CN110298858A - A kind of image cropping method and device - Google Patents
A kind of image cropping method and device Download PDFInfo
- Publication number
- CN110298858A CN110298858A CN201910585564.9A CN201910585564A CN110298858A CN 110298858 A CN110298858 A CN 110298858A CN 201910585564 A CN201910585564 A CN 201910585564A CN 110298858 A CN110298858 A CN 110298858A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- pixel unit
- edge
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention provides a kind of image cropping method and devices, it is related to computer image processing technology field, wherein, the above method includes: to carry out edge extracting to image to be processed, the differential image for indicating above-mentioned edge image pixel point difference value is calculated again, it carries out edge extracting again to above-mentioned differential image and obtains second edge image, calculate the distribution characteristics of edge pixel point in the above-mentioned each pixel unit of second edge image, the fuzzy region in image to be processed is determined according to above-mentioned distribution characteristics, and the fuzzy region determined is cut and is removed.When cutting removal to the fuzzy region in image using the embodiment of the present invention, it calculates and converts by continuous image, increase the fuzzy region in image and the comparison degree in non-fuzzy region, then finds out the fuzzy region of image vertical or horizontal direction two sides and cut removal.Image is cut using scheme provided in an embodiment of the present invention, the accuracy rate that image obscuring area is cut to removal can be improved.
Description
Technical field
The present invention relates to computer image processing technology fields, more particularly to a kind of image cropping method and device.
Background technique
When showing to image, the size of image itself is less than the size of display area sometimes, leads in this case
Often it can increase fuzzy region in image peripheral, so that the size of image and viewing area according to the pixel value of image surrounding pixel
The size in domain is consistent.Since the pixel value size of fuzzy region is close, when analyzing image, above-mentioned fuzzy region is basic
Useful information will not be brought, or even redundancy can be generated, needs to cut above-mentioned increased fuzzy region again in this case
Removal.
In the prior art, in order to remove above-mentioned increased fuzzy region from image, usually first with edge detection algorithm
Edge detection is carried out to the image after increase fuzzy region and determines the fuzzy region in image then according to edge detection results,
And the fuzzy region that will test cuts removal.
Inventor has found that at least there are the following problems for the prior art in the implementation of the present invention:
The factors such as the detection accuracy by edge detection algorithm in the prior art are influenced, difficult according to above-mentioned edge detection results
Accurately to identify the boundary between fuzzy region and non-fuzzy region, therefore, when removing fuzzy region, Ke Nengwu
Method removes whole fuzzy regions, it is also possible to non-fuzzy zone errors be judged as to fuzzy region and removed.
As it can be seen that accuracy rate is low when cutting the fuzzy region in removal image using the prior art.
Summary of the invention
The embodiment of the present invention is designed to provide a kind of image cropping method and device, cuts removal figure to realize to improve
As the accuracy rate of fuzzy region.Specific technical solution is as follows:
In a first aspect, the embodiment of the invention provides a kind of image cropping methods, which comprises
Edge extracting is carried out to image to be processed, obtains first edge image；
Obtain the differential image formed by the corresponding difference value of pixel each in the first edge image, wherein every
The corresponding difference value of one pixel indicates: the pixel and the pixel the margin of image element between pixel within a preset range
It is different, the preset range are as follows: along the range of pixel unit direction；
Edge extracting is carried out to the differential image, obtains second edge image；
Obtain the distribution characteristics of edge pixel point in each pixel unit in the second edge image；
According to distribution characteristics obtained, determine to include fuzzy region to Cutting Edge in the image to be processed, and right
The fuzzy region carries out cutting removal, wherein described to Cutting Edge are as follows: the image to be processed is where the pixel unit
The image side in direction.
In one embodiment of the present of invention, the acquisition is by the corresponding difference of pixel each in the first edge image
It is worth the differential image formed, comprising:
The corresponding difference value of each pixel along the first edge image is calculated along pixel unit direction, obtains the
One differential image；
The corresponding difference value of each pixel along first differential image is calculated along pixel unit direction, obtains the
Two differential images；
It is the first new differential image with second differential image, and returns described along the calculating of pixel unit direction
In first differential image the step of each pixel corresponding difference value, until the calculation times of difference value reach default time
Number；
Using the second differential image finally obtained as by the corresponding difference of pixel each in the first edge image
It is worth the differential image formed.
It is described according to distribution characteristics obtained in one embodiment of the present of invention, it determines and is wrapped in the image to be processed
Include the fuzzy region to Cutting Edge, comprising:
Calculate the changing value in the second edge image between the corresponding distribution characteristics of every two adjacent pixel unit；
According to the changing value being calculated, determine to include fuzzy region to Cutting Edge in the image to be processed.
In one embodiment of the present of invention, the changing value that the basis is calculated is determined and is wrapped in the image to be processed
Include the fuzzy region to Cutting Edge, comprising:
Along the direction vertical with the pixel unit direction, determine that first distribution is special in the second edge image
The first pixel unit that changing value is greater than preset threshold between sign is greater than changing value between, the last one distribution characteristics described pre-
If the second pixel unit pair of threshold value；
First pixel unit and first in the image to be processed is determined as fuzzy region to the region between Cutting Edge,
And the second pixel unit and second in the image to be processed is determined as fuzzy region to the region between Cutting Edge, wherein
First pixel unit are as follows: first pixel unit is to one in the image to be processed in corresponding pixel unit
Pixel unit, described first to Cutting Edge are as follows: edge first pixel unit vertical with pixel unit direction direction,
Second pixel unit are as follows: second pixel unit is to one in the image to be processed in corresponding pixel unit
Pixel unit, described second to Cutting Edge are as follows: along the last one pixel list vertical with pixel unit direction direction
Member.
In one embodiment of the present of invention, the pixel unit includes: pixel column and/or pixel column.
Second aspect, the embodiment of the invention provides a kind of image cropping device, described device includes:
First edge image obtains module, for carrying out edge extracting to image to be processed, obtains first edge image；
Differential image obtains module, for obtaining by the corresponding difference value shape of pixel each in the first edge image
At differential image, wherein the corresponding difference value of each pixel indicates: the pixel and pixel institute are within a preset range
Value differences between pixel, the preset range are as follows: along the range of pixel unit direction；
Second edge image obtains module, for carrying out edge extracting to the differential image, obtains second edge image；
Distribution characteristics obtains module, for obtaining in the second edge image edge pixel point in each pixel unit
Distribution characteristics；
Fuzzy region cuts module, for according to distribution characteristics obtained, determine in the image to be processed include to
The fuzzy region of Cutting Edge, and cutting removal is carried out to the fuzzy region, wherein it is described to Cutting Edge are as follows: described to be processed
Image is on the image side of the pixel unit direction.
In one embodiment of the present of invention, the differential image obtains module, comprising:
First differential image obtaining unit, it is each in the first edge image for being calculated along pixel unit direction
The corresponding difference value of pixel, obtains the first differential image；
Second differential image obtaining unit, it is each in first differential image for being calculated along pixel unit direction
The corresponding difference value of pixel, obtains the second differential image；
New differential image determination unit, for second differential image to be determined as to the first new differential image, and is touched
Send out the second differential image obtaining unit described, until the calculation times of difference value reach preset times；
Differential image determination unit, the second differential image for that will finally obtain are determined as by the first edge image
In the differential image that is formed of the corresponding difference value of each pixel.
In one embodiment of the present of invention, the fuzzy region cuts module, comprising:
Changing value computing unit, for calculating the corresponding distribution of every two adjacent pixel unit in the second edge image
Changing value between feature；
Fuzzy region determination unit, for according to the changing value that is calculated, determine in the image to be processed include to
The fuzzy region of Cutting Edge；
Fuzzy region cuts unit, for carrying out cutting removal to the fuzzy region.
In one embodiment of the present of invention, the fuzzy region determination unit is specifically used for edge and the pixel unit institute
In the vertical direction in direction, determine that changing value is greater than preset threshold between first distribution characteristics in the second edge image
First pixel unit is greater than the second pixel unit pair of the preset threshold to changing value between, the last one distribution characteristics；
First pixel unit and first in the image to be processed is determined as fuzzy region to the region between Cutting Edge,
And the second pixel unit and second in the image to be processed is determined as fuzzy region to the region between Cutting Edge, wherein
First pixel unit are as follows: first pixel unit is to one in the image to be processed in corresponding pixel unit
Pixel unit, described first to Cutting Edge are as follows: edge first pixel unit vertical with pixel unit direction direction,
Second pixel unit are as follows: second pixel unit is to one in the image to be processed in corresponding pixel unit
Pixel unit, described second to Cutting Edge are as follows: along the last one pixel list vertical with pixel unit direction direction
Member.
The third aspect, the embodiment of the invention provides a kind of electronic equipment, including processor, communication interface, memory and
Communication bus, wherein processor, communication interface, memory complete mutual communication by communication bus；
Memory, for storing computer program；
Processor when for executing the program stored on memory, realizes any method and step of first aspect.
Fourth aspect, the embodiment of the invention also provides a kind of computer program products comprising instruction, when it is being calculated
When being run on machine, so that computer executes method and step described in any of the above-described first aspect.
As seen from the above, when carrying out image cropping using scheme provided in an embodiment of the present invention, image to be processed is carried out
Edge extracting, then the differential image for indicating above-mentioned edge image pixel point difference value is calculated, again to above-mentioned differential image
It carries out edge extracting and obtains second edge image, calculate minute of edge pixel point in the above-mentioned each pixel unit of second edge image
Cloth feature determines the fuzzy region in image to be processed according to above-mentioned distribution characteristics, and the fuzzy region determined cutting is gone
It removes.Compared with prior art, scheme provided in an embodiment of the present invention carries out edge extracting and difference meter twice to image to be processed
It calculates, the pixel variation degree of the fuzzy region and non-fuzzy region in image to be processed is enhanced, after then obtaining calculating
The distribution characteristics of edge pixel point in each pixel unit of image, determines the fuzzy region in image in turn using distribution characteristics
Carry out cutting removal.As it can be seen that the accuracy rate that image obscuring area is cut to removal can be improved using the embodiment of the present invention.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of image cropping method provided in an embodiment of the present invention；
Fig. 2 is a kind of image schematic diagram to be processed provided in an embodiment of the present invention；
Fig. 3 is a kind of edge extracting image schematic diagram provided in an embodiment of the present invention；
Fig. 4 is a kind of differential image schematic diagram provided in an embodiment of the present invention；
Fig. 5 is a kind of pixel distribution characteristics schematic diagram provided in an embodiment of the present invention；
Fig. 6 is image schematic diagram after a kind of processing provided in an embodiment of the present invention；
Fig. 7 is a kind of structural schematic diagram of image cropping device provided in an embodiment of the present invention；
Fig. 8 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
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 only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The embodiment of the invention provides a kind of image cropping method and devices, are described in detail separately below.
Firstly, the executing subject for being provided for the embodiments of the invention image cropping scheme is illustrated.
Above-mentioned executing subject can be software client, for example, it may be Video processing software, image processing software etc..
In addition, above-mentioned executing subject can also be that operation has the electronic equipment of above-mentioned client, for example, it may be desk-top meter
Calculation machine, laptop, tablet computer, smart phone etc..
Image cropping method provided in an embodiment of the present invention is illustrated by specific embodiment again below.
Referring to Fig. 1, Fig. 1 is a kind of flow diagram of image cropping method provided in an embodiment of the present invention, the above method
Include the following steps 101-105.
Step 101, edge extracting is carried out to image to be processed, obtains first edge image.
Above-mentioned image to be processed can be gray level image, be also possible to color image.
When above-mentioned image to be processed is color image, gray level image first can be converted by above-mentioned image to be processed, so
Edge extracting is carried out to the gray level image that conversion obtains afterwards, obtains first edge image.
Specifically, when carrying out edge extracting edge extracting can be carried out to image using preset edge detection operator.
For example, above-mentioned edge detection operator can be Sobel (Sobel) operator, Roberts (Luo Baici) operator, Log
(Laplce Gauss) operator etc., the present invention is defined not to this.
Grayscale image as shown in Figure 2 indicates image to be processed, using edge detection operator Canny (Tuscany) operator to shown
Grayscale image carries out edge extracting, to obtain first edge image, as shown in Figure 3.
When handling using Canny operator image to be processed, non-peak signal in image can be suppressed, to improve
The violent non-fuzzy region of color change, inhibits the fuzzy region that color change is small in image to be processed in image to be processed.
Step 102, the differential image formed by the corresponding difference value of pixel each in above-mentioned first edge image is obtained.
Wherein, the corresponding difference value of each pixel indicates: the pixel and the pixel institute pixel within a preset range
Value differences between point, above-mentioned preset range are as follows: along the range of pixel unit direction.
Wherein, above-mentioned pixel unit can be pixel column, be also possible to pixel column.
In the case where above-mentioned pixel unit is pixel column, pixel unit direction is horizontal direction, above-mentioned default model
It encloses for range in the horizontal direction.In this case, pixel pixel within a preset range can be above-mentioned picture
The preset quantity pixel of the preset quantity pixel and/or above-mentioned pixel of vegetarian refreshments level to the left horizontally to the right.
In the case where above-mentioned pixel unit is pixel column, pixel unit direction is vertical direction, above-mentioned default model
It encloses for range vertically.In this case, pixel pixel within a preset range can be above-mentioned picture
The preset quantity pixel of the preset quantity pixel and/or above-mentioned pixel of vegetarian refreshments vertically upward vertically downward.
The corresponding difference value of one pixel can pass through the picture of the pixel in the above-mentioned pixel of calculating and preset range
The mean difference of plain value, variance, very poor etc. obtain.
The corresponding difference value of above-mentioned each pixel, in as each pixel and preset range between other pixels
Difference value.For example, can by calculating the average value of the gradient value in each pixel and preset range between other pixels,
To obtain the corresponding difference value of each pixel.
In one embodiment of the present of invention, above-mentioned differential image can be obtained by following steps A-D.
Step A: calculating the corresponding difference value of each pixel along above-mentioned first edge image along pixel unit direction,
Obtain the first differential image.
Specifically, since each pixel in first edge image all has a difference value, so, it is believed that the
Each pixel in each pixel and first edge image in one differential image corresponds.It is every in first differential image
The pixel value of one pixel is the difference value of the pixel corresponding pixel in first edge image.
Step B: calculating the corresponding difference value of each pixel along above-mentioned first differential image along pixel unit direction,
Obtain the second differential image.
Since each pixel in the first differential image all has a difference value, so, it is believed that the second difference
Each pixel in each pixel and the first differential image in image corresponds.Each pixel in second differential image
The pixel value of point is the difference value of the pixel corresponding pixel in the first differential image.
Step C: being the first new differential image with above-mentioned second differential image, and return to above-mentioned steps B, until difference value
Calculation times reach preset times.
Wherein, preset times can be 3 times, 6 times, it is 7 inferior.Specific number is according to application scenarios, image type, big spirogram
As the accuracy rate that fuzzy region cuts removal determines.Specifically, application scenarios include picture software, video software, picture webpage,
Video web-pages etc., image type can be divided according to picture size, pixel size, personage, landscape, material object etc..
Step D: using the second differential image finally obtained as corresponding by pixel each in above-mentioned first edge image
Difference value formed differential image.
Each pixel in first edge image is calculated along pixel column direction for example, can use Sobel edge detection operator
The corresponding difference value of point, is calculated differential image by 7 times.First along pixel column direction, Sobel edge detection is utilized
Operator calculates the corresponding difference value of each pixel in first edge image, obtains the first differential image；Then along pixel column institute
The corresponding difference value of each pixel, obtains the second differential image in above-mentioned first differential image of direction calculating；Again with above-mentioned
Second differential image returns as the first new differential image and calculates each picture in the first differential image along pixel column direction
The step of corresponding difference value of vegetarian refreshments obtains the second differential image, until the calculation times of difference value reach 7 times；7 times are calculated
The differential image that the second differential image obtained afterwards is formed as the corresponding difference value of pixel each in first edge image.
Step 103, edge extracting is carried out to above-mentioned differential image, obtains second edge image.
Likewise, above-mentioned edge extracting can be calculated by edge detections such as Sobel operator, Roberts operator, Log operators
Son realizes that the present invention is defined not to this.
For example, as shown in figure 4, carrying out edge to differential image using Laplacian (Laplce) edge detection operator
It extracts, obtains second edge image.
Step 104, the distribution characteristics of edge pixel point in each pixel unit in above-mentioned second edge image is obtained.
Specifically, above-mentioned distribution characteristics can be the pixel of edge pixel point in each pixel unit in second edge image
Variance, standard deviation, mean difference between value etc.；Above-mentioned pixel unit is consistent with the pixel unit direction in step 102.
For example, vertically calculating the variance of edge pixel point in each pixel column in above-mentioned second edge image, make
For distribution characteristics.A series of variance for from left to right calculating the pixel value of each column pixel unit in second edge image, by sides
Difference forms array A (n) [i0, i1, i2... ... in], wherein i0Indicate the edge of first pixel column on the left of second edge image
The distribution characteristics of pixel, i1Indicate the distribution characteristics ... of the edge pixel point of second pixel column on the left of second edge image
inIndicate the distribution characteristics of the edge pixel point of (n+1)th pixel column on the left of second edge image.Above-mentioned array can indicate
In two edge images from left to right in each pixel column edge pixel point distribution characteristics.
Step 105, according to distribution characteristics obtained, determine to include confusion region to Cutting Edge in above-mentioned image to be processed
Domain, and cutting removal is carried out to above-mentioned fuzzy region.
Wherein, above-mentioned to Cutting Edge are as follows: above-mentioned image to be processed is on the image side of above-mentioned pixel unit direction.Upper
It is the side where two pixel columns of image left and right ends to be processed to Cutting Edge in the case where pixel unit is stated as pixel column；
In the case where above-mentioned pixel unit is pixel column, to Cutting Edge for where two pixel columns of image upper and lower ends to be processed
Side.
In one embodiment of the present of invention, above-mentioned steps 105 may include following first steps and step 2:
The first step calculates the change in above-mentioned second edge image between the corresponding distribution characteristics of every two adjacent pixel unit
Change value.
Specifically, the variation in above-mentioned second edge image between the corresponding distribution characteristics of every two adjacent pixel unit
Value, can be indicated by the difference of the corresponding distribution characteristics of two neighboring pixel unit, can also be by two neighboring pixel unit pair
Quotient that the distribution characteristics answered is divided by indicates that the present invention is defined not to this.
For example, indicating every two adjacent pixel unit in second edge image using the first-order difference of above-mentioned array A (n)
Changing value between corresponding distribution characteristics.The first-order difference of above-mentioned array is calculated using following formula:
B[in]=A [in+1]-A[in]
To obtain new array B (n-1) [A1-A0, A2-A1... ... An-An-1]。
Array B (n-a) is the change in second edge image between the corresponding distribution characteristics of every two adjacent pixel unit
Change value.
Second step determines to include confusion region to Cutting Edge in above-mentioned image to be processed according to the changing value being calculated
Domain.
In one embodiment of the present of invention, along the direction vertical with above-mentioned pixel unit direction, above-mentioned second is determined
To be greater than the first pixel unit of preset threshold special to, the last one distribution for changing value between first distribution characteristics in edge image
Changing value is greater than the second pixel unit pair of above-mentioned preset threshold between sign.
Specifically, in order to represent the pixel distributional difference between adjacent pixel unit more obviously, to array B into
Arrangement is gone.Specifically, as shown in figure 5, given threshold a, is set to 100 for the element for being greater than a in array B, the element less than a is set
It is 0, the element value after arrangement in array B only includes 0 or 100.The value of threshold value a can be 10,30,80 etc., specific value according to
Application scenarios, image type, great amount of images fuzzy region cut accuracy rate of removal etc. and determine.
Wherein, above-mentioned pixel unit be pixel column in the case where, the first pixel unit to and the second pixel unit to table
Show that the image left and right sides to be processed pixel difference changes pixel unit pair greatly；The case where above-mentioned pixel unit is pixel column
Under, the first pixel unit to and the second pixel unit to indicating that image to be processed or more two sides pixel difference changes pixel list greatly
Member is right.It is possible thereby to think the first pixel unit to and the second pixel unit to for image obscuring area to be processed and non-fuzzy area
The boundary in domain.
Therefore, the first pixel unit and first in above-mentioned image to be processed is determined as obscuring to the region between Cutting Edge
Region, and the second pixel unit and second in above-mentioned image to be processed is determined as fuzzy region to the region between Cutting Edge.
Wherein, above-mentioned first pixel unit are as follows: above-mentioned first pixel unit is to the corresponding picture in above-mentioned image to be processed
A pixel unit in plain unit, above-mentioned first to Cutting Edge are as follows: along vertical with above-mentioned pixel unit direction direction
First pixel unit, above-mentioned second pixel unit are as follows: above-mentioned second pixel unit is to corresponding in above-mentioned image to be processed
A pixel unit in pixel unit, above-mentioned second to Cutting Edge are as follows: along vertical with above-mentioned pixel unit direction direction
The last one pixel unit.
Wherein, above-mentioned first pixel unit can be any pixel unit of the first pixel unit centering, similarly, above-mentioned
Two pixel units can be any pixel unit of the second pixel unit centering.
Above-mentioned pixel unit be pixel column in the case where, above-mentioned first to Cutting Edge be the image leftmost side to be processed picture
Element column, above-mentioned second to Cutting Edge be the rightmost side pixel column；In the case where above-mentioned pixel unit is pixel column, above-mentioned first
To Cutting Edge be image the top to be processed pixel column, above-mentioned second to Cutting Edge be the lowermost pixel column.
For example, find the left end array B rise corresponding first pixel unit of first non-zero element to and right end rise first it is non-
Corresponding second pixel unit pair of 0 element.Pixel unit on the left of first pixel unit centering is considered the first pixel unit,
Pixel unit of second pixel unit to right side is considered the second pixel unit.Then by the first pixel list of image to be processed
The first of member and the leftmost side is to region and the second pixel unit and the rightmost side between Cutting Edge second between Cutting Edge
Region be determined as fuzzy region.
A kind of implementation of the invention can also be directly according to every two adjacent pixel unit in second edge image
Corresponding distribution characteristics determines the fuzzy region of image to be processed.Specifically, vertical with above-mentioned pixel unit direction
On direction, first pixel unit that distribution characteristics value is greater than default characteristic value is searched from both ends to centre respectively, as wait locate
The boundary of image obscuring area and non-fuzzy region is managed, so that it is determined that the part other than boundary is fuzzy region.
For example, searching first to the right from the left end of image to be processed in the case where above-mentioned pixel unit is vertical direction
A distribution characteristics value is greater than the first pixel unit of default characteristic value, then searches the first point to the left from the right end of image to be processed
Cloth characteristic value is greater than the second pixel unit of default characteristic value, using above-mentioned two found out pixel unit as image to be processed
The boundary of fuzzy region and non-fuzzy region, by the region on the left of the first pixel unit and the area on the right side of the second pixel unit
Domain is determined as fuzzy region.
As shown in fig. 6, determining fuzzy region is cut removal, image after being handled.
As it can be seen that using image cropping method provided in an embodiment of the present invention, by carrying out edge extracting to image to be processed,
The differential image for indicating above-mentioned edge image pixel point difference value is calculated again, carries out edge again to above-mentioned differential image and mentions
Second edge image is obtained, the distribution characteristics of edge pixel point in the above-mentioned each pixel unit of second edge image, root are calculated
The fuzzy region in image to be processed is determined according to above-mentioned distribution characteristics, and the fuzzy region determined is cut and is removed.With it is existing
Technology is compared, and the embodiment of the present invention enhances the mould in image to be processed by the way that image to be processed is repeatedly converted and calculated
Paste the pixel variation degree in region and non-fuzzy region, edge picture in each pixel unit of image after then being calculated
The distribution characteristics of vegetarian refreshments, distribution characteristics and preset threshold are compared, and are determined the fuzzy region in image and then are cut
Removal.As it can be seen that the accuracy rate that image obscuring area is cut to removal can be improved using the embodiment of the present invention.
Corresponding with above-mentioned image cropping method, the embodiment of the invention also provides a kind of image cropping devices.
Fig. 7 is a kind of Graphics Clipping apparatus structure schematic diagram provided in an embodiment of the present invention, which includes:
First edge image obtains module 701, for carrying out edge extracting to image to be processed, obtains first edge figure
Picture；
Differential image obtains module 702, for obtaining by the corresponding difference of pixel each in above-mentioned first edge image
It is worth the differential image formed, wherein the corresponding difference value of each pixel indicates: model is preset where the pixel and the pixel
Enclose the value differences between interior pixel, above-mentioned preset range are as follows: along the range of pixel unit direction；
Second edge image obtains module 703, for carrying out edge extracting to above-mentioned differential image, obtains second edge figure
Picture；
Distribution characteristics obtains module 704, for obtaining in above-mentioned second edge image edge pixel in each pixel unit
The distribution characteristics of point；
Fuzzy region cuts module 705, includes for determining in above-mentioned image to be processed according to distribution characteristics obtained
Cutting removal is carried out to the fuzzy region of Cutting Edge, and to above-mentioned fuzzy region, wherein above-mentioned to Cutting Edge are as follows: above-mentioned wait locate
Image is managed on the image side of above-mentioned pixel unit direction.
In one embodiment of the present of invention, above-mentioned differential image obtains module 702, comprising:
First differential image obtaining unit is specifically used for calculating in above-mentioned first edge image along pixel unit direction
The corresponding difference value of each pixel, obtains the first differential image；
Second differential image obtaining unit is specifically used for calculating in first differential image along pixel unit direction
The corresponding difference value of each pixel, obtains the second differential image；
New differential image determination unit, specifically for second differential image to be determined as to the first new differential image,
And the second differential image obtaining unit is returned, until the calculation times of difference value reach preset times；
Differential image determination unit is determined as specifically for the second differential image that will be finally obtained by above-mentioned first edge
The differential image that the corresponding difference value of each pixel is formed in image.
In a kind of implementation of the invention, above-mentioned fuzzy region cuts module 705, comprising:
Changing value computing unit, for calculating the corresponding distribution of every two adjacent pixel unit in above-mentioned second edge image
Changing value between feature；
Fuzzy region determination unit, for according to the changing value that is calculated, determine in above-mentioned image to be processed include to
The fuzzy region of Cutting Edge；
Fuzzy region cuts unit, for carrying out cutting removal to above-mentioned fuzzy region.
In a kind of implementation of the invention, above-mentioned fuzzy region determination unit is specifically used for edge and above-mentioned pixel unit
The vertical direction of direction determines that changing value is greater than preset threshold between first distribution characteristics in above-mentioned second edge image
The first pixel unit be greater than the second pixel unit pair of above-mentioned preset threshold to changing value between, the last one distribution characteristics；
First pixel unit and first in above-mentioned image to be processed is determined as fuzzy region to the region between Cutting Edge,
And the second pixel unit and second in above-mentioned image to be processed is determined as fuzzy region to the region between Cutting Edge, wherein
Above-mentioned first pixel unit are as follows: above-mentioned first pixel unit is to one in above-mentioned image to be processed in corresponding pixel unit
Pixel unit, above-mentioned first to Cutting Edge are as follows: edge first pixel unit vertical with above-mentioned pixel unit direction direction,
Above-mentioned second pixel unit are as follows: above-mentioned second pixel unit is to one in above-mentioned image to be processed in corresponding pixel unit
Pixel unit, above-mentioned second to Cutting Edge are as follows: along the last one pixel list vertical with above-mentioned pixel unit direction direction
Member.
As it can be seen that using image cropping device provided in an embodiment of the present invention, by carrying out edge extracting to image to be processed,
The differential image for indicating above-mentioned edge image pixel point difference value is calculated again, carries out edge again to above-mentioned differential image and mentions
Second edge image is obtained, the distribution characteristics of edge pixel point in the above-mentioned each pixel unit of second edge image, root are calculated
The fuzzy region in image to be processed is determined according to above-mentioned distribution characteristics, and the fuzzy region determined is cut and is removed.With it is existing
Technology is compared, and the embodiment of the present invention enhances the mould in image to be processed by the way that image to be processed is repeatedly converted and calculated
Paste the pixel variation degree in region and non-fuzzy region, edge picture in each pixel unit of image after then being calculated
The distribution characteristics of vegetarian refreshments, distribution characteristics and preset threshold are compared, and are determined the fuzzy region in image and then are cut
Removal.As it can be seen that the accuracy rate that image obscuring area is cut to removal can be improved using the embodiment of the present invention.
The embodiment of the invention also provides a kind of electronic equipment, as shown in figure 8, include processor 801, communication interface 802,
Memory 803 and communication bus 804, wherein processor 801, communication interface 802, memory 803 are complete by communication bus 804
At mutual communication,
Memory 803, for storing computer program；
Processor 801 when for executing the program stored on memory 803, realizes figure provided in an embodiment of the present invention
As method of cutting out.
The communication bus that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect, PCI) bus or expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..The communication bus can be divided into address bus, data/address bus, control bus etc..For just
It is only indicated with a thick line in expression, figure, it is not intended that an only bus or a type of bus.
Communication interface is for the communication between above-mentioned electronic equipment and other equipment.
Memory may include random access memory (Random Access Memory, RAM), also may include non-easy
The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be storage device that at least one is located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
CPU), network processing unit (Network Processor, NP) etc.；It can also be digital signal processor (Digital Signal
Processing, DSP), it is specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
It is field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete
Door or transistor logic, discrete hardware components.
In another embodiment provided by the invention, a kind of computer readable storage medium is additionally provided, which can
It reads to be stored with computer program in storage medium, the computer program realizes any of the above-described image cropping when being executed by processor
The step of method.
In another embodiment provided by the invention, a kind of computer program product comprising instruction is additionally provided, when it
When running on computers, so that computer executes any image method of cutting out in above-described embodiment.
As it can be seen that using electronic equipment provided by the above embodiment carry out image cropping when, execute it is provided by the above embodiment
Run when the computer program stored in computer readable storage medium carries out image cropping and on computers above-mentioned implementation
Computer program product that example provides and when carrying out image cropping, by carrying out edge extracting to image to be processed, then calculate
To the differential image for indicating above-mentioned edge image pixel point difference value, carries out edge extracting again to above-mentioned differential image and obtain the
Two edge images calculate the distribution characteristics of edge pixel point in the above-mentioned each pixel unit of second edge image, according to above-mentioned point
Cloth feature determines the fuzzy region in image to be processed, and the fuzzy region determined is cut and is removed.
Electronic equipment, readable storage medium storing program for executing and computer program product provided in an embodiment of the present invention, can be quickly quasi-
Really realize image cropping method provided in an embodiment of the present invention.Compared with prior art, the embodiment of the present invention is by treating place
Reason image is repeatedly converted and is calculated, and the fuzzy region in image to be processed and the pixel variation in non-fuzzy region are enhanced
Degree, after then being calculated in each pixel unit of image edge pixel point distribution characteristics, by distribution characteristics and default
Threshold value compares, and determines the fuzzy region in image and then carries out cutting removal.It, can be with as it can be seen that using the embodiment of the present invention
Improve the accuracy rate that image obscuring area is cut to removal.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer program
Product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all or
It partly generates according to process or function described in the embodiment of the present invention.The computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage medium
In, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, the computer
Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center
User's line (DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another web-site, computer, server or
Data center is transmitted.The computer readable storage medium can be any usable medium that computer can access or
It is comprising data storage devices such as one or more usable mediums integrated server, data centers.The usable medium can be with
It is magnetic medium, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk
Solid State Disk (SSD)) etc..
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is all made of relevant mode and describes, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, electronic equipment embodiment, computer readable storage medium embodiment and computer program product embodiments, due to
It is substantially similar to embodiment of the method, so being described relatively simple, related place is referring to the part explanation of embodiment of the method
It can.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (10)
1. a kind of image cropping method, which is characterized in that the described method includes:
Edge extracting is carried out to image to be processed, obtains first edge image；
Obtain the differential image formed by the corresponding difference value of pixel each in the first edge image, wherein each picture
The corresponding difference value of vegetarian refreshments indicates: the pixel and the pixel value differences between pixel within a preset range,
The preset range are as follows: along the range of pixel unit direction；
Edge extracting is carried out to the differential image, obtains second edge image；
Obtain the distribution characteristics of edge pixel point in each pixel unit in the second edge image；
According to distribution characteristics obtained, determine to include fuzzy region to Cutting Edge in the image to be processed, and to described
Fuzzy region carries out cutting removal, wherein described to Cutting Edge are as follows: the image to be processed is in the pixel unit direction
Image side.
2. the method according to claim 1, wherein the acquisition is by each pixel in the first edge image
The differential image that the corresponding difference value of point is formed, comprising:
The corresponding difference value of each pixel along the first edge image is calculated along pixel unit direction, it is poor to obtain first
Different image；
The corresponding difference value of each pixel along first differential image is calculated along pixel unit direction, it is poor to obtain second
Different image；
It is the first new differential image with second differential image, and returns described along described in the calculating of pixel unit direction
In first differential image the step of each pixel corresponding difference value, until the calculation times of difference value reach preset times；
Using the second differential image finally obtained as by the corresponding difference value shape of pixel each in the first edge image
At differential image.
3. method according to claim 1 or 2, which is characterized in that it is described according to distribution characteristics obtained, determine described in
It include the fuzzy region to Cutting Edge in image to be processed, comprising:
Calculate the changing value in the second edge image between the corresponding distribution characteristics of every two adjacent pixel unit；
According to the changing value being calculated, determine to include fuzzy region to Cutting Edge in the image to be processed.
4. according to the method described in claim 3, it is characterized in that, the changing value that the basis is calculated, determine it is described to
It include the fuzzy region to Cutting Edge in processing image, comprising:
Along the direction vertical with the pixel unit direction, determine in the second edge image first distribution characteristics it
Between changing value be greater than the first pixel unit of preset threshold the default threshold be greater than to changing value between, the last one distribution characteristics
Second pixel unit pair of value；
First pixel unit in the image to be processed and first are determined as fuzzy region to the region between Cutting Edge, and will
Second pixel unit and second is determined as fuzzy region to the region between Cutting Edge in the image to be processed, wherein described
First pixel unit are as follows: first pixel unit is to a pixel in the image to be processed in corresponding pixel unit
Unit, described first to Cutting Edge are as follows: described along first pixel unit vertical with pixel unit direction direction
Second pixel unit are as follows: second pixel unit is to a pixel in the image to be processed in corresponding pixel unit
Unit, described second to Cutting Edge are as follows: along the last one pixel unit vertical with pixel unit direction direction.
5. method according to claim 1 or 2, which is characterized in that the pixel unit includes: pixel column and/or pixel
Column.
6. a kind of image cropping device, which is characterized in that described device includes:
First edge image obtains module, for carrying out edge extracting to image to be processed, obtains first edge image；
Differential image obtains module, is formed for obtaining by the corresponding difference value of pixel each in the first edge image
Differential image, wherein the corresponding difference value of each pixel indicates: the pixel and the pixel institute pixel within a preset range
Value differences between point, the preset range are as follows: along the range of pixel unit direction；
Second edge image obtains module, for carrying out edge extracting to the differential image, obtains second edge image；
Distribution characteristics obtains module, for obtaining the distribution of edge pixel point in each pixel unit in the second edge image
Feature；
Fuzzy region cuts module, for determining that in the image to be processed include wait cut according to distribution characteristics obtained
The fuzzy region on side, and cutting removal is carried out to the fuzzy region, wherein it is described to Cutting Edge are as follows: the image to be processed
On the image side of the pixel unit direction.
7. device according to claim 6, which is characterized in that the differential image obtains module, comprising:
First differential image obtaining unit, for calculating each pixel in the first edge image along pixel unit direction
The corresponding difference value of point, obtains the first differential image；
Second differential image obtaining unit, for calculating each pixel in first differential image along pixel unit direction
The corresponding difference value of point, obtains the second differential image；
New differential image determination unit, for second differential image to be determined as to the first new differential image, and triggers institute
The second differential image obtaining unit is stated, until the calculation times of difference value reach preset times；
Differential image determination unit, the second differential image for that will finally obtain are determined as by every in the first edge image
The differential image that the corresponding difference value of one pixel is formed.
8. device according to claim 6 or 7, which is characterized in that the fuzzy region cuts module, comprising:
Changing value computing unit, for calculating the corresponding distribution characteristics of every two adjacent pixel unit in the second edge image
Between changing value；
Fuzzy region determination unit, for determining that in the image to be processed include wait cut according to the changing value being calculated
The fuzzy region on side；
Fuzzy region cuts unit, for carrying out cutting removal to the fuzzy region.
9. device according to claim 8, which is characterized in that
The fuzzy region determination unit, described in determining along the direction vertical with the pixel unit direction
In second edge image between first distribution characteristics changing value be greater than preset threshold the first pixel unit to, the last one point
Changing value is greater than the second pixel unit pair of the preset threshold between cloth feature；
First pixel unit in the image to be processed and first are determined as fuzzy region to the region between Cutting Edge, and will
Second pixel unit and second is determined as fuzzy region to the region between Cutting Edge in the image to be processed, wherein described
First pixel unit are as follows: first pixel unit is to a pixel in the image to be processed in corresponding pixel unit
Unit, described first to Cutting Edge are as follows: described along first pixel unit vertical with pixel unit direction direction
Second pixel unit are as follows: second pixel unit is to a pixel in the image to be processed in corresponding pixel unit
Unit, described second to Cutting Edge are as follows: along the last one pixel unit vertical with pixel unit direction direction.
10. a kind of electronic equipment, which is characterized in that including processor, communication interface, memory and communication bus, wherein processing
Device, communication interface, memory complete mutual communication by communication bus；
Memory, for storing computer program；
Processor when for executing the program stored on memory, realizes any method and step of claim 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910585564.9A CN110298858B (en) | 2019-07-01 | 2019-07-01 | Image clipping method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910585564.9A CN110298858B (en) | 2019-07-01 | 2019-07-01 | Image clipping method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110298858A true CN110298858A (en) | 2019-10-01 |
| CN110298858B CN110298858B (en) | 2021-06-22 |
Family
ID=68029690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910585564.9A Active CN110298858B (en) | 2019-07-01 | 2019-07-01 | Image clipping method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298858B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929675A (en) * | 2019-12-03 | 2020-03-27 | 广州酷狗计算机科技有限公司 | Image processing method, image processing device, computer equipment and computer readable storage medium |
| CN111405314A (en) * | 2020-03-09 | 2020-07-10 | 腾讯科技（深圳）有限公司 | Information processing method, device, equipment and storage medium |
| CN111754487A (en) * | 2020-06-24 | 2020-10-09 | 北京奇艺世纪科技有限公司 | Black frame area clipping method and device and electronic equipment |
| CN113628229A (en) * | 2021-08-04 | 2021-11-09 | 展讯通信（上海）有限公司 | Image cropping method and related product |
| CN116542987A (en) * | 2023-04-19 | 2023-08-04 | 翼存(上海)智能科技有限公司 | Image clipping method and device, electronic equipment and storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102306377A (en) * | 2011-09-21 | 2012-01-04 | 深圳市理邦精密仪器股份有限公司 | Method and device for reducing noise in ultrasound image |
| US8094958B2 (en) * | 2006-11-09 | 2012-01-10 | Electronics And Telecommunications Research Institute | Apparatus and method for sharpening blurred enlarged image |
| CN103530878A (en) * | 2013-10-12 | 2014-01-22 | 北京工业大学 | Edge extraction method based on fusion strategy |
| US20140193094A1 (en) * | 2013-01-10 | 2014-07-10 | Broadcom Corporation | Edge smoothing block filtering and blending |
| CN104778669A (en) * | 2015-04-16 | 2015-07-15 | 北京邮电大学 | Fast image denoising method and device |
| CN104794696A (en) * | 2015-05-04 | 2015-07-22 | 长沙金定信息技术有限公司 | Image motion blur removing method and device |
| CN105374047A (en) * | 2015-12-15 | 2016-03-02 | 西安电子科技大学 | Improved bilateral filtering and clustered SAR based image change detection method |
| CN106127729A (en) * | 2016-06-08 | 2016-11-16 | 浙江传媒学院 | A kind of picture noise level estimation method based on gradient |
| CN107563977A (en) * | 2017-08-28 | 2018-01-09 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
| KR20180034027A (en) * | 2016-09-27 | 2018-04-04 | 청주대학교 산학협력단 | Apparatus for detecting edge with image blur |
| WO2018070844A1 (en) * | 2016-10-13 | 2018-04-19 | 경북대학교 산학협력단 | Method for setting edge blur for edge modeling |
| CN108846818A (en) * | 2018-06-25 | 2018-11-20 | Oppo（重庆）智能科技有限公司 | Remove method, apparatus, terminal and the computer readable storage medium of moire fringes |
| CN109035158A (en) * | 2018-06-25 | 2018-12-18 | 东软集团股份有限公司 | Image fuzzy processing method, device, storage medium and electronic equipment |
| CN109523469A (en) * | 2018-11-16 | 2019-03-26 | 深圳朗田亩半导体科技有限公司 | Image-scaling method and device |
| CN109934785A (en) * | 2019-03-12 | 2019-06-25 | 湖南国科微电子股份有限公司 | Image sharpening method and device |
-
2019
- 2019-07-01 CN CN201910585564.9A patent/CN110298858B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8094958B2 (en) * | 2006-11-09 | 2012-01-10 | Electronics And Telecommunications Research Institute | Apparatus and method for sharpening blurred enlarged image |
| CN102306377A (en) * | 2011-09-21 | 2012-01-04 | 深圳市理邦精密仪器股份有限公司 | Method and device for reducing noise in ultrasound image |
| US20140193094A1 (en) * | 2013-01-10 | 2014-07-10 | Broadcom Corporation | Edge smoothing block filtering and blending |
| CN103530878A (en) * | 2013-10-12 | 2014-01-22 | 北京工业大学 | Edge extraction method based on fusion strategy |
| CN104778669A (en) * | 2015-04-16 | 2015-07-15 | 北京邮电大学 | Fast image denoising method and device |
| CN104794696A (en) * | 2015-05-04 | 2015-07-22 | 长沙金定信息技术有限公司 | Image motion blur removing method and device |
| CN105374047A (en) * | 2015-12-15 | 2016-03-02 | 西安电子科技大学 | Improved bilateral filtering and clustered SAR based image change detection method |
| CN106127729A (en) * | 2016-06-08 | 2016-11-16 | 浙江传媒学院 | A kind of picture noise level estimation method based on gradient |
| KR20180034027A (en) * | 2016-09-27 | 2018-04-04 | 청주대학교 산학협력단 | Apparatus for detecting edge with image blur |
| WO2018070844A1 (en) * | 2016-10-13 | 2018-04-19 | 경북대학교 산학협력단 | Method for setting edge blur for edge modeling |
| CN107563977A (en) * | 2017-08-28 | 2018-01-09 | 维沃移动通信有限公司 | A kind of image processing method, mobile terminal and computer-readable recording medium |
| CN108846818A (en) * | 2018-06-25 | 2018-11-20 | Oppo（重庆）智能科技有限公司 | Remove method, apparatus, terminal and the computer readable storage medium of moire fringes |
| CN109035158A (en) * | 2018-06-25 | 2018-12-18 | 东软集团股份有限公司 | Image fuzzy processing method, device, storage medium and electronic equipment |
| CN109523469A (en) * | 2018-11-16 | 2019-03-26 | 深圳朗田亩半导体科技有限公司 | Image-scaling method and device |
| CN109934785A (en) * | 2019-03-12 | 2019-06-25 | 湖南国科微电子股份有限公司 | Image sharpening method and device |
Non-Patent Citations (3)
| Title |
|---|
| SOUMYADEEP BHATTACHARJEE 等: "Automated Threshold Driven Edge Detection Using 2-way Difference Calculation and Neighborhood Comparison", 《2015 INTERNATIONAL CONFERENCE ON SOFT COMPUTING TECHNIQUES AND IMPLEMENTATIONS- (ICSCTI)》 * |
| 严洪悦: "高动态图像运动去模糊还原方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 苗璐 等: "基于梯度方向的非局部均值图像去噪算法", 《中北大学学报（自然科学版）》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110929675A (en) * | 2019-12-03 | 2020-03-27 | 广州酷狗计算机科技有限公司 | Image processing method, image processing device, computer equipment and computer readable storage medium |
| CN110929675B (en) * | 2019-12-03 | 2024-03-01 | 广州酷狗计算机科技有限公司 | Image processing method, device, computer equipment and computer readable storage medium |
| CN111405314A (en) * | 2020-03-09 | 2020-07-10 | 腾讯科技（深圳）有限公司 | Information processing method, device, equipment and storage medium |
| CN111754487A (en) * | 2020-06-24 | 2020-10-09 | 北京奇艺世纪科技有限公司 | Black frame area clipping method and device and electronic equipment |
| CN111754487B (en) * | 2020-06-24 | 2023-07-25 | 北京奇艺世纪科技有限公司 | Black frame region cutting method and device and electronic equipment |
| CN113628229A (en) * | 2021-08-04 | 2021-11-09 | 展讯通信（上海）有限公司 | Image cropping method and related product |
| CN116542987A (en) * | 2023-04-19 | 2023-08-04 | 翼存(上海)智能科技有限公司 | Image clipping method and device, electronic equipment and storage medium |
| CN116542987B (en) * | 2023-04-19 | 2024-06-04 | 翼存(上海)智能科技有限公司 | Image clipping method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110298858B (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298858A (en) | A kind of image cropping method and device | |
| CN111340752A (en) | Screen detection method and device, electronic equipment and computer readable storage medium | |
| CN108596944B (en) | Method and device for extracting moving target and terminal equipment | |
| US20130016884A1 (en) | Methods, apparatuses, and computer program products for identifying a region of interest within a mammogram image | |
| EP3640804B1 (en) | Screen recording preparation method for evaluating software usability, computing system, computer program and computer-readable storage medium implementing the method | |
| CN110598622A (en) | Video subtitle positioning method, electronic device, and computer storage medium | |
| CN117011250A (en) | Defect detection method, device and storage medium | |
| CN113033346A (en) | Text detection method and device and electronic equipment | |
| KR20180117619A (en) | Object management and visualization using computing devices | |
| RU2592457C2 (en) | Apparatus for identifying area of moving image and method | |
| Kim et al. | A texture-aware salient edge model for image retargeting | |
| CN111814628A (en) | Display cabinet identification method, device, equipment and storage medium | |
| JP2012094068A (en) | Information processing apparatus, processing method thereof and program | |
| US9875528B2 (en) | Multi-frame patch correspondence identification in video | |
| CN110287361A (en) | A kind of personage's picture screening technique and device | |
| CN104318236B (en) | A kind of method and system for obtaining image local feature | |
| CN111444834A (en) | Image text line detection method, device, equipment and storage medium | |
| Bhattacharjee et al. | Automatic detection and classification of damage zone (s) for incorporating in digital image correlation technique | |
| CN113807410B (en) | Image recognition method and device and electronic equipment | |
| CN115829929A (en) | Method, device and equipment for detecting defects of product surface image and storage medium | |
| CN113221742B (en) | Video split screen line determining method, device, electronic equipment, medium and program product | |
| CN113313642A (en) | Image denoising method and device, storage medium and electronic equipment | |
| CN114092925A (en) | Video subtitle detection method and device, terminal equipment and storage medium | |
| Li et al. | Fast Image Segmentation Based on Efficient Implementation of the Chan‐Vese Model with Discrete Gray Level Sets | |
| CN111160358A (en) | Image binarization method, device, equipment and medium |
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 |