CN103295217A - Method and device for processing picture information - Google Patents
Method and device for processing picture information Download PDFInfo
- Publication number
- CN103295217A CN103295217A CN2012100520312A CN201210052031A CN103295217A CN 103295217 A CN103295217 A CN 103295217A CN 2012100520312 A CN2012100520312 A CN 2012100520312A CN 201210052031 A CN201210052031 A CN 201210052031A CN 103295217 A CN103295217 A CN 103295217A
- Authority
- CN
- China
- Prior art keywords
- pictures
- detected
- sub
- picture
- similarity
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method and device for processing picture information. The method comprises a step of respectively segmenting a reference picture and a zoomed second picture to be detected into sub-pictures into the preset size when a received first picture to be detected is zoomed according to the preset specific value, a step of selecting sub-pictures in a similar content area of the zoomed second picture to be detected and the reference picture to serve as sub-pictures to be detected and reference sub-pictures respectively, a step of carrying out grey processingon the selected sub-pictures to be detected and the reference sub-pictures and then determining the similarity of each sub-picture to be detected and the corresponding reference sub-picture, a step of determining the similarity of the second picture to be detected and the reference picture according to the determined similarity, and a step of storing the received first picture to be detected when the similarity of the second picture to be detected and the reference picture is not smaller than the first preset threshold value. The method is suitable for most pictures to be detected, and the detecting efficiency is high.
Description
Technical field
The application relates to the computer information technology field, refers to a kind of pictorial information disposal route and device especially.
Background technology
Along with the continuous development of network technology, uploading pictures becomes a kind of fashion.There are a lot of picture uploading systems to allow the user to upload specific picture, the automatic uploading pictures of some meetings is also arranged, and the sectional drawing in for example playing, state service chart etc. can only be by manually carrying out and filter for the detection of uploading pictures, this detection mode takes time and effort, and efficient is very low.
In order to improve the efficient that detects uploading pictures, often adopt the pixel inspection technique, this method need judge one by one whether picture to be detected is in full accord with the pixel with reference to some coordinate of picture, and for size and the quality of picture to be detected strict requirement is arranged.Because this method is based on coordinate picture to be detected is detected, if picture to be detected with different with reference to the size of picture, the coordinate of respective pixel point is just different so, the testing result that obtains like this is exactly mistake; In addition, in order to reduce the picture file size, a lot of pictures can be compressed when uploading, and the picture pixel after the compression can change, and also mistake can occur when adopting the pixel inspection technique to detect picture, can't correctly detect picture.Though the efficient of this method is higher than the mode of hand inspection, this method has strict demand to size and the quality of picture to be detected, and is not suitable for most picture to be detected is detected; And owing to need and compare one by one with reference to the pixel in the picture the pixel in the picture to be detected, this just causes detection efficiency still very low.Therefore, lack in the prior art and can be applicable to most of pictures to be detected and detection efficiency higher detection method.
Summary of the invention
The embodiment of the present application provides a kind of pictorial information disposal route and device, in order to solve the problem that is applicable to most of pictures to be detected and detection efficiency higher detection method that lacks that exists in the prior art.
A kind of pictorial information disposal route comprises:
With first picture to be detected that receives according to after setting the ratio convergent-divergent, respectively with the second picture cutting to be detected behind reference picture and the convergent-divergent for setting the sub-pictures of size;
Choose the sub-pictures in the similar content area of second picture to be detected and described reference picture, as sub-pictures to be detected with reference to sub-pictures;
Carry out after gray scale handles with the sub-pictures to be detected chosen with reference to sub-pictures, determine the similarity of each sub-pictures to be detected and corresponding reference sub-pictures;
According to the similarity of determining, determine the similarity of second picture to be detected and reference picture;
When the similarity of second picture of determining to be detected and reference picture is not less than first setting threshold, first picture to be detected that storage receives.
A kind of pictorial information treating apparatus comprises:
Picture cutting unit, first picture to be detected that is used for receiving is according to after setting the ratio convergent-divergent, respectively with the sub-pictures of the second picture cutting to be detected behind reference picture and the convergent-divergent for the setting size;
Sub-pictures is chosen the unit, for the sub-pictures of the similar content area of choosing second picture to be detected and described reference picture, as sub-pictures to be detected with reference to sub-pictures;
Sub-pictures similarity determining unit is used for the sub-pictures to be detected that will choose and carries out after gray scale handles with reference to sub-pictures, determines the similarity of each sub-pictures to be detected and corresponding reference sub-pictures;
Picture analogies degree determining unit is used for determining the similarity of second picture to be detected and reference picture according to the similarity of determining;
The picture-storage unit is used for when the similarity of second picture of determining to be detected and reference picture is not less than first setting threshold first picture to be detected that storage receives.
First picture to be detected that pictorial information disposal route and device that the embodiment of the present application provides, this scheme will receive is according to after setting the ratio convergent-divergent, respectively with the sub-pictures of the second picture cutting to be detected behind reference picture and the convergent-divergent for the setting size; Choose the sub-pictures in the similar content area of second picture to be detected and reference picture, as sub-pictures to be detected with reference to sub-pictures; Carry out after gray scale handles with the sub-pictures to be detected chosen with reference to sub-pictures, determine the similarity of each sub-pictures to be detected and corresponding reference sub-pictures; According to the similarity of determining, determine the similarity of second picture to be detected and reference picture; When the similarity of second picture of determining to be detected and reference picture is not less than first setting threshold, first picture to be detected that storage receives.This scheme just can be got rid of the interference of color greatly by to the sub-pictures to be detected chosen with carry out gray scale with reference to sub-pictures and handle, and is no longer dependent on the color of picture to be detected, and this has just improved the accuracy of judgement; By determining sub-pictures to be detected and determine whether with reference to sub-pictures is whether similar whether picture to be detected is similar to reference picture, thereby determine whether to store the picture to be detected that receives.Because this side does not have specific requirement for size and the quality of picture to be detected, therefore go for most of pictures to be detected.
Description of drawings
Accompanying drawing described herein is used to provide the further understanding to the application, constitutes the application's a part, and the application's illustrative examples and explanation thereof are used for explaining the application, do not constitute the improper restriction to the application.In the accompanying drawings:
Fig. 1 is the process flow diagram of pictorial information disposal route in the embodiment of the present application;
Fig. 2 is the synoptic diagram of the reference picture in the embodiment of the present application;
Fig. 3 is the synoptic diagram of the picture to be detected in the embodiment of the present application;
Fig. 4 is the synoptic diagram of the reference picture after the cutting in the embodiment of the present application;
Fig. 5 is the synoptic diagram of the picture to be detected after the cutting in the embodiment of the present application;
Fig. 6 is the synoptic diagram of a reference pixel point sequence determining in the embodiment of the present application;
Fig. 7 is the synoptic diagram of determining in the embodiment of the present application corresponding to the pixel sequence to be detected of Fig. 6;
Fig. 8 is the structural representation of pictorial information treating apparatus in the embodiment of the present application.
Embodiment
In order to make the application's technical matters to be solved, technical scheme and beneficial effect is clearer, understand, below in conjunction with drawings and Examples, the application is further elaborated.Should be appreciated that specific embodiment described herein only in order to explaining the application, and be not used in restriction the application.
In order to solve the problem that is applicable to most of pictures to be detected and detection efficiency higher detection method that lacks that exists in the prior art, a kind of pictorial information disposal route that the embodiment of the present application provides, this method can be applied in the pictorial information treating apparatus, its flow process comprises the steps: as shown in Figure 1
S10: first picture to be detected that will receive is according to after setting the ratio convergent-divergent, respectively with the sub-pictures of the second picture cutting to be detected behind reference picture and the convergent-divergent for the setting size.
Store own needed picture in the figure piece treating apparatus, these pictures just are called reference picture, and for example the picture among Fig. 2 can be used as reference picture.When receiving the picture that will upload just during first picture to be detected, judge that at first first picture to be detected is whether similar to the reference picture of self storage, for example the picture among Fig. 3 can be used as first and detects picture.
Because treat first detect picture may be different with the size of reference picture, like this just needs setting ratio carries out convergent-divergent to first picture to be detected, makes second picture to be detected behind the convergent-divergent try one's best consistent with the size of reference picture.According to after setting the ratio convergent-divergent, for setting the sub-pictures of size, the size of sub-pictures can be set according to actual needs with the second to be detected and reference picture cutting behind the convergent-divergent with first picture to be detected.
Continue to continue to use example, the synoptic diagram after first picture to be detected and the reference picture cutting respectively as shown in Figure 4 and Figure 5.
S11: choose the sub-pictures in the similar content area of second picture to be detected and reference picture, as sub-pictures to be detected with reference to sub-pictures.
After with second picture to be detected and reference picture cutting, can select certain zone to detect, for example, can choose sub-pictures in the similar content area of second picture to be detected and reference picture as detected object, sub-pictures in second picture of choosing to be detected and the similar content area of reference picture is as sub-pictures to be detected, sub-pictures in the reference picture of choosing and the similar content area second picture to be detected is as the reference sub-pictures, example two pictures as shown in Figures 2 and 3, has only the fractional part difference, other parts all are identical, so just can join in detection list or the detection sequence the sub-pictures of removing the part outside the fractional part in the second detection picture and the reference picture as detected object.
S12: the sub-pictures to be detected that will choose and carry out after gray scale handles with reference to sub-pictures, determine the similarity of each sub-pictures to be detected and corresponding reference sub-pictures.
Because a lot of pictures are coloured, and the picture after overcompression is handled, noise level of its pixel color value, picture etc. information all can seriously influence, and therefore, need do gray scale to picture and handle.In this application, just to and carry out gray scale with reference to sub-pictures and handle the sub-pictures to be detected chosen, so just can remove its color, obtain such gray-scale map after discoloring, the transition of this gray-scale map is to be consistent fully with the color transition that carries out the picture of gray scale before handling.Can adopt gray scale processing method of the prior art, repeat no more here.
By carrying out the gray scale processing to sub-pictures to be detected with reference to sub-pictures, just can obtain having only the image information of GTG, so just can get rid of the interference of color greatly, after handling, gray scale can keep the gray scale variation of brightness.This way just can avoid the pixel inspection technique to be too dependent on the problem of the quality of picture to be detected itself.
S13: according to the similarity of determining, determine the similarity of second picture to be detected and reference picture.
After determining the similarity of each sub-pictures to be detected and corresponding reference sub-pictures, just can determine the similarity of second picture to be detected and reference picture.
S14: judge whether the second definite picture to be detected and the similarity of reference picture are not less than first setting threshold, if carry out S15; Otherwise, carry out S16.
Wherein, this first setting threshold can arrange according to actual needs or situation, when to the accuracy requirement of testing result when higher, that first setting threshold can be set is bigger; When the accuracy requirement to testing result when not being very high, that first setting threshold can be set is smaller.
S15: first picture to be detected that storage receives.
When the similarity of determining second picture to be detected and reference picture is not less than first setting threshold, just think that first picture to be detected is similar to reference picture, so, just store first picture to be detected that receives.
S16: first picture to be detected that deletion receives.
When the similarity of determining second picture to be detected and reference picture during less than first setting threshold, just think that first picture to be detected and reference picture are dissimilar, can delete first picture to be detected that receives.
This scheme can be got rid of the interference of color greatly by to the sub-pictures to be detected chosen with carry out gray scale with reference to sub-pictures and handle, and is no longer dependent on the color of picture to be detected, and this has improved the accuracy of judging; By determining sub-pictures to be detected and determine whether with reference to sub-pictures is whether similar whether picture to be detected is similar to reference picture, thereby determine whether to store the picture to be detected that receives.Because this side does not have specific requirement for size and the quality of picture to be detected, therefore go for most of pictures to be detected.
Above-mentioned step is described in further detail below.
Concrete, the process of the definite setting ratio among the above-mentioned S10 comprises: in the length direction and Width of reference picture, the big direction of selected pixels number is as selected directions; And get the ratio of first picture to be detected pixel count on selected directions at the pixel count on the selected directions and reference picture, with the ratio that obtains as setting ratio.
Because picture convergent-divergent from big to small can distortion, and from little to the distortion that just is bound to of big convergent-divergent, thereby when choosing reference picture, generally can choose the less picture of size as the reference picture according to actual demand.For example: the size of the reference picture of choosing is 640*480, the size of picture to be detected is 1024*800, because the pixel count of reference picture length direction is more than the pixel count on the Width, can be with length direction as selected directions, then first picture to be detected pixel count and reference picture pixel count in the longitudinal direction in the longitudinal direction done ratio, namely get 1024 and 640 ratio 1.6, with 1.6 as setting ratio.The size of second picture to be detected that obtains behind first image zooming to be detected be 640*500 (1024/1.6=640,800/1.6=500).
Concrete, the similarity of determining each sub-pictures to be detected and corresponding reference sub-pictures among the above-mentioned S12, comprise: at each sub-pictures to be detected and corresponding reference sub-pictures, carry out following operation: choose the pixel of setting number at the desired location of sub-pictures to be detected and corresponding reference sub-pictures respectively; Form pixel sequence to be detected by the pixel of the sub-pictures of choosing to be detected, and form the reference pixel point sequence by the pixel of the reference sub-pictures of choosing; Determine the gray scale variation information of pixel sequence to be detected and reference pixel point sequence; And according to the pixel sequence of determining to be detected and the gray scale variation information of reference pixel point sequence, determine the similarity of sub-pictures to be detected and corresponding reference sub-pictures.
Can determine successively each sub-pictures to be detected with reference to the similarity of sub-pictures, the method that adopts can have multiple, linearity test method, non-linear detection method etc. method for example, be that example describes to adopt the linearity test method below, because sub-pictures to be detected and be rectangle with reference to sub-pictures, adopt the zone at the inspection place that the linearity test method can be maximum, and can avoid the picture noise.
Continue to continue to use example, Fig. 6 and Figure 7 shows that the diagonal line that to find out sub-pictures to be detected and corresponding reference sub-pictures, be benchmark with this diagonal line, the linear transitions that detects GTG on this line changes, and then this variation is come out with the mode quantization means of numerical value.At first can choose the pixel of setting number at the diagonal line of sub-pictures to be detected, for example on average get 7 pixels, form pixel sequence to be detected, note the gray level information of these 7 pixels, calculate the gray scale variation information between a back pixel and the previous pixel then, can certainly choose more pixel, the pixel of choosing is more many, and accuracy is just more high; Choosing the pixel of setting number with the identical diagonal line of sub-pictures corresponding reference sub-pictures to be detected, form the reference pixel point sequence, record the gray level information of these pixels, calculate the gray scale variation information between a back pixel and the previous pixel then.Can according to the gray scale variation information of the pixel sequence to be detected that obtains and reference pixel point sequence determine sub-pictures to be detected with reference to the similarity of sub-pictures.
Concrete, the pixel sequence to be detected that above-mentioned basis is determined and the gray scale variation information of reference pixel point sequence, determine the similarity of sub-pictures to be detected and corresponding reference sub-pictures, comprise: the number of identical gray scale variation information in the pixel sequence to be detected that will determine and the gray scale variation information of reference pixel point sequence, the perhaps ratio of the sum of the number of identical gray scale variation information and gray scale variation information in the gray scale variation information of the pixel sequence to be detected of Que Dinging and reference pixel point sequence is as the similarity of sub-pictures to be detected and corresponding reference sub-pictures.
Continue to continue to use example, when gray scale variation information greater than 0 the time, think that this pixel has brightened with respect to previous pixel; When gray scale variation information less than 0 the time, think that this pixel is with respect to previous pixel deepening.Can with bright, secretly identify gray scale variation information, the identical number of gray scale variation information in pixel sequence more to be detected and the reference pixel point sequence then, with this number as sub-pictures to be detected and corresponding similarity with reference to sub-pictures; Perhaps determine the ratio of the sum of the number of gray scale variation information identical in the gray scale variation information of pixel sequence to be detected and reference pixel point sequence and gray scale variation information, as the similarity of sub-pictures to be detected and corresponding reference sub-pictures.
For example: the gray scale variation information in the pixel sequence of determining to be detected is " bright, bright, dark, dark, dark, dark, bright ", gray scale variation information in the reference pixel point sequence is " bright, dark, dark, dark, dark, bright, bright ", wherein first and third, four, five, seven these 4 gray scale variation information is identical, can be with 4 similarities as sub-pictures to be detected and corresponding reference sub-pictures; Also can with 4 with the ratio 0.57 of the sum 7 of the gray scale variation information ratio as the sum of gray scale variation information.
Concrete, the similarity that basis among the above-mentioned S13 is determined, determine the similarity of second picture to be detected and reference picture, specifically comprise: when the similarity of sub-pictures to be detected and corresponding reference sub-pictures is not less than second setting threshold, determine that sub-pictures to be detected is similar to the corresponding reference sub-pictures; According to the number of the to be detected sub-pictures of determining similar to the corresponding reference sub-pictures and the total number of sub-pictures to be detected, determine the similarity of second picture to be detected and reference picture.
Concrete, above-mentioned basis is determined the number of the to be detected sub-pictures similar to the corresponding reference sub-pictures and the total number of sub-pictures to be detected, determine the similarity of second picture to be detected and reference picture, specifically comprise: obtain the ratio of the total number of the number of definite to be detected sub-pictures similar to the corresponding reference sub-pictures and sub-pictures to be detected, with the ratio that the obtains similarity as second picture to be detected and reference picture.
Can be with the ratio of the total number of the number of the to be detected sub-pictures similar to the corresponding reference sub-pictures and sub-pictures to be detected similarity as second picture to be detected and reference picture; Also can be with the product of the total number of the number of the to be detected sub-pictures similar to the corresponding reference sub-pictures and sub-pictures to be detected similarity as second picture to be detected and reference picture, here two kinds of methods of determining the similarity of second picture to be detected and reference picture have only been enumerated, can certainly adopt method of the prior art, repeat no more here.
Based on same inventive concept, a kind of pictorial information treating apparatus that the embodiment of the present application also provides, the structure of this device comprises shown in 8 figure:
Sub-pictures is chosen unit 81, for the sub-pictures of the similar content area of choosing second picture to be detected and reference picture, as sub-pictures to be detected with reference to sub-pictures.
Sub-pictures similarity determining unit 82 is used for the sub-pictures to be detected that will choose and carries out after gray scale handles with reference to sub-pictures, determines the similarity of each sub-pictures to be detected and corresponding reference sub-pictures.
Picture analogies degree determining unit 83 is used for determining the similarity of second picture to be detected and reference picture according to the similarity of determining.
Picture-storage unit 84 is used for when the similarity of second picture of determining to be detected and reference picture is not less than first setting threshold first picture to be detected that storage receives.
Concrete, above-mentioned picture cutting unit 80 specifically is used for: in length direction and the big direction of Width selected pixels number of reference picture, as selected directions; And get the ratio of first picture to be detected pixel count on selected directions at the pixel count on the selected directions and reference picture, with the ratio that obtains as setting ratio.
Concrete, above-mentioned sub-pictures similarity determining unit 82 concrete being used at each sub-pictures to be detected and corresponding reference sub-pictures, is carried out: choose the pixel of setting number at the desired location of sub-pictures to be detected and corresponding reference sub-pictures respectively; Form pixel sequence to be detected by the pixel of the sub-pictures of choosing to be detected, and form the reference pixel point sequence by the pixel of the reference sub-pictures of choosing; Determine the gray scale variation information of pixel sequence to be detected and reference pixel point sequence; And according to the pixel sequence of determining to be detected and the gray scale variation information of reference pixel point sequence, determine the similarity of sub-pictures to be detected and corresponding reference sub-pictures.
Concrete, above-mentioned sub-pictures similarity determining unit 82, specifically be used for: the number of the gray scale variation information that the pixel sequence to be detected that will determine is identical with the gray scale variation information of reference pixel point sequence, the perhaps ratio of the sum of the number of identical gray scale variation information and gray scale variation information in the gray scale variation information of the pixel sequence to be detected of Que Dinging and reference pixel point sequence is as the similarity of sub-pictures to be detected and corresponding reference sub-pictures.
Concrete, above-mentioned picture analogies degree determining unit 83 specifically is used for: when the similarity of sub-pictures to be detected and corresponding reference sub-pictures is not less than second setting threshold, determine that sub-pictures to be detected is similar to the corresponding reference sub-pictures; According to the number of the to be detected sub-pictures of determining similar to the corresponding reference sub-pictures and the total number of sub-pictures to be detected, determine the similarity of second picture to be detected and reference picture.
Concrete, above-mentioned picture analogies degree determining unit 83, specifically be used for: obtain the ratio of the total number of the number of definite to be detected sub-pictures similar to the corresponding reference sub-pictures and sub-pictures to be detected, with the ratio that the obtains similarity as second picture to be detected and reference picture.
Those skilled in the art should understand that the application's embodiment can be provided as method, system or computer program.Therefore, the application can adopt complete hardware embodiment, complete software embodiment or in conjunction with the form of the embodiment of software and hardware aspect.And the application can adopt the form of the computer program of implementing in one or more computer-usable storage medium (including but not limited to magnetic disk memory, CD-ROM, optical memory etc.) that wherein include computer usable program code.
The application is that reference is described according to process flow diagram and/or the block scheme of method, equipment (system) and the computer program of the embodiment of the present application.Should understand can be by the flow process in each flow process in computer program instructions realization flow figure and/or the block scheme and/or square frame and process flow diagram and/or the block scheme and/or the combination of square frame.Can provide these computer program instructions to the processor of multi-purpose computer, special purpose computer, Embedded Processor or other programmable data processing device to produce a machine, make the instruction of carrying out by the processor of computing machine or other programmable data processing device produce to be used for the device of the function that is implemented in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame appointments.
These computer program instructions also can be stored in energy vectoring computer or the computer-readable memory of other programmable data processing device with ad hoc fashion work, make the instruction that is stored in this computer-readable memory produce the manufacture that comprises command device, this command device is implemented in the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame.
These computer program instructions also can be loaded on computing machine or other programmable data processing device, make and carry out the sequence of operations step producing computer implemented processing at computing machine or other programmable devices, thereby be provided for being implemented in the step of the function of appointment in flow process of process flow diagram or a plurality of flow process and/or square frame of block scheme or a plurality of square frame in the instruction that computing machine or other programmable devices are carried out.
Although described the application's preferred embodiment, in a single day those skilled in the art get the basic creative concept of cicada, then can make other change and modification to these embodiment.So claims are intended to all changes and the modification that are interpreted as comprising preferred embodiment and fall into the application's scope.
Above-mentioned explanation has illustrated and has described the application's preferred embodiment, but as previously mentioned, be to be understood that the application is not limited to the disclosed form of this paper, should not regard the eliminating to other embodiment as, and can be used for various other combinations, modification and environment, and can in invention contemplated scope described herein, change by technology or the knowledge of above-mentioned instruction or association area.And the spirit and scope that the change that those skilled in the art carry out and variation do not break away from the application, then all should be in the protection domain of the application's claims.
Claims (10)
1. a pictorial information disposal route is characterized in that, comprising:
With first picture to be detected that receives according to after setting the ratio convergent-divergent, respectively with the second picture cutting to be detected behind reference picture and the convergent-divergent for setting the sub-pictures of size;
Choose the sub-pictures in the similar content area of second picture to be detected and described reference picture, as sub-pictures to be detected with reference to sub-pictures;
Carry out after gray scale handles with the sub-pictures to be detected chosen with reference to sub-pictures, determine the similarity of each sub-pictures to be detected and corresponding reference sub-pictures;
According to the similarity of determining, determine the similarity of second picture to be detected and reference picture;
When the similarity of second picture of determining to be detected and reference picture is not less than first setting threshold, first picture to be detected that storage receives.
2. the method for claim 1 is characterized in that, determines the process of described setting ratio, specifically comprises:
The big direction of selected pixels number in the length direction of reference picture and Width is as selected directions; And
Get the ratio of first picture to be detected pixel count on described selected directions at the pixel count on the described selected directions and reference picture, with the ratio that obtains as setting ratio.
3. the method for claim 1 is characterized in that, determines the similarity of each sub-pictures to be detected and corresponding reference sub-pictures, specifically comprises:
At each sub-pictures to be detected and corresponding reference sub-pictures, carry out:
Choose the pixel of setting number at the desired location of sub-pictures to be detected and corresponding reference sub-pictures respectively;
Form pixel sequence to be detected by the pixel of the sub-pictures of choosing to be detected, and form the reference pixel point sequence by the pixel of the reference sub-pictures of choosing;
Determine the gray scale variation information of described pixel sequence to be detected and described reference pixel point sequence; And
According to the pixel sequence of determining described to be detected and the gray scale variation information of described reference pixel point sequence, determine the similarity of sub-pictures to be detected and corresponding reference sub-pictures.
4. method as claimed in claim 3 is characterized in that, according to the pixel sequence of determining described to be detected and the gray scale variation information of described reference pixel point sequence, determines the similarity of sub-pictures to be detected and corresponding reference sub-pictures, specifically comprises:
The number of identical gray scale variation information in the gray scale variation information with definite pixel sequence described to be detected and described reference pixel point sequence, the perhaps ratio of the sum of the number of identical gray scale variation information and gray scale variation information in the gray scale variation information of the pixel sequence described to be detected of Que Dinging and described reference pixel point sequence is as the similarity of sub-pictures to be detected and corresponding reference sub-pictures.
5. the method for claim 1 is characterized in that, according to the similarity of determining, determines the similarity of second picture to be detected and reference picture, specifically comprises:
When the similarity of sub-pictures to be detected and corresponding reference sub-pictures is not less than second setting threshold, determine that described sub-pictures to be detected is similar to the corresponding reference sub-pictures;
According to the number of the to be detected sub-pictures of determining similar to the corresponding reference sub-pictures and the total number of sub-pictures to be detected, determine the similarity of second picture to be detected and reference picture.
6. method as claimed in claim 5 is characterized in that, according to the number of the to be detected sub-pictures of determining similar to the corresponding reference sub-pictures and the total number of sub-pictures to be detected, determines the similarity of second picture to be detected and reference picture, specifically comprises:
Obtain the ratio of the total number of the number of definite to be detected sub-pictures similar to the corresponding reference sub-pictures and sub-pictures to be detected, with the ratio that the obtains similarity as second picture to be detected and reference picture.
7. a pictorial information treating apparatus is characterized in that, comprising:
Picture cutting unit, first picture to be detected that is used for receiving is according to after setting the ratio convergent-divergent, respectively with the sub-pictures of the second picture cutting to be detected behind reference picture and the convergent-divergent for the setting size;
Sub-pictures is chosen the unit, for the sub-pictures of the similar content area of choosing second picture to be detected and described reference picture, as sub-pictures to be detected with reference to sub-pictures;
Sub-pictures similarity determining unit is used for the sub-pictures to be detected that will choose and carries out after gray scale handles with reference to sub-pictures, determines the similarity of each sub-pictures to be detected and corresponding reference sub-pictures;
Picture analogies degree determining unit is used for determining the similarity of second picture to be detected and reference picture according to the similarity of determining;
The picture-storage unit is used for when the similarity of second picture of determining to be detected and reference picture is not less than first setting threshold first picture to be detected that storage receives.
8. device as claimed in claim 7, it is characterized in that, described sub-pictures similarity determining unit, concrete being used at each sub-pictures to be detected and corresponding reference sub-pictures, carry out: choose the pixel of setting number at the desired location of sub-pictures to be detected and corresponding reference sub-pictures respectively; Form pixel sequence to be detected by the pixel of the sub-pictures of choosing to be detected, and form the reference pixel point sequence by the pixel of the reference sub-pictures of choosing; Determine the gray scale variation information of described pixel sequence to be detected and described reference pixel point sequence; And according to the pixel sequence of determining described to be detected and the gray scale variation information of described reference pixel point sequence, determine the similarity of sub-pictures to be detected and corresponding reference sub-pictures.
9. device as claimed in claim 8, it is characterized in that, described sub-pictures similarity determining unit, concrete number for the identical gray scale variation information of the gray scale variation information of the pixel sequence described to be detected that will determine and described reference pixel point sequence, the perhaps ratio of the sum of the number of identical gray scale variation information and gray scale variation information in the gray scale variation information of the pixel sequence described to be detected of Que Dinging and described reference pixel point sequence is as the similarity of sub-pictures to be detected and corresponding reference sub-pictures.
10. device as claimed in claim 7, it is characterized in that, described picture analogies degree determining unit, concrete being used for determines that described sub-pictures to be detected is similar to the corresponding reference sub-pictures when the similarity of sub-pictures to be detected and corresponding reference sub-pictures is not less than second setting threshold; According to the number of the to be detected sub-pictures of determining similar to the corresponding reference sub-pictures and the total number of sub-pictures to be detected, determine the similarity of second picture to be detected and reference picture.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210052031.2A CN103295217B (en) | 2012-03-01 | 2012-03-01 | Pictorial information disposal route and device |
| HK13112079.4A HK1184897A1 (en) | 2012-03-01 | 2013-10-28 | Method for processing image information and device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210052031.2A CN103295217B (en) | 2012-03-01 | 2012-03-01 | Pictorial information disposal route and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103295217A true CN103295217A (en) | 2013-09-11 |
| CN103295217B CN103295217B (en) | 2016-03-30 |
Family
ID=49096023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210052031.2A Active CN103295217B (en) | 2012-03-01 | 2012-03-01 | Pictorial information disposal route and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN103295217B (en) |
| HK (1) | HK1184897A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832473A (en) * | 2017-11-30 | 2018-03-23 | 奕响（大连）科技有限公司 | A kind of picture similar decision method after non-equal proportion stretching |
| CN107886134A (en) * | 2017-11-30 | 2018-04-06 | 奕响（大连）科技有限公司 | A kind of local creative similar decision method of picture |
| CN108932279A (en) * | 2018-04-28 | 2018-12-04 | 华为技术有限公司 | A kind of application page processing method and processing device |
| CN109947965A (en) * | 2017-09-04 | 2019-06-28 | 阿里巴巴集团控股有限公司 | Object identifying, the update of data acquisition system, data processing method and device |
| CN110490898A (en) * | 2018-05-15 | 2019-11-22 | 苏州欧菲光科技有限公司 | Animation play processing method, liquid crystal instrument system and vehicle based on sequence frame |
| CN112668636A (en) * | 2020-12-25 | 2021-04-16 | 展讯通信（上海）有限公司 | Camera shielding detection method and system, electronic equipment and storage medium |
| CN113139589A (en) * | 2021-04-12 | 2021-07-20 | 网易（杭州）网络有限公司 | Picture similarity detection method and device, processor and electronic device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101136015A (en) * | 2006-09-01 | 2008-03-05 | 北大方正集团有限公司 | Method for calculating similarity between images |
| CN101667299A (en) * | 2009-09-27 | 2010-03-10 | 汲业 | Method for staining digital image |
| CN102054177A (en) * | 2010-12-29 | 2011-05-11 | 北京新媒传信科技有限公司 | Image similarity calculation method and device |
| CN102087652A (en) * | 2009-12-08 | 2011-06-08 | 百度在线网络技术（北京）有限公司 | Method for screening images and system thereof |
-
2012
- 2012-03-01 CN CN201210052031.2A patent/CN103295217B/en active Active
-
2013
- 2013-10-28 HK HK13112079.4A patent/HK1184897A1/en unknown
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101136015A (en) * | 2006-09-01 | 2008-03-05 | 北大方正集团有限公司 | Method for calculating similarity between images |
| CN101667299A (en) * | 2009-09-27 | 2010-03-10 | 汲业 | Method for staining digital image |
| CN102087652A (en) * | 2009-12-08 | 2011-06-08 | 百度在线网络技术（北京）有限公司 | Method for screening images and system thereof |
| CN102054177A (en) * | 2010-12-29 | 2011-05-11 | 北京新媒传信科技有限公司 | Image similarity calculation method and device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947965A (en) * | 2017-09-04 | 2019-06-28 | 阿里巴巴集团控股有限公司 | Object identifying, the update of data acquisition system, data processing method and device |
| CN109947965B (en) * | 2017-09-04 | 2023-09-05 | 阿里巴巴集团控股有限公司 | Object recognition, data set updating and data processing method and device |
| CN107832473A (en) * | 2017-11-30 | 2018-03-23 | 奕响（大连）科技有限公司 | A kind of picture similar decision method after non-equal proportion stretching |
| CN107886134A (en) * | 2017-11-30 | 2018-04-06 | 奕响（大连）科技有限公司 | A kind of local creative similar decision method of picture |
| CN108932279A (en) * | 2018-04-28 | 2018-12-04 | 华为技术有限公司 | A kind of application page processing method and processing device |
| CN110490898A (en) * | 2018-05-15 | 2019-11-22 | 苏州欧菲光科技有限公司 | Animation play processing method, liquid crystal instrument system and vehicle based on sequence frame |
| CN112668636A (en) * | 2020-12-25 | 2021-04-16 | 展讯通信（上海）有限公司 | Camera shielding detection method and system, electronic equipment and storage medium |
| CN112668636B (en) * | 2020-12-25 | 2023-08-08 | 展讯通信（上海）有限公司 | Camera shielding detection method and system, electronic equipment and storage medium |
| CN113139589A (en) * | 2021-04-12 | 2021-07-20 | 网易（杭州）网络有限公司 | Picture similarity detection method and device, processor and electronic device |
| CN113139589B (en) * | 2021-04-12 | 2023-02-28 | 网易（杭州）网络有限公司 | Picture similarity detection method and device, processor and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| HK1184897A1 (en) | 2014-01-30 |
| CN103295217B (en) | 2016-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103295217A (en) | Method and device for processing picture information | |
| JP4981128B2 (en) | Keyframe extraction from video | |
| US20100201880A1 (en) | Shot size identifying apparatus and method, electronic apparatus, and computer program | |
| EP1857977A3 (en) | Image inspection method and image inspection apparatus employing the same | |
| US9600298B2 (en) | Active and efficient monitoring of a graphical user interface | |
| CN103970445A (en) | Display interface mobile type screenshot method, system and device | |
| CN105573888A (en) | Method and apparatus for detecting disk performance in distributed file system | |
| JP4327827B2 (en) | Video recording / reproducing system and video recording / reproducing method | |
| CN107360435A (en) | Blockiness detection methods, block noise filtering method and device | |
| JP2014095979A (en) | Electronic device, image data processing method and program | |
| CN104410790A (en) | Information processing method and electronic equipment | |
| EP2669894A1 (en) | Method for creating thumbnail images of videos and an electronic device for display thereof | |
| EP3023987A1 (en) | Method and apparatus for visualizing information of a digital video stream | |
| CN1992916A (en) | Method of detecting image definition | |
| CN110637227A (en) | Detection parameter determining method and detection device | |
| CN106445355A (en) | Method and small screen device for showing contents of large screen | |
| CN104602096B (en) | A kind of detection method and device in video caption area | |
| CN109348288A (en) | A kind of processing method of video, device, storage medium and terminal | |
| CN111611151B (en) | Method and device for detecting overdrawing of user interface | |
| CN106055532A (en) | Processing method and device for data replication | |
| CN105635791A (en) | Detection method and apparatus for blurred video image | |
| WO2011161723A1 (en) | Drawing device and drawing method | |
| CN104780310A (en) | Image blurring detection method and system and camera | |
| CN111757182B (en) | Image splash screen detection method, device, computer device and readable storage medium | |
| CN113160083A (en) | Media asset video cover map optimization method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1184897 Country of ref document: HK |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: GR Ref document number: 1184897 Country of ref document: HK |