CN104484853A - Method and device for clipping pictures containing graphical signs - Google Patents
Method and device for clipping pictures containing graphical signs Download PDFInfo
- Publication number
- CN104484853A CN104484853A CN201410818268.6A CN201410818268A CN104484853A CN 104484853 A CN104484853 A CN 104484853A CN 201410818268 A CN201410818268 A CN 201410818268A CN 104484853 A CN104484853 A CN 104484853A
- Authority
- CN
- China
- Prior art keywords
- original image
- target photo
- image
- cutting
- size
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 230000000717 retained effect Effects 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 230000006835 compression Effects 0.000 description 18
- 238000007906 compression Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 6
- 238000003704 image resize Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 230000008034 disappearance Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 2
- 230000006378 damage Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- G06T3/10—
Abstract
The invention provides a method and device for clipping pictures containing graphical signs, mainly belongs to the technical field of internet, and mainly aims to provide a technical scheme suitable for clipping of the pictures containing the graphical signs. The method comprises the following steps: detecting an original picture to be clipped and thus obtaining part or all characteristics of one or more graphical signs in the original picture; clipping the original picture to obtain a target picture to enable the part or all characteristics of at least one graphical sign in the target picture to be retained. According to the method, when the original picture is the picture containing the graphical signs through detection, the clipped target picture needs to contain part or all characteristics of at least one graphical sign; the graphical sign generally represents a specific meaning, for example, brand names and logos, so that the clipped target picture still can reflect the specific meaning by retaining the characteristics of the graphical sign.
Description
Technical field
The present invention relates to Internet technical field, carrying out the device of cutting in particular to a kind of picture to comprising logotype.
Background technology
At internet arena, usually need to capture a large amount of pictures on internet.Because the picture size on internet is different, the dimension of picture grabbed can be caused to be difficult to meet demand, now just need computing machine automatically to complete cutting to picture, make the size conforms demand of picture.
For different pictures, because the content of showing in picture is different, cause in picture, needing the part of cutting to be also different, such as, for the picture comprising logotype, it is exactly a difficult problem that the Target Photo how carrying out obtaining after cutting makes cutting still plays marked effect.Current employing trisection composition, golden ratio composition carry out the mode of cutting, completely that cutting is carried out to the fixed position in picture, very large to the destruction of logotype, be so then difficult to the picture effect after ensureing cutting satisfactory, or adopting manual type cutting again, efficiency is not high.
Summary of the invention
In view of the above problems, the present invention is proposed to provide a kind of method and apparatus picture comprising logotype being carried out to cutting overcoming the problems referred to above or solve the problem at least in part.
According to one aspect of the present invention, provide a kind of method that picture to comprising logotype carries out cutting, it comprises: the original image treating cutting detects, and detects in described original image the part or all of feature of the one or more logotypes comprised; Cutting is carried out to described original image and obtains Target Photo, in described Target Photo, remain with the part or all of feature of logotype described at least one.
Alternatively, aforesaid method, carries out cutting to described original image and obtains Target Photo, specifically comprise: the size obtaining described Target Photo; According to the size of described Target Photo, convergent-divergent is carried out to described original image, make the size of described original image be no more than the size of described Target Photo; Clipping region is marked by the size of described Target Photo, and by the copying image of described original image in described clipping region, cutting is carried out to described clipping region and obtains described Target Photo, to retain whole features of all described logotypes in described original image.
Alternatively, aforesaid method, also comprises: the size detecting described original image, comprises height and the width of described original image; Obtain the size of described Target Photo, specifically comprise: the height and the width that obtain described Target Photo; According to the size of described Target Photo, convergent-divergent is carried out to described original image, specifically comprise: the ratio calculating the height of described original image and the height of described Target Photo, and calculate the ratio of the width of described original image and the width of described Target Photo, and using the maximal value in obtained ratio as the ratio of described original image being carried out to convergent-divergent, and in described ratio, convergent-divergent is carried out to described original image.
Alternatively, aforesaid method, also comprise: the image of described original image cannot fill completely described clipping region time, according to the background colour of the logotype retained in described Target Photo, in described clipping region not by the image of described original image the part of filling fill.
Alternatively, aforesaid method, at the background colour according to the logotype retained in described Target Photo, to in described clipping region not by the image of described original image before the part of filling fills, also comprise: by the marginal position of described original image, select the region at described background colour place to be extracted from described original image and carry out color extraction.
Alternatively, aforesaid method, also comprises: the image of described original image cannot fill completely described clipping region time, the image of described original image is placed in described clipping region between two parties.
According to another aspect of the present invention, provide the device that a kind of picture to comprising logotype carries out cutting, it comprises: logotype detection module, original image for treating cutting detects, and detects in described original image the part or all of feature of the one or more logotypes comprised; Cutting module, obtaining Target Photo for carrying out cutting to described original image, remaining with the part or all of feature of logotype described at least one in described Target Photo.
Alternatively, aforesaid device, also comprises: dimension acquisition module, for obtaining the size of described Target Photo; Zoom module, for the size according to described Target Photo, carries out convergent-divergent to described original image, makes the size of described original image be no more than the size of described Target Photo; Cutting module, for marking clipping region by the size of described Target Photo, and by the copying image of described original image in described clipping region, cutting is carried out to described clipping region and obtains described Target Photo, to retain whole features of all described logotypes in described original image.
Alternatively, aforesaid device, also comprises: size detection module, for detecting the size of described original image, comprises height and the width of described original image; Described dimension acquisition module obtains height and the width of described Target Photo; Described Zoom module calculates the ratio of the height of described original image and the height of described Target Photo, and calculate the ratio of the width of described original image and the width of described Target Photo, and using the maximal value in obtained ratio as the ratio of described original image being carried out to convergent-divergent, and in described ratio, convergent-divergent is carried out to described original image.
Alternatively, aforesaid device, also comprise: color filling module, the image of described original image cannot fill completely described clipping region time, according to the background colour of the logotype retained in described Target Photo, and by clipping region described in extracted Color pair not by the image of described original image the part of filling fill.
Alternatively, aforesaid device, described color filling module, by the marginal position of described original image, is selected the region at described background colour place to be extracted from described original image and carries out color extraction.
Alternatively, aforesaid device, described cutting module the image of described original image cannot fill completely described clipping region time, the image of described original image is placed in described clipping region between two parties.
According to above technical scheme, the method and apparatus that the known picture to comprising logotype of the present invention carries out cutting at least has the following advantages:
According to technical scheme of the present invention, when detecting that original image is the picture comprising logotype, then require the part or all of technical characteristic comprising at least one logotype in the Target Photo of cutting; Logotype generally represents specific meaning, such as, represents the brand, logo etc. of commodity, so the Target Photo that the feature retaining logotype can make cutting obtain still can reflect certain sense.
Above-mentioned explanation is only the general introduction of technical solution of the present invention, in order to technological means of the present invention can be better understood, and can be implemented according to the content of instructions, and can become apparent, below especially exemplified by the specific embodiment of the present invention to allow above and other objects of the present invention, feature and advantage.
Accompanying drawing explanation
By reading hereafter detailed description of the preferred embodiment, various other advantage and benefit will become cheer and bright for those of ordinary skill in the art.Accompanying drawing only for illustrating the object of preferred implementation, and does not think limitation of the present invention.And in whole accompanying drawing, represent identical parts by identical reference symbol.In the accompanying drawings:
Fig. 1 shows the process flow diagram that the picture to comprising logotype according to an embodiment of the invention carries out the method for cutting;
Fig. 2 shows the process flow diagram that the picture to comprising logotype according to an embodiment of the invention carries out the method for cutting;
Fig. 3 shows the process flow diagram that the picture to comprising logotype according to an embodiment of the invention carries out the method for cutting;
Fig. 4 shows the process flow diagram that the picture to comprising logotype according to an embodiment of the invention carries out the method for cutting;
Fig. 5 shows the original image that the picture to comprising logotype according to an embodiment of the invention carries out the method cutting of cutting;
Fig. 6 shows the Target Photo that the picture to comprising logotype according to an embodiment of the invention carries out the method cutting of cutting;
Fig. 7 shows the block diagram that the picture to comprising logotype according to an embodiment of the invention carries out the device of cutting;
Fig. 8 shows the block diagram that the picture to comprising logotype according to an embodiment of the invention carries out the device of cutting;
Fig. 9 shows the block diagram that the picture to comprising logotype according to an embodiment of the invention carries out the device of cutting;
Figure 10 shows the block diagram that the picture to comprising logotype according to an embodiment of the invention carries out the device of cutting.
Embodiment
Below with reference to accompanying drawings exemplary embodiment of the present disclosure is described in more detail.Although show exemplary embodiment of the present disclosure in accompanying drawing, however should be appreciated that can realize the disclosure in a variety of manners and not should limit by the embodiment set forth here.On the contrary, provide these embodiments to be in order to more thoroughly the disclosure can be understood, and complete for the scope of the present disclosure can be conveyed to those skilled in the art.
As described in Figure 1, provide a kind of method that picture to comprising logotype carries out cutting in one embodiment of the present of invention, it comprises:
Step 110, the original image treating cutting detects, and detects the part or all of feature of the one or more logotypes comprised in original image.In the present embodiment, the feature for logotype does not limit, and it includes but not limited to color, the shape of logotype self, and the background colour of logotype.
Step 120, carries out cutting to original image and obtains Target Photo, remains with the part or all of feature of at least one logotype in Target Photo.In the present embodiment, the feature of reservation can not be identical with the feature detected.According to the technical scheme of the present embodiment, when detecting that original image is the picture comprising logotype, then require the part or all of technical characteristic comprising at least one logotype in the Target Photo of cutting; Logotype generally represents specific meaning, such as, represents the brand etc. of commodity, so the Target Photo that the feature retaining logotype can make cutting obtain still can reflect certain sense.
According to Fig. 1, on the picture of certain trade mark (logotype); After identifying this trade mark, when cutting is carried out to the picture of this trade mark, the region (whole feature) at trade mark place under cutting, or the contour shape (Partial Feature) extracting trade mark; Further, when having multiple similar trade mark to coexist in picture, only can carry out cutting according to the trade mark of one of them commodity.
As described in Figure 2, provide a kind of method that picture to comprising logotype carries out cutting in one embodiment of the present of invention, it comprises:
Step 210, the original image treating cutting detects, and detects the part or all of feature of the one or more logotypes comprised in original image.
Step 220, obtains the size of Target Photo.
Step 230, according to the size of Target Photo, carries out convergent-divergent to original image, makes the size of original image be no more than the size of Target Photo.In the present embodiment, make the size of original image be no more than the size of Target Photo, be conducive to the whole features retaining original image.
Step 240, according to target the size of picture marks clipping region, and by the copying image of original image in clipping region, carries out cutting obtain Target Photo to clipping region, to retain whole features of all logotypes in original image.According to the technical scheme of the present embodiment, carry out cutting again, can retain all images of original image after carrying out convergent-divergent to original image, also namely can preserve whole features of logotype, after being conducive to cutting, picture is complete reflects the implication of logotype.Further, when the image of original image cannot fill full clipping region, the image of original image is placed in clipping region between two parties, is conducive to ensureing that picture that cutting obtains presents the effect of symmetrical expression like this.
As described in Figure 3, provide a kind of method that picture to comprising logotype carries out cutting in one embodiment of the present of invention, it comprises:
Step 310, the original image treating cutting detects, and detects the part or all of feature of the one or more logotypes comprised in original image.
Step 320, detects height and the width of original image.
Step 330, comprises height and the width of original image.
Step 340, calculate the ratio of the height of original image and the height of Target Photo, and calculate the ratio of the width of original image and the width of Target Photo, and using the maximal value in obtained ratio as the ratio of original image being carried out to convergent-divergent, and in proportion convergent-divergent is carried out to original image.In the present embodiment, be actually and carry out convergent-divergent according to maximum compression ratio, under this mode can ensure that the size after original image compression is less than the prerequisite of the size of Target Photo, original image size is maximum, thus is conducive to the feature of the clear present graphical mark of Target Photo.
Step 350, according to target the size of picture marks clipping region, and by the copying image of original image in clipping region, carries out cutting obtain Target Photo to clipping region, to retain whole features of all logotypes in original image.
According to Fig. 3, if original image is designated as image
src, its wide and height is respectively width
srcwith height
src, the Target Photo that cutting will obtain is designated as image
dst, its wide and height is respectively width
dstwith heigth
dst, unit is all pixel.Then compressed according to maximum compression ratio by original image, maximum compression ratio computing formula is: max_scale=MAX (width
src/ width
dst, height
src/ height
dst).If the picture obtained after compression is image
resize, its wide and height is respectively width
resize, height
resize, then: width
resize=width
src/ max_scale; Height
resize=height
src/ max_scale.
It should be noted that, above-mentioned the separate equations is not realize unique formula of the present invention, only as a kind of implementation of embodiment.Technician can do suitable distortion according to service needed to formula, such as, increase constant or the mode such as variable or coefficient, still drop within protection scope of the present invention.
As described in Figure 4, provide a kind of method that picture to comprising logotype carries out cutting in one embodiment of the present of invention, it comprises:
Step 410, the original image treating cutting detects, and detects the part or all of feature of the one or more logotypes comprised in original image.
Step 420, obtains the size of Target Photo.
Step 430, according to the size of Target Photo, carries out convergent-divergent to original image, makes the size of original image be no more than the size of Target Photo.In the present embodiment, make the size of original image be no more than the size of Target Photo, be conducive to the whole features retaining original image.
Step 440, according to target the size of picture marks clipping region, and by the copying image of original image in clipping region, carries out cutting obtain Target Photo to clipping region, to retain whole features of all logotypes in original image.
Step 450, when the image of original image cannot fill full clipping region, by the marginal position of original image, selects the region at background colour place to be extracted from original image and carries out color extraction.In the present embodiment, the original image edge usually comprising logotype is the background of logotype.
Step 460, according to the background colour of the logotype retained in Target Photo, in clipping region not by the image of original image the part of filling fill.According to the technical scheme of the present embodiment, select background colour to fill, the color of filling can be made basically identical with the image border color copying the past, and globality effect is very good.
According to Fig. 4, in conjunction with aforesaid embodiment, by image
resizepixel value copy image to
dstmiddle time, if image
resizesize be less than image
dst, i.e. width
resize<width
dstor height
resize<heigth
dst, then the pixel background colour of disappearance is filled.
According to above-mentioned two embodiments, the logo picture shown in Fig. 5, its original size is 194x60.The picture of a present hope acquisition 100x100, then need by following process process: a) first detect that this picture is logo picture, determines that background colour is pure white simultaneously.B) maximum compression ratio is calculated, max_sacle=MAX (192/100,60/100)=1.92.C) by maximum compression ratio compressed picture, the length of the picture after compression and be widely respectively 100,31.D) picture pixels after compression is copied in Target Photo between two parties, and the pixel background colour of disappearance is filled, obtain picture as shown in Figure 6.
As described in Figure 7, provide the device that a kind of picture to comprising logotype carries out cutting in one embodiment of the present of invention, it comprises:
Logotype detection module 710, the original image treating cutting detects, and detects the part or all of feature of the one or more logotypes comprised in original image.In the present embodiment, the feature for logotype does not limit, and it includes but not limited to color, the shape of logotype self, and the background colour of logotype.
Cutting module 720, carries out cutting to original image and obtains Target Photo, remains with the part or all of feature of at least one logotype in Target Photo.In the present embodiment, the feature of reservation can not be identical with the feature detected.According to the technical scheme of the present embodiment, when detecting that original image is the picture comprising logotype, then require the part or all of technical characteristic comprising at least one logotype in the Target Photo of cutting; Logotype generally represents specific meaning, such as, represents the brand etc. of commodity, so the Target Photo that the feature retaining logotype can make cutting obtain still can reflect certain sense.
According to Fig. 7, on the picture of certain trade mark (logotype); After identifying this trade mark, when cutting is carried out to the picture of this trade mark, the region (whole feature) at trade mark place under cutting, or the contour shape (Partial Feature) extracting trade mark; Further, when having multiple similar trade mark to coexist in picture, only can carry out cutting according to the trade mark of one of them commodity.
As described in Figure 8, provide the device that a kind of picture to comprising logotype carries out cutting in one embodiment of the present of invention, it comprises:
Logotype detection module 810, the original image treating cutting detects, and detects the part or all of feature of the one or more logotypes comprised in original image.
Dimension acquisition module 820, obtains the size of Target Photo.
Zoom module 830, according to the size of Target Photo, carries out convergent-divergent to original image, makes the size of original image be no more than the size of Target Photo.In the present embodiment, make the size of original image be no more than the size of Target Photo, be conducive to the whole features retaining original image.
Cutting module 840, according to target the size of picture marks clipping region, and by the copying image of original image in clipping region, carries out cutting obtain Target Photo to clipping region, to retain whole features of all logotypes in original image.According to the technical scheme of the present embodiment, carry out cutting again, can retain all images of original image after carrying out convergent-divergent to original image, also namely can preserve whole features of logotype, after being conducive to cutting, picture is complete reflects the implication of logotype.Further, when the image of original image cannot fill full clipping region, the image of original image is placed in clipping region between two parties, is conducive to ensureing that picture that cutting obtains presents the effect of symmetrical expression like this.
As described in Figure 9, provide the device that a kind of picture to comprising logotype carries out cutting in one embodiment of the present of invention, it comprises:
Logotype detection module 910, the original image treating cutting detects, and detects the part or all of feature of the one or more logotypes comprised in original image.
Size detection module 920, detects height and the width of original image.
Dimension acquisition module 930, comprises height and the width of original image.
Zoom module 940, calculate the ratio of the height of original image and the height of Target Photo, and calculate the ratio of the width of original image and the width of Target Photo, and using the maximal value in obtained ratio as the ratio of original image being carried out to convergent-divergent, and in proportion convergent-divergent is carried out to original image.In the present embodiment, be actually and carry out convergent-divergent according to maximum compression ratio, under this mode can ensure that the size after original image compression is less than the prerequisite of the size of Target Photo, original image size is maximum, thus is conducive to the feature of the clear present graphical mark of Target Photo.
Cutting module 950, according to target the size of picture marks clipping region, and by the copying image of original image in clipping region, carries out cutting obtain Target Photo to clipping region, to retain whole features of all logotypes in original image.
According to Fig. 9, if original image is designated as image
src, its wide and height is respectively width
srcwith height
src, the Target Photo that cutting will obtain is designated as image
dst, its wide and height is respectively width
dstwith heigth
dst, unit is all pixel.Then compressed according to maximum compression ratio by original image, maximum compression ratio computing formula is: max_scale=MAX (width
src/ width
dst, height
src/ height
dst).If the picture obtained after compression is image
resize, its wide and height is respectively width
resize, height
resize, then: width
resize=width
src/ max_scale; Height
resize=height
src/ max_scale.
It should be noted that, above-mentioned the separate equations is not realize unique formula of the present invention, only as a kind of implementation of embodiment.Technician can do suitable distortion according to service needed to formula, such as, increase constant or the mode such as variable or coefficient, still drop within protection scope of the present invention.
As shown in Figure 10, provide the device that a kind of picture to comprising logotype carries out cutting in one embodiment of the present of invention, it comprises:
Logotype detection module 1010, the original image treating cutting detects, and detects the part or all of feature of the one or more logotypes comprised in original image.
Dimension acquisition module 1020, obtains the size of Target Photo.
Zoom module 1030, according to the size of Target Photo, carries out convergent-divergent to original image, makes the size of original image be no more than the size of Target Photo.In the present embodiment, make the size of original image be no more than the size of Target Photo, be conducive to the whole features retaining original image.
Cutting module 1040, according to target the size of picture marks clipping region, and by the copying image of original image in clipping region, carries out cutting obtain Target Photo to clipping region, to retain whole features of all logotypes in original image.
Color filling module 1050, when the image of original image cannot fill full clipping region, by the marginal position of original image, selects the region at background colour place to be extracted from original image and carries out color extraction.In the present embodiment, the original image edge usually comprising logotype is the background of logotype.
Color filling module 1050 according to the background colour of the logotype retained in Target Photo, in clipping region not by the image of original image the part of filling fill.According to the technical scheme of the present embodiment, select background colour to fill, the color of filling can be made basically identical with the image border color copying the past, and globality effect is very good.
According to Figure 10, in conjunction with aforesaid embodiment, by image
resizepixel value copy image to
dstmiddle time, if image
resizesize be less than image
dst, i.e. width
resize<width
dstor height
resize<heigth
dst, then the pixel background colour of disappearance is filled.
According to above-mentioned two embodiments, the logo picture shown in Fig. 5, its original size is 194x60.The picture of a present hope acquisition 100x100, then need by following process process: a) first detect that this picture is logo picture, determines that background colour is pure white simultaneously.B) maximum compression ratio is calculated, max_sacle=MAX (192/100,60/100)=1.92.C) by maximum compression ratio compressed picture, the length of the picture after compression and be widely respectively 100,31.D) picture pixels after compression is copied in Target Photo between two parties, and the pixel background colour of disappearance is filled, obtain picture as shown in Figure 6.
Intrinsic not relevant to any certain computer, virtual system or miscellaneous equipment with display at this algorithm provided.Various general-purpose system also can with use based on together with this teaching.According to description above, the structure constructed required by this type systematic is apparent.In addition, the present invention is not also for any certain programmed language.It should be understood that and various programming language can be utilized to realize content of the present invention described here, and the description done language-specific is above to disclose preferred forms of the present invention.
In instructions provided herein, describe a large amount of detail.But can understand, embodiments of the invention can be put into practice when not having these details.In some instances, be not shown specifically known method, structure and technology, so that not fuzzy understanding of this description.
Similarly, be to be understood that, in order to simplify the disclosure and to help to understand in each inventive aspect one or more, in the description above to exemplary embodiment of the present invention, each feature of the present invention is grouped together in single embodiment, figure or the description to it sometimes.But, the method for the disclosure should be construed to the following intention of reflection: namely the present invention for required protection requires feature more more than the feature clearly recorded in each claim.Or rather, as claims below reflect, all features of disclosed single embodiment before inventive aspect is to be less than.Therefore, the claims following embodiment are incorporated to this embodiment thus clearly, and wherein each claim itself is as independent embodiment of the present invention.
Those skilled in the art are appreciated that and adaptively can change the module in the equipment in embodiment and they are arranged in one or more equipment different from this embodiment.Module in embodiment or unit or assembly can be combined into a module or unit or assembly, and multiple submodule or subelement or sub-component can be put them in addition.Except at least some in such feature and/or process or unit be mutually repel except, any combination can be adopted to combine all processes of all features disclosed in this instructions (comprising adjoint claim, summary and accompanying drawing) and so disclosed any method or equipment or unit.Unless expressly stated otherwise, each feature disclosed in this instructions (comprising adjoint claim, summary and accompanying drawing) can by providing identical, alternative features that is equivalent or similar object replaces.
In addition, those skilled in the art can understand, although embodiments more described herein to comprise in other embodiment some included feature instead of further feature, the combination of the feature of different embodiment means and to be within scope of the present invention and to form different embodiments.Such as, in the following claims, the one of any of embodiment required for protection can use with arbitrary array mode.
All parts embodiment of the present invention with hardware implementing, or can realize with the software module run on one or more processor, or realizes with their combination.It will be understood by those of skill in the art that the some or all functions of the picture comprising logotype being carried out to the some or all parts in the device of cutting that microprocessor or digital signal processor (DSP) can be used in practice to realize according to the embodiment of the present invention.The present invention can also be embodied as part or all equipment for performing method as described herein or device program (such as, computer program and computer program).Realizing program of the present invention and can store on a computer-readable medium like this, or the form of one or more signal can be had.Such signal can be downloaded from internet website and obtain, or provides on carrier signal, or provides with any other form.
The present invention will be described instead of limit the invention to it should be noted above-described embodiment, and those skilled in the art can design alternative embodiment when not departing from the scope of claims.In the claims, any reference symbol between bracket should be configured to limitations on claims.Word " comprises " not to be got rid of existence and does not arrange element in the claims or step.Word "a" or "an" before being positioned at element is not got rid of and be there is multiple such element.The present invention can by means of including the hardware of some different elements and realizing by means of the computing machine of suitably programming.In the unit claim listing some devices, several in these devices can be carry out imbody by same hardware branch.Word first, second and third-class use do not represent any order.Can be title by these word explanations.
Claims (12)
1. the picture comprising logotype is carried out to a method for cutting, it comprises:
The original image treating cutting detects, and detects in described original image the part or all of feature of the one or more logotypes comprised;
Cutting is carried out to described original image and obtains Target Photo, in described Target Photo, remain with the part or all of feature of logotype described at least one.
2. method according to claim 1, wherein, cutting is carried out to described original image and obtains Target Photo, specifically comprise:
Obtain the size of described Target Photo;
According to the size of described Target Photo, convergent-divergent is carried out to described original image, make the size of described original image be no more than the size of described Target Photo;
Clipping region is marked by the size of described Target Photo, and by the copying image of described original image in described clipping region, cutting is carried out to described clipping region and obtains described Target Photo, to retain whole features of all described logotypes in described original image.
3. method according to claim 2, wherein, also comprises:
Detect the size of described original image, comprise height and the width of described original image;
Obtain the size of described Target Photo, specifically comprise:
Obtain height and the width of described Target Photo;
According to the size of described Target Photo, convergent-divergent is carried out to described original image, specifically comprises:
Calculate the ratio of the height of described original image and the height of described Target Photo, and calculate the ratio of the width of described original image and the width of described Target Photo, and using the maximal value in obtained ratio as the ratio of described original image being carried out to convergent-divergent, and in described ratio, convergent-divergent is carried out to described original image.
4. method according to claim 2, wherein, also comprises:
The image of described original image cannot fill completely described clipping region time, according to the background colour of the logotype retained in described Target Photo, in described clipping region not by the image of described original image the part of filling fill.
5. method according to claim 4, wherein, at the background colour according to the logotype retained in described Target Photo, in described clipping region not by the image of described original image before the part of filling fills, also comprise:
By the marginal position of described original image, select the region at described background colour place to be extracted from described original image and carry out color extraction.
6. the method according to any one of claim 2 to 5, wherein, also comprises:
The image of described original image cannot fill completely described clipping region time, the image of described original image is placed in described clipping region between two parties.
7. the picture comprising logotype is carried out to a device for cutting, it comprises:
Logotype detection module, detects for the original image treating cutting, detects in described original image the part or all of feature of the one or more logotypes comprised;
Cutting module, obtaining Target Photo for carrying out cutting to described original image, remaining with the part or all of feature of logotype described at least one in described Target Photo.
8. device according to claim 7, wherein, also comprises:
Dimension acquisition module, for obtaining the size of described Target Photo;
Zoom module, for the size according to described Target Photo, carries out convergent-divergent to described original image, makes the size of described original image be no more than the size of described Target Photo;
Cutting module, for marking clipping region by the size of described Target Photo, and by the copying image of described original image in described clipping region, cutting is carried out to described clipping region and obtains described Target Photo, to retain whole features of all described logotypes in described original image.
9. device according to claim 8, wherein, also comprises:
Size detection module, for detecting the size of described original image, comprises height and the width of described original image;
Described dimension acquisition module obtains height and the width of described Target Photo;
Described Zoom module calculates the ratio of the height of described original image and the height of described Target Photo, and calculate the ratio of the width of described original image and the width of described Target Photo, and using the maximal value in obtained ratio as the ratio of described original image being carried out to convergent-divergent, and in described ratio, convergent-divergent is carried out to described original image.
10. device according to claim 8, wherein, also comprises:
Color filling module, the image of described original image cannot fill completely described clipping region time, according to the background colour of the logotype retained in described Target Photo, and by clipping region described in extracted Color pair not by the image of described original image the part of filling fill.
11. devices according to claim 10, wherein,
Described color filling module, by the marginal position of described original image, is selected the region at described background colour place to be extracted from described original image and carries out color extraction.
Device according to any one of 12. according to Claim 8 to 11, wherein,
Described cutting module the image of described original image cannot fill completely described clipping region time, the image of described original image is placed in described clipping region between two parties.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410818268.6A CN104484853A (en) | 2014-12-24 | 2014-12-24 | Method and device for clipping pictures containing graphical signs |
| PCT/CN2015/095862 WO2016101767A1 (en) | 2014-12-24 | 2015-11-27 | Picture cropping method and device and image detecting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410818268.6A CN104484853A (en) | 2014-12-24 | 2014-12-24 | Method and device for clipping pictures containing graphical signs |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104484853A true CN104484853A (en) | 2015-04-01 |
Family
ID=52759393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410818268.6A Pending CN104484853A (en) | 2014-12-24 | 2014-12-24 | Method and device for clipping pictures containing graphical signs |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104484853A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016101767A1 (en) * | 2014-12-24 | 2016-06-30 | 北京奇虎科技有限公司 | Picture cropping method and device and image detecting method and device |
| CN105975204A (en) * | 2016-04-28 | 2016-09-28 | 深圳市金立通信设备有限公司 | Picture processing method and terminal |
| CN108898045A (en) * | 2018-04-23 | 2018-11-27 | 杭州电子科技大学 | The multi-tag image pre-processing method of gesture identification based on deep learning |
| CN109727257A (en) * | 2018-12-28 | 2019-05-07 | 北京金山安全软件有限公司 | Method, device and terminal for automatically cutting picture |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799653A (en) * | 2012-06-29 | 2012-11-28 | 中国科学院自动化研究所 | Logo detection method based on spatial connected domain prepositioning |
| CN103336954A (en) * | 2013-07-08 | 2013-10-02 | 北京捷成世纪科技股份有限公司 | Identification method and device of station caption in video |
| CN103824252A (en) * | 2014-02-10 | 2014-05-28 | 安徽科大讯飞信息科技股份有限公司 | Picture processing method and system |
| CN103914689A (en) * | 2014-04-09 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Picture cropping method and device based on face recognition |
| CN103971087A (en) * | 2013-07-12 | 2014-08-06 | 湖南纽思曼导航定位科技有限公司 | Method and device for searching and recognizing traffic signs in real time |
| CN104156413A (en) * | 2014-07-30 | 2014-11-19 | 中国科学院自动化研究所 | Trademark density based personalized trademark matching recognition method |
-
2014
- 2014-12-24 CN CN201410818268.6A patent/CN104484853A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799653A (en) * | 2012-06-29 | 2012-11-28 | 中国科学院自动化研究所 | Logo detection method based on spatial connected domain prepositioning |
| CN103336954A (en) * | 2013-07-08 | 2013-10-02 | 北京捷成世纪科技股份有限公司 | Identification method and device of station caption in video |
| CN103971087A (en) * | 2013-07-12 | 2014-08-06 | 湖南纽思曼导航定位科技有限公司 | Method and device for searching and recognizing traffic signs in real time |
| CN103824252A (en) * | 2014-02-10 | 2014-05-28 | 安徽科大讯飞信息科技股份有限公司 | Picture processing method and system |
| CN103914689A (en) * | 2014-04-09 | 2014-07-09 | 百度在线网络技术（北京）有限公司 | Picture cropping method and device based on face recognition |
| CN104156413A (en) * | 2014-07-30 | 2014-11-19 | 中国科学院自动化研究所 | Trademark density based personalized trademark matching recognition method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016101767A1 (en) * | 2014-12-24 | 2016-06-30 | 北京奇虎科技有限公司 | Picture cropping method and device and image detecting method and device |
| CN105975204A (en) * | 2016-04-28 | 2016-09-28 | 深圳市金立通信设备有限公司 | Picture processing method and terminal |
| CN108898045A (en) * | 2018-04-23 | 2018-11-27 | 杭州电子科技大学 | The multi-tag image pre-processing method of gesture identification based on deep learning |
| CN108898045B (en) * | 2018-04-23 | 2021-05-25 | 杭州电子科技大学 | Multi-label image preprocessing method based on deep learning gesture recognition |
| CN109727257A (en) * | 2018-12-28 | 2019-05-07 | 北京金山安全软件有限公司 | Method, device and terminal for automatically cutting picture |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3061234B1 (en) | Guided color grading for an extended dynamic range image | |
| Krawetz et al. | A picture’s worth | |
| CN106778996B (en) | It is embedded with the generation system and method for the two dimensional code of visual pattern and reads system | |
| CN104484855B (en) | The method and apparatus that picture is cut | |
| US20140029841A1 (en) | Mapping colors of an image | |
| CN104484853A (en) | Method and device for clipping pictures containing graphical signs | |
| JP2006091980A5 (en) | ||
| CN103761315A (en) | Method and system for displaying webpage content | |
| CN104484854A (en) | Cropping method and device for people pictures | |
| CN107393459A (en) | Method for displaying image and device | |
| US7848567B2 (en) | Determining regions of interest in synthetic images | |
| CN111310134B (en) | Screen watermark generation method, device and equipment | |
| CN106204693B (en) | Animation generation method and device based on picture detection | |
| CN107424206B (en) | Interaction method for influencing shadow expression of virtual scene by using real environment | |
| US20160093079A1 (en) | Enhanced document readability on devices | |
| CN104700354A (en) | Information embedding method and device | |
| US8456717B2 (en) | Method of pressure detection for selective scanning of a document | |
| Hamandawana et al. | Proposed methodology for georeferencing and mosaicking Corona photographs | |
| US10123052B2 (en) | Elimination of artifacts from lossy encoding of digital images by color channel expansion | |
| CN112000908A (en) | Picture loading method, device and system, electronic equipment and readable storage medium | |
| CN104363466B (en) | A kind of Picture Generation Method and device | |
| CN110533748A (en) | Seal minimizing technology and equipment | |
| CN105512595A (en) | Barcode correcting method and device | |
| CN113391779B (en) | Parameter adjusting method, device and equipment for paper-like screen | |
| US7145573B2 (en) | Method and system to combine a digital graphics object and a digital picture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150401 |
|
| RJ01 | Rejection of invention patent application after publication |