CN105744141A - Intelligent shooting method and apparatus - Google Patents
Intelligent shooting method and apparatus Download PDFInfo
- Publication number
- CN105744141A CN105744141A CN201410765226.0A CN201410765226A CN105744141A CN 105744141 A CN105744141 A CN 105744141A CN 201410765226 A CN201410765226 A CN 201410765226A CN 105744141 A CN105744141 A CN 105744141A
- Authority
- CN
- China
- Prior art keywords
- photo
- group
- feature object
- frame
- picture
- 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
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
- H04N23/61—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
- H04N23/63—Control of cameras or camera modules by using electronic viewfinders
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent shooting method and apparatus, and relates to the field of an intelligent mobile device. The method comprises the following steps: within one time period, capturing one frame or multiple frames of an image; performing similarity analysis on each obtained frame of the image with a feature object of a corresponding type; and when the similarity between at least one frame of the image and the feature object meets a preset condition, outputting a frame of the image, having the highest similarity with the feature object. According to the invention, the method and apparatus can be based on user demands and can realize automatic learning, images with expressions, motion and postures closer to the user demands can be obtained through capture of frame images, and the problem of shooting delay is solved accordingly.
Description
Technical field
The present invention relates to Intelligent mobile equipment field, be specifically related to the method and apparatus that a kind of intelligence is taken pictures.
Background technology
Becoming better and better along with the photographic head on intelligent movable equipment (such as smart mobile phone, panel computer) configures, captured picture quality is also more and more higher, and people start more and more to use intelligent movable equipment to carry out photograph taking.The photographic quality of shooting, is subject to the impact of a lot of objective factor, wants to shoot the photo that quality is higher, not only need the photographic head that resolution is higher, but also need photographer to possess certain photography general knowledge.
Such as: when clapping travelling fish, capture less than the picture wanted；When clapping smiling face, photographed nictation, or facial expression was not reciprocity；When skyborne photo is takeoff in take, it not be exactly too late too early, repeat to clap more than once.
The problems referred to above are concentrated mainly on several aspects:
1, see that moment to the moment that shutter is pressed of picture has individual brain poor for reflex time, cause that picture that eyes see and shutter are pressed the picture of moment and be there is difference；
2, differently configured for camera, shutter is pressed a delay between imaging, the picture of picture and cameras record that shutter presses moment exists difference；
3, the focus on shooting base plate changes at any time, including, the macro position change of whole focus, and the micro-variations of each ingredient of focus, it is impossible to capture the moment wanted most；
4, cannot take, according to the demand difference of every user, the photo being best suitable for each user.
Reason above causes that the success rate when taking pictures is not high, and Consumer's Experience is bad, it is difficult to position picture accurately.
Reduce these only by the configuration improving equipment at present for problem 1,2 to postpone；
For problem 3, current solution is mainly the motor pattern of camera, it is captured object and is kept in motion (relative motion), the movement tendency of captured object can be predicted by camera, and change corresponding time of exposure, shutter speed, and starting stabilization pattern etc., main purpose is used to the focusing success being more prone to, thus obtaining the photograph that quality is higher；
For problem 4, current photographing device cannot go to shoot the picture meeting user's request according to the demand of user.
In a word, current technology scheme mainly addresses how location shooting focus, goes dynamically to adjust the parameter of camera lens according to the picture that camera lens catches, carries out process of refinement for focus, to expect close to the desirable requirement of user；It is not solved by time delay and the process problem to content of taking pictures, it does not have relate to the specific demand problem of user.
Summary of the invention
In order to solve above-mentioned technical problem, the present invention provides the method and apparatus that a kind of intelligence is taken pictures, it is possible to the demand according to user, and frame picture is captured, and solves the problem postponed of taking pictures.
In order to reach the object of the invention, the invention provides a kind of method that intelligence is taken pictures, including:
Within a time cycle, capture a frame or multiframe picture；
The each frame picture obtained is carried out similarity analysis with the feature object of corresponding classification；
When there is at least one frame picture similarity with described feature object and meeting pre-conditioned, the frame picture that output is the highest with described feature object similarity.
Further, before described crawl one frame or multiframe picture, also include:
Preset photo for one group by learning described classification, it is thus achieved that this group presets the similitude of photo, produces the feature object of this described classification.
Further, when the similarity of the whole frame pictures captured with described feature object is all unsatisfactory for pre-conditioned, normally takes pictures and/or adjust pre-conditioned.
Further, described within a time cycle, capture a frame or multiframe picture includes: within the described time cycle, at interval of Preset Time, capture a frame picture, described Preset Time is less than or equal to the time cycle.
Further, after described crawl one frame or multiframe picture, also include: a frame described in buffer memory or multiframe picture.
Further, after the frame picture that output and described feature object similarity are the highest, also include:
A frame picture the highest for described similarity is added this group and presets photo, relearn and obtain this group and preset the similitude of photo, produce the feature object of described classification.
Further, photo is preset for one group by learning described classification, it is thus achieved that this group presets the similitude of photo, and the feature object producing described classification includes:
The size that this group is all preset photo is unified for same specification；
According to heterochromia in image processing algorithm and photo, the feature of the default photo of this group every is modeled simulation, generates characteristics of image；
The characteristics of image generated by default for this group every photo, in conjunction with the coordinate that described characteristics of image is corresponding, generates this group and presets the feature object of photo.
In order to reach the object of the invention, the invention provides the device that a kind of intelligence is taken pictures, including:
Image-forming module, for, within a time cycle, capturing a frame or multiframe picture；
Image processing module, carries out similarity analysis by each frame picture obtained with the feature object of corresponding classification；When there is at least one frame picture similarity with described feature object and meeting pre-conditioned, trigger display module；
Display module, for exporting a frame picture the highest with described feature object similarity.
Preferably, described device also includes:
Study module, presets photo for a group by learning described classification, it is thus achieved that this group presets the similitude of photo, produces the feature object of described classification.
Preferably, described device also includes: adjusting module；
Described image processing module is additionally operable to, when the similarity of the whole frame pictures captured with described feature object is all unsatisfactory for pre-conditioned, trigger adjusting module；
Described adjusting module, is used for normally taking pictures and/or adjust pre-conditioned.
Preferably, described image-forming module specifically for: within the described time cycle, at interval of Preset Time, capturing a frame picture, described Preset Time is less than or equal to the time cycle.
Preferably, described device also includes: cache module, a frame or multiframe picture described in buffer memory.
Preferably, described study module, it is additionally operable to that a frame picture the highest for described similarity is added this group and presets photo, relearn and obtain this group and preset the similitude of photo, produce the feature object of described classification.
Preferably, told study module specifically for:
The size that this group is all preset photo is unified for same specification；
According to heterochromia in image processing algorithm and photo, the feature of the default photo of this group every is modeled simulation, generates characteristics of image；
The characteristics of image generated by default for this group every photo, in conjunction with the coordinate that described characteristics of image is corresponding, generates this group and presets the feature object of photo.
Compared with prior art, Intelligent photographing method that the present invention proposes and device based on user's request, can autonomic learning, frame picture is captured and can obtain an expression being more nearly user's request, action, the image of posture, solve, with this, the problem postponed of taking pictures.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from description, or understand by implementing the present invention.The purpose of the present invention and other advantages can be realized by structure specifically noted in description, claims and accompanying drawing and be obtained.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, and the schematic description and description of the present invention is used for explaining the present invention, is not intended that inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is the method flow diagram that a kind of intelligence of the embodiment of the present invention is taken pictures；
Fig. 2 is the structural representation of the device that a kind of intelligence of the embodiment of the present invention is taken pictures；
Fig. 3 is the method flow diagram that the intelligence of the embodiment of the present invention one is taken pictures.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with accompanying drawing, embodiments of the invention are described in detail.It should be noted that when not conflicting, the embodiment in the application and the feature in embodiment can combination in any mutually.
As it is shown in figure 1, the present invention provides a kind of method that intelligence is taken pictures, including:
S110, within a time cycle, capture a frame or multiframe picture；
S120, by obtain each frame picture carry out similarity analysis with the feature object of corresponding classification；
S130, when the similarity that there is at least one frame picture and described feature object meets pre-conditioned, the frame picture that output is the highest with described feature object similarity.
Also include before step S110:
S100, preset photo by learning one group of described classification, it is thus achieved that this group presets the similitude of photo, produces the feature object of described classification.
In S130 when the similarity of the whole frame pictures captured with described feature object is all unsatisfactory for pre-conditioned, normally take pictures and/or adjust pre-conditioned.
Step S110 can be in the following way: within the described time cycle, at interval of Preset Time, captures a frame picture, and described Preset Time is less than or equal to the time cycle.
After step S110, also include S115: a frame described in buffer memory or multiframe picture.
After step S130, also include:
A frame picture the highest for described similarity is added this group and presets photo by step S140, relearns and obtains this group and preset the similitude of photo, produces the feature object of described classification.
Step S100 can be in the following way:
The size that this group is all preset photo is unified for same specification；
According to heterochromia in image processing algorithm and photo, the feature of the default photo of this group every is modeled simulation, generates characteristics of image；
The characteristics of image generated by default for this group every photo, in conjunction with the coordinate that described characteristics of image is corresponding, generates this group and presets the feature object of photo.
Wherein, the main contents of the default photo of this group every should be same or like, and the characteristics of image extracted by image processing algorithm from default photo can be the view image of respective pixel, or intercepts the position of window size on described default photo.
Those skilled in the art know, and before imaging, generally also include arranging lens parameters and the initialization step such as ambient parameter, lens focus.From the lens focus successful moment, change over time and the picture in camera lens is cached with continuous print frame format；
In the process of taking pictures, successive frame picture according to the feature object model generated in advance and buffer memory carries out similarity analysis, when similarity is more than default imaging threshold value, selects to meet in pre-conditioned frame picture and select the frame picture that similarity is the highest, record the picture of this moment.
In the learning process of step S100, user according to the demand of oneself, can select the desirable photograph one group similar of a certain classification to go study by equipment, by this group is preset the study of similitude in photo, produces the feature object model of category photo；When step S130 shoots after successfully, feature object model can carry out a process learnt again for this photo.
As in figure 2 it is shown, the present invention provides the device that a kind of intelligence is taken pictures, including:
Image-forming module 210, for, within a time cycle, capturing a frame or multiframe picture；
Image processing module 220, carries out similarity analysis by each frame picture obtained with the feature object of corresponding classification；When there is at least one frame picture similarity with described feature object and meeting pre-conditioned, trigger display module；
Display module 230, for exporting a frame picture the highest with described feature object similarity.
Described device also includes:
Study module 200, presets photo for a group by learning described classification, it is thus achieved that this group presets the similitude of photo, produces the feature object of described classification.
Described device also includes: adjusting module；
Described image processing module is additionally operable to, when the similarity of the whole frame pictures captured with described feature object is all unsatisfactory for pre-conditioned, trigger adjusting module；
Described adjusting module, is used for normally taking pictures and/or adjust pre-conditioned.
Wherein, described image-forming module 210 specifically for: within the described time cycle, at interval of Preset Time, capturing a frame picture, described Preset Time is less than or equal to the time cycle.
Described device also includes: cache module 215, a frame or multiframe picture described in buffer memory.
Wherein, described study module 200, it is additionally operable to that a frame picture the highest for described similarity is added this group and presets photo, relearn and obtain this group and preset the similitude of photo, produce the feature object of described classification.
Told study module 200 specifically for:
The size that this group is all preset photo is unified for same specification；
According to heterochromia in image processing algorithm and photo, the feature of the default photo of this group every is modeled simulation, generates characteristics of image；
The characteristics of image generated by default for this group every photo, in conjunction with the coordinate that described characteristics of image is corresponding, generates this group and presets the feature object of photo.
The device of the embodiment of the present invention mainly includes image-forming module 210, study module 200 and image processing module 220；Study module 200 primary responsibility is according to the different demands of user and hobby, by learning the similitude in the desirable photograph that user provides, generate user desired effect picture feature object model in advance, can after display module 230 exports successfully at this feature object model, this photo is learnt again, feature object model is improved further so that it is closer to the demand of user with this；Image-forming module 210 primary responsibility, after lens focus success, starts to be cached continuous print frame picture from this moment point；Image processing module 220 primary responsibility obtains feature object model at study module 200, continuous print frame picture is obtained from image-forming module 210, after feature object model and frame picture are carried out similarity analysis, the result of output similarity, when similarity meets the similarity of user preset, select the frame picture that Similarity value is the highest, obtain this frame picture as output.
The method and apparatus that the embodiment of the present invention provides according to the demand of user, can take the most conceivable photo of user in the process of taking pictures.
According to User Defined demand, the hobby of oneself, by learning one group of default photo specified in advance, generate the feature object model of this group photo；
In the process of taking pictures, the frame picture after focusing on dynamically is captured, the frame picture of one time cycle of buffer memory；
By comparing the similarity of each frame picture and feature object model, find out and meet pre-conditioned and that similarity is the highest frame picture, as final output picture.
Embodiment one
In conjunction with Fig. 2 and 3 illustrate described in the embodiment of the present invention one can the Intelligent photographing method of autonomic learning based on user's request:
Step 1, study module initializes, and comprises a study warehouse in study module 200, feature object model list model_list{model_1, model_2, model_3 ... model_n} and type property value, wherein, type property value instruction classification, n is the quantity of classification；
The photo group list_pic{list_pic_1 of multiple classification can be placed in this study warehouse, list_pic_2, list_pic_3 ... list_pic_n}, user can according to the demand of oneself, hobby, the desirable photograph while oneself being liked with certain similarity leaves in a photo group, for the generation of feature object model below；Such as: list_pic_1 can place multiple and takeoff and leave ground and stretch out the photo of both arms；List_pic_2 can place multiple photos having V-type gesture；List_pic_3 can place the expression recent photograph of multiple same persons；List_pic_4 can place the shoal of fish etc. that multiple are travelling；
The model list of this feature object is used to deposit in study warehouse often organizes photo by learning the feature object model generated, the photo of the corresponding classification of each feature object model, there is relation one to one with the path of category photo simultaneously, this corresponding relation is left in a map<model, path>table；
Whether this type property value is primarily used to labelling photo relevant with feature object model, these photos include the photo for generating feature object model preset in photo group in study warehouse, and in electrophotographic process by and feature object model contrast and the new photo that generates, feature object model value one_to_one corresponding in the span of type property value and feature object model list, such as: { type_1_value, type_2_value, type_3_value ... type_n_value}；
The generation of feature object model, process is step 2-4 such as:
Step 2, selecting a photo group in study warehouse, the number scanning this group photo generates array object pic_list{pic_1, a pic_2 based on this group photo number, pic_3 ... .pic_m}, wherein, m is the quantity of this group photo, and each object pic_i is 2 dimension group pic_i [coordinates, view], the size of this group photo is uniformly processed, processes the photo into unified specification size, draw coordinate diagram from upper left corner pixel for this photo；
Step 3, the study starting point upper left corner (0 from picture, 0) coordinate sets out, in x-axis and y-axis according to the N number of pixel of increment preset, intercept the elemental area of N*N size, the substantially image that pixel according to the color value on different pixels point and same color value is constituted in this region, generate the visual views substantially of this coordinates regional, the visual views of the coordinate in this upper left corner, region and generation is stored in pic_i [coordinate, view] in this array, the coordinate figure in the amendment upper left corner, it is made to travel through whole pictures region, update pic_i [coordinate simultaneously, view] member, 2 dimension group pic_i [coordinates can be exported, view].Other photos in this photo group being done interior every photo and carries out identical operation, after terminating, every photo correspondence generates a 2 dimension group pic_i [coordinate, view]；
Step 4, according to fuzzy image matching algorithm, the array pic_list{pic_1 that this group photo is generated, pic_2, pic_3 ... the object in .pic_m}, contrast according to coordinate and two factors of view image, preserve the view image that similarity is higher, delete indivedual view image occurred, coordinate finally according to image, reconstruct the feature object model of this group photo, this feature object model is deposited in model_list list object, the same characteristic features of this feature object this group photo of model essential record, simultaneously to the type property value that every photograph tags in this group one is identical with feature object model.
Such as: in list_pic_1, multiple takeoff and leave ground and stretch out the photo of both arms, in the feature object model generated, the principal character of record includes, and the foot on ground is left on ground relatively, the both arms stretched out, and have ignored the background jumped up and the leading role etc. jumped up；In list_pic_2, multiple have the photo of V-type gesture, and in the feature object model of generation, the principal character of record includes V-type gesture, and ignore the background of this gesture and perform the main body of this gesture, and this main body whether band eyes, are branded as；The expression recent photograph of multiple people in list_pic_3, in the feature object model generated, the principal character of record includes: the face contour of this people, the deflection angle of head, whether eyes are opened, whether the corners of the mouth upwarps, the shape of mouth, the shape etc. of eyebrow, and ignore the hair style of this people, clothes and background etc.；
nullStep 5，Image-forming module 210 initializes，Image-forming module 210 is except supporting that normal imaging function (includes shutter speed，Time of exposure，Light scene，White balance etc.) outward，The array frame_list{frame_1 of a frame type is defined exclusively with cache module 215,frame_2…..frame_w}，Wherein，W is the number of pictures captured，It is used for focusing on after successfully at camera，Buffer memory is from the successive frame picture in the appointment cycle that this time point starts，Frame picture is stored in the frame number group frame_list of correspondence simultaneously，This cycle time is to starting the successive frame picture in one new cycle of buffer memory from the time point terminated afterwards，Until stopping buffer memory after receiving the successful message of taking pictures that image processing module 220 is sent，Delete the data in buffer memory simultaneously.
Step 6, first image processing module 220 can obtain the type property value of feature object model list and its correspondence from study module, when camera lens focuses on after successfully, continuously from the buffer area getting frame structured data of image-forming module 210, similar fractional analysis is carried out with feature object model by image recognition technology with the frame picture in this array, a Similarity value is returned according to the result analyzed, range between 0～1, when similarity meets default similarity threshold, select the result output that the picture that similarity is the highest is taken pictures as this time, this picture is saved in memory area, and one type property value consistent with feature object model of this picture of labelling.
Step 7, the autonomic learning of study module 200, user can arrange time point, allows the autonomic learning flow process of study module 200 in default time point self-starting；
Feature object model list model_list{model_1, model_2, model_3 ... each object in model_n} can according to map<model, path>mapping table scans the picture whether depositing unmarked type attribute under one's own picture path again, if existed, select these pictures to carry out the operation of step 3, step 4, extract the place that these photos are similar with feature object model, the principal character comprised in feature object model is carried out perfect；If it does not exist, then proceed the route searching of next feature object model, until all objects in traversal model list；Such as: user is can actively add a photo at ordinary times in this group photo, and this photo is as the photo newly increased, it does not have labelling type object, it is meant that not past the learning process of feature object model；
nullStep 8，Feature object model learns again，Time point in user setup，Feature object model list model_list{model_1,model_2,Model_3 ... each object in model_n} can travel through all picture files (this specified path refers in particular to photo corresponding to photo module and generates path) under specified path，Search and the picture oneself with identical type property value，These pictures are selected to carry out step 3、The operation of step 4，Feature object model is learnt again，The principal character having in this feature object model is made more to meet the demand of user oneself，Record the current time point learnt again simultaneously，When starting again learning process next time，Have only to picture file newly-increased after scanning this time point；If it does not exist, then proceed the route searching of next feature object model, until all objects in traversal model list.
Wherein, study is started in 3 kinds of situations that the study module 200 of the embodiment of the present invention can be said below
1, before beginning of taking pictures, default one group of similar photo is learnt, generate a feature object model of this group photo by capturing its photo principal character, simultaneously to its corresponding model object properties of the photograph tags learnt；
2, at default time point, study module 200 self-starting, each photo group under scanning learning warehouse, search does not have the photo of type attribute, again carries out the learning process of feature object model；
3, at default time point, study module 200 self-starting, by scanning file under specified path, search has the photo of type attribute, again carries out the learning process of feature object model.
The scheme adopting the embodiment of the present invention has the advantage that
1, the self-defined demand according to user, many group photos are learnt, and often group broadly falls into the photo that a class is similar, generates multiple independent characteristic object model, here the similar photo said, one or more in can having the characteristics that, including reference object, posture of taking pictures, facial expression, take pictures action, scene etc. of taking pictures, generate the multiple different feature object model under User Defined pattern；
2, using this Intelligent photographing method, user is not at the picture worrying that bat is wanted less than oneself most, and equipment can be contrasted according to the frame picture of buffer memory and the feature object model previously generated, and selects the photo closest to user's request；
3, using this Intelligent photographing method, do not worry that user's brain response time and photographing device self configure the delay issue brought, because the crawl of last photo is that code level is other, delay can be ignored.
The above, be only the preferred embodiments of the present invention, be not intended to limit protection scope of the present invention.All within the spirit and principles in the present invention, any amendment of making, equivalent replacement, improvement etc., should be included within protection scope of the present invention.
Claims (14)
1. the method that an intelligence is taken pictures, it is characterised in that including:
Within a time cycle, capture a frame or multiframe picture；
The each frame picture obtained is carried out similarity analysis with the feature object of corresponding classification；
When there is at least one frame picture similarity with described feature object and meeting pre-conditioned, the frame picture that output is the highest with described feature object similarity.
2. method according to claim 1, it is characterised in that before described crawl one frame or multiframe picture, also include:
Preset photo for one group by learning described classification, it is thus achieved that this group presets the similitude of photo, produces the feature object of this described classification.
3. method according to claim 1, it is characterised in that when the similarity of the whole frame pictures captured with described feature object is all unsatisfactory for pre-conditioned, normally takes pictures and/or adjust pre-conditioned.
4. method according to claim 1 and 2, it is characterised in that described within a time cycle, capture a frame or multiframe picture includes: within the described time cycle, at interval of Preset Time, capturing a frame picture, described Preset Time is less than or equal to the time cycle.
5. method according to claim 1, it is characterised in that after described crawl one frame or multiframe picture, also include a: frame described in buffer memory or multiframe picture.
6. method according to claim 2, it is characterised in that after the frame picture that output and described feature object similarity are the highest, also include:
A frame picture the highest for described similarity is added this group and presets photo, relearn and obtain this group and preset the similitude of photo, produce the feature object of described classification.
7. method according to claim 2, it is characterised in that preset photo for a group by learning described classification, it is thus achieved that this group presets the similitude of photo, and the feature object producing described classification includes:
The size that this group is all preset photo is unified for same specification；
According to heterochromia in image processing algorithm and photo, the feature of the default photo of this group every is modeled simulation, generates characteristics of image；
The characteristics of image generated by default for this group every photo, in conjunction with the coordinate that described characteristics of image is corresponding, generates this group and presets the feature object of photo.
8. the device that an intelligence is taken pictures, it is characterised in that including:
Image-forming module, for, within a time cycle, capturing a frame or multiframe picture；
Image processing module, carries out similarity analysis by each frame picture obtained with the feature object of corresponding classification；When there is at least one frame picture similarity with described feature object and meeting pre-conditioned, trigger display module；
Display module, for exporting a frame picture the highest with described feature object similarity.
9. device according to claim 8, it is characterised in that also include:
Study module, presets photo for a group by learning described classification, it is thus achieved that this group presets the similitude of photo, produces the feature object of described classification.
10. device according to claim 8, it is characterised in that also include: adjusting module；
Described image processing module is additionally operable to, when the similarity of the whole frame pictures captured with described feature object is all unsatisfactory for pre-conditioned, trigger adjusting module；
Described adjusting module, is used for normally taking pictures and/or adjust pre-conditioned.
11. device according to claim 8 or claim 9, it is characterised in that described image-forming module specifically for: within the described time cycle, at interval of Preset Time, capturing a frame picture, described Preset Time is less than or equal to the time cycle.
12. device according to claim 8, it is characterised in that also include: cache module, a frame or multiframe picture described in buffer memory.
13. device according to claim 9, it is characterised in that
Described study module, is additionally operable to that a frame picture the highest for described similarity adds this group and presets photo, relearn and obtain this group and preset the similitude of photo, produce the feature object of described classification.
14. device according to claim 9, it is characterised in that told study module specifically for:
The size that this group is all preset photo is unified for same specification；
According to heterochromia in image processing algorithm and photo, the feature of the default photo of this group every is modeled simulation, generates characteristics of image；
The characteristics of image generated by default for this group every photo, in conjunction with the coordinate that described characteristics of image is corresponding, generates this group and presets the feature object of photo.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410765226.0A CN105744141A (en) | 2014-12-11 | 2014-12-11 | Intelligent shooting method and apparatus |
| PCT/CN2015/074132 WO2016090759A1 (en) | 2014-12-11 | 2015-03-12 | Intelligently photographing method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410765226.0A CN105744141A (en) | 2014-12-11 | 2014-12-11 | Intelligent shooting method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105744141A true CN105744141A (en) | 2016-07-06 |
Family
ID=56106534
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410765226.0A Pending CN105744141A (en) | 2014-12-11 | 2014-12-11 | Intelligent shooting method and apparatus |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105744141A (en) |
| WO (1) | WO2016090759A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108156385A (en) * | 2018-01-02 | 2018-06-12 | 联想(北京)有限公司 | Image acquiring method and image acquiring device |
| CN108184051A (en) * | 2017-12-22 | 2018-06-19 | 努比亚技术有限公司 | A kind of main body image pickup method, equipment and computer readable storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889354B (en) * | 2019-11-19 | 2023-04-07 | 三星电子（中国）研发中心 | Image capturing method and device of augmented reality glasses |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764238A (en) * | 2004-10-18 | 2006-04-26 | 欧姆龙株式会社 | Image pickup unit |
| CN103079034A (en) * | 2013-01-06 | 2013-05-01 | 北京百度网讯科技有限公司 | Perception shooting method and system |
| CN103220466A (en) * | 2013-03-27 | 2013-07-24 | 华为终端有限公司 | Method and device for outputting pictures |
| CN103795918A (en) * | 2013-11-29 | 2014-05-14 | 深圳市中兴移动通信有限公司 | Shooting method and shooting device |
| CN104125396A (en) * | 2014-06-24 | 2014-10-29 | 小米科技有限责任公司 | Image shooting method and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1501695A (en) * | 2002-11-18 | 2004-06-02 | 矽峰光电科技股份有限公司 | Method for amending internal delay in digital camera imaging |
| US7639889B2 (en) * | 2004-11-10 | 2009-12-29 | Fotonation Ireland Ltd. | Method of notifying users regarding motion artifacts based on image analysis |
| JP2009296141A (en) * | 2008-06-03 | 2009-12-17 | Canon Inc | Imaging apparatus and control method therefor |
| CN102592131A (en) * | 2011-01-06 | 2012-07-18 | 上海银晨智能识别科技有限公司 | Device for comparing a plurality of photos of the same user |
-
2014
- 2014-12-11 CN CN201410765226.0A patent/CN105744141A/en active Pending
-
2015
- 2015-03-12 WO PCT/CN2015/074132 patent/WO2016090759A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764238A (en) * | 2004-10-18 | 2006-04-26 | 欧姆龙株式会社 | Image pickup unit |
| CN103079034A (en) * | 2013-01-06 | 2013-05-01 | 北京百度网讯科技有限公司 | Perception shooting method and system |
| CN103220466A (en) * | 2013-03-27 | 2013-07-24 | 华为终端有限公司 | Method and device for outputting pictures |
| CN103795918A (en) * | 2013-11-29 | 2014-05-14 | 深圳市中兴移动通信有限公司 | Shooting method and shooting device |
| CN104125396A (en) * | 2014-06-24 | 2014-10-29 | 小米科技有限责任公司 | Image shooting method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108184051A (en) * | 2017-12-22 | 2018-06-19 | 努比亚技术有限公司 | A kind of main body image pickup method, equipment and computer readable storage medium |
| CN108156385A (en) * | 2018-01-02 | 2018-06-12 | 联想(北京)有限公司 | Image acquiring method and image acquiring device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2016090759A1 (en) | 2016-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6101397B2 (en) | Photo output method and apparatus | |
| US9918007B2 (en) | Photographing method and apparatus | |
| WO2019137131A1 (en) | Image processing method, apparatus, storage medium, and electronic device | |
| CN202018662U (en) | Image acquisition and processing equipment | |
| JP5880182B2 (en) | Image generating apparatus, image generating method, and program | |
| US20100245610A1 (en) | Method and apparatus for processing digital image | |
| CN105303161A (en) | Method and device for shooting multiple people | |
| WO2019214574A1 (en) | Image capturing method and apparatus, and electronic terminal | |
| CN103079034A (en) | Perception shooting method and system | |
| CN104144289A (en) | Photographing method and device | |
| US20090231628A1 (en) | Image Processing Apparatus, Image Processing Method, Computer Program for Image Processing | |
| WO2022042670A1 (en) | Eye state detection-based image processing method and apparatus, and storage medium | |
| CN103369238B (en) | Image creating device and image creating method | |
| WO2022001806A1 (en) | Image transformation method and apparatus | |
| CN108600610A (en) | Shoot householder method and device | |
| JP2012003539A (en) | Image processing device | |
| CN111640165A (en) | Method and device for acquiring AR group photo image, computer equipment and storage medium | |
| CN110611768A (en) | Multiple exposure photographic method and device | |
| CN105744141A (en) | Intelligent shooting method and apparatus | |
| CN109451234A (en) | Optimize method, equipment and the storage medium of camera function | |
| JP2011211349A (en) | Information processing device and operating method thereof | |
| JP7027101B2 (en) | Information processing equipment, control methods, and programs | |
| CN108259766A (en) | A kind of mobile intelligent terminal is taken pictures image pickup processing method | |
| WO2023149135A1 (en) | Image processing device, image processing method, and program | |
| US20090231627A1 (en) | Image Processing Apparatus, Image Processing Method, Computer Program for Image Processing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160706 |
|
| WD01 | Invention patent application deemed withdrawn after publication |