CN110084298A - Method and device for detection image similarity - Google Patents
Method and device for detection image similarity Download PDFInfo
- Publication number
- CN110084298A CN110084298A CN201910327769.7A CN201910327769A CN110084298A CN 110084298 A CN110084298 A CN 110084298A CN 201910327769 A CN201910327769 A CN 201910327769A CN 110084298 A CN110084298 A CN 110084298A
- Authority
- CN
- China
- Prior art keywords
- image
- district area
- area image
- pending district
- processed
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
Embodiment of the disclosure discloses the method and device for detection image similarity.One specific embodiment of this method includes: the reference picture for obtaining image to be processed and corresponding above-mentioned image to be processed;Above-mentioned image to be processed and reference picture are analyzed respectively under different sizes, calculate the similarity information between above-mentioned image to be processed and above-mentioned reference picture;The testing result information of above-mentioned application to be tested is exported according to above-mentioned similarity information.This embodiment improves the accuracy and efficiencies of the testing result information of application to be tested.
Description
Technical field
Embodiment of the disclosure is related to technical field of image processing, and in particular to for detection image similarity method and
Device.
Background technique
With the development of science and technology, the data-handling capacity of smart machine is also stronger and stronger.User can be set by intelligence
The types of applications of standby installation carries out the operation such as map inquiry, information search, improves the working efficiency of user and the information of life
Change horizontal.Technical staff can according to actual needs be updated application, to improve the data-handling efficiency of application.
Summary of the invention
Embodiment of the disclosure proposes the method and device for detection image similarity.
In a first aspect, embodiment of the disclosure provides a kind of method for detection image similarity, this method comprises:
Obtain the reference picture of image to be processed and corresponding above-mentioned image to be processed;Respectively to above-mentioned figure to be processed under different sizes
Picture and above-mentioned reference picture are analyzed, and the similarity information between above-mentioned image to be processed and above-mentioned reference picture is calculated;Root
The testing result information of above-mentioned application to be tested is exported according to above-mentioned similarity information.
In some embodiments, it is above-mentioned under different sizes respectively to above-mentioned image to be processed and above-mentioned reference picture into
Row analysis, calculates the similarity information between above-mentioned image to be processed and above-mentioned reference picture, comprising: be sized according to first
Obtain the first pending district area image of above-mentioned at least one the first designated position of image to be processed, wherein above-mentioned first wait locate
Reason area image includes the number of corresponding above-mentioned first designated position;It is sized according to above-mentioned first and obtains above-mentioned reference picture
First reference zone image of at least one above-mentioned first designated position, wherein above-mentioned first reference zone image includes corresponding to
The number of above-mentioned first designated position;For above-mentioned first pending district area image and corresponding above-mentioned first pending district area image
The first reference zone image, determine similar between above-mentioned first pending district area image and above-mentioned first reference zone image
Property.
In some embodiments, above-mentioned determination the first pending district area image and the first reference zone image it
Between similitude, comprising: obtain the first finger image information to be processed and above-mentioned of the first pending district area image respectively
First reference picture finger print information of one reference zone image;In response to the above-mentioned first finger image information to be processed and above-mentioned the
The first Hamming distance between one reference picture finger print information determines above-mentioned first pending area figure less than the first given threshold
As between above-mentioned first reference zone image have similitude.
In some embodiments, it is above-mentioned under different sizes respectively to above-mentioned image to be processed and above-mentioned reference picture into
Row analysis, calculates the similarity information between above-mentioned image to be processed and above-mentioned reference picture, comprising: in response to above-mentioned first to
There is similitude between processing region image and corresponding first reference zone image, be sized according to second and obtain above-mentioned the
Second pending district area image of one at least one the second designated position of pending district area image, is sized according to above-mentioned second
Obtain the second reference zone image of above-mentioned at least one above-mentioned second designated position of first reference zone image, wherein above-mentioned
Second pending district area image includes the number of corresponding above-mentioned second designated position, and above-mentioned second is sized less than above-mentioned first
It is sized, above-mentioned second reference zone image includes the number of corresponding above-mentioned second designated position;According to above-mentioned second wait locate
Similitude between reason area image and corresponding second reference zone image determines the similar of the first pending district area image
Spend information.
In some embodiments, above-mentioned according to above-mentioned second pending district area image and corresponding second reference zone image
Between similitude determine the similarity information of the first pending district area image, comprising: it is to be processed to obtain above-mentioned second respectively
Second reference picture finger print information of the finger image information to be processed of the second of area image and above-mentioned second reference zone image;
It is less than in response to the second Hamming distance between the above-mentioned second finger image information to be processed and the second reference picture finger print information
Second given threshold, determining has similitude between above-mentioned second pending district area image and above-mentioned second reference zone image;
By the ratio between the quantity of the second pending district area image with similitude and the total quantity of the second pending district area image
It is set as the similarity information of the first pending district area image.
In some embodiments, it is above-mentioned under different sizes respectively to above-mentioned image to be processed and above-mentioned reference picture into
Row analysis, calculates the similarity information between above-mentioned image to be processed and above-mentioned reference picture, comprising: according to above-mentioned first wait locate
The similarity information for managing area image determines the quantity with the first pending district area image of similitude;It will be with similitude
Ratio between the quantity of first pending district area image and the total quantity of the first pending district area image is set as above-mentioned wait locate
Manage the similarity information between image and reference picture.
Second aspect, embodiment of the disclosure provide a kind of device for detection image similarity, which includes:
Image acquisition unit is configured to obtain the reference picture of image to be processed and corresponding above-mentioned image to be processed;Similarity information
Computing unit is configured under different sizes respectively analyze above-mentioned image to be processed and above-mentioned reference picture, meter
It counts in stating the similarity information between image to be processed and above-mentioned reference picture;Testing result information output unit, is configured to
The testing result information of above-mentioned application to be tested is exported according to above-mentioned similarity information.
In some embodiments, above-mentioned similarity information computing unit includes: that pending district area image divides subelement, quilt
It is configured to be sized the first pending area for obtaining above-mentioned at least one the first designated position of image to be processed according to first
Image, wherein above-mentioned first pending district area image includes the number of corresponding above-mentioned first designated position;Reference zone image is drawn
Molecular cell is configured to be sized above-mentioned at least one above-mentioned first designated position of reference picture of acquisition according to above-mentioned first
The first reference zone image, wherein above-mentioned first reference zone image includes the number of corresponding above-mentioned first designated position;Phase
Subelement is determined like property, for the first reference area of above-mentioned first pending district area image and corresponding first pending district area image
Area image, the similitude being configured to determine between above-mentioned first pending district area image and above-mentioned first reference zone image.
In some embodiments, above-mentioned similitude determines that subelement includes: the first finger image data obtaining module, is matched
It is set to the first finger image information to be processed for obtaining the first pending district area image respectively and above-mentioned first reference zone figure
First reference picture finger print information of picture;First similarity determining module, in response to the above-mentioned first finger image information to be processed
The first Hamming distance between above-mentioned first reference picture finger print information is configured to determine above-mentioned less than the first given threshold
There is similitude between first pending district area image and the first reference zone image.
In some embodiments, above-mentioned similarity information computing unit includes: that area image divides subelement, in response to upper
Stating has similitude between the first pending district area image and corresponding first reference zone image, be configured to set according to second
Scale cun obtains the second pending district area image of at least one the second designated position of above-mentioned first pending district area image, according to
Above-mentioned second is sized the second reference area for obtaining above-mentioned at least one above-mentioned second designated position of first reference zone image
Area image, wherein above-mentioned second pending district area image includes the number of corresponding above-mentioned second designated position, above-mentioned second setting
Size is less than above-mentioned first and is sized, and above-mentioned second reference zone image includes the number of corresponding above-mentioned second designated position;
Similarity information determines subelement, is configured to according to above-mentioned second pending district area image and corresponding second reference zone figure
Similitude between picture determines the similarity information of the first pending district area image.
In some embodiments, above-mentioned similarity information determines that subelement includes: the second finger image data obtaining module,
It is configured to obtain the second finger image information to be processed and above-mentioned second reference of above-mentioned second pending district area image respectively
Second reference picture finger print information of area image;Second similarity determining module refers in response to the above-mentioned second image to be processed
The second Hamming distance between line information and the second reference picture finger print information is configured to determine less than the second given threshold
Stating has similitude between the second pending district area image and above-mentioned second reference zone image;Mould is arranged in second similarity information
Block, the total quantity of the quantity and the second pending district area image that are configured to have the second pending district area image of similitude
Between ratio be set as the similarity information of the first pending district area image.
In some embodiments, above-mentioned similarity information computing unit includes: that similar image quantity obtains subelement, is matched
It is set to the first pending district area image for determining according to the similarity information of above-mentioned first pending district area image and there is similitude
Quantity;Image similarity information determines subelement, the number for being configured to have the first pending district area image of similitude
Ratio between amount and the total quantity of the first pending district area image is set as between above-mentioned image to be processed and reference picture
Similarity information.
The third aspect, embodiment of the disclosure provide a kind of electronic equipment, comprising: one or more processors;Storage
Device is stored thereon with one or more programs, when said one or multiple programs are executed by said one or multiple processors,
So that said one or multiple processors execute the method for detection image similarity of above-mentioned first aspect.
Fourth aspect, embodiment of the disclosure provide a kind of computer-readable medium, are stored thereon with computer program,
It is characterized in that, the program realizes the method for detection image similarity of above-mentioned first aspect when being executed by processor.
The method and device for detection image similarity that embodiment of the disclosure provides, obtains image to be processed first
With the reference picture of the above-mentioned image to be processed of correspondence;Then respectively to above-mentioned image to be processed and with reference to figure under different sizes
As being analyzed, the similarity information between image and reference picture to be processed is calculated;It is finally defeated according to the similarity information
The testing result information of the application to be tested out.Technical scheme can obtain the similarity information of image to be processed,
Improve the accuracy and efficiency of the testing result information of application to be tested.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the disclosure is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the disclosure can be applied to exemplary system architecture figure therein;
Fig. 2 is the flow chart according to one embodiment of the method for detection image similarity of the disclosure;
Fig. 3 is the schematic diagram according to an application scenarios of the method for detection image similarity of the disclosure;
Fig. 4 is the flow chart according to one embodiment of the method for the calculating image similarity information of the disclosure;
Fig. 5 is the structural schematic diagram according to one embodiment of the device for detection image similarity of the disclosure;
Fig. 6 is adapted for the electronic devices structure schematic diagram for realizing embodiment of the disclosure.
Specific embodiment
The disclosure is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the disclosure can phase
Mutually combination.The disclosure is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using embodiment of the disclosure for the method for detection image similarity or for detection figure
As the exemplary system architecture 100 of the device of similarity.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various applications, such as screenshotss application, picture editting's application, net can be installed on terminal device 101,102,103
The application of page browsing device, shopping class application, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, the various electronic equipments of image procossing, including but not limited to smart phone, plate are can be with display screen and supported
Computer, pocket computer on knee and desktop computer etc..When terminal device 101,102,103 is software, can install
In above-mentioned cited electronic equipment.Multiple softwares or software module may be implemented into (such as providing distributed clothes in it
Business), single software or software module also may be implemented into, be not specifically limited herein.
Server 105 can be to provide the server of various services, for example, to terminal device 101,102,103 send to
The server that the image to be processed of test application is handled.Server can carry out the data such as the image to be processed received
The processing such as analysis, and processing result (such as testing result information) is fed back into terminal device.
It should be noted that the method provided by embodiment of the disclosure for detection image similarity can be by terminal
Equipment 101,102,103 is individually performed, or can also be executed jointly by terminal device 101,102,103 and server 105.Phase
Ying Di, the device for detection image similarity can be set in terminal device 101,102,103, also can be set in service
In device 105.
It should be noted that server can be hardware, it is also possible to software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server also may be implemented into.It, can when server is software
To be implemented as multiple softwares or software module (such as providing Distributed Services), single software or software also may be implemented into
Module is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, one embodiment of the method for detection image similarity according to the disclosure is shown
Process 200.This for detection image similarity method the following steps are included:
Step 201, the reference picture of image to be processed and corresponding above-mentioned image to be processed is obtained.
In the present embodiment, for the executing subject of the method for detection image similarity (such as terminal device shown in FIG. 1
101,102,103 and/or server 105) to be tested answer can be got by wired connection mode or radio connection
Image to be processed.Wherein, what image to be processed can be application to be tested is able to reflect application to be tested difference and its
The application setting image etc. that he applies.For example, application to be tested is based on a certain template development, in the version updating mistake of application
Cheng Zhong, the template should not change, and otherwise application is likely to occur significant trouble.Then, the image where template can be
The image to be processed of the application.It should be pointed out that above-mentioned radio connection can include but is not limited to 3G/4G connection,
WiFi connection, bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection and other now
The radio connection known or developed in the future.
In the prior art, technical staff needs according to actual needs to be updated the version of application.After version updating,
It needs for the key content of updated application to be compared with the key content of the application before update, to ensure updated version
Originally it can sequentially run.In practice, the key content of application is usually using fixed template, which can be more with application
A specific function image has correlation.For this purpose, the technical staff of application needs and updated specific function figure preceding to update
As being compared, judge that updated application can be operated normally by the similitude of specific function image.But technical staff
The similitude that specific function image is usually judged by manual type leads to the standard of the judgement to specific function image similarity
True property and inefficient, and then the accurate detection result information of updated version can not be got.
In order to compare the similitude for applying correspondence image.The executing subject of the application can obtain first image to be processed with
And the reference picture of corresponding above-mentioned image to be processed.Image and reference picture to be processed can be to be obtained by modes such as screenshotss.
Step 202, above-mentioned image to be processed and above-mentioned reference picture are analyzed respectively under different sizes, is calculated
Similarity information between above-mentioned image to be processed and above-mentioned reference picture.
After getting image and reference picture to be processed, executing subject can color, different sizes, line by image
Whether the modes such as item, content are similar to judge image and reference picture to be processed, and obtain corresponding similarity information.Such as:
Similarity information may is that the similar area image quantity of image and reference picture to be processed is X, and the total quantity of area image is
Y etc..In this way, improving the judgment accuracy and efficiency of the similarity to image to be processed.According to actual needs, similarity information
It can also be other expression ways, no longer repeat one by one herein.
Step 203, the testing result information of above-mentioned application to be tested is exported according to above-mentioned similarity information.
After obtaining similarity information, executing subject can export the inspection of above-mentioned application to be tested according to above-mentioned similarity information
Survey result information.For example, testing result information may is that the image to be processed of application to be tested shares X, wherein similarity
There is a Y for 100%;Similarity is 80% to have Z etc., and the failure rate of application to be tested is 90%.Testing result information is also
It can be other kinds of information, no longer repeat one by one herein.As can be seen from the above description, the present embodiment method is qualitative first
The accuracy and efficiency of the testing result information of application to be tested can be improved.
With continued reference to one that Fig. 3, Fig. 3 are according to the application scenarios of the method for detection image similarity of the present embodiment
A schematic diagram.In the application scenarios of Fig. 3, user can send a certain application to be tested to server by terminal device 102
Image to be processed " A ".Later, after server 105 finds the reference picture of corresponding image " A " to be processed, server 105 can
To be determined between image to be processed " A " and reference picture by low-dimensional large scale first by a variety of methods (such as hash algorithm)
Then similitude calculates the similarity information between image " A " to be processed and reference picture by higher-dimension small size again.Finally,
The testing result information of the corresponding application to be tested of the output of server 105.
The method provided by the above embodiment of the disclosure obtains image to be processed first and corresponds to above-mentioned image to be processed
Reference picture;Then above-mentioned image to be processed and reference picture are analyzed respectively under different sizes, calculate it is above-mentioned to
Handle the similarity information between image and above-mentioned reference picture;Finally to be tested answered according to similarity information output is described
Testing result information.Technical scheme can obtain the similarity information of image to be processed, improve to be tested answer
The accuracy and efficiency of testing result information.
With further reference to Fig. 4, it illustrates divide respectively image to be processed and reference picture under different sizes
Analysis, calculates the process 400 of another embodiment of the method for the similarity information between image and reference picture to be processed.The meter
Process 400 of the nomogram as the method for similarity information, comprising the following steps:
Step 401, it is sized according to first and obtains the first of above-mentioned at least one the first designated position of image to be processed
Pending district area image.
In the present embodiment, method executing subject (such as the terminal device shown in FIG. 1 of image similarity information is calculated
101,102,103 and/or server 105) wired connection mode or radio connection can be passed through receive image to be processed
And reference picture.
For the similitude between image more to be processed and reference picture, executing subject can obtain at least one first
First pending district area image of the first designated position obtains at least one first designated position for corresponding to above-mentioned image to be processed
The first pending district area image.Wherein, first designated position of the present embodiment is that can characterize image uniqueness to be processed
Position where key images feature on image etc. is set.Wherein, the first pending district area image may include corresponding above-mentioned
The number of first designated position.For example, image to be processed is rectangle, content is a certain personage.First designated position can be to
Handle a certain range of region in 4 angles of image.There should be the pattern etc. of special pattern structure in the area.
Step 402, it is sized according to above-mentioned first and obtains above-mentioned at least one above-mentioned first designated position of reference picture
The first reference zone image.
Wherein, the first reference zone image includes the number of corresponding above-mentioned first designated position.Processing to reference picture
Process with it is above-mentioned identical to the treatment process of image to be processed, no longer repeat one by one herein.
Step 403, for the first reference of above-mentioned first pending district area image and corresponding first pending district area image
Area image determines the similitude between above-mentioned first pending district area image and above-mentioned first reference zone image.
After obtaining the first pending district area image and the first reference zone image, executing subject can be by the first pending district
Area image is compared with the first reference zone image of corresponding first pending district area image, determines between the two similar
Property.In the application, similitude is for the similarity relation between qualitative description image.In this way, improving the phase to image to be processed
Like the judgment accuracy and efficiency of degree.
In some optional implementations of the present embodiment, the above-mentioned above-mentioned first pending district area image of determination with it is above-mentioned
Similitude between first reference zone image, may comprise steps of:
The first step obtains the first finger image information to be processed and above-mentioned of above-mentioned first pending district area image respectively
First reference picture finger print information of one reference zone image.
In order to accurately compare the first pending district area image and the first reference zone image, executing subject can obtain respectively
First pending district area image and the corresponding first finger image information to be processed of the first reference zone image and first are with reference to figure
As finger print information.Wherein, the first finger image information to be processed is identical with the data length of the first reference picture finger print information.Figure
As finger print information can characterize the uniqueness of correspondence image.Finger image information can be obtained by the methods of hash algorithm.
Second step, in response between the above-mentioned first finger image information to be processed and above-mentioned first reference picture finger print information
The first Hamming distance less than the first given threshold, determine above-mentioned first pending district area image and above-mentioned first reference zone figure
There is similitude as between.
After obtaining the first finger image information to be processed and the first reference picture finger print information, executing subject can calculate
Hamming distance between one finger image information to be processed and the first reference picture finger print information.Hamming distance indicates two (phases
Same length) word the different quantity in correspondence position.When the first Hamming distance is less than the first given threshold, illustrate the first pending district
The difference very little of area image and the first reference zone image.In view of various possible interference, this difference can be ignored, and execute master
Body, which can consider, has similitude between the first pending district area image and the first reference zone image.At this point, executing subject can
Think corresponding first pending district area image setting image similar marker.For example, image similar marker can indicate when being " 1 "
First pending district area image is similar to the first reference zone image;Image similar marker can be indicated when being " 0 " first wait locate
It manages area image and the first reference zone image is dissimilar.Executing subject can also identify the first pending district by other means
Similitude between area image and the first reference zone image, no longer repeats one by one herein.
In some optional implementations of the present embodiment, above-mentioned the present embodiment method be may comprise steps of:
The first step, in response to having phase between above-mentioned first pending district area image and corresponding first reference zone image
Like property, obtain at least one the second designated position of above-mentioned first pending district area image second is sized wait locate according to second
Area image is managed, is sized according to above-mentioned second and obtains above-mentioned at least one above-mentioned second specific bit of first reference zone image
The the second reference zone image set.
Determined between the first pending district area image and corresponding first reference zone image have similitude after, hold
Row main body can also further determine that the size of similarity.Executing subject can according to second be sized acquisition above-mentioned first to
Second pending district area image of at least one the second designated position of processing region image;Acquisition is sized according to above-mentioned second
Second reference zone image of above-mentioned at least one above-mentioned second designated position of first reference zone image.Wherein, second wait locate
Reason area image may include the number of corresponding second designated position, and above-mentioned second is sized less than above-mentioned first setting ruler
It is very little.For example, second is sized can be and is sized the size after being divided into N equal part by first.Second reference zone image
It may include the number of corresponding above-mentioned second designated position.
Second step, according to similar between the second pending district area image and corresponding second reference zone image
Property determines the similarity information of the first pending district area image.
After obtaining the second pending district area image and the second reference zone image, executing subject can determine that second is to be processed
Similarity information between area image and corresponding second reference zone image.In the application, similarity information is for quantitative
Similarity relation between image is described.
In some optional implementations of the present embodiment, it is above-mentioned according to the second pending district area image with it is corresponding
The second reference zone image between similitude determine the similarity information of the first pending district area image, may include with
Lower step:
The first step obtains the second finger image information to be processed and above-mentioned of above-mentioned second pending district area image respectively
Second reference picture finger print information of two reference zone images.
Similar with the above process, executing subject can get the second figure to be processed of the second pending district area image respectively
As the second reference picture finger print information of finger print information and corresponding second reference zone image.
Second step, in response between the above-mentioned second finger image information to be processed and the second reference picture finger print information
Two Hamming distances less than the second given threshold, determine above-mentioned second pending district area image and above-mentioned second reference zone image it
Between have similitude.
When the second Hamming distance between the second finger image information to be processed and the second reference picture finger print information is less than
When the second given threshold, illustrate that there is similitude between the second pending district area image and corresponding second reference zone image.
At this point, image similar marker can be arranged for corresponding first pending district area image in executing subject.Image similar marker herein
Process can be similar with the process of above-mentioned image similar marker, no longer repeat one by one herein.
Third step, by the total of the quantity of the second pending district area image with similitude and the second pending district area image
Ratio between quantity is set as the similarity information of the first pending district area image.
Executing subject can count the quantity of the second pending district area image with similitude, and by the second pending district
Ratio in the quantity of area image and the second pending area image collection between the total quantity of the second pending district area image is set
It is set to the similarity information of the first pending district area image.
In some optional implementations of the present embodiment, above-mentioned the present embodiment method be may comprise steps of:
The first step, according to determining first with similitude of the similarity information of above-mentioned first pending district area image wait locate
Manage the quantity of area image.
The process for determining the similarity information of each the first pending district area image is described above.Later, master is executed
Body can determine the quantity of the first pending district area image with similitude.
Second step, by the total of the quantity of the first pending district area image with similitude and the first pending district area image
Ratio between quantity is set as the similarity information between above-mentioned image to be processed and reference picture.
Executing subject can by the total quantity of the quantity of the first pending district area image and the first pending district area image it
Between ratio be set as the similarity information between above-mentioned image to be processed and reference picture.Similarity information at this time is to correspond to
The whole similarity information of image to be processed.For example, the similarity information between image to be processed and reference picture is 90%,
Wherein, it 90% can characterize in the total quantity of the first pending district area image of image to be processed, have the first of 90% to be processed
Area image is similar to the first reference zone image of reference picture.Executing subject can also be according to the number of the first designated position
And/or second the number of designated position determine different first pending district area image between image and reference picture to be processed
With the information such as the first reference zone image.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, present disclose provides one kind for detecting figure
As one embodiment of the device of similarity, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, and the device is specific
It can be applied in various electronic equipments.
As shown in figure 5, the device 500 for detection image similarity of the present embodiment may include: image acquisition unit
501, similarity information computing unit 502 and testing result information output unit 503.Wherein, image acquisition unit 501 is configured
At the reference picture for obtaining image to be processed and corresponding above-mentioned image to be processed;Similarity information computing unit 502 is configured to
Above-mentioned image to be processed and reference picture are analyzed respectively under different sizes, calculate above-mentioned image to be processed and above-mentioned
Similarity information between reference picture;Testing result information output unit 503 is configured to defeated according to above-mentioned similarity information
The testing result information of above-mentioned application to be tested out.
In some optional implementations of the present embodiment, above-mentioned similarity information computing unit 502 may include: to
Processing region image divides subelement (not shown), reference zone image divides subelement (not shown) and similitude
Determine subelement (not shown).Wherein, pending district area image divides subelement and is configured to be sized according to first
Obtain the first pending district area image of above-mentioned at least one the first designated position of image to be processed, wherein above-mentioned first wait locate
Reason area image includes the number of corresponding above-mentioned first designated position;Reference zone image divides subelement and is configured to according to upper
It states first and is sized the first reference zone image for obtaining above-mentioned at least one above-mentioned first designated position of reference picture,
In, above-mentioned first reference zone image includes the number of corresponding above-mentioned first designated position;Similitude determines subelement, for upper
The the first reference zone image for stating the first pending district area image and the corresponding first pending district area image, is configured to determine
Similitude between above-mentioned first pending district area image and above-mentioned first reference zone image.
In some optional implementations of the present embodiment, above-mentioned similitude determines that subelement may include: the first figure
As finger print information obtains module (not shown) and first similarity determining module (not shown).Wherein, the first image
Finger print information obtains the first finger image information to be processed that module is configured to obtain the first pending district area image respectively
With the first reference picture finger print information of above-mentioned first reference zone image;First similarity determining module, in response to above-mentioned
The first Hamming distance between one finger image information to be processed and above-mentioned first reference picture finger print information is less than the first setting
Threshold value, being configured to determine between above-mentioned first pending district area image and above-mentioned first reference zone image has similitude.
In some optional implementations of the present embodiment, above-mentioned similarity information computing unit 502 may include: area
Area image divides subelement (not shown) and similarity information determines subelement (not shown).Wherein, area image
Subelement is divided, it is similar in response to having between above-mentioned first pending district area image and corresponding first reference zone image
Property, it is configured to be sized according to second and obtains the of at least one the second designated position of above-mentioned first pending district area image
Two pending district area images, be sized according to above-mentioned second obtain above-mentioned first reference zone image at least one above-mentioned second
Second reference zone image of designated position, wherein above-mentioned second pending district area image includes corresponding above-mentioned second specific bit
The number set, above-mentioned second is sized and is sized less than above-mentioned first, and above-mentioned second reference zone image includes on corresponding
State the number of the second designated position;Similarity information determines subelement, is configured to according to the second pending district area image
Similitude between corresponding second reference zone image determines the similarity information of the first pending district area image.
In some optional implementations of the present embodiment, above-mentioned similarity information determines that subelement may include:
Two finger image data obtaining module (not shown)s, second similarity determining module (not shown) and the second similarity
Information setup module (not shown).Wherein, the second finger image data obtaining module is configured to obtain above-mentioned respectively
Second reference picture of the second of two pending district area images finger image information to be processed and above-mentioned second reference zone image
Finger print information;Second similarity determining module refers in response to the above-mentioned second finger image information to be processed with the second reference picture
The second Hamming distance between line information less than the second given threshold, be configured to determine above-mentioned second pending district area image with
There is similitude between above-mentioned second reference zone image;Second similarity information setup module is configured to have similitude
The quantity of the second pending district area image and the total quantity of the second pending district area image between ratio be set as first to
The similarity information of processing region image.
In some optional implementations of the present embodiment, above-mentioned similarity information computing unit 502 may include: phase
Subelement (not shown) is obtained like amount of images and image similarity information determines subelement (not shown).Wherein,
Similar image quantity obtains subelement and is configured to be had according to the determination of the similarity information of above-mentioned first pending district area image
The quantity of first pending district area image of similitude;Image similarity information determines that subelement is configured to have similitude
The quantity of the first pending district area image and the total quantity of the first pending district area image between ratio be set as it is above-mentioned to
Handle the similarity information between image and reference picture.
The present embodiment additionally provides a kind of electronic equipment, comprising: one or more processors;Memory is stored thereon with
One or more programs, when said one or multiple programs are executed by said one or multiple processors, so that said one
Or multiple processors execute the above-mentioned method for detection image similarity.
The present embodiment additionally provides a kind of computer-readable medium, is stored thereon with computer program, and the program is processed
Device realizes the above-mentioned method for detection image similarity when executing.
Below with reference to Fig. 6, it illustrates the electronic equipments for being suitable for being used to realize embodiment of the disclosure (for example, in Fig. 1
Server 105) computer system 600 structural schematic diagram.Electronic equipment shown in Fig. 6 is only an example, should not be right
The function and use scope of embodiment of the disclosure bring any restrictions.
As shown in fig. 6, electronic equipment 600 may include processing unit (such as central processing unit, graphics processor etc.)
601, random access can be loaded into according to the program being stored in read-only memory (ROM) 602 or from storage device 608
Program in memory (RAM) 603 and execute various movements appropriate and processing.In RAM 603, it is also stored with electronic equipment
Various programs and data needed for 600 operations.Processing unit 601, ROM 602 and RAM603 are connected with each other by bus 604.
Input/output (I/O) interface 605 is also connected to bus 604.
In general, following device can connect to I/O interface 605: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 606 of head, microphone, accelerometer, gyroscope etc.;Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 607 of dynamic device etc.;Storage device 608 including such as tape, hard disk etc.;And communication device 609.Communication device
609, which can permit electronic equipment 600, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 6 shows tool
There is the electronic equipment 600 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with
Alternatively implement or have more or fewer devices.Each box shown in Fig. 6 can represent a device, can also root
According to needing to represent multiple devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communication device 609, or from storage device 608
It is mounted, or is mounted from ROM 602.When the computer program is executed by processing unit 601, the implementation of the disclosure is executed
The above-mentioned function of being limited in the method for example.
It is situated between it should be noted that the above-mentioned computer-readable medium of embodiment of the disclosure can be computer-readable signal
Matter or computer readable storage medium either the two any combination.Computer readable storage medium for example can be with
System, device or the device of --- but being not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than
Combination.The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires
Electrical connection, portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type are programmable
Read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic are deposited
Memory device or above-mentioned any appropriate combination.In embodiment of the disclosure, computer readable storage medium, which can be, appoints
What include or the tangible medium of storage program that the program can be commanded execution system, device or device use or and its
It is used in combination.And in embodiment of the disclosure, computer-readable signal media may include in a base band or as carrier wave
The data-signal that a part is propagated, wherein carrying computer-readable program code.The data-signal of this propagation can be adopted
With diversified forms, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal is situated between
Matter can also be any computer-readable medium other than computer readable storage medium, which can be with
It sends, propagate or transmits for by the use of instruction execution system, device or device or program in connection.Meter
The program code for including on calculation machine readable medium can transmit with any suitable medium, including but not limited to: electric wire, optical cable,
RF (radio frequency) etc. or above-mentioned any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned electronic equipment;It is also possible to individualism, and not
It is fitted into the electronic equipment.Above-mentioned computer-readable medium carries one or more program, when said one or more
When a program is executed by the electronic equipment, so that the electronic equipment: obtaining image to be processed and correspond to above-mentioned image to be processed
Reference picture;Above-mentioned image to be processed and reference picture are analyzed respectively under different sizes, calculated above-mentioned to be processed
Similarity information between image and above-mentioned reference picture;The detection of above-mentioned application to be tested is exported according to above-mentioned similarity information
Result information.
The behaviour for executing embodiment of the disclosure can be write with one or more programming languages or combinations thereof
The computer program code of work, above procedure design language include object oriented program language-such as Java,
Smalltalk, C++ further include conventional procedural programming language-such as " C " language or similar program design language
Speech.Program code can be executed fully on the user computer, partly be executed on the user computer, as an independence
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
It includes local area network (LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as benefit
It is connected with ISP by internet).
Flow chart and block diagram in attached drawing illustrate system, method and the computer of the various embodiments according to the disclosure
The architecture, function and operation in the cards of program product.In this regard, each box in flowchart or block diagram can be with
A part of a module, program segment or code is represented, a part of the module, program segment or code includes one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, Ke Yiyong
The dedicated hardware based system of defined functions or operations is executed to realize, or can be referred to specialized hardware and computer
The combination of order is realized.
Being described in unit involved in embodiment of the disclosure can be realized by way of software, can also be passed through
The mode of hardware is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor
Including image acquisition unit, similarity information computing unit and testing result information output unit.Wherein, the title of these units
The restriction to the unit itself is not constituted under certain conditions, for example, similarity information computing unit is also described as
" for calculating the unit of similarity ".
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member is it should be appreciated that invention scope involved in the disclosure, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Any combination and the other technical solutions formed.Such as features described above has similar function with (but being not limited to) disclosed in the disclosure
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (14)
1. a kind of method for detection image similarity, comprising:
Obtain the reference picture of image to be processed and the corresponding image to be processed;
The image to be processed and the reference picture are analyzed respectively under different sizes, calculate the figure to be processed
Similarity information between picture and the reference picture;
The testing result information of the application to be tested is exported according to the similarity information.
2. according to the method described in claim 1, wherein, it is described under different sizes respectively to the image to be processed and institute
It states reference picture to be analyzed, calculates the similarity information between the image to be processed and the reference picture, comprising:
The the first pending area figure for obtaining at least one first designated position of image to be processed is sized according to first
Picture, wherein the first pending district area image includes the number of corresponding first designated position;
The first reference area for obtaining at least one first designated position of reference picture is sized according to described first
Area image, wherein the first reference zone image includes the number of corresponding first designated position;
For the first reference zone image of the first pending district area image and corresponding first pending district area image, determine
Similitude between the first pending district area image and the first reference zone image.
3. according to the method described in claim 2, wherein, determination the first pending district area image and described first is joined
Similitude between the area image of examination district, comprising:
Obtain respectively the first pending district area image the first finger image information to be processed and first reference zone
First reference picture finger print information of image;
In response to the first Hamming between the described first finger image information to be processed and the first reference picture finger print information
Less than the first given threshold, determine has between the first pending district area image and the first reference zone image distance
Similitude.
4. according to the method described in claim 3, wherein, it is described under different sizes respectively to the image to be processed and institute
It states reference picture to be analyzed, calculates the similarity information between the image to be processed and the reference picture, comprising:
In response to having similitude between the first pending district area image and corresponding first reference zone image, according to the
Two are sized the second pending district area image for obtaining at least one the second designated position of the first pending district area image,
The second ginseng for obtaining at least one second designated position of the first reference zone image is sized according to described second
Examination district area image, wherein the second pending district area image includes the number of corresponding second designated position, and described second
It is sized and is sized less than described first, the second reference zone image includes the volume of corresponding second designated position
Number;
First is determined according to the similitude between the second pending district area image and corresponding second reference zone image
The similarity information of pending district area image.
5. described according to the second pending district area image and corresponding second according to the method described in claim 4, wherein
Similitude between reference zone image determines the similarity information of the first pending district area image, comprising:
Obtain respectively the second pending district area image the second finger image information to be processed and second reference zone
Second reference picture finger print information of image;
In response to the second Hamming distance between the described second finger image information to be processed and the second reference picture finger print information
Less than the second given threshold, determine between the second pending district area image and the second reference zone image with similar
Property;
It will be between the quantity of the second pending district area image with similitude and the total quantity of the second pending district area image
Ratio is set as the similarity information of the first pending district area image.
6. according to the method described in claim 5, wherein, it is described under different sizes respectively to the image to be processed and institute
It states reference picture to be analyzed, calculates the similarity information between the image to be processed and the reference picture, comprising:
The first pending district area image with similitude is determined according to the similarity information of the first pending district area image
Quantity;
It will be between the quantity of the first pending district area image with similitude and the total quantity of the first pending district area image
Ratio is set as the similarity information between the image to be processed and reference picture.
7. a kind of device for detection image similarity, comprising:
Image acquisition unit is configured to obtain the reference picture of image to be processed and the corresponding image to be processed;
Similarity information computing unit is configured under different sizes respectively to the image to be processed and described with reference to figure
As being analyzed, the similarity information between the image to be processed and the reference picture is calculated;
Testing result information output unit is configured to export the detection knot of the application to be tested according to the similarity information
Fruit information.
8. device according to claim 7, wherein the similarity information computing unit includes:
Pending district area image divides subelement, is configured to be sized the acquisition image to be processed at least one according to first
First pending district area image of a first designated position, wherein the first pending district area image includes corresponding described the
The number of one designated position;
Reference zone image divides subelement, is configured to be sized the acquisition reference picture at least one according to described first
First reference zone image of a first designated position, wherein the first reference zone image includes corresponding described the
The number of one designated position;
Similitude determines subelement, for the first pending district area image and the first of corresponding first pending district area image
Reference zone image, the phase being configured to determine between the first pending district area image and the first reference zone image
Like property.
9. device according to claim 8, wherein the similitude determines that subelement includes:
First finger image data obtaining module is configured to obtain the first of the first pending district area image respectively wait locate
Manage the first reference picture finger print information of finger image information and the first reference zone image;
First similarity determining module, in response to the described first finger image information to be processed and the first reference picture fingerprint
The first Hamming distance between information is configured to determine the first pending district area image and institute less than the first given threshold
Stating has similitude between the first reference zone image.
10. device according to claim 9, wherein the similarity information computing unit includes:
Area image divides subelement, in response to the first pending district area image and corresponding first reference zone image it
Between there is similitude, be configured to be sized according to second and obtain the first pending district area image at least one second refers to
The the second pending district area image set is positioned, is sized according to described second and obtains the first reference zone image at least one
Second reference zone image of a second designated position, wherein the second pending district area image includes described in correspondence
The number of second designated position, described second is sized and is sized less than described first, the second reference zone image
Number including correspondence second designated position;
Similarity information determines subelement, is configured to according to the second pending district area image and corresponding second reference area
Similitude between area image determines the similarity information of the first pending district area image.
11. device according to claim 10, wherein the similarity information determines that subelement includes:
Second finger image data obtaining module is configured to obtain the second of the second pending district area image respectively wait locate
Manage the second reference picture finger print information of finger image information and the second reference zone image;
Second similarity determining module, in response to the described second finger image information to be processed and the second reference picture finger print information
Between the second Hamming distance less than the second given threshold, be configured to determine the second pending district area image and described the
There is similitude between two reference zone images;
Second similarity information setup module is configured to will to have the quantity of the second pending district area image of similitude and the
Ratio between the total quantity of two pending district area images is set as the similarity information of the first pending district area image.
12. device according to claim 11, wherein the similarity information computing unit includes:
Similar image quantity obtains subelement, is configured to be determined according to the similarity information of the first pending district area image
The quantity of the first pending district area image with similitude;
Image similarity information determines subelement, be configured to will to have the quantity of the first pending district area image of similitude with
Ratio between the total quantity of first pending district area image is set as similar between the image to be processed and reference picture
Spend information.
13. a kind of electronic equipment, comprising:
One or more processors;
Memory is stored thereon with one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors
Perform claim requires any method in 1 to 6.
14. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that the program is executed by processor
Method of the Shi Shixian as described in any in claim 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910327769.7A CN110084298B (en) | 2019-04-23 | 2019-04-23 | Method and device for detecting image similarity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910327769.7A CN110084298B (en) | 2019-04-23 | 2019-04-23 | Method and device for detecting image similarity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110084298A true CN110084298A (en) | 2019-08-02 |
CN110084298B CN110084298B (en) | 2021-09-28 |
Family
ID=67416252
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910327769.7A Active CN110084298B (en) | 2019-04-23 | 2019-04-23 | Method and device for detecting image similarity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110084298B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325712A (en) * | 2020-01-20 | 2020-06-23 | 北京百度网讯科技有限公司 | Method and device for detecting image validity |
Citations (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103324650A (en) * | 2012-10-23 | 2013-09-25 | 深圳市宜搜科技发展有限公司 | Image retrieval method and system |
CN103699691A (en) * | 2014-01-10 | 2014-04-02 | 五八同城信息技术有限公司 | Method for generating image fingerprint and method for searching similar image based on same |
US20150010240A1 (en) * | 2012-01-17 | 2015-01-08 | Konica Minolta, Inc. | Image processing apparatus, image processing method, and image processing program |
CN104349021A (en) * | 2013-07-24 | 2015-02-11 | 腾讯科技(深圳)有限公司 | Image acquisition method, device and terminal |
US20150281597A1 (en) * | 2014-03-26 | 2015-10-01 | Thomson Licensing | Method and an apparatus for generating an approximate nearest neighbor field (annf) for images and video sequences |
CN105025392A (en) * | 2015-06-25 | 2015-11-04 | 西北工业大学 | Video abstract key frame extraction method based on abstract space feature learning |
CN105069426A (en) * | 2015-07-31 | 2015-11-18 | 小米科技有限责任公司 | Similar picture determining method and apparatus |
CN105550381A (en) * | 2016-03-17 | 2016-05-04 | 北京工业大学 | Efficient image retrieval method based on improved SIFT (scale invariant feature transform) feature |
CN106126572A (en) * | 2016-06-17 | 2016-11-16 | 中国科学院自动化研究所 | Image search method based on area validation |
CN106203461A (en) * | 2015-05-07 | 2016-12-07 | 中国移动通信集团公司 | A kind of image processing method and device |
US20170084030A1 (en) * | 2014-06-20 | 2017-03-23 | Varian Medical Systems International Ag | Shape similarity measure for body tissue |
CN107067389A (en) * | 2017-01-05 | 2017-08-18 | 佛山科学技术学院 | A kind of blind evidence collecting method of distorted image based on Sobel rim detections Yu image block brightness |
CN107480704A (en) * | 2017-07-24 | 2017-12-15 | 南开大学 | It is a kind of that there is the real-time vision method for tracking target for blocking perception mechanism |
CN107622193A (en) * | 2016-05-27 | 2018-01-23 | 广东欧珀移动通信有限公司 | Unlocked by fingerprint method and Related product |
CN107632773A (en) * | 2017-10-17 | 2018-01-26 | 北京百度网讯科技有限公司 | For obtaining the method and device of information |
CN107705286A (en) * | 2017-08-23 | 2018-02-16 | 南京航空航天大学 | A kind of color image quality integrated evaluating method |
CN107729820A (en) * | 2017-09-27 | 2018-02-23 | 五邑大学 | A kind of finger vein identification method based on multiple dimensioned HOG |
CN108694411A (en) * | 2018-04-03 | 2018-10-23 | 南昌奇眸科技有限公司 | A method of identification similar image |
CN108845998A (en) * | 2018-04-03 | 2018-11-20 | 南昌奇眸科技有限公司 | A kind of trademark image retrieval matching process |
CN108876756A (en) * | 2017-05-09 | 2018-11-23 | 普天信息技术有限公司 | The measure and device of image similarity |
CN109325518A (en) * | 2018-08-20 | 2019-02-12 | Oppo广东移动通信有限公司 | Classification method, device, electronic equipment and the computer readable storage medium of image |
CN109376277A (en) * | 2018-11-23 | 2019-02-22 | 北京京东金融科技控股有限公司 | Determine the method and device of device-fingerprint homology |
-
2019
- 2019-04-23 CN CN201910327769.7A patent/CN110084298B/en active Active
Patent Citations (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150010240A1 (en) * | 2012-01-17 | 2015-01-08 | Konica Minolta, Inc. | Image processing apparatus, image processing method, and image processing program |
CN103324650A (en) * | 2012-10-23 | 2013-09-25 | 深圳市宜搜科技发展有限公司 | Image retrieval method and system |
CN104349021A (en) * | 2013-07-24 | 2015-02-11 | 腾讯科技(深圳)有限公司 | Image acquisition method, device and terminal |
CN103699691A (en) * | 2014-01-10 | 2014-04-02 | 五八同城信息技术有限公司 | Method for generating image fingerprint and method for searching similar image based on same |
US20150281597A1 (en) * | 2014-03-26 | 2015-10-01 | Thomson Licensing | Method and an apparatus for generating an approximate nearest neighbor field (annf) for images and video sequences |
US9781357B2 (en) * | 2014-03-26 | 2017-10-03 | Thomson Licensing | Method and an apparatus for generating an approximate nearest neighbor field (ANNF) for images and video sequences |
US20170084030A1 (en) * | 2014-06-20 | 2017-03-23 | Varian Medical Systems International Ag | Shape similarity measure for body tissue |
CN106203461A (en) * | 2015-05-07 | 2016-12-07 | 中国移动通信集团公司 | A kind of image processing method and device |
CN105025392A (en) * | 2015-06-25 | 2015-11-04 | 西北工业大学 | Video abstract key frame extraction method based on abstract space feature learning |
CN105069426A (en) * | 2015-07-31 | 2015-11-18 | 小米科技有限责任公司 | Similar picture determining method and apparatus |
CN105550381A (en) * | 2016-03-17 | 2016-05-04 | 北京工业大学 | Efficient image retrieval method based on improved SIFT (scale invariant feature transform) feature |
CN107622193A (en) * | 2016-05-27 | 2018-01-23 | 广东欧珀移动通信有限公司 | Unlocked by fingerprint method and Related product |
CN106126572A (en) * | 2016-06-17 | 2016-11-16 | 中国科学院自动化研究所 | Image search method based on area validation |
CN107067389A (en) * | 2017-01-05 | 2017-08-18 | 佛山科学技术学院 | A kind of blind evidence collecting method of distorted image based on Sobel rim detections Yu image block brightness |
CN108876756A (en) * | 2017-05-09 | 2018-11-23 | 普天信息技术有限公司 | The measure and device of image similarity |
CN107480704A (en) * | 2017-07-24 | 2017-12-15 | 南开大学 | It is a kind of that there is the real-time vision method for tracking target for blocking perception mechanism |
CN107705286A (en) * | 2017-08-23 | 2018-02-16 | 南京航空航天大学 | A kind of color image quality integrated evaluating method |
CN107729820A (en) * | 2017-09-27 | 2018-02-23 | 五邑大学 | A kind of finger vein identification method based on multiple dimensioned HOG |
CN107632773A (en) * | 2017-10-17 | 2018-01-26 | 北京百度网讯科技有限公司 | For obtaining the method and device of information |
CN108845998A (en) * | 2018-04-03 | 2018-11-20 | 南昌奇眸科技有限公司 | A kind of trademark image retrieval matching process |
CN108694411A (en) * | 2018-04-03 | 2018-10-23 | 南昌奇眸科技有限公司 | A method of identification similar image |
CN109325518A (en) * | 2018-08-20 | 2019-02-12 | Oppo广东移动通信有限公司 | Classification method, device, electronic equipment and the computer readable storage medium of image |
CN109376277A (en) * | 2018-11-23 | 2019-02-22 | 北京京东金融科技控股有限公司 | Determine the method and device of device-fingerprint homology |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111325712A (en) * | 2020-01-20 | 2020-06-23 | 北京百度网讯科技有限公司 | Method and device for detecting image validity |
CN111325712B (en) * | 2020-01-20 | 2024-01-23 | 北京百度网讯科技有限公司 | Method and device for detecting image validity |
Also Published As
Publication number | Publication date |
---|---|
CN110084298B (en) | 2021-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109117358A (en) | test method and test device for electronic equipment | |
CN108287927B (en) | For obtaining the method and device of information | |
CN106455056B (en) | Positioning method and device | |
CN108322855A (en) | Method and device for obtaining audio-frequency information | |
CN111209202A (en) | Terminal application testing method and device | |
CN110070076A (en) | Method and apparatus for choosing trained sample | |
US20210264198A1 (en) | Positioning method and apparatus | |
CN110059623A (en) | Method and apparatus for generating information | |
CN109241722A (en) | For obtaining method, electronic equipment and the computer-readable medium of information | |
CN108364648A (en) | Method and device for obtaining audio-frequency information | |
CN110287950A (en) | Target detection and the training method of target detection model, device and electronic equipment | |
CN109508361A (en) | Method and apparatus for output information | |
CN109614549B (en) | Method and apparatus for pushed information | |
CN110414613A (en) | Method, apparatus, equipment and the computer readable storage medium of region clustering | |
CN110334650A (en) | Object detecting method, device, electronic equipment and storage medium | |
CN109614327A (en) | Method and apparatus for output information | |
JP7090131B2 (en) | Methods and equipment for generating information | |
CN109064464A (en) | Method and apparatus for detecting battery pole piece burr | |
CN110084298A (en) | Method and device for detection image similarity | |
CN111311358B (en) | Information processing method and device and electronic equipment | |
CN109144864A (en) | Method and device for test window | |
CN109948636A (en) | Data fusion method and device | |
CN112379967B (en) | Simulator detection method, device, equipment and medium | |
CN108595095A (en) | Method and apparatus based on gesture control simulated target body movement locus | |
CN111401182B (en) | Image detection method and device for feeding rail |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |