new folder, execution in step S312 then.
Step S311: at the position new folder that sets in advance, then execution in step S312.
Step S312: with the copying image that finds in new folder.
In this embodiment, can further the image that finds be outputed in new folder, for the user provides convenience.
Correspondingly, as shown in Figure 4, the embodiment of the present invention also proposes a kind of image processing apparatus, comprising:
Detecting unit 401, the people's face that comprises for detection of each image in image collection;
Determining unit 402 is used for determining respectively the similarity of detected everyone face and default target people's face;
Preferably, as shown in Figure 5, described device also comprises:
Preferably, as shown in Figure 5, described device also comprises:
Set up indexing units 405, be used for and set up index between the image under detected people's face and described people's face.
Preferably, described output unit 403 comprises:
Search module, be used for according to index, search the image under people's face that similarity with target people face is not less than preset value from image collection;
Output module, the image that output finds.
Preferably, as shown in Figure 5, described device also comprises:
Copied cells 406 is used for copying image under people's face that similarity with image collection and target people face is not less than preset value in the identical file folder.
The method and apparatus that the embodiment of the present invention provides compares by the people's face that will comprise in image and target people's face of presetting, determines and exports the image that comprises target people face, can realize the function of image being classified according to target people face.
Those skilled in the art should understand, the embodiment of the present invention can be provided as method, system or computer program.Therefore, the embodiment of the present invention can adopt complete hardware to realize, software is realized or in conjunction with the form of the realization of software and hardware aspect fully.And the embodiment of the present invention can adopt the form that wherein includes the upper computer program of implementing of computer-usable storage medium (including but not limited to magnetic disk memory and optical memory etc.) of computer usable program code one or more.
The embodiment of the present invention is that process flow diagram and/or the block scheme of reference method, equipment (system) and computer program described.Should understand can be by the flow process in each flow process in computer program instructions realization flow figure and/or block scheme and/or square frame and process flow diagram and/or block scheme and/or the combination of square frame.Can provide these computer program instructions to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine, make the instruction of carrying out by the processor of computing machine or other programmable data processing device produce to be used for the device of realizing in the function of flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame appointments.
These computer program instructions also can be stored in energy vectoring computer or the computer-readable memory of other programmable data processing device with ad hoc fashion work, make the instruction that is stored in this computer-readable memory produce the manufacture that comprises command device, this command device is realized the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame.
These computer program instructions also can be loaded on computing machine or other programmable data processing device, make on computing machine or other programmable device and to carry out the sequence of operations step producing computer implemented processing, thereby be provided for realizing the step of the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame in the instruction of carrying out on computing machine or other programmable device.
Obviously, those skilled in the art can carry out various changes and modification and not break away from the spirit and scope of the embodiment of the present invention the embodiment of the present invention.Like this, if within these of the embodiment of the present invention are revised and modification belongs to the scope of claim and equivalent technologies thereof, the embodiment of the present invention also is intended to comprise these changes and modification interior.
Claims (10)
1. an image processing method, is characterized in that, comprises the following steps:
People's face that each image in the detected image set comprises;
Determine respectively the similarity of detected everyone face and default target people's face;
Output and the similarity of target people face are not less than the image under people's face of preset value from image collection.
2. method according to claim 1, is characterized in that, the people's face that will select from the detected people's face of image collection is defined as described default target people's face.
3. method according to claim 1 and 2, is characterized in that, after the step of people's face that each image in described detected image set comprises, also comprises:
To set up index between the image under detected people's face and described people's face.
4. method according to claim 3, is characterized in that, the step that output and the similarity of target people face are not less than the image under people's face of preset value from image collection comprises:
According to index, search the image under people's face that similarity with target people face is not less than preset value from image collection;
The image that output finds.
5. method according to claim 1, is characterized in that, and is described after output and the similarity of target people face are not less than image under people's face of preset value from image collection, also comprises:
To be not less than copying image under people's face of preset value in the identical file folder with the similarity of target people face in image collection.
6. an image processing apparatus, is characterized in that, comprising:
Detecting unit, the people's face that comprises for detection of each image in image collection;
Determining unit is used for determining respectively the similarity of detected everyone face and default target people's face;
Output unit is used for being not less than image under people's face of preset value from the similarity of image collection output and target people face.
7. device according to claim 6, is characterized in that, described device also comprises:
Default unit is used for being defined as from people's face that the detected people's face of image collection is selected described default target people's face.
8. according to claim 6 or 7 described devices, is characterized in that, described device also comprises:
Set up indexing units, be used for and set up index between the image under detected people's face and described people's face.
9. device according to claim 8, is characterized in that, described output unit comprises:
Search module, be used for according to index, search the image under people's face that similarity with target people face is not less than preset value from image collection;
Output module, the image that output finds.
10. device according to claim 6, is characterized in that, described device also comprises:
Copied cells is used for copying image under people's face that similarity with image collection and target people face is not less than preset value in the identical file folder.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100948620A CN103177102A (en) | 2013-03-22 | 2013-03-22 | Method and device of image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100948620A CN103177102A (en) | 2013-03-22 | 2013-03-22 | Method and device of image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103177102A true CN103177102A (en) | 2013-06-26 |
Family
ID=48636963
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013100948620A Pending CN103177102A (en) | 2013-03-22 | 2013-03-22 | Method and device of image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103177102A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133917A (en) * | 2014-08-15 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Method and device for storing pictures in classified mode |
| CN105320406A (en) * | 2015-11-06 | 2016-02-10 | 深圳市金立通信设备有限公司 | Picture management method and terminal |
| WO2017088470A1 (en) * | 2015-11-27 | 2017-06-01 | 小米科技有限责任公司 | Image classification method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5034901A (en) * | 1985-10-07 | 1991-07-23 | Mitsubishi Denki Kabushiki Kaisha | Interactive graphic recognition and data processing system |
| CN101021870A (en) * | 2007-03-20 | 2007-08-22 | 北京中星微电子有限公司 | Picture inquiry method and system |
| CN101510934A (en) * | 2009-03-20 | 2009-08-19 | 北京中星微电子有限公司 | Digital plate frame and method for displaying photo |
| CN102682091A (en) * | 2012-04-25 | 2012-09-19 | 腾讯科技（深圳）有限公司 | Cloud-service-based visual search method and cloud-service-based visual search system |
-
2013
- 2013-03-22 CN CN2013100948620A patent/CN103177102A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5034901A (en) * | 1985-10-07 | 1991-07-23 | Mitsubishi Denki Kabushiki Kaisha | Interactive graphic recognition and data processing system |
| CN101021870A (en) * | 2007-03-20 | 2007-08-22 | 北京中星微电子有限公司 | Picture inquiry method and system |
| CN101510934A (en) * | 2009-03-20 | 2009-08-19 | 北京中星微电子有限公司 | Digital plate frame and method for displaying photo |
| CN102682091A (en) * | 2012-04-25 | 2012-09-19 | 腾讯科技（深圳）有限公司 | Cloud-service-based visual search method and cloud-service-based visual search system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104133917A (en) * | 2014-08-15 | 2014-11-05 | 百度在线网络技术（北京）有限公司 | Method and device for storing pictures in classified mode |
| CN104133917B (en) * | 2014-08-15 | 2018-08-10 | 百度在线网络技术（北京）有限公司 | The classification storage method and device of photo |
| US10146796B2 (en) | 2014-08-15 | 2018-12-04 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for photograph classification and storage |
| CN105320406A (en) * | 2015-11-06 | 2016-02-10 | 深圳市金立通信设备有限公司 | Picture management method and terminal |
| WO2017088470A1 (en) * | 2015-11-27 | 2017-06-01 | 小米科技有限责任公司 | Image classification method and device |
| US10282597B2 (en) | 2015-11-27 | 2019-05-07 | Xiaomi Inc. | Image classification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI684922B (en) | Image-based vehicle damage determination method, device, electronic equipment and system | |
| CN107403424B (en) | Vehicle loss assessment method and device based on image and electronic equipment | |
| CN102033958B (en) | Photo sort management system and method | |
| US8626762B2 (en) | Display apparatus and method of providing a user interface | |
| CN103729120A (en) | Method for generating thumbnail image and electronic device thereof | |
| JP2021533497A (en) | High-speed detection methods for video objects, devices, servers and storage media | |
| JP5235691B2 (en) | Information processing apparatus and information processing method | |
| CN108960163A (en) | Gesture identification method, device, equipment and storage medium | |
| WO2012124000A1 (en) | Image recognition system, image recognition method, and nontemporary computer- readable medium in which program for image recognition is stored | |
| CN104050449A (en) | Face recognition method and device | |
| CN102819726A (en) | System and method for processing photograph of mobile terminal | |
| CN102955664A (en) | Method and system for electronic book display adjustment | |
| CN105760533A (en) | Photo management method and photo management device | |
| CN106101540A (en) | Focusing determines method and device | |
| CN103186770B (en) | Subject means of identification and dictionary data registration method | |
| CN106294549A (en) | A kind of image processing method and terminal | |
| CN106982326A (en) | Its focalization method and terminal | |
| CN106056138A (en) | Picture processing device and method | |
| US20230297609A1 (en) | Systems and methods for naming objects based on object content | |
| CN111310634B (en) | Certificate type recognition template generation method, certificate recognition method and device | |
| CN103177102A (en) | Method and device of image processing | |
| CN108833881B (en) | Method and device for constructing image depth information | |
| US11429660B2 (en) | Photo processing method, device and computer equipment | |
| CN105787131A (en) | Information processing method and device and mobile terminal | |
| CN111860287A (en) | Target detection method and device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 100085 Beijing city Haidian District Qinghe Street No. 68 Huarun colorful city shopping center two floor 13 Applicant after: Xiaomi Technology Co., Ltd. Address before: 100102 Beijing Wangjing West Road, a volume of stone world building, A, block, floor 12 Applicant before: Beijing Xiaomi Technology Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130626 |
|
| RJ01 | Rejection of invention patent application after publication |