CN109615631A - Picture specific region extracting method, device, computer equipment and storage medium - Google Patents
Picture specific region extracting method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109615631A CN109615631A CN201811207783.5A CN201811207783A CN109615631A CN 109615631 A CN109615631 A CN 109615631A CN 201811207783 A CN201811207783 A CN 201811207783A CN 109615631 A CN109615631 A CN 109615631A
- Authority
- CN
- China
- Prior art keywords
- picture
- search
- interception
- target
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000001514 detection method Methods 0.000 claims description 37
- 238000000605 extraction Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 22
- 241000282376 Panthera tigris Species 0.000 description 12
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 12
- 235000011613 Pinus brutia Nutrition 0.000 description 12
- 241000018646 Pinus brutia Species 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present application discloses a kind of picture specific region extracting method, device, computer equipment and storage medium, this method comprises: obtaining search condition comprising multiple search terms and multiple priority parameters corresponding with multiple search terms；Multiple search terms are ranked up according to multiple priority parameters and generate search sequence；Target search item is obtained from search sequence；Picture to be shown is scanned for obtain target object according to target search item；If the number of target object is not zero, the target object to obtain at first intercepts the interception object in picture to be shown as interception object according to the first default interception parameter to generate the first interception picture, is shown in destination display area.The picture specific region extracting method is based on image zooming-out technology, can extract the target object in picture to be shown and is shown in destination display area, so as to improve display effect, promotes the experience of user.
Description
Technical field
This application involves field of computer technology more particularly to a kind of picture specific region extracting methods, device, computer
Equipment and storage medium.
Background technique
In the prior art, the size and Aspect Ratio for showing the display area of picture are fixed and invariable, however
For certain pictures, the Aspect Ratio of Aspect Ratio and display area be it is inconsistent, this will lead in the display
The problem of will appear picture deformation when showing these pictures in region；In addition, for certain pictures, it is main interior in picture
Hold picture whole region account for it is smaller, which results in display area show picture entirety when picture in it is main in
Appearance does not protrude, and affects user experience.Therefore, how to carry out display to picture preferably in fixed display area becomes urgently
Problem to be solved.
Summary of the invention
This application provides a kind of picture specific region extracting method, device, computer equipment and storage mediums, to improve
Display effect promotes user experience.
In a first aspect, this application provides a kind of picture specific region extracting methods comprising:
Search condition is obtained, described search condition includes multiple search terms and corresponding with multiple described search items multiple excellent
First grade parameter；
It multiple described search items is ranked up and generates search sequence from high to low according to multiple priority parameters；
Target search item is obtained from described search sequence, the target search item is searched for what is be not acquired in search sequence
The search terms of Suo Xiangzhong highest priority；
Picture to be shown is scanned for obtain target object according to the target search item；
If the number of the target object is not zero, using the target object that obtains at first as interception object, according to first
Default interception parameter intercepts the interception object in the picture to be shown to generate the first interception picture, by described first
Interception picture is shown in destination display area.
Second aspect, this application provides a kind of picture specific region extraction elements comprising:
First acquisition unit, for obtaining search condition, described search condition include multiple search terms and with it is multiple described
The corresponding multiple priority parameters of search terms；
Generation unit, for being ranked up to multiple described search items according to multiple priority parameters from high to low and
Generate search sequence；
Second acquisition unit, for obtaining target search item from described search sequence, the target search item is search
The search terms of highest priority in the search terms not being acquired in sequence；
Search unit, for being scanned for picture to be shown to obtain target object according to the target search item；
Interception unit, if the number for the target object is not zero, using the target object that obtains at first as interception
Object intercepts to generate the first interception figure the interception object in the picture to be shown according to the first default interception parameter
The first interception picture is shown in destination display area by piece.
The third aspect, the application provide a kind of computer equipment again, including memory, processor and are stored in described deposit
On reservoir and the computer program that can run on the processor, the processor realize this when executing the computer program
The described in any item picture specific regions extracting method provided is provided.
Fourth aspect, present invention also provides a kind of storage mediums, wherein the storage medium is stored with computer program,
The computer program includes program instruction, and described program instruction makes the processor execute the application when being executed by a processor
The described in any item picture specific regions extracting method provided.
The application provides a kind of picture specific region extracting method, device, computer equipment and storage medium.This method packet
It includes: obtaining search condition comprising multiple search terms and multiple priority parameters corresponding with multiple search terms；According to multiple excellent
First grade parameter is ranked up multiple search terms and generates search sequence；Target search item is obtained from search sequence, target is searched
The search terms of highest priority in the search terms not being acquired in Suo Xiangwei search sequence；According to target search item to figure to be shown
Piece is scanned for obtain target object；If the number of target object is not zero, using the target object that obtains at first as interception
Object intercepts the interception object in picture to be shown according to the first default interception parameter to generate the first interception picture,
It is shown in destination display area.The picture specific region extracting method, can extract the target object in picture to be shown
And be shown in destination display area, so as to improve display effect, promote the experience of user.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of schematic flow diagram for picture specific region extracting method that the application first embodiment provides；
Fig. 2 is a kind of schematic flow diagram for picture specific region extracting method that the application second embodiment provides；
Fig. 3 is a kind of schematic flow diagram for picture specific region extracting method that the application 3rd embodiment provides；
Fig. 4 is a kind of schematic flow diagram for picture specific region extracting method that the application fourth embodiment provides；
Fig. 5 is a kind of schematic flow diagram for picture specific region extracting method that the 5th embodiment of the application provides；
Fig. 6 is a kind of schematic flow diagram for picture specific region extracting method that the application sixth embodiment provides；
Fig. 7 is a kind of schematic block diagram for picture specific region extraction element that the application first embodiment proposes；
Fig. 8 is a kind of schematic flow diagram for picture specific region extraction element that the application second embodiment provides；
Fig. 9 is a kind of schematic flow diagram for picture specific region extraction element that the application 3rd embodiment provides；
Figure 10 is a kind of schematic flow diagram for picture specific region extraction element that the application fourth embodiment provides；
Figure 11 is a kind of schematic flow diagram for picture specific region extraction element that the 5th embodiment of the application provides；
Figure 12 is a kind of schematic flow diagram for picture specific region extraction element that the application sixth embodiment provides；
Figure 13 is a kind of schematic block diagram of computer equipment provided by the embodiments of the present application.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this present specification merely for the sake of description specific embodiment
And be not intended to limit the application.As present specification and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in present specification and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Referring to Fig. 1, Fig. 1 is a kind of exemplary flow of picture specific region extracting method provided by the embodiments of the present application
Figure.The picture specific region extracting method is applied in terminal.As shown in Figure 1, the picture specific region extracting method include with
Lower step S10~S14:
S10, search condition is obtained, described search condition includes multiple search terms and corresponding more with multiple described search items
A priority parameters.
Typically, include multiple objects (such as people, animal and plant) and background in a picture to be shown, exist
The lower situation of multiple objects pixel ratio shared in picture to be shown.If destination display area is smaller, in the mesh
Mark shows the picture to be shown in display area, and will lead to user can not differentiate multiple institutes when browsing the picture to be shown
The problem of stating object.By the way that search condition is arranged, described search condition is for searching the object in the picture to be shown
Rope is to obtain target object.Wherein, described search condition includes multiple search terms and associated preferential with multiple described search items
Grade parameter.For example, following search terms and priority parameters are set:
Search terms: face priority parameters: 1
Search terms: tiger priority parameters: 2
Search terms: pine tree priority parameters: 3
The meaning represented by the search terms and priority parameters of above-mentioned setting are as follows: preferentially using face as search terms, secondly
Using tiger as search terms, finally using pine tree as search terms, the search of corresponding object is carried out on picture to be shown.
In some embodiments, such as the present embodiment, before step S10, the method also includes:
S10a, the first user interface is generated, first user interface includes multiple first parameters input area and multiple the
Two parameter input areas, multiple first parameter input areas are used to input multiple described search items for user, and multiple described second
Parameter input area is used to input multiple priority parameters for user.
For the ease of obtaining search condition, the first user interface is generated so that user inputs search condition.Wherein, described
One user interface includes multiple first parameters input area and multiple second parameters input area, and the first parameter input area is used for for user
Search terms are inputted, and the second parameter input area is used for for user's input priority parameter.
S11, it multiple described search items is ranked up and generates search from high to low according to multiple priority parameters
Sequence.
Multiple search terms are ranked up according to priority parameters corresponding thereto, generate search sequence.Described search
The search terms that ranking value is one in sequence are the search terms of highest priority, and ranking value is searching for tail-end value in described search sequence
Rope item is the minimum search terms of priority.
S12, target search item is obtained from described search sequence, the target search item is not to be acquired in search sequence
Search terms in highest priority search terms.
When being scanned for according to described search sequence to picture to be shown, according to search terms priority orders successively into
Row search, i.e., obtain target search item from described search sequence, wherein the target search item is not obtained in search sequence
The search terms of highest priority in the search terms taken.
S13, picture to be shown is scanned for obtain target object according to the target search item.
Picture to be shown is scanned for according to target search item, for example, if described search item is " face ", to described
Picture to be shown carries out Face datection and positioning, if described search item is Tiger, carries out object to the picture to be shown
For the detection and positioning of tiger, the detection that object is pine tree is carried out to the picture to be shown if described search item is " pine tree "
And positioning.For different search terms, picture to be shown can be carried out according to object detection model corresponding with described search item
Search and detection.
In some embodiments, such as the present embodiment, the step S13 includes:
S130, object detection model parameter corresponding with the target search item is obtained.
For example, if the target search item is " face ", the object detection model parameter is " Face datection model "
Parameter；If the target search item is Tiger, the object detection model parameter is the parameter of " tiger detection model "；
If the target search item is " pine tree ", the object detection model parameter is the parameter of " pine tree detection model ".Wherein, people
Face detection model can be used the Face datection model based on geometrical characteristic, the Face datection model based on Local Features Analysis with
And the Face datection model based on eigenface.
S131, the picture to be shown is detected to obtain target object according to the object detection model parameter.
For example, picture to be shown is detected to search for the picture of simultaneously locating human face with the parameter of " Face datection model "
Plain region.When being detected according to corresponding detection model parameter to picture to be shown, detection direction can for for
Display picture is scanned from left to right, from top to bottom, or is turned left for picture to be shown from the right side, is carried out from the bottom up
Scanning preferentially uses the former in the present embodiment.
Whether S14a, the number for judging target object are zero.
When scanning for the picture to be shown to obtain target object according to current target search item, mesh is coped with
The number of mark object is judged whether be zero according to the number of target object, carry out corresponding operation.
If the number of S14, the target object are not zero, using the target object that obtains at first as interception object, according to
First default interception parameter intercepts the interception object in the picture to be shown to generate the first interception picture, will be described
First interception picture is shown in destination display area.
Wherein, the described first default interception parameter includes the first interception length-width ratio and the first intercepted length, and described first section
Take length-width ratio consistent with the length-width ratio of the destination display area, first intercepted length is less than the destination display area
Length.
If the object more than one of the condition of satisfaction is searched in the picture to be shown according to the target search item,
Target object to obtain at first presets interception parameter to the interception in the picture to be shown according to first as interception object
Object is intercepted to generate the first interception picture.Obtain the central point of the region of the interception object.Described first is pre-
If intercepting parameter includes the first interception length-width ratio and the first intercepted length, described first intercepts length-width ratio and the target viewing area
The length-width ratio in domain is consistent, and first intercepted length is less than the length of the destination display area, is for example arranged described first section
Taking length is 60 pixels.Interception is carried out to picture to be shown according to the described first default interception parameter and generates the first interception picture,
The central point of the first interception picture is the central point of the region of the interception object, the first interception picture
Length-width ratio is consistent with the length-width ratio of destination display area, then is showing the first interception picture in the destination display area
When, the first interception picture will not be deformed, and the first shown interception picture contains acquired interception object.
In some embodiments, such as the present embodiment, after the step S13, the method also includes:
If the number of S15, the target object are zero, judge the target search item whether be described search sequence most
The latter search terms；
If the last one search terms of the target search Xiang Buwei search sequence, return is obtained from described search sequence
The step of target search item.
If the number of the target object is zero, that is, can not get target object, carry out judging presently described target
Whether search terms are that the last one search terms of described search sequence execute different processes according to the difference of judging result.When
If the last one search terms of the target search Xiang Buwei search sequence, return obtains target search from described search sequence
The step of item, i.e. step S13.
In some embodiments, such as the present embodiment, after the step S15, the method also includes:
If S16, the target search item are the last one search terms of described search sequence, according to the second default interception ginseng
It is several the picture to be shown to be intercepted to generate the second interception picture, the second interception picture is shown in target and is shown
In region.
Wherein, the described second default interception parameter includes the second interception length-width ratio and the second intercepted length, and described second section
Take length-width ratio consistent with the length-width ratio of the destination display area, second intercepted length is according to the length of the picture to be shown
Width is determined than the length-width ratio with the destination display area, if the length-width ratio of the picture to be shown is greater than the target and shows
The length-width ratio in region then sets second intercepted length to the width and the destination display area of the picture to be shown
Length-width ratio product, on the contrary, setting second intercepted length to the length of the picture to be shown.Default is with described to aobvious
First pixel in the diagram piece upper left corner is interception starting point, is intercepted according to the described second default interception parameter.
Wherein, the setting of second intercepted length is executed according to following methods:
Obtain the length a and width b of picture to be shown；
Obtain the length-width ratio p of destination display area；
If a/b > p sets the second intercepted length as b × p, on the contrary, then setting the second intercepted length as a.
Picture to be shown is intercepted according to the second default interception parameter, can get the length-width ratio with destination display area
Consistent second interception picture, and the second interception picture is shown in the destination display area.
In some embodiments, such as the present embodiment, after the step S15, the method also includes:
If S17, the target search item be described search sequence the last one search terms, generate prompting message with to
It is reminded at family.
Target object corresponding with the target search item can not be being got, is generating prompting message to mention to user
It wakes up, the target object for meeting the search terms set by it can not be got by so that user is informed in picture to be shown.
S18, second user interface is generated, the second user interface includes that image interception parameter input area and image are shown
Area, described image intercept parameter input area and are used to intercept parameter for user's input picture, and described image viewing area is used for picture
It is shown, wherein the length-width ratio of described image viewing area is consistent with the length-width ratio of the destination display area.
Manual interception is carried out to picture to be shown for the ease of user and generates second user interface in the present embodiment.
S19, described image interception parameter is obtained, parameter is intercepted according to described image, the picture to be shown is intercepted
To generate third interception picture, and third interception picture is shown in described image viewing area.
Picture to be shown is intercepted according to the image interception parameter of user setting and generates third interception picture, display
The third interception picture is in image display area, in order to image display effect of user's direct feel to after intercepting.
S20, judge whether for third interception picture to be shown in the destination display area.
There may be unsatisfied situations for the image display effect after interception by user, in this case, Yong Huying
Multiple intercept operation can be carried out to picture to be shown to obtain the interception picture for meeting user's requirement.In the present embodiment, it holds
Row judges whether for third interception picture to be shown in the destination display area.
Third interception picture is shown in the destination display area by S21, if the determination result is YES.
In some embodiments, such as the present embodiment, after the step S20, the method also includes:
If judging result is no, the return acquisition described image interception parameter, according to described image interception parameter to institute
It states picture to be shown to be intercepted to generate third interception picture, and third interception picture is shown in described image and is shown
Step in area, i.e. step S19.
The embodiment of the present application also provides a kind of picture specific region extraction element, and picture specific region extraction element is used
In aforementioned any one picture specific region extracting method of execution.Fig. 7 is referred to, Fig. 7 is a kind of figure provided by the embodiments of the present application
The schematic block diagram of piece specific region extraction element.As shown in fig. 7, picture specific region extraction element 30 is obtained including first
Take unit 300, generation unit 310, second acquisition unit 320, search unit 330 and the first interception unit 340.
First acquisition unit 300, for obtaining search condition, described search condition include multiple search terms and with multiple institutes
State the corresponding multiple priority parameters of search terms.
Specifically, multiple objects (such as people, animal and plant) and background have been generally comprised in a picture to be shown, have been deposited
In the lower situation of multiple objects pixel ratio shared in picture to be shown.If destination display area is smaller, described
The picture to be shown is shown in destination display area, will lead to user can not be differentiated when browsing the picture to be shown it is multiple
The problem of object.By the way that search condition is arranged, described search condition is used to carry out the object in the picture to be shown
Search is to obtain target object.Wherein, described search condition includes multiple search terms and associated excellent with multiple described search items
First grade parameter.
Generation unit 310, for being arranged from high to low multiple described search items according to multiple priority parameters
Sequence and generate search sequence.
Specifically, multiple search terms are ranked up according to priority parameters corresponding thereto, generate search sequence.Institute
The search terms that the search terms that ranking value is one in search sequence are highest priority are stated, ranking value is tail in described search sequence
The search terms of value are the minimum search terms of priority.
Second acquisition unit 320, for obtaining target search item from described search sequence, the target search item is to search
The search terms of highest priority in the search terms not being acquired in Suo Xulie.
Specifically, suitable according to the priority of search terms when being scanned for according to described search sequence to picture to be shown
Sequence successively scans for, i.e., target search item is obtained from described search sequence, wherein the target search item is search sequence
In in the search terms that are not acquired highest priority search terms.
Search unit 330, for being scanned for picture to be shown to obtain target object according to the target search item.
Specifically, picture to be shown is scanned for according to target search item, for example, if described search item is " face ",
Face datection and positioning then are carried out to the picture to be shown, if described search item is Tiger, to the picture to be shown
The detection and positioning that object is tiger are carried out, carrying out object to the picture to be shown if described search item is " pine tree " is pine
The detection and positioning of tree.It, can be according to object detection model corresponding with described search item, to be shown for different search terms
Picture is scanned for and is detected.
First interception unit 340 is made if the number for the target object is not zero with the target object obtained at first
To intercept object, the interception object in the picture to be shown is intercepted to generate first according to the first default interception parameter
Picture is intercepted, the first interception picture is shown in destination display area.
Specifically, the described first default interception parameter includes the first interception length-width ratio and the first intercepted length, and described first
It is consistent with the length-width ratio of the destination display area to intercept length-width ratio, first intercepted length is less than the destination display area
Length.If search obtains the target object for meeting the target search item in the picture to be shown, with what is obtained at first
Target object obtains the central point of the region of the interception object as interception object.Described first default interception parameter
Including the first interception length-width ratio and the first intercepted length, the length-width ratio of the first interception length-width ratio and the destination display area
Unanimously, first intercepted length is less than the length of the destination display area, and it is 60 that first intercepted length, which is for example arranged,
Pixel.Interception is carried out to picture to be shown according to the described first default interception parameter and generates the first interception picture, described first section
Take picture central point be it is described interception object region central point, it is described first interception picture length-width ratio and mesh
The length-width ratio for marking display area is consistent, then when showing that the first interception picture is in the destination display area, described the
One interception picture will not be deformed, and the first shown interception picture contains acquired interception object.
Fig. 8 is referred to, Fig. 8 is a kind of the schematic of picture specific region extraction element that the another embodiment of the application provides
Block diagram.As shown in figure 8, picture specific region extraction element 30 includes first acquisition unit 300, generation unit 310, second
Acquiring unit 320, search unit 330, the first interception unit 340 and the first user interface generation unit 300a.Wherein, first
Acquiring unit 300, generation unit 310, second acquisition unit 320, search unit 330 and the first interception unit 340 are in above-mentioned reality
It applies in example and has been described, details are not described herein again.The first user interface generation unit 300a is illustrated below.
First user interface generation unit 300a, for generating the first user interface, first user interface includes more
A first parameter input area and multiple second parameters input area, multiple first parameter input areas are used to input for user multiple
Described search item, multiple second parameter input areas are used to input multiple priority parameters for user.
Specifically, for the ease of obtaining search condition, the first user interface is generated so that user inputs search condition.Its
In, first user interface includes multiple first parameters input area and multiple second parameters input area, the first parameter input area
For inputting search terms for user, and the second parameter input area is used for for user's input priority parameter.
Fig. 9 is referred to, Fig. 9 is a kind of the schematic of picture specific region extraction element that the another embodiment of the application provides
Block diagram.As shown in figure 9, picture specific region extraction element 30 includes first acquisition unit 300, generation unit 310, second
Acquiring unit 320, search unit 330, the first interception unit 340 and the first user interface generation unit 300a, wherein described
Search unit 320 includes third acquiring unit 331 and detection unit 332.Wherein, first acquisition unit 300, generation unit 310,
Second acquisition unit 320, search unit 330, the first interception unit 340 and the first user interface generation unit 300a, above-mentioned
It is had been described in embodiment, details are not described herein again.Two subelements for being included to described search unit 320 below: third obtains
Unit 331 and detection unit 332 is taken to be illustrated.
Third acquiring unit 331, for obtaining object detection model parameter corresponding with the target search item.
Specifically, for example, if the target search item is " face ", the object detection model parameter is " face inspection
The parameter of survey model "；If the target search item is Tiger, the object detection model parameter is " tiger detection model "
Parameter；If the target search item is " pine tree ", the object detection model parameter is the parameter of " pine tree detection model ".
Wherein, the Face datection model based on geometrical characteristic, the inspection of the face based on Local Features Analysis can be used in Face datection model
Survey model and the Face datection model based on eigenface.
Detection unit 332, for being detected the picture to be shown to obtain according to the object detection model parameter
Take target object.
Specifically, for example, picture to be shown is detected with the parameter of " Face datection model " to search for and position
The pixel region of face detects picture to be shown with the parameter of " tiger detection model " to search for and position tiger
Pixel region, the parameter with " pine tree detection model " is for detecting picture to be shown to search for and position the picture of pine tree
Plain region.When being detected according to corresponding detection model parameter to picture to be shown, detection direction can for for
Display picture is scanned from left to right, from top to bottom, or is turned left for picture to be shown from the right side, is carried out from the bottom up
Scanning preferentially uses the former in the present embodiment.
0, Figure 10 is a kind of signal for picture specific region extraction element that the another embodiment of the application provides referring to Figure 1
Property block diagram.As shown in Figure 10, picture specific region extraction element 30 include first acquisition unit 300, generation unit 310,
Second acquisition unit 320, search unit 330, the first interception unit 340, the first judging unit 340a and second judgment unit
350.Wherein, the first acquisition unit 300, generation unit 310, second acquisition unit 320, search unit 330 and first section
Unit 340 is taken, is had been described in the above-described embodiments, details are not described herein again.Below to the first judging unit 340a and
Second judgment unit 350 is illustrated.
First judging unit 340a, for judging whether the number of target object is zero.
Specifically, the picture to be shown is being scanned for obtain target object according to current target search item
When, the number of target object should be judged, whether be zero according to the number of target object, carry out corresponding operation.
Second judgment unit 350, for judging whether the target search item is that the last one of described search sequence is searched
Suo Xiang.
Specifically, if the target pair that can not be obtained in the picture to be shown according to the current target search item
As, then judge the target search item whether be described search sequence last, for judging whether according to
Whole search terms of search sequence scan for picture to be shown.
1, Figure 11 is a kind of signal for picture specific region extraction element that the another embodiment of the application provides referring to Figure 1
Property block diagram.As shown in figure 11, picture specific region extraction element 30 include first acquisition unit 300, generation unit 310,
Second acquisition unit 320, search unit 330, the first interception unit 340, the first judging unit 340a, second judgment unit 350
And second interception unit 360.Wherein, the first acquisition unit 300, generation unit 310, second acquisition unit 320, search
Unit 330, the first interception unit 340, the first judging unit 340a and second judgment unit 350, have in the above-described embodiments
Description, details are not described herein again.The second interception unit 360 is illustrated below.
Second interception unit 360, if being the last one search terms of described search sequence, root for the target search item
The picture to be shown is intercepted according to the second default interception parameter to generate the second interception picture, second interception is schemed
Piece is shown in destination display area.
Specifically, the described second default interception parameter includes the second interception length-width ratio and the second intercepted length, and described second
Interception length-width ratio is consistent with the length-width ratio of the destination display area, and second intercepted length is according to the picture to be shown
Length-width ratio and the length-width ratio of the destination display area and determine, if the length-width ratio of the picture to be shown is aobvious greater than the target
Show the length-width ratio in region, then by second intercepted length be set as the picture to be shown width and the target viewing area
The product of the length-width ratio in domain, on the contrary, setting second intercepted length to the length of the picture to be shown.
2, Figure 12 is a kind of signal for picture specific region extraction element that the another embodiment of the application provides referring to Figure 1
Property block diagram.As shown in figure 12, picture specific region extraction element 30 include first acquisition unit 300, generation unit 310,
Second acquisition unit 320, search unit 330, the first interception unit 340, the first judging unit 340a, second judgment unit 350,
Reminding unit 370, second user interface generation unit 380, third interception unit 390, third judging unit 400 and display are single
Member 410.Wherein, the first acquisition unit 300, generation unit 310, second acquisition unit 320,330, first sections of search unit
Unit 340, the first judging unit 340a and second judgment unit 350 are taken, is had been described in the above-described embodiments, it is no longer superfluous herein
It states.Below to the reminding unit 370, second user interface generation unit 380, third interception unit 390, third judging unit
400 and display unit 410 be illustrated.
Reminding unit 370, for generating prompting message to remind user.
Specifically, if presently described target search item is the last one search terms of described search sequence, i.e., according to institute
The whole search terms stated in search sequence scan for picture to be shown, can not still get corresponding with the target search item
Target object, then generate prompting message to remind user, so that user is informed in picture to be shown can not obtain
Get the target object for meeting the search terms set by it.
Second user interface generation unit 380, for generating second user interface, the second user interface includes image
Parameter input area and image display area are intercepted, described image intercepts parameter input area and is used to intercept parameter for user's input picture,
Described image viewing area is for showing picture, wherein the length-width ratio of described image viewing area and the target viewing area
The length-width ratio in domain is consistent.
Specifically, Manual interception is carried out to picture to be shown for the ease of user, in the present embodiment, generates second user
Interface, wherein the second user interface includes image interception parameter input area and image display area, and described image intercepts parameter
Input area is used to intercept parameter for user's input picture, and described image viewing area is for showing picture, wherein the figure
As the length-width ratio of viewing area is consistent with the length-width ratio of the destination display area.
Third interception unit 390, for obtain described image interception parameter, according to described image intercept parameter to it is described to
Display picture is intercepted to generate third interception picture, and third interception picture is shown in described image viewing area
In.
Specifically, picture to be shown is intercepted according to the image interception parameter of user setting and generates third interception figure
Piece shows the third interception picture in image display area, in order to which picture of user's direct feel to after intercepting is aobvious
Show effect.
Third interception picture is shown in the destination display area for judging whether by third judging unit 400
In.
Specifically, there may be unsatisfied situations for the image display effect after interception by user, in this case,
User should can carry out multiple intercept operation to picture to be shown to obtain the interception picture for meeting user's requirement.In the present embodiment
In, execution judges whether for third interception picture to be shown in the destination display area.
Display unit 410, for third interception picture to be shown in the destination display area.
Above-mentioned picture specific region extraction element can be implemented as a kind of form of computer program, which can
To be run in computer equipment as shown in fig. 13 that.
Figure 13 is please referred to, Figure 13 is a kind of schematic block diagram of computer equipment provided by the embodiments of the present application.The calculating
500 equipment of machine equipment can be terminal.
Refering to fig. 13, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 include program instruction, which is performed, and processor 502 may make to execute at a kind of extraction of picture specific region
Reason method.
The processor 502 supports the operation of entire computer equipment 500 for providing calculating and control ability.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute a kind of picture specific region extracting method.
The network interface 505 such as sends the task dispatching of distribution for carrying out network communication.Those skilled in the art can manage
It solves, structure shown in Figure 13, only the block diagram of part-structure relevant to application scheme, is not constituted to the application side
The restriction for the computer equipment 500 that case is applied thereon, specific computer equipment 500 may include more than as shown in the figure
Or less component, perhaps combine certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following function
Can: search condition is obtained, described search condition includes multiple search terms and multiple priority corresponding with multiple described search items
Parameter；It multiple described search items is ranked up and generates search sequence from high to low according to multiple priority parameters；From
Target search item is obtained in described search sequence, the target search item is preferential in the search terms not being acquired in search sequence
The highest search terms of grade；Picture to be shown is scanned for obtain target object according to the target search item；If the mesh
The number of mark object is not zero, and the target object to obtain at first presets interception parameter to institute according to first as interception object
It states the interception object in picture to be shown to be intercepted to generate the first interception picture, the first interception picture is shown in mesh
It marks in display area.
In one embodiment, processor 502 execute obtain search condition, described search condition include multiple search terms and
It before multiple priority parameters corresponding with multiple described search items, also implements function such as: generating the first user interface, it is described
First user interface includes multiple first parameters input area and multiple second parameters input area, multiple first parameter input areas
For inputting multiple described search items for user, multiple second parameter input areas are used for multiple described preferential for user's input
Grade parameter.
In one embodiment, processor 502 execute according to the target search item to picture to be shown scan for
Target object is obtained, function is implemented as follows: obtaining object detection model parameter corresponding with the target search item；Root
The picture to be shown is detected to obtain target object according to the object detection model parameter.
In one embodiment, processor 502 execute according to the target search item to picture to be shown scan for
After obtaining target object, also implements function such as: if the number of the target object is zero, judging that the target search item is
No the last one search terms for described search sequence；If the last one search of the target search Xiang Buwei search sequence
, return to the step of target search item is obtained from described search sequence.
In one embodiment, processor 502 execute judge the target search item whether be described search sequence most
It after the latter search terms, also implements function such as: if the target search item is the last one search of described search sequence
, the picture to be shown is intercepted according to the second default interception parameter to generate the second interception picture, by described second
Interception picture is shown in destination display area.
In one embodiment, if processor 502 executing the number of the target object is zero, judge presently described target
Search terms whether be described search sequence the last one search terms after, also implement function such as: if the target search item
For the last one search terms of described search sequence, prompting message is generated to remind user；Second user interface is generated,
The second user interface includes image interception parameter input area and image display area, and described image interception parameter input area is used for
Parameter is intercepted for user's input picture, described image viewing area is for showing picture, wherein described image viewing area
Length-width ratio is consistent with the length-width ratio of the destination display area；It obtains described image and intercepts parameter, intercepted and joined according to described image
It is several the picture to be shown to be intercepted to generate third interception picture, and third interception picture is shown in the figure
As in viewing area；Judge whether for third interception picture to be shown in the destination display area；If the determination result is YES,
Third interception picture is shown in the destination display area.
In one embodiment, processor 502 is executing generation selection parameter so that user judges whether to cut the third
After taking picture to be shown in the destination display area, also implement function such as: if judging result be it is no, return to the acquisition
Described image intercepts parameter, intercepts parameter according to described image and is intercepted to the picture to be shown to generate third interception figure
Piece, and third interception picture is shown in the step in described image viewing area.
It should be appreciated that in the embodiment of the present application, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
Person's processor is also possible to any conventional processor etc..
A kind of storage medium is provided in another embodiment of the application.The storage medium can be non-volatile computer
Readable storage medium storing program for executing, as USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), magnetic or disk etc. are each
Kind can store the medium of program code.
The storage medium is stored with computer program, and wherein computer program includes program instruction.The program instruction is located
Reason device execute when make processor execute following procedure: obtain search condition, described search condition include multiple search terms and with it is more
The corresponding multiple priority parameters of a described search item；According to multiple priority parameters from high to low to multiple described searches
Item is ranked up and generates search sequence；Target search item is obtained from described search sequence, the target search item is search
The search terms of highest priority in the search terms not being acquired in sequence；Picture to be shown is carried out according to the target search item
Search is to obtain target object；If the number of the target object is not zero, using the target object that obtains at first as interception pair
As being intercepted the interception object in the picture to be shown to generate the first interception figure according to the first default interception parameter
The first interception picture is shown in destination display area by piece.
In one embodiment, which is executed by processor acquisition search condition, and described search condition includes multiple
Before search terms and multiple priority parameters corresponding with multiple described search items, following procedure is also executed: generating the first user
Interface, first user interface include multiple first parameters input area and multiple second parameters input area, and multiple described first
Parameter input area is used to input multiple described search items for user, and multiple second parameter input areas are used to input for user more
A priority parameters.
In one embodiment, which, which is executed by processor, carries out picture to be shown according to the target search item
Search specifically executes following procedure to obtain target object: obtaining object detection model corresponding with the target search item
Parameter；The picture to be shown is detected to obtain target object according to the object detection model parameter.
In one embodiment, which, which is executed by processor, carries out picture to be shown according to the target search item
After search is to obtain target object, also executes following procedure: if the number of the target object is zero, judging that the target is searched
Rope item whether be described search sequence the last one search terms；If the last one of the target search Xiang Buwei search sequence
Search terms return to the step of target search item is obtained from described search sequence.
In one embodiment, which, which is executed by processor, judges whether the target search item is described search sequence
After the last one search terms of column, following procedure is also executed: if the target search item is last of described search sequence
A search terms intercept the picture to be shown according to the second default interception parameter to generate the second interception picture, by institute
The second interception picture is stated to be shown in destination display area.
In one embodiment, if the number that the program instruction is executed by processor the target object is zero, judgement is current
The target search item whether be described search sequence the last one search terms after, also execution following procedure: if the mesh
The last one search terms that search terms are described search sequence are marked, generate prompting message to remind user；Generate second
User interface, the second user interface include image interception parameter input area and image display area, and described image intercepts parameter
Input area is used to intercept parameter for user's input picture, and described image viewing area is for showing picture, wherein the figure
As the length-width ratio of viewing area is consistent with the length-width ratio of the destination display area；It obtains described image and intercepts parameter, according to described
Image interception parameter intercepts the picture to be shown to generate third interception picture, and third interception picture is shown
It is shown in described image viewing area；Judge whether for third interception picture to be shown in the destination display area；If sentencing
Disconnected result be it is yes, the third is intercepted into picture and is shown in the destination display area.
In one embodiment, which, which is executed by processor, generates selection parameter so that judge whether will be described by user
After third interception picture is shown in the destination display area, following procedure is also executed: if judging result is no, return institute
It states and obtains described image interception parameter, parameter is intercepted according to described image, the picture to be shown is intercepted to generate third
Picture is intercepted, and third interception picture is shown in the step in described image viewing area.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond scope of the present application.In several embodiments provided herein, it should be understood that disclosed device and
Method may be implemented in other ways.For example, the apparatus embodiments described above are merely exemplary.For example, each
The division of a unit, only a kind of logical function partition, there may be another division manner in actual implementation.Such as multiple lists
Member or component can be combined or can be integrated into another system, or some features can be ignored or not executed.The application is real
The step applied in a method can be sequentially adjusted, merged and deleted according to actual needs.In the embodiment of the present application device
Unit can be combined, divided and deleted according to actual needs.In addition, each functional unit in each embodiment of the application
It can integrate in one processing unit, be also possible to each unit and physically exist alone, be also possible to two or more
Unit is integrated in one unit.Above-mentioned integrated unit both can take the form of hardware realization, can also use software function
The form of energy unit is realized.If the integrated unit is realized in the form of SFU software functional unit and sells as independent product
Or it in use, can store in one storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Come, which is stored in a storage medium, including some instructions are used so that a computer equipment (can
To be personal computer, terminal or the network equipment etc.) execute all or part of step of each embodiment the method for the application
Suddenly.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. a kind of picture specific region extracting method characterized by comprising
Search condition is obtained, described search condition includes multiple search terms and multiple priority corresponding with multiple described search items
Parameter；
It multiple described search items is ranked up and generates search sequence from high to low according to multiple priority parameters；
Target search item is obtained from described search sequence, the target search item is the search terms not being acquired in search sequence
The search terms of middle highest priority；
Picture to be shown is scanned for obtain target object according to the target search item；
If the number of the target object is not zero, the target object to obtain at first is preset as interception object according to first
Interception parameter intercepts the interception object in the picture to be shown to generate the first interception picture, and described first is intercepted
Picture is shown in destination display area.
2. picture specific region according to claim 1 extracting method, which is characterized in that the acquisition search condition it
Before, the method also includes:
The first user interface is generated, first user interface includes multiple first parameters input area and the input of multiple second parameters
Area, multiple first parameter input areas are used to input multiple described search items, multiple second parameter input areas for user
For inputting multiple priority parameters for user.
3. picture specific region according to claim 1 extracting method, which is characterized in that described according to the target search
Item scans for picture to be shown to obtain target object and include:
Obtain object detection model parameter corresponding with the target search item；
The picture to be shown is detected to obtain target object according to the object detection model parameter.
4. picture specific region according to claim 1 extracting method, which is characterized in that searched described according to the target
After rope item scans for obtain target object picture to be shown, the method also includes:
If the number of the target object is zero, judge whether the target search item is that the last one of described search sequence is searched
Suo Xiang；
If the last one search terms of the target search Xiang Buwei search sequence, return obtains target from described search sequence
The step of search terms.
5. picture specific region according to claim 4 extracting method, which is characterized in that searched in the judgement target
Rope item whether be described search sequence the last one search terms after, the method also includes:
If the target search item is the last one search terms of described search sequence, according to the second default interception parameter to described
Picture to be shown is intercepted to generate the second interception picture, and the second interception picture is shown in destination display area.
6. picture specific region according to claim 4 extracting method, which is characterized in that in the presently described mesh of judgement
Mark search terms whether be described search sequence the last one search terms after, the method also includes:
If the target search item is the last one search terms of described search sequence, prompting message is generated to mention to user
It wakes up；
Second user interface is generated, the second user interface includes image interception parameter input area and image display area, described
Image interception parameter input area is used to intercept parameter for user's input picture, and described image viewing area is for showing picture
Show, wherein the length-width ratio of described image viewing area is consistent with the length-width ratio of the destination display area；
It obtains described image and intercepts parameter, parameter is intercepted according to described image and the picture to be shown is intercepted to generate the
Three interception pictures, and third interception picture is shown in described image viewing area；
Judge whether for third interception picture to be shown in the destination display area；
If the determination result is YES, third interception picture is shown in the destination display area.
7. picture specific region according to claim 6 extracting method, which is characterized in that judge whether will be described described
After third interception picture is shown in the destination display area, the method also includes:
If judging result be it is no, return to the acquisitions described image and intercept parameter, according to described image interception parameter to it is described to
Display picture is intercepted to generate third interception picture, and third interception picture is shown in described image viewing area
The step of.
8. a kind of picture specific region extraction element characterized by comprising
First acquisition unit, for obtaining search condition, described search condition include multiple search terms and with multiple described searches
The corresponding multiple priority parameters of item；
Generation unit, for being ranked up and generating to multiple described search items from high to low according to multiple priority parameters
Search sequence；
Second acquisition unit, for obtaining target search item from described search sequence, the target search item is search sequence
In in the search terms that are not acquired highest priority search terms；
Search unit, for being scanned for picture to be shown to obtain target object according to the target search item；
Interception unit, if the number for the target object is not zero, using the target object that obtains at first as interception object,
The interception object in the picture to be shown is intercepted according to the first default interception parameter to generate the first interception picture, it will
The first interception picture is shown in destination display area.
9. a kind of computer equipment, including memory, processor and it is stored on the memory and can be on the processor
The computer program of operation, which is characterized in that the processor realizes such as claim 1 to 7 when executing the computer program
Any one of picture specific region extracting method.
10. a kind of computer readable storage medium, which is characterized in that the storage medium is stored with computer program, the meter
Calculation machine program includes program instruction, and described program instruction makes the processor execute such as claim 1- when being executed by a processor
Picture specific region extracting method described in any one of 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811207783.5A CN109615631A (en) | 2018-10-17 | 2018-10-17 | Picture specific region extracting method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811207783.5A CN109615631A (en) | 2018-10-17 | 2018-10-17 | Picture specific region extracting method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109615631A true CN109615631A (en) | 2019-04-12 |
Family
ID=66001665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811207783.5A Pending CN109615631A (en) | 2018-10-17 | 2018-10-17 | Picture specific region extracting method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109615631A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110275971A (en) * | 2019-06-28 | 2019-09-24 | 维沃移动通信有限公司 | A kind of method and mobile terminal of target object lookup |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09231231A (en) * | 1996-02-26 | 1997-09-05 | Dainippon Screen Mfg Co Ltd | Data retrieval device |
| US20090052787A1 (en) * | 2007-08-24 | 2009-02-26 | Naoyuki Satoh | Image search apparatus, image search method, and storage medium storing a program for causing a search apparatus to execute a search method |
| CN101389022A (en) * | 2007-09-14 | 2009-03-18 | 索尼株式会社 | Image processing apparatus, image processing method and image pickup apparatus |
| JP2010263439A (en) * | 2009-05-07 | 2010-11-18 | Panasonic Corp | Electronic camera, image processing device, and image processing method |
| US9280565B1 (en) * | 2014-10-03 | 2016-03-08 | EyeEm Mobile GmbH. | Systems, methods, and computer program products for displaying images |
| CN106296717A (en) * | 2016-08-25 | 2017-01-04 | 中国电子科技集团公司第十研究所 | Multiband SAR images coupling object localization method |
| CN106708823A (en) * | 2015-07-20 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Search processing method, apparatus and system |
-
2018
- 2018-10-17 CN CN201811207783.5A patent/CN109615631A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH09231231A (en) * | 1996-02-26 | 1997-09-05 | Dainippon Screen Mfg Co Ltd | Data retrieval device |
| US20090052787A1 (en) * | 2007-08-24 | 2009-02-26 | Naoyuki Satoh | Image search apparatus, image search method, and storage medium storing a program for causing a search apparatus to execute a search method |
| CN101389022A (en) * | 2007-09-14 | 2009-03-18 | 索尼株式会社 | Image processing apparatus, image processing method and image pickup apparatus |
| JP2010263439A (en) * | 2009-05-07 | 2010-11-18 | Panasonic Corp | Electronic camera, image processing device, and image processing method |
| US9280565B1 (en) * | 2014-10-03 | 2016-03-08 | EyeEm Mobile GmbH. | Systems, methods, and computer program products for displaying images |
| CN106708823A (en) * | 2015-07-20 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Search processing method, apparatus and system |
| CN106296717A (en) * | 2016-08-25 | 2017-01-04 | 中国电子科技集团公司第十研究所 | Multiband SAR images coupling object localization method |
Non-Patent Citations (2)
| Title |
|---|
| BINDITA CHAUDHURI ET AL.: "Region-Based Retrieval of Remote Sensing Images Using an Unsupervised Graph-Theoretic Approach", IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, vol. 13, no. 7, 31 July 2016 (2016-07-31), pages 987 - 991, XP011613764, DOI: 10.1109/LGRS.2016.2558289 * |
| 张立保 等: "基于自适应半径搜索的图像感兴趣区域检测", 中国激光, vol. 40, no. 07, 31 July 2013 (2013-07-31), pages 206 - 210 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110275971A (en) * | 2019-06-28 | 2019-09-24 | 维沃移动通信有限公司 | A kind of method and mobile terminal of target object lookup |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6526909B2 (en) | Measurement information provision system, measurement information provision method, server apparatus, communication terminal, and computer program | |
| US10019779B2 (en) | Browsing interface for item counterparts having different scales and lengths | |
| US10299568B2 (en) | Makeup application assistance device, makeup application assistance method, and makeup application assistance program | |
| CN102113012B (en) | Finger shape estimating device, the presumption method of finger shape and program | |
| CN109003168A (en) | Virtual fit method, smart television and computer readable storage medium | |
| US20160300393A1 (en) | Virtual trial-fitting system, virtual trial-fitting program, virtual trial-fitting method, and storage medium in which virtual fitting program is stored | |
| CN107851328A (en) | For the method and system for recommending to be adapted to footwear | |
| JP6242768B2 (en) | Virtual try-on device, virtual try-on method, and program | |
| JP6320237B2 (en) | Virtual try-on device, virtual try-on method, and program | |
| CN105989617A (en) | Virtual try-on apparatus and virtual try-on method | |
| JP6338966B2 (en) | Virtual try-on device, virtual try-on system, virtual try-on method, and program | |
| US10395404B2 (en) | Image processing device for composite images, image processing system and storage medium | |
| US10026176B2 (en) | Browsing interface for item counterparts having different scales and lengths | |
| CN111767817B (en) | Dress collocation method and device, electronic equipment and storage medium | |
| JP6656572B1 (en) | Information processing apparatus, display control method, and display control program | |
| JP2018106736A (en) | Virtual try-on apparatus, virtual try-on method and program | |
| JP2019109843A (en) | Classification device, classification method, attribute recognition device, and machine learning device | |
| JP5293636B2 (en) | Model image creation device and model image creation program for model image creation device | |
| CN109615631A (en) | Picture specific region extracting method, device, computer equipment and storage medium | |
| CN111309220B (en) | Interaction method, picture processing method and device | |
| JP4241235B2 (en) | Layout system, layout program, and layout method | |
| KR20210064442A (en) | Apparatus for providing image of nail design | |
| US20150139558A1 (en) | Searching device, searching method, and computer program product | |
| JP5044664B2 (en) | Human image search device | |
| CN109624574A (en) | A kind of engraving path generating method and device for leaf carving |
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 |