CN104243814A - Analysis method for object layout in image and image shoot reminding method and device - Google Patents
Analysis method for object layout in image and image shoot reminding method and device Download PDFInfo
- Publication number
- CN104243814A CN104243814A CN201410364752.6A CN201410364752A CN104243814A CN 104243814 A CN104243814 A CN 104243814A CN 201410364752 A CN201410364752 A CN 201410364752A CN 104243814 A CN104243814 A CN 104243814A
- Authority
- CN
- China
- Prior art keywords
- image
- captured
- information
- rationally distributed
- layout
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Processing Or Creating Images (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses an analysis method for the object layout in an image and an image shoot reminding method and device. The analysis method for the object layout in the image comprises the steps that object classification is firstly carried out on the image to obtain an object classification result; the image is segmented according to the object classification result to obtain an image segmentation result; the object layout rationality measurement information of the image is obtained through the image segmentation result and the standard layout information corresponding to the image. The image shoot reminding method comprises the steps that the object layout rationality measurement information of the image to be shot is obtained through the analysis method for the object layout in the image, and then the object layout rationality measurement information of the image to be shot is fed back to a user. When the object layout of the image to be shot is irrational, the user adjusts the shooting direction and angle and other shooting parameters of a terminal according to reminding information, the layout of the image to be shot is changed, and therefore the object layout in the image shot by the user is more reasonable, and the image shoot effect is better.
Description
Technical field
The disclosure relates to image taking technical field, particularly relates to a kind of analytical method of objects in images layout, image taking reminding method and device.
Background technology
Along with popularizing of intelligent terminal, and the raising of intelligent terminal shooting effect, increasing user carrys out photographic images by intelligent terminal.
When user utilizes intelligent terminal to carry out image taking, to the layout of taking the objects in images obtained be caused unreasonable if the parameter choose such as shooting angle or position is improper, such as, when carrying out personage and taking, personage's ratio is in the picture less, the distributed layout of primary objects (personage) and secondary object (background) in the image taken will be caused unreasonable, and then reduce the shooting effect of image.And in relevant image taking technology, also there is no analytical method and the reminding method of objects in images distributed layout, therefore, need the distributed layout situation that a kind of image taking reminding method points out objects in images to be captured badly.
Summary of the invention
For overcoming Problems existing in correlation technique, the disclosure provides a kind of analytical method of objects in images layout, image taking reminding method and device.
In order to solve the problems of the technologies described above, disclosure embodiment discloses following technical scheme:
According to the first aspect of disclosure embodiment, a kind of image taking reminding method is provided, comprises:
Treat photographic images and carry out object classification, obtain object classification result;
According to described object classification result, Iamge Segmentation is carried out to described image to be captured, obtain image object segmentation result;
According to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtain the object rationally distributed property metric of described image to be captured;
To the object rationally distributed property metric that image to be captured described in user feedback is corresponding.
In conjunction with first aspect, in the first possible implementation of first aspect, according to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtain the object rationally distributed property metric in described image to be captured, in the following way:
According to described image object segmentation result, calculate the area ratio/occupancy ratio of each type objects in described image to be captured;
According to area ratio/occupancy ratio and standard layout's information of each type objects in described image to be captured, calculate the object rationally distributed property metric of described image to be captured.
In conjunction with the first possible implementation of first aspect, in the implementation that the second of first aspect is possible, according to area ratio/occupancy ratio and standard layout's information of each type objects in described image to be captured, calculate the object rationally distributed property metric of described image to be captured, in the following way:
According to the difference between the standard item area ratio/occupancy ratio that the area ratio/occupancy ratio of each type objects in described image to be captured is corresponding with described standard layout information, obtain the object placement differences information of described image to be captured;
The object rationally distributed property metric of described image to be captured is obtained according to described object placement differences information.
In conjunction with the first possible implementation of first aspect, in the third possible implementation of first aspect, according to area ratio/occupancy ratio and standard layout's information of each type objects in described image to be captured, calculate the object rationally distributed property metric of described image to be captured, in the following way:
According to the area ratio/occupancy ratio of each type objects in described image to be captured, determine the screening-mode of described image to be captured;
According to the difference weight of area ratio/occupancy ratio corresponding to each type objects described, the corresponding object of described screening-mode, and described standard layout information, obtain the object placement differences information of described image to be captured;
According to described object placement differences information, obtain described object rationally distributed property metric.
In conjunction with the first of first aspect and first aspect to any one in the third possible implementation, in the 4th kind of possible implementation of first aspect, the described object rationally distributed property metric corresponding to image to be captured described in user feedback, in the following way:
By object rationally distributed property information described in text prompt information, auditory tone cues information and/or graphical cues information feed back.
In conjunction with the first of first aspect and first aspect to any one in the third possible implementation, in the 5th kind of possible implementation of first aspect, to the object rationally distributed property metric that image to be captured described in user feedback is corresponding, in the following way:
According to the number range of the object of described image rationally distributed property metric, point out corresponding information to user.
According to the second aspect of disclosure embodiment, a kind of analytical method of objects in images layout is provided, comprises:
Object classification is carried out to target image, obtains object classification result;
According to described object classification result, Iamge Segmentation is carried out to described target image, obtain image object segmentation result;
According to described image object segmentation result and standard layout's information corresponding to described target image, obtain the object rationally distributed property metric of described target image.
In conjunction with second aspect, in the first possible implementation of second aspect, according to described image object segmentation result and standard layout's information corresponding to described target image, obtain the object rationally distributed property metric in described target image, in the following way:
According to described image object segmentation result, calculate the area ratio/occupancy ratio of each type objects in described target image;
According to area ratio/occupancy ratio and standard layout's information of each type objects in described target image, calculate the object rationally distributed property metric of described target image.
According to the third aspect of disclosure embodiment, a kind of image taking suggestion device is provided, comprises:
Object classification unit, carrying out object classification for treating photographic images, obtaining object classification result;
Image segmentation unit, for carrying out Iamge Segmentation according to described object classification result to described image to be captured, obtains image object segmentation result;
Layout metric element, for according to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtains the object rationally distributed property metric of described image to be captured;
Feedback unit, for object rationally distributed property metric corresponding to image to be captured described in user feedback.
In conjunction with the third aspect, in the first possible implementation of the third aspect, described layout metric element comprises:
First computation subunit, for according to described image object segmentation result, calculates the area ratio/occupancy ratio of each type objects in described image to be captured;
Second computation subunit, for according to the area ratio/occupancy ratio of each type objects and standard layout's information, calculates the object rationally distributed property metric of described image to be captured.
In conjunction with the first possible implementation of the third aspect, in the implementation that the second of the third aspect is possible, described second computation subunit, comprising:
Screening-mode determination subelement, for the area ratio/occupancy ratio according to each type objects in described image to be captured, determines the screening-mode of described image to be captured;
First placement differences obtains subelement, for the difference weight according to area ratio/occupancy ratio corresponding to each type objects described, the corresponding object of described screening-mode, and described standard layout information, obtain the object placement differences information of described image to be captured;
3rd computation subunit, for according to described object placement differences information, obtains described object rationally distributed property metric.
According to the fourth aspect of disclosure embodiment, a kind of analytical equipment of objects in images layout is provided, comprises:
Object classification unit, for carrying out object classification to target image, obtains object classification result;
Image segmentation unit, for carrying out Iamge Segmentation according to described object classification result to described target image, obtains image object segmentation result;
Layout metric element, for according to described image object segmentation result and standard layout's information corresponding to described target image, obtains the object rationally distributed property metric of described target image.
According to the 5th aspect of disclosure embodiment, a kind of terminal equipment is provided, comprises: processor; For the memory of storage of processor executable instruction; Wherein, described processor is configured to:
Treat photographic images and carry out object classification, obtain object classification result;
According to described object classification result, Iamge Segmentation is carried out to described image to be captured, obtain image object segmentation result;
According to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtain the object rationally distributed property metric of described image to be captured.
In conjunction with the 5th aspect, in the first the possible implementation in the 5th, described processor is also configured to: to the object rationally distributed property metric that image to be captured described in user feedback is corresponding.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: the image taking reminding method that the disclosure provides, and first treats the sorting objects in photographic images, obtains object classification result; Treat photographic images according to object classification result to split, obtain image segmentation result; Utilize image segmentation result and standard layout's information corresponding to image to be captured, obtain the object rationally distributed property metric of image to be captured; And to the object rationally distributed property metric of image to be captured described in user feedback.Thus whether the object layout of reminding user image to be captured is reasonable.Especially when the object layout of image to be captured is unreasonable, user is according to the acquisition parameters such as shooting direction, angle of the information adjustment terminal of prompting, change the layout of image to be captured, thus the objects in images layout that user is taken is more reasonable, the shooting effect of image is better.
The disclosure additionally provides the analytical method of objects in images layout, carries out rude classification to the object in image, obtains object classification result.According to the object classification result of image, to Image Segmentation Using, obtain image object segmentation result.According to image object segmentation result and standard layout's information, obtain at the object of image rationally distributed property metric, thus the layout of image is analyzed, evaluated.
Should be understood that, it is only exemplary that above general description and details hereinafter describe, and can not limit the disclosure.
Accompanying drawing explanation
Accompanying drawing to be herein merged in specification and to form the part of this specification, shows embodiment according to the invention, and is used from specification one and explains principle of the present invention.
Fig. 1 is the flow chart of a kind of image taking reminding method according to an exemplary embodiment;
Fig. 2 is the interface display schematic diagram of a kind of terminal equipment according to an exemplary embodiment;
Fig. 3 is a kind of method flow diagram obtaining object rationally distributed property metric according to an exemplary embodiment;
Fig. 4 is the method flow diagram of S220 shown in a kind of Fig. 3 according to an exemplary embodiment;
Fig. 5 is the method flow diagram of S220 shown in the another kind of Fig. 3 according to an exemplary embodiment;
Fig. 6 is the flow chart of a kind of objects in images topological analysis method according to an exemplary embodiment;
Fig. 7 is a kind of image taking suggestion device block diagram according to an exemplary embodiment;
Fig. 8 is the analytical equipment block diagram of a kind of objects in images layout according to an exemplary embodiment;
Fig. 9 is the block diagram of a kind of device according to an exemplary embodiment;
Figure 10 is the block diagram of a kind of device for image taking reminding method according to an exemplary embodiment.
By above-mentioned accompanying drawing, illustrate the embodiment that the disclosure is clear and definite more detailed description will be had hereinafter.These accompanying drawings be not in order to limited by any mode the disclosure design scope, but by reference to specific embodiment for those skilled in the art illustrate concept of the present disclosure.
Embodiment
Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Execution mode described in following exemplary embodiment does not represent all execution modes consistent with the disclosure.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that aspects more of the present disclosure are consistent.
Fig. 1 is the flow chart of a kind of image taking reminding method according to an exemplary embodiment, and as shown in Figure 1, described method can be applied in terminal equipment or server, comprises the following steps:
In step s 110, treat photographic images and carry out object classification, obtain object classification result.
When user utilizes terminal equipment (such as, smart mobile phone, panel computer, intelligent photographing device etc.) carry out taking pictures and obtain image to be captured after, terminal equipment can extract specific characteristic from image to be captured, such as, the feature such as personage, scenery, then, Bag of Features algorithm and deep learning algorithm is utilized to carry out rude classification to the object in image, the rough low layer obtaining objects in images is semantic, such as, mainly comprise tree, high building and blue sky in an image, then the rough low layer semanteme that this image is corresponding is: sky, building and tree.
In the step s 120, according to described object classification result, Iamge Segmentation is carried out to described image to be captured, obtain image object segmentation result.
Rough image segmentation is carried out according to objects in images classification results to be captured, obtain rough image object segmentation result, rough low layer semanteme according to the objects in images obtained in step S110 is split the object in image, adopt above-mentioned example, an image mainly comprising tree, high building and blue sky, corresponding image object is divided into sky, building and tree three part.
Owing to only needing to obtain each details object that rough image segmentation result corresponding to image to be captured does not need in Accurate Segmentation image herein.Therefore, rough image dividing method is adopted, such as, based on the active dividing method, Grab-Cut dividing method etc. of viewpoint.
In step s 130, which, according to described image object segmentation result and standard layout's information corresponding to described image to be captured, the object rationally distributed property metric of described image to be captured is obtained.
Can preset standard layout's information that image is corresponding, such as, the number range that primary objects occupies the area ratio/occupancy ratio of whole image can be set, such as 0.4 ~ 0.6, and in image, other object is balancedly distributed in image.
Obtain the area ratio/occupancy ratio of each object in image to be captured, with the area ratio/occupancy ratio of object compares the practical layout that obtains image to be captured and the difference between corresponding standard layout information in standard layout's information, difference is larger, shows that the layout effect of image to be captured is poorer.And then obtain rationally distributed property metric according to the placement differences of described image to be captured, judge that whether the layout of image to be captured is reasonable according to this rationally distributed property metric.
In step S140, to the object rationally distributed property metric that image to be captured described in user feedback is corresponding.
In the disclosure one embodiment, only when detecting that the layout effect of the image to be captured that user takes is unreasonable, just to the object rationally distributed property metric of image to be captured described in user feedback.
In another embodiment of the present disclosure, no matter detect that whether the layout effect of image to be captured is reasonable, all to the object rationally distributed property metric of image to be captured described in user feedback.
Mode to user feedback object rationally distributed property metric can in the following ways:
(1), the display interface of terminal equipment shows text prompt information to user, as shown in Figure 2, the image to be captured on the display interface 200 of terminal equipment 100 shows corresponding information: " photo layout poor effect does not recommend to take pictures ".
(2), to play sound information to user;
(3), the display interface of terminal equipment shows text prompt information, play sound information simultaneously;
(4), on the display interface of terminal equipment, display graphics information.
In another embodiment of the present disclosure, can according to the number range of object rationally distributed property metric, to the information that user feedback is different.Namely, when the rationally distributed degree of the image to be captured that object rationally distributed property metric characterizes is not identical, show different text prompt information, play different auditory tone cues information, show different graphical cues information
Showing different graphical cues information can be the shape difference of figure or the color difference of figure.Such as, green prompting frame represents rationally distributed, and yellow prompting frame represents that layout is general, and red prompting frame represents that layout is very poor.And for example, utilize " √ " to represent rationally distributed, represent that layout is very poor by "×".
The image taking reminding method that the present embodiment provides, first treats the sorting objects in photographic images, obtains object classification result; Treat photographic images according to object classification result to split, obtain image segmentation result; Utilize image segmentation result and standard layout's information corresponding to image to be captured, obtain the object rationally distributed property metric of image to be captured.And to the object rationally distributed property metric of image to be captured described in user feedback.Thus whether the object layout of reminding user image to be captured is reasonable.Especially when the object layout of image to be captured is unreasonable, user is according to the acquisition parameters such as shooting direction, angle of the information adjustment terminal of prompting, change the layout of image to be captured, thus the objects in images layout that user is taken is more reasonable, the shooting effect of image is better.
Fig. 3 is a kind of flow chart obtaining the object rationally distributed property metric method of image according to an exemplary embodiment, and as shown in Figure 3, described method can be applied in terminal equipment or server, comprises the following steps:
In step S210, according to described image object segmentation result, calculate the area ratio/occupancy ratio of each type objects in described image to be captured.
In step S220, according to area ratio/occupancy ratio and standard layout's information of each type objects described, calculate the object rationally distributed property metric of described image to be captured.
Wherein, standard layout's information can default settings, in the disclosure one exemplary embodiment, the area ratio/occupancy ratio that can set the primary objects in image to be captured must in preset range (such as, 0.4 ~ 0.6) in, and the area ratio/occupancy ratio of other object is more or less the same in image to be captured, other object equiblibrium mass distribution namely in image to be captured is in image.Suppose, comprise N number of object in image, in standard layout's information setting image, the area ratio/occupancy ratio of primary objects is 0.5, and other object equiblibrium mass distribution except primary objects, namely the area ratio/occupancy ratio of other object is
In the disclosure one exemplary embodiment, step S220 can adopt method flow as shown in Figure 4 to realize, and as shown in Figure 4, described method can comprise the following steps:
In step S221, according to the difference between the standard item area ratio/occupancy ratio that the area ratio/occupancy ratio of each type objects in described image to be captured is corresponding with described standard layout information, obtain the object placement differences information of described image to be captured.
Suppose N number of object to be detected in image, the area ratio/occupancy ratio calculating any one object is Rate
i, wherein, i is positive integer, and 1≤i≤N.Wherein, m object is the primary objects in image.In tentative standard layout information setting image, the area ratio/occupancy ratio of primary objects is 0.5, then, the area ratio/occupancy ratio of other each object is
Then the object placement differences information Delta of described image to be captured is:
In formula 1, Rate
mfor the area ratio/occupancy ratio of primary objects, Rate
jfor the area ratio/occupancy ratio of any one object except primary objects.
Delta characterizes the difference between the layout of image to be captured and corresponding standard layout's information, and numerical value shows that more greatly the layout effect of image to be captured is poorer; Otherwise numerical value is less shows that the layout effect of image to be captured is better.
In step S222, according to described object placement differences information, obtain described object rationally distributed property metric.
Score=100-100*Delta (formula 2)
According to the score that formula 2 calculates, be roughly divided into 3 grades: 70 ~ 100, show the rationally distributed of image to be captured, strong preference is taken pictures, and can show green prompting frame prompting user on image to be captured; 40 ~ 70, show that the layout of image to be captured is general, do not recommend to take pictures, can show yellow prompting frame on image to be captured, user can make image to be captured reach better layout effect by translation terminal equipment; 0 ~ 40, show that the layout of image to be captured is very poor, do not recommend to take pictures, image to be captured shows red prompting frame, and user must improve the layout effect of image to be captured by translation terminal equipment.
The method of the object rationally distributed property metric of the acquisition that the present embodiment provides image to be captured, according to the area ratio/occupancy ratio of each object in image to be captured, and standard layout's information that image to be captured is corresponding, calculate the object placement differences information between the layout of image to be captured and standard layout's information, obtain the object rationally distributed property metric of image to be captured according to described object placement differences information, judge that whether the layout of image to be captured is reasonable according to object rationally distributed property metric.
In another embodiment of the present disclosure, step S220 can adopt method flow as shown in Figure 5 to realize, and as shown in Figure 5, described method can comprise the following steps:
In step S223, according to the area ratio/occupancy ratio of each type objects in described image to be captured, determine the screening-mode of described image to be captured.
According to image object segmentation result to be captured, judge the classification of each object in image object segmentation result, and the area ratio/occupancy ratio of the object that computed segmentation obtains, determines the screening-mode of image to be captured.Described screening-mode comprises personage's close shot pattern, personage's landscape mode, natural scene close shot pattern and natural scene landscape mode.
If comprise personage in image object segmentation result, and the area ratio/occupancy ratio of each object is more or less the same, then determine that the screening-mode of image to be captured is personage's landscape mode; If only comprise natural scene in image object segmentation result, and the area ratio/occupancy ratio of each object is more or less the same, then determine that the screening-mode of image to be captured is natural scene landscape mode; If comprise personage in image object segmentation result, and the area ratio/occupancy ratio of personage is all greater than the area ratio/occupancy ratio of other object, then determine that the screening-mode of image to be captured is personage's close shot pattern; If comprise personage in image object segmentation result, and personage's area ratio/occupancy ratio is far away higher than the area ratio/occupancy ratio of other object, then determine that the screening-mode of image to be captured is personage's close shot pattern.
In step S224, according to the difference weight of the area ratio/occupancy ratio of each type objects in described image to be captured, object that described screening-mode is corresponding, and standard layout's information, obtain the object placement differences information of described image to be captured.
No matter for which kind of screening-mode, standard layout's information all thinks that the area ratio/occupancy ratio of the primary objects in image must in preset range, and for other object in image must equiblibrium mass distribution in image.But, the difference weighted of different screening-mode object.The difference weight of object comprises two classes, and a class is the difference weight of primary objects; Another kind of is the difference weight of other object except primary objects, and the difference weight of primary objects and the difference weight sum of other object equal 1, can set the difference weight of primary objects, try to achieve the difference weight of other object; Or, the difference weight of other object can be set, try to achieve the difference weight of other object main.Difference weight can obtain according to many experiments, and such as, the difference weight that the corresponding primary objects of personage's close shot pattern is corresponding is 0.8, and the difference weight that other object is corresponding is 0.2.
For close shot pattern, more focus on the difference of primary objects, therefore, the difference weight of primary objects is comparatively large, and the difference weight of other object is less; And for landscape mode, more value the equilibrium situation of object, therefore, the difference weight of primary objects is less, and the difference weight of other object is larger.
Suppose N number of object to be detected in image, the area ratio/occupancy ratio calculating any one object is Rate
i, wherein, i is positive integer, and 1≤i≤N.Wherein, m object is the primary objects in image.In tentative standard layout information setting image, the area ratio/occupancy ratio of primary objects is 0.5, and the area ratio/occupancy ratio of other each object is
Then the object placement differences information Delta of described image to be captured is:
In formula 3, w
patternthe difference weight that other object in the image under different screening-mode except primary objects is corresponding, w
patternless, show that the layout of primary objects is more important under this kind of screening-mode.
In step S225, according to described object placement differences information, obtain described object rationally distributed property metric.
The numerical value of the Delta utilizing formula 3 to calculate is substituted in formula 2, calculates the score of image current arrangements to be captured, i.e. the object of image to be captured rationally distributed property metric.Judge that whether rational the object layout of image to be captured process be identical with above-mentioned process according to object rationally distributed property metric, repeat no more herein.
The method of the acquisition object rationally distributed property metric that the present embodiment provides, according to the area ratio/occupancy ratio of each type objects in image segmentation result, determines the screening-mode of image to be captured.Set different difference weights according to for different screening-modes, in the difference weight that the area ratio/occupancy ratio of binding object, this object are corresponding and standard layout's information, the area ratio/occupancy ratio of the standard item of this object, obtains the object placement differences information of image.Last according to object placement differences information acquisition object rationally distributed property metric.Due to graphic collection to be captured is become different screening-modes, degree difference is valued to different objects in different patterns, therefore different difference weights is set, like this, the object placement differences information calculated can more be biased in the object more valued, and the object calculated rationally distributed property metric is more accurate.
Fig. 6 is the flow chart of a kind of objects in images topological analysis method according to an exemplary embodiment, and as shown in Figure 6, described method may be used for, in terminal equipment or server, comprising the following steps:
In step S310, object classification is carried out to target image, obtain object classification result.
In step s 320, according to described object classification result, Iamge Segmentation is carried out to described target image, obtain image object segmentation result.
In step S330, according to described image object segmentation result and standard layout's information corresponding to described target image, obtain the object rationally distributed property metric of described target image.
Wherein, the implementation of step S330 is identical with the implementation of the step S130 in above-described embodiment, repeats no more herein.
The analytical method of the objects in images layout that the present embodiment provides, carries out rude classification to the object in image, obtains object classification result.According to the object classification result of image, to Image Segmentation Using, obtain image object segmentation result.According to image object segmentation result and standard layout's information, obtain at the object of image rationally distributed property metric, thus the layout of image is analyzed, evaluated.
Fig. 7 is a kind of image taking suggestion device block diagram according to an exemplary embodiment.As shown in Figure 7, this device comprises: object classification unit 110, image segmentation unit 120, layout metric element 130 and feedback unit 140.
Object classification unit 110 is configured to treat photographic images and carries out object classification, obtains object classification result.
Image segmentation unit 120 is configured to carry out Iamge Segmentation according to described object classification result to described image to be captured, obtains image object segmentation result.
Layout metric element 130 is configured to, according to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtain the object rationally distributed property metric of described image to be captured.
In the disclosure one embodiment, described layout metric element can comprise: the first computation subunit and the second computation subunit.
Described first computation subunit is configured to, according to described image object segmentation result, calculate the area ratio/occupancy ratio of each type objects in described image to be captured.
Described second computation subunit is configured to area ratio/occupancy ratio according to each type objects and standard layout's information, calculates the object rationally distributed property metric of described image to be captured.
Wherein, in the disclosure one exemplary embodiment, described second computation subunit can comprise: screening-mode determination subelement, the first placement differences obtain subelement and the 3rd computation subunit.
Described screening-mode determination subelement is configured to, according to the area ratio/occupancy ratio of each type objects in described image to be captured, determine the screening-mode of described image to be captured;
Described first placement differences obtains the difference weight that subelement is configured to according to area ratio/occupancy ratio corresponding to each type objects described, the corresponding object of described screening-mode, and described standard layout information, obtain the object placement differences information of described image to be captured;
Described 3rd computation subunit is configured to, according to described object placement differences information, obtain described object rationally distributed property metric.
In another embodiment of the disclosure, described second computation subunit can comprise: the second placement differences obtains subelement and the 4th computation subunit.
Described second placement differences obtain subelement to be configured to according to the area ratio/occupancy ratio of each type objects in the described image to be captured standard item area ratio/occupancy ratio corresponding with described standard layout information between difference, obtain the object placement differences information of described image to be captured.
Described 4th computation subunit is configured to the object rationally distributed property metric obtaining described image to be captured according to described object placement differences information.
Feedback unit 140 is configured to object rationally distributed property metric corresponding to image to be captured described in user feedback.
The image taking suggestion device that the present embodiment provides, is first treated the sorting objects in photographic images, obtains object classification result by object classification unit; Treat photographic images by image segmentation unit according to object classification result to split, obtain image segmentation result.Layout metric element utilizes image segmentation result and standard layout's information corresponding to image to be captured, obtains the object rationally distributed property metric of image to be captured.And by the object rationally distributed property metric of feedback unit to image to be captured described in user feedback.Thus whether the object layout of reminding user image to be captured is reasonable.Especially when the object layout of image to be captured is unreasonable, user is according to the acquisition parameters such as shooting direction, angle of the information adjustment terminal of prompting, change the layout of image to be captured, thus the objects in images layout that user is taken is more reasonable, the shooting effect of image is better.
Corresponding to the analytical method embodiment of above-mentioned objects in images layout, the disclosure additionally provides corresponding device embodiment.
Fig. 8 is the analytical equipment block diagram of a kind of objects in images layout according to an exemplary embodiment, and as shown in Figure 8, described device comprises: object classification unit 210, image segmentation unit 220 and layout metric element 230.
Object classification unit 210 is configured to carry out object classification to target image, obtains object classification result.
Image segmentation unit 220 is configured to carry out Iamge Segmentation according to described object classification result to described target image, obtains image object segmentation result.
Layout metric element 230 is configured to, according to described image object segmentation result and standard layout's information corresponding to described target image, obtain the object rationally distributed property metric of described target image.
Wherein, the implementation procedure of layout metric element 230 is identical with the implementation procedure of the layout metric element 130 in above-mentioned device embodiment, repeats no more herein.
The analytical equipment of the objects in images layout that the present embodiment provides, carries out rude classification to the object in image, obtains object classification result.According to the object classification result of image, to Image Segmentation Using, obtain image object segmentation result.According to image object segmentation result and standard layout's information, obtain at the object of image rationally distributed property metric, thus the layout of image is analyzed, evaluated.
About the device in above-described embodiment, wherein the concrete mode of modules executable operations has been described in detail in about the embodiment of the method, will not elaborate explanation herein.
Fig. 9 is the block diagram of a kind of terminal equipment 800 for image taking reminding method according to an exemplary embodiment.Such as, terminal equipment 800 can be mobile phone, computer, digital broadcast terminal, messaging devices, game console, flat-panel devices, Medical Devices, body-building equipment, personal digital assistant, photographing device etc.
With reference to Fig. 9, terminal equipment 800 can comprise following one or more assembly: processing components 802, memory 804, power supply module 806, multimedia groupware 808, audio-frequency assembly 810, the interface 812 of I/O (I/O), sensor cluster 814, and communications component 816.
The integrated operation of the usual control terminal 800 of processing components 802, such as with display, call, data communication, camera operation and record operate the operation be associated.Processing components 802 can comprise one or more processor 820 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 802 can comprise one or more module, and what be convenient between processing components 802 and other assemblies is mutual.Such as, processing components 802 can comprise multi-media module, mutual with what facilitate between multimedia groupware 808 and processing components 802.
Memory 804 is configured to store various types of data to be supported in the operation of terminal equipment 800.The example of these data comprises for any application program of operation on terminal equipment 800 or the instruction of method, contact data, telephone book data, message, picture, video etc.Memory 804 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or CD.
The various assemblies that power supply module 806 is terminal equipment 800 provide electric power.Power supply module 806 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for terminal equipment 800 and be associated.
Multimedia groupware 808 is included in the screen providing an output interface between described terminal equipment 800 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Described touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant to described touch or slide and pressure.In certain embodiments, multimedia groupware 808 comprises a front-facing camera and/or post-positioned pick-up head.When terminal equipment 800 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.
Audio-frequency assembly 810 is configured to export and/or input audio signal.Such as, audio-frequency assembly 810 comprises a microphone (MIC), and when terminal equipment 800 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The audio signal received can be stored in memory 804 further or be sent via communications component 816.In certain embodiments, audio-frequency assembly 810 also comprises a loud speaker, for output audio signal.
I/O interface 812 is for providing interface between processing components 802 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.
Sensor cluster 814 comprises one or more transducer, for providing the state estimation of various aspects for terminal equipment 800.Such as, sensor cluster 814 can detect the opening/closing state of terminal equipment 800, the relative positioning of assembly, such as described assembly is display and the keypad of terminal equipment 800, the position of all right sense terminals equipment 800 of sensor cluster 814 or terminal equipment 800 1 assemblies changes, the presence or absence that user contacts with terminal equipment 800, the variations in temperature of terminal equipment 800 orientation or acceleration/deceleration and terminal equipment 800.Sensor cluster 814 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor cluster 814 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor cluster 814 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communications component 816 is configured to the communication being convenient to wired or wireless mode between terminal equipment 800 and other equipment.Terminal equipment 800 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communications component 816 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, described communications component 816 also comprises near-field communication (NFC) module, to promote junction service.Such as, can based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.
In the exemplary embodiment, terminal equipment 800 can be realized, for performing said method by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.
In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the memory 804 of instruction, above-mentioned instruction can perform said method by the processor 820 of terminal equipment 800.Such as, described non-transitory computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc.
A kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is performed by the processor of terminal equipment, make terminal equipment can perform a kind of image taking reminding method, described method comprises:
Treat photographic images and carry out object classification, obtain object classification result;
According to described object classification result, Iamge Segmentation is carried out to described image to be captured, obtain image object segmentation result;
According to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtain the object rationally distributed property metric of described image to be captured;
To the object rationally distributed property metric that image to be captured described in user feedback is corresponding.
Alternatively, described terminal equipment 800 also comprises another kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is performed by the processor of terminal equipment, make terminal equipment can perform a kind of analytical method of objects in images layout, described method comprises:
Treat photographic images and carry out object classification, obtain object classification result;
According to described object classification result, Iamge Segmentation is carried out to described image to be captured, obtain image object segmentation result;
According to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtain the object rationally distributed property metric of described image to be captured.
Figure 10 is the block diagram of a kind of device 1900 for image taking reminding method according to an exemplary embodiment.Such as, device 1900 may be provided in a server.With reference to Figure 10, device 1900 comprises processing components 1922, and it comprises one or more processor further, and the memory resource representated by memory 1932, can such as, by the instruction of the execution of processing components 1922, application program for storing.The application program stored in memory 1932 can comprise each module corresponding to one group of instruction one or more.In addition, processing components 1922 is configured to perform instruction, to perform the embodiment of the method shown in above-mentioned Fig. 1 ~ Fig. 6.
Device 1900 can also comprise the power management that a power supply module 1926 is configured to final controlling element 1900, and a wired or wireless network interface 1950 is configured to device 1900 to be connected to network, and input and output (I/O) interface 1958.Device 1900 can operate the operating system based on being stored in memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
Those skilled in the art, at consideration specification and after putting into practice invention disclosed herein, will easily expect other embodiment of the present invention.The application is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Specification and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.
Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.Scope of the present invention is only limited by appended claim.
Claims (14)
1. an image taking reminding method, is characterized in that, comprising:
Treat photographic images and carry out object classification, obtain object classification result;
According to described object classification result, Iamge Segmentation is carried out to described image to be captured, obtain image object segmentation result;
According to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtain the object rationally distributed property metric of described image to be captured;
To the object rationally distributed property metric that image to be captured described in user feedback is corresponding.
2. method according to claim 1, is characterized in that, according to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtains the object rationally distributed property metric in described image to be captured, in the following way:
According to described image object segmentation result, calculate the area ratio/occupancy ratio of each type objects in described image to be captured;
According to area ratio/occupancy ratio and standard layout's information of each type objects in described image to be captured, calculate the object rationally distributed property metric of described image to be captured.
3. method according to claim 2, is characterized in that, according to area ratio/occupancy ratio and standard layout's information of each type objects in described image to be captured, calculates the object rationally distributed property metric of described image to be captured, in the following way:
According to the difference between the standard item area ratio/occupancy ratio that the area ratio/occupancy ratio of each type objects in described image to be captured is corresponding with described standard layout information, obtain the object placement differences information of described image to be captured;
The object rationally distributed property metric of described image to be captured is obtained according to described object placement differences information.
4. method according to claim 2, is characterized in that, according to area ratio/occupancy ratio and standard layout's information of each type objects in described image to be captured, calculates the object rationally distributed property metric of described image to be captured, in the following way:
According to the area ratio/occupancy ratio of each type objects in described image to be captured, determine the screening-mode of described image to be captured;
According to the difference weight of area ratio/occupancy ratio corresponding to each type objects described, the corresponding object of described screening-mode, and described standard layout information, obtain the object placement differences information of described image to be captured;
According to described object placement differences information, obtain described object rationally distributed property metric.
5. the method according to any one of claim 1-4, is characterized in that, the described object rationally distributed property metric corresponding to image to be captured described in user feedback, in the following way:
By object rationally distributed property information described in text prompt information, auditory tone cues information and/or graphical cues information feed back.
6. the method according to any one of claim 1-4, is characterized in that, to the object rationally distributed property metric that image to be captured described in user feedback is corresponding, in the following way:
According to the number range of the object of described image rationally distributed property metric, point out corresponding information to user.
7. an analytical method for objects in images layout, is characterized in that, comprising:
Object classification is carried out to target image, obtains object classification result;
According to described object classification result, Iamge Segmentation is carried out to described target image, obtain image object segmentation result;
According to described image object segmentation result and standard layout's information corresponding to described target image, obtain the object rationally distributed property metric of described target image.
8. method according to claim 7, is characterized in that, according to described image object segmentation result and standard layout's information corresponding to described target image, obtains the object rationally distributed property metric in described target image, in the following way:
According to described image object segmentation result, calculate the area ratio/occupancy ratio of each type objects in described target image;
According to area ratio/occupancy ratio and standard layout's information of each type objects in described target image, calculate the object rationally distributed property metric of described target image.
9. an image taking suggestion device, is characterized in that, comprising:
Object classification unit, carrying out object classification for treating photographic images, obtaining object classification result;
Image segmentation unit, for carrying out Iamge Segmentation according to described object classification result to described image to be captured, obtains image object segmentation result;
Layout metric element, for according to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtains the object rationally distributed property metric of described image to be captured;
Feedback unit, for object rationally distributed property metric corresponding to image to be captured described in user feedback.
10. device according to claim 9, is characterized in that, described layout metric element, comprising:
First computation subunit, for according to described image object segmentation result, calculates the area ratio/occupancy ratio of each type objects in described image to be captured;
Second computation subunit, for according to the area ratio/occupancy ratio of each type objects and standard layout's information, calculates the object rationally distributed property metric of described image to be captured.
11. devices according to claim 10, is characterized in that, described second computation subunit, comprising:
Screening-mode determination subelement, for the area ratio/occupancy ratio according to each type objects in described image to be captured, determines the screening-mode of described image to be captured;
First placement differences obtains subelement, for the difference weight according to area ratio/occupancy ratio corresponding to each type objects described, the corresponding object of described screening-mode, and described standard layout information, obtain the object placement differences information of described image to be captured;
3rd computation subunit, for according to described object placement differences information, obtains described object rationally distributed property metric.
The analytical equipment of 12. 1 kinds of objects in images layouts, is characterized in that, comprising:
Object classification unit, for carrying out object classification to target image, obtains object classification result;
Image segmentation unit, for carrying out Iamge Segmentation according to described object classification result to described target image, obtains image object segmentation result;
Layout metric element, for according to described image object segmentation result and standard layout's information corresponding to described target image, obtains the object rationally distributed property metric of described target image.
13. 1 kinds of terminal equipments, is characterized in that, comprising:
Processor;
For the memory of storage of processor executable instruction;
Wherein, described processor is configured to:
Treat photographic images and carry out object classification, obtain object classification result;
According to described object classification result, Iamge Segmentation is carried out to described image to be captured, obtain image object segmentation result;
According to described image object segmentation result and standard layout's information corresponding to described image to be captured, obtain the object rationally distributed property metric of described image to be captured.
14. terminal equipments according to claim 13, is characterized in that, described processor is also configured to: to the object rationally distributed property metric that image to be captured described in user feedback is corresponding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410364752.6A CN104243814B (en) | 2014-07-28 | 2014-07-28 | Analysis method, image taking reminding method and the device of objects in images layout |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410364752.6A CN104243814B (en) | 2014-07-28 | 2014-07-28 | Analysis method, image taking reminding method and the device of objects in images layout |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104243814A true CN104243814A (en) | 2014-12-24 |
| CN104243814B CN104243814B (en) | 2018-02-02 |
Family
ID=52231068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410364752.6A Active CN104243814B (en) | 2014-07-28 | 2014-07-28 | Analysis method, image taking reminding method and the device of objects in images layout |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104243814B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105323491A (en) * | 2015-11-27 | 2016-02-10 | 小米科技有限责任公司 | Image shooting method and device |
| CN105812665A (en) * | 2016-03-29 | 2016-07-27 | 联想(北京)有限公司 | Shooting processing method and device, electronic apparatus |
| CN106293070A (en) * | 2016-07-27 | 2017-01-04 | 网易（杭州）网络有限公司 | Virtual role view directions control method and device |
| CN106791204A (en) * | 2017-02-27 | 2017-05-31 | 努比亚技术有限公司 | Mobile terminal and its image pickup method |
| CN107852459A (en) * | 2015-07-21 | 2018-03-27 | 高通股份有限公司 | Camera orients notice system |
| CN107895041A (en) * | 2017-11-30 | 2018-04-10 | 北京小米移动软件有限公司 | Screening-mode method to set up, device and storage medium |
| WO2018094648A1 (en) * | 2016-11-24 | 2018-05-31 | 华为技术有限公司 | Guiding method and device for photography composition |
| CN109218609A (en) * | 2018-07-23 | 2019-01-15 | 麒麟合盛网络技术股份有限公司 | Image composition method and device |
| CN112385207A (en) * | 2018-07-03 | 2021-02-19 | 富士胶片株式会社 | Shooting plan prompting device and method |
| CN113055593A (en) * | 2021-03-11 | 2021-06-29 | 百度在线网络技术（北京）有限公司 | Image processing method and device |
| CN115242923A (en) * | 2022-07-28 | 2022-10-25 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0698245A (en) * | 1992-09-07 | 1994-04-08 | Nippon Telegr & Teleph Corp <Ntt> | Spatial image input device |
| CN103188423A (en) * | 2011-12-27 | 2013-07-03 | 富泰华工业（深圳）有限公司 | Camera shooting device and camera shooting method |
| CN103402058A (en) * | 2013-08-22 | 2013-11-20 | 深圳市金立通信设备有限公司 | Shot image processing method and device |
-
2014
- 2014-07-28 CN CN201410364752.6A patent/CN104243814B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0698245A (en) * | 1992-09-07 | 1994-04-08 | Nippon Telegr & Teleph Corp <Ntt> | Spatial image input device |
| CN103188423A (en) * | 2011-12-27 | 2013-07-03 | 富泰华工业（深圳）有限公司 | Camera shooting device and camera shooting method |
| CN103402058A (en) * | 2013-08-22 | 2013-11-20 | 深圳市金立通信设备有限公司 | Shot image processing method and device |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107852459A (en) * | 2015-07-21 | 2018-03-27 | 高通股份有限公司 | Camera orients notice system |
| CN105323491B (en) * | 2015-11-27 | 2019-04-23 | 小米科技有限责任公司 | Image capturing method and device |
| CN105323491A (en) * | 2015-11-27 | 2016-02-10 | 小米科技有限责任公司 | Image shooting method and device |
| CN105812665B (en) * | 2016-03-29 | 2019-01-15 | 联想(北京)有限公司 | A kind of shooting processing method, device and electronic equipment |
| CN105812665A (en) * | 2016-03-29 | 2016-07-27 | 联想(北京)有限公司 | Shooting processing method and device, electronic apparatus |
| CN106293070A (en) * | 2016-07-27 | 2017-01-04 | 网易（杭州）网络有限公司 | Virtual role view directions control method and device |
| US10893204B2 (en) | 2016-11-24 | 2021-01-12 | Huawei Technologies Co., Ltd. | Photography composition guiding method and apparatus |
| WO2018094648A1 (en) * | 2016-11-24 | 2018-05-31 | 华为技术有限公司 | Guiding method and device for photography composition |
| EP3496386A4 (en) * | 2016-11-24 | 2019-07-03 | Huawei Technologies Co., Ltd. | Guiding method and device for photography composition |
| CN106791204A (en) * | 2017-02-27 | 2017-05-31 | 努比亚技术有限公司 | Mobile terminal and its image pickup method |
| CN107895041A (en) * | 2017-11-30 | 2018-04-10 | 北京小米移动软件有限公司 | Screening-mode method to set up, device and storage medium |
| CN107895041B (en) * | 2017-11-30 | 2020-12-29 | 北京小米移动软件有限公司 | Shooting mode setting method and device and storage medium |
| CN112385207A (en) * | 2018-07-03 | 2021-02-19 | 富士胶片株式会社 | Shooting plan prompting device and method |
| CN109218609A (en) * | 2018-07-23 | 2019-01-15 | 麒麟合盛网络技术股份有限公司 | Image composition method and device |
| CN109218609B (en) * | 2018-07-23 | 2020-10-23 | 麒麟合盛网络技术股份有限公司 | Image composition method and device |
| CN113055593A (en) * | 2021-03-11 | 2021-06-29 | 百度在线网络技术（北京）有限公司 | Image processing method and device |
| CN113055593B (en) * | 2021-03-11 | 2022-08-16 | 百度在线网络技术（北京）有限公司 | Image processing method and device |
| CN115242923A (en) * | 2022-07-28 | 2022-10-25 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium |
| CN115242923B (en) * | 2022-07-28 | 2024-07-23 | 腾讯科技（深圳）有限公司 | Data processing method, device, equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104243814B (en) | 2018-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104243814A (en) | Analysis method for object layout in image and image shoot reminding method and device | |
| KR101906827B1 (en) | Apparatus and method for taking a picture continously | |
| CN104219445B (en) | Screening-mode method of adjustment and device | |
| CN104902189A (en) | Picture processing method and picture processing device | |
| CN105430262A (en) | Photographing control method and photographing control device | |
| CN105225647A (en) | Luminance regulating method and device | |
| CN105631797A (en) | Watermarking method and device | |
| CN108010060A (en) | Object detection method and device | |
| CN105957037B (en) | Image enchancing method and device | |
| CN104063865B (en) | Disaggregated model creation method, image partition method and relevant apparatus | |
| CN105184313A (en) | Classification model construction method and device | |
| CN112219224B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN104918107A (en) | Video file identification processing method and device | |
| CN104517271B (en) | Image processing method and device | |
| CN107424130B (en) | Picture beautifying method and device | |
| CN107563994A (en) | The conspicuousness detection method and device of image | |
| CN108108671A (en) | Description of product information acquisition method and device | |
| CN105528078A (en) | Method and device controlling electronic equipment | |
| CN105528765A (en) | Method and device for processing image | |
| CN106598429A (en) | Method and device for adjusting window of mobile terminal | |
| CN105139033A (en) | Classifier construction method and device and image processing method and device | |
| CN105117706A (en) | Image processing method and apparatus and character recognition method and apparatus | |
| CN107967459A (en) | convolution processing method, device and storage medium | |
| CN106228193B (en) | Image classification method and device | |
| CN103996211A (en) | Image relocation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |