CN109741394A - Image processing method, device, electronic equipment and storage medium - Google Patents
Image processing method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109741394A CN109741394A CN201811506464.4A CN201811506464A CN109741394A CN 109741394 A CN109741394 A CN 109741394A CN 201811506464 A CN201811506464 A CN 201811506464A CN 109741394 A CN109741394 A CN 109741394A
- Authority
- CN
- China
- Prior art keywords
- tangent line
- image
- boundary
- pixel point
- boundary pixel
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 238000006243 chemical reaction Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 43
- 238000000034 method Methods 0.000 claims description 32
- 230000008859 change Effects 0.000 claims description 3
- 241000239290 Araneae Species 0.000 claims description 2
- 230000006854 communication Effects 0.000 description 19
- 238000004891 communication Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000000977 initiatory effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the present disclosure provides a kind of image processing method, device, electronic equipment and storage medium.Image processing method includes: to obtain the image to be processed containing non-blank-white image-region；Binary conversion treatment is executed to the image to be processed, obtains binary image；Since a vertex pixel of the binary image, the binary image is traversed along orthogonal two image boundaries respectively, the multiple summits tangent line tangent with the profile of the non-blank-white image-region is obtained, on the side tangent line include at least one black pixel point and one side only includes white pixel point；According to the multiple summits tangent line of acquisition, at least one boundary rectangle is obtained；The smallest boundary rectangle of area in multiple boundary rectangles is chosen for the minimum circumscribed rectangle region of the non-blank-white image-region.The minimum circumscribed rectangle of image can relatively easily be calculated, and reduce the computation complexity of minimum circumscribed rectangle.
Description
Technical field
The embodiment of the present disclosure is related to technical field of information processing more particularly to a kind of image processing method, device, electronics are set
Standby and storage medium.
Background technique
Minimum circumscribed rectangle is an important technology during graphics standard.As shown in Figure 1, carrying out two to original image a
Value processing, obtains binary picture b；Hereafter, binary picture b is analyzed, obtains minimum circumscribed rectangle c；Finally, according to most
Small boundary rectangle c carries out necessary direction to original image a or angle adjusts, obtains the standardization figure d of original image a.
The mathematic(al) treatment of minimum circumscribed rectangle is: providing a plane point set S, the smallest rectangle of area is asked to make its packet
Containing all points of S.
Currently, usually being solved by way of the convex closure of Calculation Plane point set to minimum circumscribed rectangle.Wherein,
Gift-Wrapping and Graham-Scan algorithm is two kinds of widely used methods for calculating convex closure.
For example, being first focused to find out a particular point in point, such as there is minimum y-coordinate and x coordinate point as small as possible, and will
It is as first vertex for calculating convex closure.After starting point has been determined, point set is calculated by following Gift-Wrapping algorithm
Convex closure:
1) it concentrates all the points all to regard fixed pillar in the plane as, imagines that we fasten on starting point pillar
A piece body；
2) rope is straightened to the right in the horizontal direction, and rotated counterclockwise, when rope runs into a pillar, then corresponded to convex
A bit wrapped；
3) continue to rotate rope, the vertex on a convex closure is determined every time, until rope returns to starting point.
Wherein, next convex closure vertex is found by rotating rope every time to need to all left points being concentrated to carry out once
Compare, so the time complexity of this step is O (n), n is the points of figure.Vertex on each convex closure requires carry out one
Secondary rotation process, and in the worst cases, convex closure number of vertices can be equal with point set number, so entire Gift-
The time complexity of Wrapping algorithm is O (n2).In the case where n representative of graphics side length, Gift-Wrapping algorithm
Time complexity is O (n2 log n2), i.e. O (n2 log n)。
In addition, using the function RotatedRect minAreaRect (InputArray in OpenCV3.4.3
Points) come when calculating minimum circumscribed rectangle, time-consuming is in 300ms or so.When graphic processing data is larger, time loss
As a big problem.
Summary of the invention
The embodiment of the present disclosure provides a kind of image processing techniques scheme, for quickly and accurately determining the minimum of figure
Boundary rectangle.
According to one aspect of the disclosure, a kind of image processing method is provided, comprising:
Obtain the image to be processed containing non-blank-white image-region；
Binary conversion treatment is executed to the image to be processed, obtains binary image；
Since a vertex pixel of the binary image, traversed respectively along orthogonal two image boundaries
The binary image obtains the multiple summits tangent line tangent with the profile of the non-blank-white image-region, wraps on the side tangent line
Containing at least one black pixel point and one side only includes white pixel point；
According to the multiple summits tangent line of acquisition, at least one boundary rectangle is obtained；
The minimum that the smallest boundary rectangle of area in multiple boundary rectangles is chosen for the non-blank-white image-region is outer
Connect rectangular area.
Optionally, described since a vertex pixel of the binary image, respectively along orthogonal two
Image boundary traverses the binary image, obtains the multiple summits tangent line tangent with the profile of the non-blank-white image-region, packet
It includes:
Since any vertex pixel of the binary image, carried out respectively along orthogonal two image boundaries
It is mobile to search, it include black by this until the line between two boundary pixel points being moved to includes black pixel point
For the line of pixel as initial edge tangent line, corresponding two boundary pixel points of the initial edge tangent line are respectively initial first side
Boundary's pixel and initial the second boundary pixel；
The mobile clockwise of traversal, institute are determined relative to the position of non-blank-white image-region according to the initial edge tangent line
It is one of clockwise and counterclockwise for stating clockwise；
Using the initial edge tangent line, initial first boundary pixel point and initial the second boundary pixel as working as front
Tangent line, current first boundary pixel point and current the second boundary pixel iteratively execute following processing, obtain at least one
A subsequent side tangent line:
Current first boundary pixel point is moved along the image boundary that it is currently located to determining clockwise, and
And determine that current first boundary pixel point after movement and the line between current the second boundary pixel whether include black picture
Vegetarian refreshments；
If it is determined that the line between current first boundary pixel point and current the second boundary pixel after mobile does not wrap
Containing black pixel point, then the image boundary that is currently located the current the second boundary pixel along it is to determining clockwise
It is mobile, and determine that the line between current first boundary pixel point and current the second boundary pixel after movement whether includes
Black pixel point；
The processing of mobile current first boundary pixel point and the current the second boundary pixel is alternately executed, directly
The line between current first boundary pixel point and current the second boundary pixel after to determining movement includes black pixel point
Until；
The line comprising black pixel point is determined as next subsequent side tangent line；
If next subsequent side tangent line is overlapped with the initial edge tangent line, stop the iteration, otherwise by institute
It states when front tangent line, current first boundary pixel point and current the second boundary pixel are respectively set to next subsequent side
Tangent line, corresponding first boundary pixel point of the next subsequent side tangent line and the second boundary pixel, continue to execute next time
Iterative processing.
Optionally, the multiple summits tangent line according to acquisition, obtains at least one boundary rectangle, comprising:
In the multiple summits tangent line, it is more than or equal to 0 ° with the angle of the initial edge tangent line and is less than or equal to 90 °
Any first side tangent line, obtain with described first while tangent line it is parallel second while tangent line and vertical with first side tangent line
Third in tangent line and the 4th tangent line, any described first while tangent line and by its obtain corresponding second while tangent line, third
In tangent line and the 4th, tangent line constitutes at least one described boundary rectangle.
Optionally, the acquisition with described first while tangent line it is parallel second while tangent line and with first side tangent line it is vertical
Straight third tangent line in tangent line and the 4th, comprising:
By binary search method, is searched in the multiple summits tangent line and obtain second parallel with first side tangent line
The tangent line when tangent line and tangent line is vertical when with described first third are in tangent line and the 4th.
Optionally, the method also includes:
The image to be processed is standardized according to the minimum circumscribed rectangle.
According to another aspect of the present disclosure, a kind of image processing apparatus is provided, comprising:
Image collection module, for obtaining the image to be processed containing non-blank-white image-region；
Binary processing module executes binary conversion treatment for obtaining the image to be processed that module obtains to described image,
Obtain binary image；
Image traversal module, for since a vertex pixel of the binary image, edge to be mutually perpendicular to respectively
Two image boundaries traverse the binary image, obtain the multiple summits tangent with the profile of the non-blank-white image-region and cut
Line, comprising at least one black pixel point and one side only includes white pixel point on the side tangent line；
Boundary rectangle constructs module and obtains at least one boundary rectangle for the multiple summits tangent line according to acquisition；
Minimum circumscribed rectangle chooses module, for the smallest boundary rectangle of area in multiple boundary rectangles to be chosen for institute
State the minimum circumscribed rectangle region of non-blank-white image-region.
Optionally, described image spider module includes:
Initial edge tangent line determination unit, for since any vertex pixel of the binary image, respectively along phase
Mutually two vertical image boundaries carry out mobile lookup, until the line between two boundary pixel points being moved to includes black
Until pixel, using this include black pixel point line as initial edge tangent line, corresponding two sides of the initial edge tangent line
Boundary's pixel is respectively initial first boundary pixel point and initial the second boundary pixel；
Traversal direction determination unit is determined for the position according to the initial edge tangent line relative to non-blank-white image-region
Mobile clockwise is traversed, the clockwise is one of clockwise and counterclockwise；
Unit is iterated over, is used for the initial edge tangent line, initial first boundary pixel point and initial the second boundary picture
Vegetarian refreshments is iteratively executed respectively as front tangent line, current first boundary pixel point and current the second boundary pixel is worked as
It handles below, obtains at least one subsequent side tangent line:
Current first boundary pixel point is moved along the image boundary that it is currently located to determining clockwise, and
And determine that current first boundary pixel point after movement and the line between current the second boundary pixel whether include black picture
Vegetarian refreshments；
If it is determined that the line between current first boundary pixel point and current the second boundary pixel after mobile does not wrap
Containing black pixel point, then the image boundary that is currently located the current the second boundary pixel along it is to determining clockwise
It is mobile, and determine that the line between current first boundary pixel point and current the second boundary pixel after movement whether includes
Black pixel point；
The processing of mobile current first boundary pixel point and the current the second boundary pixel is alternately executed, directly
The line between current first boundary pixel point and current the second boundary pixel after to determining movement includes black pixel point
Until；
The line comprising black pixel point is determined as next subsequent side tangent line；
If next subsequent side tangent line is overlapped with the initial edge tangent line, stop the iteration, otherwise by institute
It states when front tangent line, current first boundary pixel point and current the second boundary pixel are respectively set to next subsequent side
Tangent line, corresponding first boundary pixel point of the next subsequent side tangent line and the second boundary pixel, continue to execute next time
Iterative processing.
Optionally, the boundary rectangle building module is used for: in the multiple summits tangent line, being cut with the initial edge
The angle of line is more than or equal to 0 ° and is less than or equal to 90 ° of any first side tangent line, obtains parallel with first side tangent line the
Two when tangent line and tangent line is vertical when with described first third are in tangent line and the 4th tangent line, any first side tangent line with
And at least one described boundary rectangle is constituted by its acquisition corresponding second tangent line and the 4th side tangent line in tangent line, third.
According to another aspect of the present disclosure, a kind of electronic equipment is provided, comprising: processor and memory；
The memory appoints the processor execution for storing at least one executable instruction, the executable instruction
The step of one aforementioned image processing method.
According to another aspect of the present disclosure, a kind of computer readable storage medium, the computer-readable storage medium are provided
The step of matter is stored with executable instruction, and the executable instruction makes the processor execute any aforementioned image processing method.
By the image procossing scheme of the embodiment of the present disclosure, the external square of minimum of image can relatively easily be calculated
Shape, and reduce the computation complexity of minimum circumscribed rectangle.Specifically, the image for being n for the number of side length pixel, entirely
The computation complexity of method is O (n2)+O (n log n)=O (n2).For this image big for pixel quantity, when calculating
Between reduction it is more significant.
Detailed description of the invention
Fig. 1 is the schematic diagram for showing graphics standardization processing；
Fig. 2 is the flow chart for showing the image processing method according to some embodiments of the disclosure；
Fig. 3 is the flow chart for showing the exemplary process of the step S230 in Fig. 2；
Fig. 4 is the flow chart for showing the exemplary process of the step S240 in Fig. 2；
Fig. 5 schematically illustrates two side tangent lines of the binary image b in Fig. 1；
Fig. 6 schematically illustrates two boundary rectangles of the binary image b in Fig. 1；
Fig. 7 is the logic diagram for showing the image processing apparatus 700 according to some embodiments of the disclosure；
Fig. 8 is the logic diagram for showing the exemplary structure of the image traversal module 730 in Fig. 7；
Fig. 9 is the structural schematic diagram for showing the electronic equipment according to some embodiments of the disclosure.
Specific embodiment
(identical label indicates identical element in several attached drawings) and embodiment with reference to the accompanying drawing, implement the disclosure
The specific embodiment of example is described in further detail.Following embodiment is not limited to the disclosure for illustrating the disclosure
Range.
It will be understood by those skilled in the art that the terms such as " first ", " second " in the embodiment of the present disclosure are only used for distinguishing
Different step, equipment or module etc., neither represent any particular technology meaning, also do not indicate that the inevitable logic between them is suitable
Sequence.
Fig. 2 is the flow chart for showing the image processing method according to some embodiments of the disclosure.
The image to be processed containing non-blank-white image-region is obtained in step S210 referring to Fig. 2.
Here, image to be processed should be non-empty white image, that is, contain non-blank-white image-region.The non-blank-white image-region can
Including subject, such as personage, animal, building, scenery etc. that one or more connects or do not connect, it is also possible to not have
The image-region that the point set of semantic meaning is constituted.
In step S220, binary conversion treatment is executed to the image to be processed, obtains binary image.
Specifically, 0 or 255 are set by the gray value of the pixel in image to be processed, makes the entire image to be processed be in
Reveal apparent black and white effect, so that the profile of target is highlighted, binary image b as shown in figure 1.Wherein, pixel value is 0
Point is rendered as black, usually indicates the foreground pixel point in image to be processed；The point that pixel value is 255 is rendered as white, usually
Indicate the background pixel point in image to be processed.
In step S230, since any vertex pixel of the binary image, respectively along orthogonal two
Image boundary traverses the binary image, obtains the multiple summits tangent line tangent with the profile of the non-blank-white image-region, institute
Stating on the tangent line of side includes at least one black pixel point and one side only includes white pixel point.
Usual any image to be processed exists with rectangular shape, therefore its binary image is also rectangular shape.Square
For the binary image tool of shape there are four vertex pixel, this four vertex pixels are inevitable on the boundary of non-blank-white image-region
Or except non-blank-white image-region.It therefore, can be since any one vertex pixel, respectively to mutually vertical in the step
Two straight image boundaries traverse binary image, search from periphery tangent with the circumference of non-blank-white image-region
Multiple summits tangent line.Each edge tangent line has two boundary pixel points intersected with the boundary of image to be processed.Each edge tangent line
Upper includes at least one black pixel point, i.e., it passes through at least one black pixel point, and in the side of side tangent line (outside)
All pixels point be white pixel point.Fig. 5 schematically illustrates two side tangent line L1 of the binary image b in Fig. 1
And L2.
By the processing of step S230, it can be searched from the periphery of non-blank-white image-region and obtain binary image/to be processed
The whole side tangent lines tangent with the circumference of non-blank-white image-region in image.
Hereafter, at least one boundary rectangle is obtained according to the multiple summits tangent line of acquisition in step S240.
Specifically, the four edges tangent line that in multiple summits tangent line, can constitute rectangle can be denoted as a boundary rectangle, by
This can get one or more boundary rectangles.Four edges due to constituting the rectangle are side tangent line, and what is obtained is outer
Connect rectangle.Fig. 6 schematically illustrates two boundary rectangles of the binary image b in Fig. 1, respectively with solid line and dotted line mark
It outpours.
In step S250, the smallest boundary rectangle of area in multiple boundary rectangles is chosen for the non-blank-white image district
The minimum circumscribed rectangle region in domain.
For example, being marked in two boundary rectangles and other boundary rectangle (not shown) that are shown in FIG. 6 with dotted line
Boundary rectangle area it is minimum, thus be chosen for the minimum circumscribed rectangle area of (the non-blank-white image-region) of image to be processed
Domain.
After obtaining aforementioned minimum circumscribed rectangle region, corresponding processing can be executed to the image to be processed.For example, according to
The minimum circumscribed rectangle is standardized image to be processed, alternatively, going out from image cut to be processed external with the minimum
Corresponding image-region of rectangle etc..
Fig. 3 is the flow chart for showing the exemplary process of the step S230 in Fig. 2.
Referring to Fig. 3, in step S310, since any vertex pixel of the binary image, respectively along mutually vertical
Two straight image boundaries carry out mobile lookup, until the line between two boundary pixel points being moved to includes black picture element
Until point, using this include black pixel point line as initial edge tangent line, the corresponding two boundary pictures of the initial edge tangent line
Vegetarian refreshments is respectively initial first boundary pixel point and initial the second boundary pixel.
Specifically, since any one vertex pixel of image/binary image to be processed, to orthogonal two
Image boundary carries out mobile traversal.During traversal, the line between determining two boundary pixel points being moved to is whether
Include one or more black pixel points；If it is determined that the line between two boundary pixel points being moved to includes one or more
A black pixel point then can determine to have obtained a line tangent line.At this point, including the line of black pixel point as initial edge using this
Tangent line, using corresponding two boundary pixel points of the initial edge tangent line as initial first boundary pixel point and initial second
Boundary pixel point.If the line between two boundary pixel points being moved to does not include black pixel point, by currently moving
To two boundary pixel points continue to be moved along image boundary, the line between two boundary pixel points being moved to
Until black pixel point.
For example, the boundary picture being moved to can be determined by the vertex pixel of selection to the mobile pixel of horizontal direction
It whether include black pixel point between vegetarian refreshments and vertex pixel, if it is determined that include black pixel point, it is determined that obtain initial
Side tangent line.If not including black pixel point, the side that will be moved between the boundary pixel point being moved to and vertex pixel
Boundary's pixel continues to move, or vertex pixel is further continued for judging whether to the mobile pixel of vertical direction
Obtain initial edge tangent line.It is made iteratively traversal as a result, to search, obtains initial edge tangent line.
For another example may be selected to be traversed line by line from left upper apex pixel, i.e., one-row pixels are first traversed from left to right
Point, it is determined whether find initial edge tangent line；It is if it is not found, then to next line, then from left to right traverse next line pixel,
It continues to determine whether to find initial edge tangent line.It so is made iteratively traversal, to determine initial edge tangent line.Following codes, which are shown, to be sought
Look for the exemplary process of initial edge tangent line:
As can be seen that handling the side tangent line that the initial edge tangent line obtained is horizontal direction according to aforementioned exemplary.Similarly,
If being scanned, traversing by column, the initial edge tangent line of vertical direction can also be obtained.Determine horizontal direction or vertical direction just
Initial line tangent line is more convenient in the exemplary process of subsequent step S240.
Here, any of both of the aforesaid boundary pixel point can be selected as to initial first boundary pixel point, another choosing
For initial the second boundary pixel.It should be noted that any " the first boundary pixel point " (such as initial first mentioned in this article
Boundary pixel point and current first boundary pixel point mentioned below) it is persistently to be moved by fixed point pixel along an image boundary
Dynamic obtained boundary pixel point；Similarly, any " the second boundary pixel " (such as initial the second boundary pixel mentioned in this article
With current the second boundary pixel mentioned below) persistently move to obtain along another image boundary by fixed point pixel
Boundary pixel point.
Hereafter, the image initial first boundary pixel point and initial the second boundary pixel being respectively currently located along it
Boundary persistently carries out mobile traversal, obtains subsequent multiple summits tangent line to calculate, hereon referred to as subsequent side tangent line.
Due to needing both to carry out mobile traversal to initial first boundary pixel point and initial the second boundary pixel, because
This is involved in the problems, such as traversal direction, to ensure to carry out traversal lookup from the periphery of non-blank-white image-region.
Correspondingly, in step S320, determine that traversal is moved relative to the position of non-blank-white image-region according to initial edge tangent line
Dynamic clockwise.
Specifically, it is assumed that using initial first boundary pixel point as the boundary pixel point for initiating traversal, if initial edge is cut
Line is in the top of non-blank-white image-region and initial first boundary pixel point in the left side of initial the second boundary pixel, then
The mobile clockwise of traversal is determined as clockwise；If initial edge tangent line is in the top of non-blank-white image-region simultaneously
And the mobile clockwise of traversal is then determined as inverse by initial first boundary pixel point on the right side of initial the second boundary pixel
Clockwise.Similarly, if initial edge tangent line is in the lower section of non-blank-white image-region and initial first boundary pixel point
In the left side of initial the second boundary pixel, then the mobile clockwise of traversal is determined as counterclockwise；If initial edge
Tangent line is in the lower section of non-blank-white image-region and initial first boundary pixel point is on the right side of initial the second boundary pixel,
Then the mobile clockwise of traversal is determined as clockwise.
Similar rule is suitable for the situation using initial the second boundary pixel as the boundary pixel point for initiating traversal.
For the situation of the boundary pixel point traversed below using initial first boundary pixel point as initiation, iteration is described
Ground carries out traversal processing to obtain the processing of subsequent side tangent line.
Hereafter, in step S330, by the initial edge tangent line, initial first boundary pixel point and initial the second boundary pixel
Point respectively as work as front tangent line, current first boundary pixel point and current the second boundary pixel, iteratively execute with
The traversal processing of lower step S331~S336 obtains at least one subsequent side tangent line.
Firstly, in step S331, the image boundary that current first boundary pixel point is currently located along it is in step
The clockwise that rapid S320 is determined is mobile.
The company between current first boundary pixel point and current the second boundary pixel in step S332, after determining movement
Line whether includes black pixel point.
If in step S332, between current first boundary pixel point and current the second boundary pixel after determining movement
Line include black pixel point, then the line constitutes next subsequent side tangent line (step S333).
On the other hand, current first boundary pixel point and current the second boundary if in step S332, after determining movement
Line between pixel does not include black pixel point, illustrates that current first boundary pixel point has been moved to far from non-empty white image
The position in region, then the image boundary being currently located the current the second boundary pixel along it is to determining in step S320
Clockwise is mobile (step S334), then executes step S335.The processing of step S335 is similar with the processing of step S332.
If in step S335, between current first boundary pixel point and current the second boundary pixel after determining movement
Line include black pixel point, then the line constitutes next subsequent side tangent line (step S333)；If in step S335,
The line between current first boundary pixel point and current the second boundary pixel after determining movement does not include black pixel point,
S331 is then returned to step, the movement of current first boundary pixel point is continued.
Hour hands by being alternately determined to current first boundary pixel point and current the second boundary pixel as a result,
The movement in direction, and determine that the line between current first boundary pixel point and current the second boundary pixel after movement has
The no processing comprising black pixel point can get next subsequent side tangent line.
Hereafter, after determining next subsequent side tangent line (step S333), step S336 is executed.In step S336, determine
Whether next subsequent side tangent line is overlapped with initial edge tangent line.
For example, if corresponding first boundary pixel point of next subsequent side tangent line and initial first boundary pixel point weight
Close, then can determine that next subsequent side tangent line is overlapped with initial edge tangent line, otherwise determine next subsequent side tangent line with it is first
Initial line tangent line is not overlapped.
For another example if on any pixel point (such as black pixel point) on next subsequent side tangent line and initial edge tangent line
Pixel it is identical in position, then can determine that next subsequent side tangent line is overlapped with initial edge tangent line, otherwise determine under this
One subsequent side tangent line is not overlapped with initial edge tangent line
If step S336, determine that next subsequent side tangent line is overlapped with the initial edge tangent line, then stops described changing
Generation processing, completes the processing of step S330.
If step S336, determine that next subsequent side tangent line is not overlapped with the initial edge tangent line, then in step
S337, by it is described when front tangent line, current first boundary pixel point and current the second boundary pixel be respectively set to it is described under
One it is subsequent in tangent line, it is described next subsequent while corresponding first boundary pixel point of tangent line and the second boundary pixel.Then,
Return to step the processing of S331 and subsequent step.
As a result, since any one vertex pixel, alternately to orthogonal two image boundaries to binary picture
As being traversed, searches and obtain and tangent a plurality of of the circumference of non-blank-white image-region from the periphery of non-blank-white image-region
Side tangent line, these side tangent lines become the boundary rectangle of non-blank-white image-region for subsequent combination.
Fig. 4 is the flow chart for showing the exemplary process of the step S240 in Fig. 2.
Referring to Fig. 4, in step S410, in multiple summits tangent line, chooses and be more than or equal to 0 ° with the angle of initial edge tangent line
And the first side tangent line less than or equal to 90 °.
That is, obtaining the side tangent line with the angle of initial edge tangent line in [0 °, 90 °] range.
Hereafter, for the first side tangent line of any selection, the processing of step S420~S430 is carried out.
In step S420, obtain with this first while tangent line it is parallel second while tangent line and vertical with first side tangent line
Third in tangent line and the 4th tangent line.
It specifically, is θ for angle1The first side tangent line, can by binary search method search angle be respectively θ2、θ3With
θ4The second side tangent line θ2, third side tangent line θ3With the 4th side tangent line θ4:
θ2=(θ1+ 180) %360
θ3=(θ1+ 90) %360
θ4=(θ1+ 270) %360
In step S430, first while tangent line and when by it obtaining corresponding second tangent line, third in tangent line and the 4th
Tangent line constitutes corresponding boundary rectangle.
By the processing of abovementioned steps S410~S430, multiple boundary rectangles of image to be processed are got.
Here, if as detailed above, initial edge tangent line is determined as to the side tangent line of such as horizontal direction, then each side tangent line
Angle with initial edge tangent line is only angle of each side tangent line relative to horizontal coordinate, and it is more easy to calculate.
By the image processing method of the embodiment of the present disclosure, the external square of minimum of image can relatively easily be calculated
Shape, and reduce the computation complexity of minimum circumscribed rectangle.Specifically, the image for being n for the number of side length pixel, operation
The computation complexity for measuring larger step S230 is O (n2), the computation complexity of step S240 is O (n log n), entire method
Computation complexity be O (n2)+O (n log n)=O (n2).For this image big for pixel quantity, the time is calculated
It reduces more significant.For example, the time-consuming according to the image processing method of the disclosure is to pass for the image of a width 1000x1000
The 1/log (1000) for calculation method of uniting, log (1000) are approximately equal to 10, that is, time-consuming is about the 1/10 of conventional method, significantly
Ground, which reduces, calculates the time.
Fig. 7 is the logic diagram for showing the image processing apparatus according to some embodiments of the disclosure.The image processing apparatus
It can be used for executing aforementioned any image processing method.
Referring to Fig. 7, the image processing apparatus 700 according to some embodiments of the disclosure includes:
Image collection module 710, for obtaining the image to be processed containing non-blank-white image-region；
Binary processing module 720, the image to be processed for obtaining to image collection module 710 execute at binaryzation
Reason obtains binary image；
Image traversal module 730, for hanging down respectively along mutual since a vertex pixel of the binary image
Two straight image boundaries traverse the binary image, obtain the multiple summits tangent with the profile of the non-blank-white image-region
Tangent line, comprising at least one black pixel point and one side only includes white pixel point on the side tangent line；
Boundary rectangle constructs module 740 and obtains at least one boundary rectangle for the multiple summits tangent line according to acquisition；
Minimum circumscribed rectangle chooses module 750, for choosing the smallest boundary rectangle of area in multiple boundary rectangles
For the minimum circumscribed rectangle region of the non-blank-white image-region.
Fig. 8 is the logic diagram for showing the exemplary structure of the image traversal module 730 in Fig. 7.
Referring to Fig. 8, image traversal module 730 includes:
Initial edge tangent line determination unit 731, for since any vertex pixel of the binary image, edge respectively
Orthogonal two image boundaries carry out mobile lookup, until the line between two boundary pixel points being moved to includes black
Until colour vegetarian refreshments, using the line comprising black pixel point as initial edge tangent line, the initial edge tangent line is two corresponding
Boundary pixel point is respectively initial first boundary pixel point and initial the second boundary pixel；
Traversal direction determination unit 732, for the position according to the initial edge tangent line relative to non-blank-white image-region
Determine that the mobile clockwise of traversal, the clockwise are one of clockwise and counterclockwise；
Unit 733 is iterated over, is used for the initial edge tangent line, initial first boundary pixel point and initial the second boundary
Pixel is iteratively held respectively as front tangent line, current first boundary pixel point and current the second boundary pixel is worked as
The following processing of row, obtains at least one subsequent side tangent line:
Current first boundary pixel point is moved along the image boundary that it is currently located to determining clockwise, and
And determine that current first boundary pixel point after movement and the line between current the second boundary pixel whether include black picture
Vegetarian refreshments；
If it is determined that the line between current first boundary pixel point and current the second boundary pixel after mobile does not wrap
Containing black pixel point, then the image boundary that is currently located the current the second boundary pixel along it is to determining clockwise
It is mobile, and determine that the line between current first boundary pixel point and current the second boundary pixel after movement whether includes
Black pixel point；
The processing of mobile current first boundary pixel point and the current the second boundary pixel is alternately executed, directly
The line between current first boundary pixel point and current the second boundary pixel after to determining movement includes black pixel point
Until；
The line comprising black pixel point is determined as next subsequent side tangent line；
If next subsequent side tangent line is overlapped with the initial edge tangent line, stop the iteration, otherwise by institute
It states when front tangent line, current first boundary pixel point and current the second boundary pixel are respectively set to next subsequent side
Tangent line, corresponding first boundary pixel point of the next subsequent side tangent line and the second boundary pixel, continue to execute next time
Iterative processing.
Optionally, boundary rectangle building module 740 is used for: in the multiple summits tangent line, being cut with the initial edge
The angle of line is more than or equal to 0 ° and is less than or equal to 90 ° of any first side tangent line, obtains parallel with first side tangent line the
Two when tangent line and tangent line is vertical when with described first third are in tangent line and the 4th tangent line, any first side tangent line with
And at least one described boundary rectangle is constituted by its acquisition corresponding second tangent line and the 4th side tangent line in tangent line, third.
Image processing apparatus 700 has the beneficial effect realized with any aforementioned image processing method, and it will not be described here.
The embodiment of the present disclosure additionally provides a kind of electronic equipment.Fig. 9 is to show to be set according to the electronics with regard to the embodiment of the present disclosure
Standby 900 structural schematic diagram.The electronic equipment 900 can be such as mobile terminal, personal computer (PC), tablet computer, clothes
Business device etc..
As shown in figure 9, electronic equipment 900 may include memory and processor.Specifically, electronic equipment 900 includes one
A or multiple processors, communication device etc., one or more of processors for example: one or more central processing unit
(CPU) 901, and/or one or more image processor (GPU) 913 etc., processor can be according to being stored in read-only memory
(ROM) it the executable instruction in 902 or is loaded into from storage section 908 executable in random access storage device (RAM) 903
It instructs and executes various movements appropriate and processing.Communication device includes communication component 912 and/or communication interface 909.Wherein,
Communication component 912 may include but be not limited to network interface card, and the network interface card may include but be not limited to IB (Infiniband) network interface card, and communication connects
Mouth 909 includes the communication interface of the network interface cards of LAN card, modem etc., and communication interface 909 is via such as because of spy
The network of net executes communication process.
Processor can with communicate in read-only memory 902 and/or random access storage device 903 to execute executable instruction,
It is connected by communication bus 904 with communication component 912 and is communicated through communication component 912 with other target devices, to completes this
The corresponding operation of any one image processing method that open embodiment provides, for example, obtain containing non-blank-white image-region to
Handle image；Binary conversion treatment is executed to the image to be processed, obtains binary image；From one of the binary image
Vertex pixel starts, and traverses the binary image along orthogonal two image boundaries respectively, obtains and the non-empty
The tangent multiple summits tangent line of the profile in white image region, on the side tangent line comprising at least one black pixel point and one side only
Include white pixel point；According to the multiple summits tangent line of acquisition, at least one boundary rectangle is obtained；By face in multiple boundary rectangles
The smallest boundary rectangle of product is chosen for the minimum circumscribed rectangle region of the non-blank-white image-region.
In addition, in RAM 903, various programs and data needed for being also stored with device operation.CPU 901 or GPU
913, ROM 902 and RAM 903 is connected with each other by communication bus 904.In the case where there is 903 RAM, ROM 902 is can
Modeling block.RAM 903 stores executable instruction, or executable instruction is written into ROM 902 at runtime, and executable instruction makes
Processor executes the corresponding operation of above-mentioned communication means.Input/output (I/O) interface 905 is also connected to communication bus 904.It is logical
Letter component 912 can integrate setting, may be set to be with multiple submodule (such as multiple IB network interface cards), and in communication bus
It chains.
I/O interface 905 is connected to lower component: the importation 906 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 907 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 908 including hard disk etc.；
And the communication interface 909 of the network interface card including LAN card, modem etc..Driver 910 also connects as needed
It is connected to I/O interface 905.Detachable media 911, such as disk, CD, magneto-optic disk, semiconductor memory etc. are pacified as needed
On driver 910, in order to be mounted into storage section 908 as needed from the computer program read thereon.
It should be noted that framework as shown in Figure 9 is only a kind of optional implementation, it, can root during concrete practice
The component count amount and type of above-mentioned Fig. 9 are selected, are deleted, increased or replaced according to actual needs；It is set in different function component
It sets, separately positioned or integrally disposed and other implementations, such as the separable setting of GPU and CPU or can be by GPU collection can also be used
At on CPU, the separable setting of communication device, can also be integrally disposed on CPU or GPU, etc..These interchangeable embodiment party
Formula each falls within the protection scope of the disclosure.
The electronic equipment of the embodiment of the present disclosure can be used to implement corresponding image processing method in above-described embodiment, the electricity
Each device in sub- equipment can be used for executing each step in above method embodiment, for example, the figure being outlined above
As processing method can be realized by the dependent instruction that the processor of electronic equipment calls memory to store, for sake of simplicity,
This is repeated no more.
According to the embodiment of the present disclosure, a kind of computer program production may be implemented as above with reference to the process of flow chart description
Product.For example, the embodiment of the present disclosure includes a kind of computer program product comprising be tangibly embodied on machine readable media
Computer program, computer program include the program code for method shown in execution flow chart, and program code may include pair
The corresponding instruction of method and step of embodiment of the present disclosure offer should be executed, for example, for obtaining containing non-blank-white image-region
The instruction of image to be processed；For executing binary conversion treatment to the image to be processed, the instruction of binary image is obtained；For
Since a vertex pixel of the binary image, the two-value is traversed along orthogonal two image boundaries respectively
Change image, obtains the instruction of the multiple summits tangent line tangent with the profile of the non-blank-white image-region, include on the side tangent line
At least one black pixel point and one side only include white pixel point；For the multiple summits tangent line according to acquisition, obtain at least
The instruction of one boundary rectangle；For the smallest boundary rectangle of area in multiple boundary rectangles to be chosen for the non-blank-white figure
As the instruction in the minimum circumscribed rectangle region in region.In such embodiments, which can pass through communication device
It is downloaded and installed from network, and/or is mounted from detachable media 911.When the computer program is executed by processor,
Execute function disclosed in the method for the embodiment of the present disclosure.
Disclosed method and device, electronic equipment and storage medium may be achieved in many ways.For example, can pass through
Software, hardware, firmware or software, hardware, firmware any combination realize method and apparatus, the electronics of the embodiment of the present disclosure
Equipment and storage medium.The said sequence of the step of for method merely to be illustrated, the method for the embodiment of the present disclosure
Step is not limited to sequence described in detail above, unless specifically stated otherwise.In addition, in some embodiments, may be used also
The disclosure is embodied as to record program in the recording medium, these programs include for realizing according to the side of the embodiment of the present disclosure
The machine readable instructions of method.Thus, the disclosure also covers program of the storage for executing the method according to the embodiment of the present disclosure
Recording medium.
The description of the embodiment of the present disclosure is given for the purpose of illustration and description, and is not exhaustively or to incite somebody to action
The disclosure is limited to disclosed form, and many modifications and variations are obvious for the ordinary skill in the art.Choosing
Selecting and describe embodiment is the principle and practical application in order to more preferably illustrate the disclosure, and makes those skilled in the art
It will be appreciated that the disclosure is to design various embodiments suitable for specific applications with various modifications.
Claims (10)
1. a kind of image processing method, comprising:
Obtain the image to be processed containing non-blank-white image-region；
Binary conversion treatment is executed to the image to be processed, obtains binary image；
Since a vertex pixel of the binary image, respectively along described in orthogonal two image boundaries traversal
Binary image obtains the multiple summits tangent line tangent with the profile of the non-blank-white image-region, includes extremely on the side tangent line
Lack a black pixel point and one side only includes white pixel point；
According to the multiple summits tangent line of acquisition, at least one boundary rectangle is obtained；
The smallest boundary rectangle of area in multiple boundary rectangles is chosen for the external square of minimum of the non-blank-white image-region
Shape region.
2. the method according to claim 1, wherein a vertex pixel from the binary image
Start, traverse the binary image along orthogonal two image boundaries respectively, obtains and the non-blank-white image-region
The tangent multiple summits tangent line of profile, comprising:
Since any vertex pixel of the binary image, moved respectively along orthogonal two image boundaries
It searches, includes black picture element by this until the line between two boundary pixel points being moved to includes black pixel point
For the line of point as initial edge tangent line, corresponding two boundary pixel points of the initial edge tangent line are respectively initial first boundary picture
Vegetarian refreshments and initial the second boundary pixel；
The mobile clockwise of traversal is determined relative to the position of non-blank-white image-region according to the initial edge tangent line, when described
Needle direction is one of clockwise and counterclockwise；
It is cut using the initial edge tangent line, initial first boundary pixel point and initial the second boundary pixel as when front
Line, current first boundary pixel point and current the second boundary pixel iteratively execute following processing, obtain at least one
Subsequent side tangent line:
Current first boundary pixel point is moved along the image boundary that it is currently located to determining clockwise, and really
The line between current first boundary pixel point and current the second boundary pixel after fixed movement whether includes black pixel point；
If it is determined that the line between current first boundary pixel point and current the second boundary pixel after mobile do not include it is black
Colour vegetarian refreshments then moves the current the second boundary pixel along the image boundary that it is currently located to determining clockwise
It is dynamic, and determine that current first boundary pixel point after movement and the line between current the second boundary pixel whether include black
Colour vegetarian refreshments；
The processing for alternately executing mobile current first boundary pixel point and the current the second boundary pixel, until true
Until the line between current first boundary pixel point and current the second boundary pixel after fixed movement includes black pixel point；
The line comprising black pixel point is determined as next subsequent side tangent line；
If next subsequent side tangent line is overlapped with the initial edge tangent line, stop the iteration, otherwise works as by described in
Front tangent line, current first boundary pixel point and current the second boundary pixel are respectively set to next subsequent side and cut
Line, corresponding first boundary pixel point of the next subsequent side tangent line and the second boundary pixel, continue to execute and change next time
Generation processing.
3. according to the method described in claim 2, it is characterized in that, the multiple summits tangent line according to acquisition, obtains at least one
A boundary rectangle, comprising:
In the multiple summits tangent line, it is more than or equal to 0 ° and appointing less than or equal to 90 ° with the angle of the initial edge tangent line
One first side tangent line, obtain with described first while tangent line it is parallel second while tangent line and vertical with first side tangent line the
Three in tangent line and the 4th tangent line, any described first in tangent line and tangent line, third side are cut when by it obtaining corresponding second
Line and the 4th side tangent line constitute at least one described boundary rectangle.
4. according to the method described in claim 3, it is characterized in that, it is described acquisition with described first while tangent line it is parallel second while
Tangent line and with described first in the third that tangent line is vertical tangent line and the 4th side tangent line, comprising:
By binary search method, searched in the multiple summits tangent line obtain with described first while tangent line it is parallel second while cut
Line and with described first in the third that tangent line is vertical tangent line and the 4th side tangent line.
5. method according to any one of claims 1 to 4, which is characterized in that the method also includes:
The image to be processed is standardized according to the minimum circumscribed rectangle.
6. a kind of image processing apparatus, comprising:
Image collection module, for obtaining the image to be processed containing non-blank-white image-region；
Binary processing module executes binary conversion treatment for obtaining the image to be processed that module obtains to described image, obtains
Binary image；
Image traversal module, for since a vertex pixel of the binary image, respectively along orthogonal two
A image boundary traverses the binary image, obtains the multiple summits tangent line tangent with the profile of the non-blank-white image-region,
Comprising at least one black pixel point and one side only includes white pixel point on the side tangent line；
Boundary rectangle constructs module and obtains at least one boundary rectangle for the multiple summits tangent line according to acquisition；
Minimum circumscribed rectangle chooses module, described non-for the smallest boundary rectangle of area in multiple boundary rectangles to be chosen for
The minimum circumscribed rectangle region in blank image region.
7. device according to claim 6, which is characterized in that described image spider module includes:
Initial edge tangent line determination unit, for hanging down respectively along mutual since any vertex pixel of the binary image
Two straight image boundaries carry out mobile lookup, until the line between two boundary pixel points being moved to includes black picture element
Until point, using this include black pixel point line as initial edge tangent line, the corresponding two boundary pictures of the initial edge tangent line
Vegetarian refreshments is respectively initial first boundary pixel point and initial the second boundary pixel；
Traversal direction determination unit determines traversal for the position according to the initial edge tangent line relative to non-blank-white image-region
Mobile clockwise, the clockwise are one of clockwise and counterclockwise；
Unit is iterated over, is used for the initial edge tangent line, initial first boundary pixel point and initial the second boundary pixel
Respectively as front tangent line, current first boundary pixel point and current the second boundary pixel is worked as, iteratively execute following
Processing, obtains at least one subsequent side tangent line:
Current first boundary pixel point is moved along the image boundary that it is currently located to determining clockwise, and really
The line between current first boundary pixel point and current the second boundary pixel after fixed movement whether includes black pixel point；
If it is determined that the line between current first boundary pixel point and current the second boundary pixel after mobile do not include it is black
Colour vegetarian refreshments then moves the current the second boundary pixel along the image boundary that it is currently located to determining clockwise
It is dynamic, and determine that current first boundary pixel point after movement and the line between current the second boundary pixel whether include black
Colour vegetarian refreshments；
The processing for alternately executing mobile current first boundary pixel point and the current the second boundary pixel, until true
Until the line between current first boundary pixel point and current the second boundary pixel after fixed movement includes black pixel point；
The line comprising black pixel point is determined as next subsequent side tangent line；
If next subsequent side tangent line is overlapped with the initial edge tangent line, stop the iteration, otherwise works as by described in
Front tangent line, current first boundary pixel point and current the second boundary pixel are respectively set to next subsequent side and cut
Line, corresponding first boundary pixel point of the next subsequent side tangent line and the second boundary pixel, continue to execute and change next time
Generation processing.
8. device according to claim 7, which is characterized in that the boundary rectangle building module is used for: for described more
In side tangent line, it is more than or equal to 0 ° with the angle of the initial edge tangent line and is less than or equal to 90 ° of any first side tangent line, obtain
Take with described first while tangent line it is parallel second while tangent line and with described first in the third that tangent line is vertical while tangent line and the 4th
Side tangent line, any described first while tangent line and by its obtain corresponding second while tangent line, third in tangent line and the 4th while tangent line
Constitute at least one described boundary rectangle.
9. a kind of electronic equipment characterized by comprising processor and memory；
The memory makes the processor execute such as right for storing at least one executable instruction, the executable instruction
It is required that the step of image processing method described in any one of 1~5.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has executable finger
It enables, the executable instruction makes the processor execute the step such as image processing method according to any one of claims 1 to 5
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811506464.4A CN109741394B (en) | 2018-12-10 | 2018-12-10 | Image processing method, image processing device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811506464.4A CN109741394B (en) | 2018-12-10 | 2018-12-10 | Image processing method, image processing device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109741394A true CN109741394A (en) | 2019-05-10 |
| CN109741394B CN109741394B (en) | 2021-02-26 |
Family
ID=66358751
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811506464.4A Active CN109741394B (en) | 2018-12-10 | 2018-12-10 | Image processing method, image processing device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109741394B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826571A (en) * | 2019-11-01 | 2020-02-21 | 云南电网有限责任公司信息中心 | Image traversal algorithm for image rapid identification and feature matching |
| CN112070817A (en) * | 2020-08-25 | 2020-12-11 | 中国科学院深圳先进技术研究院 | Image depth estimation method, terminal equipment and computer readable storage medium |
| CN112070708A (en) * | 2020-08-21 | 2020-12-11 | 杭州睿琪软件有限公司 | Image processing method, image processing apparatus, electronic device, and storage medium |
| CN112700391A (en) * | 2019-10-22 | 2021-04-23 | 北京易真学思教育科技有限公司 | Image processing method, electronic equipment and computer readable storage medium |
| CN112634124B (en) * | 2020-12-10 | 2024-04-12 | 深兰工业智能创新研究院(宁波)有限公司 | Image warping method, image warping device, electronic apparatus, and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10198813A (en) * | 1997-01-07 | 1998-07-31 | Dainippon Screen Mfg Co Ltd | Editing method, its device, and storage medium recording program |
| US6400365B1 (en) * | 1996-12-05 | 2002-06-04 | Ryozo Setoguchi | Display method of three-dimensional shape |
| US7308650B2 (en) * | 2003-08-29 | 2007-12-11 | Seiko Epson Corporation | Image layout device |
| CN101281112A (en) * | 2008-04-30 | 2008-10-08 | 浙江理工大学 | Image type automatic analysis method for mesh adhesion rice corn |
| CN101727580A (en) * | 2008-10-29 | 2010-06-09 | 株式会社东芝 | Image processing apparatus, electronic medium, and image processing method |
| CN102346913A (en) * | 2011-09-20 | 2012-02-08 | 宁波大学 | Simplification method of polygon models of image |
| CN103793712A (en) * | 2014-02-19 | 2014-05-14 | 华中科技大学 | Image recognition method and system based on edge geometric features |
| CN104463167A (en) * | 2014-11-20 | 2015-03-25 | 中国科学院上海微系统与信息技术研究所 | Automatic restaurant settlement method and system |
| US20150169970A1 (en) * | 2012-08-30 | 2015-06-18 | Fujitsu Limited | Image processing apparatus and image processing method |
| CN106846404A (en) * | 2017-01-16 | 2017-06-13 | 河海大学常州校区 | A kind of quick position and posture detection method based on workpiece inside and outside contour geometric properties |
| CN107993235A (en) * | 2017-11-27 | 2018-05-04 | 中国计量大学 | A kind of ripple back-fire relief disk wave height measuring method based on image processing techniques |
-
2018
- 2018-12-10 CN CN201811506464.4A patent/CN109741394B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6400365B1 (en) * | 1996-12-05 | 2002-06-04 | Ryozo Setoguchi | Display method of three-dimensional shape |
| JPH10198813A (en) * | 1997-01-07 | 1998-07-31 | Dainippon Screen Mfg Co Ltd | Editing method, its device, and storage medium recording program |
| US7308650B2 (en) * | 2003-08-29 | 2007-12-11 | Seiko Epson Corporation | Image layout device |
| CN101281112A (en) * | 2008-04-30 | 2008-10-08 | 浙江理工大学 | Image type automatic analysis method for mesh adhesion rice corn |
| CN101727580A (en) * | 2008-10-29 | 2010-06-09 | 株式会社东芝 | Image processing apparatus, electronic medium, and image processing method |
| CN102346913A (en) * | 2011-09-20 | 2012-02-08 | 宁波大学 | Simplification method of polygon models of image |
| US20150169970A1 (en) * | 2012-08-30 | 2015-06-18 | Fujitsu Limited | Image processing apparatus and image processing method |
| CN103793712A (en) * | 2014-02-19 | 2014-05-14 | 华中科技大学 | Image recognition method and system based on edge geometric features |
| CN104463167A (en) * | 2014-11-20 | 2015-03-25 | 中国科学院上海微系统与信息技术研究所 | Automatic restaurant settlement method and system |
| CN106846404A (en) * | 2017-01-16 | 2017-06-13 | 河海大学常州校区 | A kind of quick position and posture detection method based on workpiece inside and outside contour geometric properties |
| CN107993235A (en) * | 2017-11-27 | 2018-05-04 | 中国计量大学 | A kind of ripple back-fire relief disk wave height measuring method based on image processing techniques |
Non-Patent Citations (2)
| Title |
|---|
| FAQUAN ZHANG等: "An Algorithm for Minimal Circumscribed Rectangle of Image Object Based on Searching Principle Axis Method", 《RESEARCH JOURNAL OF APPLIED SCIENCES, ENGINEERING AND TECHNOLOGY》 * |
| 陈晓红: "基于机器视觉的触摸屏玻璃缺陷检测方法研究", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700391A (en) * | 2019-10-22 | 2021-04-23 | 北京易真学思教育科技有限公司 | Image processing method, electronic equipment and computer readable storage medium |
| CN112700391B (en) * | 2019-10-22 | 2022-07-12 | 北京易真学思教育科技有限公司 | Image processing method, electronic equipment and computer readable storage medium |
| CN110826571A (en) * | 2019-11-01 | 2020-02-21 | 云南电网有限责任公司信息中心 | Image traversal algorithm for image rapid identification and feature matching |
| CN110826571B (en) * | 2019-11-01 | 2023-10-20 | 云南电网有限责任公司信息中心 | Image traversal algorithm for rapid image identification and feature matching |
| CN112070708A (en) * | 2020-08-21 | 2020-12-11 | 杭州睿琪软件有限公司 | Image processing method, image processing apparatus, electronic device, and storage medium |
| CN112070708B (en) * | 2020-08-21 | 2024-03-08 | 杭州睿琪软件有限公司 | Image processing method, image processing apparatus, electronic device, and storage medium |
| US11985287B2 (en) | 2020-08-21 | 2024-05-14 | Hangzhou Glority Software Limited | Image processing method, image processing device, electronic apparatus and storage medium |
| CN112070817A (en) * | 2020-08-25 | 2020-12-11 | 中国科学院深圳先进技术研究院 | Image depth estimation method, terminal equipment and computer readable storage medium |
| CN112070817B (en) * | 2020-08-25 | 2024-05-28 | 中国科学院深圳先进技术研究院 | Image depth estimation method, terminal equipment and computer readable storage medium |
| CN112634124B (en) * | 2020-12-10 | 2024-04-12 | 深兰工业智能创新研究院(宁波)有限公司 | Image warping method, image warping device, electronic apparatus, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109741394B (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109741394A (en) | Image processing method, device, electronic equipment and storage medium | |
| Kopf et al. | Depixelizing pixel art | |
| WO2020078236A1 (en) | Two-dimensional code generation method and apparatus, storage medium and electronic device | |
| CN107610200B (en) | Character library rapid generation method based on characteristic template | |
| CN108520247A (en) | To the recognition methods of the Object node in image, device, terminal and readable medium | |
| CN112288665B (en) | Image fusion method and device, storage medium and electronic equipment | |
| CN105765624B (en) | Perception of content image rotation | |
| US9330466B2 (en) | Methods and apparatus for 3D camera positioning using a 2D vanishing point grid | |
| US8587584B1 (en) | Techniques for interior coordinates | |
| KR20050121263A (en) | Determining a coverage mask for a pixel | |
| CN107944324A (en) | A kind of Quick Response Code distortion correction method and device | |
| CN109308734B (en) | 3D character generation method and device, equipment and storage medium thereof | |
| CN109684005B (en) | Method and device for determining similarity of components in graphical interface | |
| US9922623B2 (en) | Emboldening of outline fonts | |
| KR20240032954A (en) | Method, system, and computer-readable storage medium for locating a target object | |
| WO2024060999A1 (en) | Polygon processing method and apparatus, and device, computer-readable storage medium and computer program product | |
| EP1600895A1 (en) | Rendering a graphical object when a corresponding outline lacks control points | |
| US8711184B2 (en) | Scalable pixel coverage function-map | |
| US8107729B2 (en) | Method for improving character outlines using multiple alignment zones | |
| US10748316B2 (en) | Identification and modification of similar objects in vector images | |
| US7292249B2 (en) | Appropriately rendering a graphical object when a corresponding outline has excessive control points | |
| Cao et al. | Orienting raw point sets by global contraction and visibility voting | |
| US7292247B2 (en) | Dynamically determining directions of freedom for control points used to represent graphical objects | |
| CN110570504B (en) | Closed symbol drawing method and device, electronic equipment and storage medium | |
| US7656408B1 (en) | Method and system for animating a border |
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 | ||
| CP03 | Change of name, title or address |
Address after: 101, 1st to 7th floors, Building 3, Yard 6, Jianfeng Road (South Extension), Haidian District, Beijing, 100070 Patentee after: TOLS INFORMATION TECHNOLOGY Co.,Ltd. Address before: 14b04, 14th floor, Jinqiu international building, 6 Zhichun Road, Haidian District, Beijing 100088 Patentee before: BEIJING TRS INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address |