CN112991375B - Method and system for remolding image area with arbitrary shape into N rectangular areas - Google Patents
Method and system for remolding image area with arbitrary shape into N rectangular areas Download PDFInfo
- Publication number
- CN112991375B CN112991375B CN202110186850.5A CN202110186850A CN112991375B CN 112991375 B CN112991375 B CN 112991375B CN 202110186850 A CN202110186850 A CN 202110186850A CN 112991375 B CN112991375 B CN 112991375B
- Authority
- CN
- China
- Prior art keywords
- rectangle
- area
- matrix
- largest
- coordinates
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 230000000379 polymerizing effect Effects 0.000 claims abstract description 5
- 238000005215 recombination Methods 0.000 claims abstract 3
- 230000006798 recombination Effects 0.000 claims abstract 3
- 239000011159 matrix material Substances 0.000 claims description 104
- 238000010008 shearing Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 8
- 230000008521 reorganization Effects 0.000 claims description 6
- 230000004931 aggregating effect Effects 0.000 claims description 5
- 230000001131 transforming effect Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 10
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006116 polymerization reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application provides a method and a system for remodelling an image area with any shape into N rectangular areas, wherein the method comprises the following steps: confirming a region of interest of the original image; marking the pixels of the region of interest as 1 and the pixels of the other regions as 0; cutting out the minimum circumscribed rectangle of the region of interest along the horizontal direction, and searching the rectangle with the largest area, namely the rectangle with the largest area, in the minimum circumscribed rectangle according to a preset rule; taking the maximum area rectangle as the center, gradually and inwards polymerizing other image pixels marked as 1 outside the maximum area rectangle and inside the minimum circumscribed rectangle into a rectangle by adopting a quicksand filling mode; if all or part of the data of the four outermost sides of the aggregated rectangle is not fully filled with 1, the data of the four outermost sides are recombined, and the sides which are not fully filled after the recombination are discarded; and cutting the processed rectangle into N rectangular areas. The method and the device facilitate the calculation of various algorithms on any region of interest, and accelerate the development of intelligent application.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a system for remolding an image area with any shape into N rectangular areas.
Background
In the field of computer vision, it is often necessary to perform computation of multiple algorithms on a picture, but inputs of many algorithms are matrices (rectangular areas in the picture), when performing computation of multiple algorithms on non-rectangular areas of interest in the picture, the areas cannot be directly used as inputs of the algorithms, edges can be filled into rectangles to perform computation, but the filling part and the areas of interest have obvious changes, and the changes may seriously affect the output of the algorithms if the changes are used as input parts of the algorithms, so it is more common practice to select 1 to N areas in the areas of interest to replace target areas to perform computation of the algorithms. But no more general algorithm is realized at present.
Disclosure of Invention
The invention aims to provide a method and a system for remolding an image area with any shape into N rectangular areas, which are convenient for carrying out various algorithm calculations on any interested area of a picture so as to accelerate the development of intelligent application.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a first aspect of the present application provides a method for reshaping an arbitrarily shaped image area into N rectangular areas, comprising:
acquiring an original image to be processed, and confirming an interested area of the original image, wherein the interested area is in any shape;
performing binarization processing on the original image, wherein the pixels of the region of interest are marked as 1, and the pixels of other regions are marked as 0;
shearing the region of interest to obtain a minimum circumscribed rectangle of the region of interest along the horizontal direction;
searching a rectangle with the largest area from the sheared minimum circumscribed rectangle according to a preset rule, namely, the rectangle with the largest area;
taking the maximum area rectangle as the center, gradually and inwards polymerizing other image pixels marked as 1 outside the maximum area rectangle and inside the minimum circumscribed rectangle into a rectangle by adopting a quicksand filling mode;
when all or part of the data of the four outermost sides of the aggregated rectangle are not filled with 1, the data of the four outermost sides are recombined, and the most sides are filled as much as possible; if the edge which is not filled with 1 still exists after the data is recombined, discarding the edge;
and cutting the processed rectangle into N rectangular areas, wherein N is a positive integer greater than 1.
Preferably, the cutting out the minimum circumscribed rectangle of the region of interest along the horizontal direction includes the following steps:
from binarization processingStarting from the left side of the four outermost sides of the obtained image, sequentially searching coordinates of the first occurrence 1 from outside to inside in a clockwise direction, and sequentially marking the coordinates as X min 、Y min 、X max 、Y max ；
The upper left corner of the area of the smallest bounding rectangle is marked (X) min ，Y min ) The lower right corner is marked as (X) max ，Y max )。
Preferably, the searching the rectangle with the largest area, i.e. the rectangle with the largest area, in the sheared minimum circumscribed rectangle according to a preset rule includes the following steps:
traversing from top to bottom in the minimum circumscribed rectangle;
each current row and the blocks with continuous 1 in the y-axis direction of the traversed rows form columns with different heights, and height values are recorded;
searching each point from left to right as a maximum rectangle which can be formed by the right lower corner coordinates in the columnar graph with different heights in the last step;
calculating the area of the largest rectangle, judging whether the area is the largest, and updating the coordinates of the largest rectangle if the area is the largest;
repeating the steps until all the rows are traversed, and obtaining the rectangular coordinates with the largest area.
In a preferred embodiment, the corresponding matrix of the minimum bounding rectangle is the minimum bounding matrix A, and A has the coordinates [ X ] min :X max ,Y min :Y max ]Wherein, (X min ，Y min ) And (X) max ，Y max ) The method comprises the steps of searching a rectangle with the largest area according to a preset rule, namely, an upper left corner coordinate and a lower right corner coordinate of a region with the smallest circumscribed rectangle respectively, and performing matrix transformation and area calculation; wherein,
the matrix transformation step includes:
transforming the minimum circumscribed matrix A into a height matrix B, wherein each value in the height matrix B represents the maximum rectangular height which can be formed by upwards arranging the position in the minimum circumscribed matrix A in the y-axis direction, namely
Wherein j represents the j-th row of the matrix, i represents the i-th column of the matrix, and i and j are natural numbers greater than or equal to 0; a is that ji Pixels representing the j-th row and i-th column in the minimum circumscribed matrix A; b (B) ji Pixels representing the j-th row and i-th column in the height matrix B;
the area calculation step includes:
according to each pixel B in the height matrix B ji Sequentially calculating according to the following formula to obtain an area matrix S corresponding to the height matrix B, namely summing pixels of the largest rectangle searched leftwards and upwards by taking pixel points at the same position as the right lower corner coordinates of the rectangle in the minimum circumscribed matrix A corresponding to each value in the area matrix S, and obtaining the pixels B ji The calculation formula of (2) is as follows:
wherein S is ji Pixels representing the j-th row and i-th column in the area matrix S; n, n 1 ,n 2 ,……n n Are natural numbers greater than or equal to 0;
searching the maximum value, namely the maximum area coordinate S, in the calculated area matrix S ji max If there are a plurality of values, the coordinate closest to the center of the area matrix S is taken, and if there are still a plurality of values, one of the coordinates is taken at random as the maximum area coordinate S ji max The method comprises the steps of carrying out a first treatment on the surface of the In the minimum circumscribed matrix A, corresponding to the maximum area coordinate S ji max The pixel point of the position is the right lower corner coordinate of the rectangle, and the largest rectangle searched leftwards and upwards is the rectangle with the largest area.
In a more preferred embodiment, the coordinates of the upper left corner of the largest area rectangle are recorded by the sparse matrix K during the calculation of the area matrix S; in calculating the maximum area coordinate S ji max When the process is maximumArea coordinates S ji max There are a plurality of values, one of which is randomly taken as the maximum area coordinate S ji max The calculation formula of (2) is as follows:
S ji max ＝random(min(abs((S j -K j )/2-H/2))+abs((S i -K i )/2-W/2))))
wherein H is the height of the matrix K, W is the width of the matrix K, K j Maximum area coordinate S recorded for matrix K ji max Row coordinates of upper left corner of maximum area rectangle, K i Maximum area coordinate S recorded for matrix K ji max Column coordinates of upper left corner of corresponding maximum area rectangle, S j Is the maximum area coordinate S ji max Row coordinates of S i Is the maximum area coordinate S ji max Is a column coordinate of (c).
Preferably, the step of gradually aggregating the other image pixels marked as 1 outside the largest area rectangle and inside the smallest circumscribed rectangle into a rectangle by adopting a quicksand filling mode with the largest area rectangle as the center includes: starting from the left side of the four sides at the outermost side of the rectangle with the largest area, searching and filling the four sides layer by layer outwards in a clockwise direction; when the nth side outside the maximum area rectangle is filled, n is a positive integer greater than or equal to 1, the pixel with 1 in the nth side is unchanged, and the pixel with 0 is filled by the pixel with 1 in the nearest pixel of the (n+1) th side which is the outer side adjacent to the nth side, wherein the nearest pixel is the (n+1) th side, and takes the maximum area rectangle as the center, and the left and right included angles of the nearest pixel are left and right included angles of the nearest pixel.
In a preferred embodiment, the step-wise inward polymerization into a rectangle by using a sand-type filling mode comprises the following steps: starting from the left side of the four outermost sides of the largest area rectangle, the first column outside of the rectangle is S k K is a natural number greater than or equal to 0, then S k The position of 1 in the column remains unchanged, S k The position in the column of 0 is from (S) k -1) column, and pixels with a search value of 1 among pixels within a left-right opening range of 45 DEG included angle left-right and left-right closing range centered on the maximum area rectangleFilling in the S k Positions listed as 0; repeating the steps, searching all data outwards layer by side in the clockwise direction on the four outermost sides of the rectangle with the largest area.
Preferably, after the other pixels outside the largest area rectangle and inside the smallest circumscribed rectangle are gradually and inwardly aggregated into a rectangle by adopting a quicksand filling mode, the data is reorganized on the four outermost sides, the sides are filled as much as possible, and if the sides which are not filled with 1 are still present after the data reorganization, the sides are discarded, including the following steps:
sequentially converging the data of the four outermost sides of the aggregated rectangle to the left upper corner point of the rectangle according to the anticlockwise direction;
and starting from the upper edge of the four outermost edges of the converged rectangle, sequentially checking the data of the four edges in a clockwise direction, reserving the edges filled with the data, and discarding the edges not filled with the data.
Preferably, the cutting the processed rectangle into N rectangular areas includes the following steps:
calculating the length of a short side, wherein the short side is the shorter side in the processed rectangle, and the longer side is the long side;
calculating the number of times of cutting the short side and the long side, wherein the number of times is X and Y respectively, and the rectangular area cut according to X, Y is closest to a square;
calculating the cut coordinates according to X, Y, and performing rectangular cutting;
if the processed rectangle is square, the short side and the long side are the side length of the square, and x=y.
More preferably, the cutting the processed rectangle into N rectangular areas includes the following steps:
let the length of the short side of the processed rectangle be h, the length of the long side be w, w > =h, and the number of parts X to be cut of the short side and the number of parts Y to be cut of the long side be calculated according to the following formula, wherein X, Y is a positive integer greater than or equal to 1:
x Y + z=n, and X, Y, Z values satisfy the following constraints at the same time,
(1) Z is 0 or 1;
(2)Y>＝X；
(3) The absolute value of (Y-X) is the smallest;
calculating the position coordinates of short-side cutting, wherein the coordinates of the x-th part of short-side cutting are as follows: x (h/X) and rounding (e.g., round rounding), x=1, … …, X-1;
calculating the position coordinates of the long-side cutting, and when z=0, calculating the y coordinates of the long-side cutting as follows: y (w/Y) and rounding (e.g., round rounding), y=1, … …, Y-1; when z=1, the coordinates of the y' th part of the long side cut are: y '× (w/(y+1)) and rounded (e.g., round), Y' =1, … …, Y, i.e., when Z is 1, the number of cut parts of the long side is actually (y+1).
A second aspect of the present application provides a system for reshaping an arbitrarily shaped image area into N rectangular areas, comprising:
the device comprises an interested region confirming module, a processing module and a processing module, wherein the interested region confirming module is used for acquiring an original image to be processed and acquiring an interested region of the original image, and the interested region is in any shape;
the original image binarization processing module is used for performing binarization processing on the original image, wherein the pixels of the region of interest are marked as 1, and the pixels of other regions are marked as 0;
the minimum circumscribed rectangle searching module is used for shearing the region of interest and shearing a minimum circumscribed rectangle of the region of interest along the horizontal direction;
the maximum area rectangle searching module is used for searching the rectangle with the largest area in the sheared minimum circumscribed rectangle according to a preset rule, namely the rectangle with the largest area;
the quicksand type filling module is used for gradually and inwards aggregating other image pixels marked as 1 outside the maximum area rectangle and inside the minimum circumscribed rectangle into a rectangle by adopting a quicksand type filling mode by taking the maximum area rectangle as the center;
the data reorganization module is used for reorganizing the data of the four outermost sides of the aggregated rectangle when all or part of the data of the four outermost sides are not filled with 1, and filling the edges with the most as much as possible; if the edge which is not filled with 1 still exists after the data is recombined, discarding the edge;
and the rectangular cutting module is used for cutting the processed rectangle into N rectangular areas, wherein N is a positive integer greater than 1.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
the method for remolding the image area with any shape into the N rectangular areas can remodel the image area with any shape of interest in the picture into the N rectangular areas, is used as the algorithm input of various image processing, facilitates various algorithm calculations on the image area with any interest, improves the accuracy of algorithm output of the image processing, effectively avoids distortion of the image processing, and accelerates development of intelligent application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a flow chart of a method provided by the present invention for reshaping arbitrarily shaped image areas into N rectangular areas;
FIG. 2 is an exemplary diagram of clipping a minimum bounding rectangle from an original image in a method provided by an embodiment of the present invention;
FIG. 3 is a diagram of an exemplary partial transformation of pixels in a minimum bounding rectangle into a height matrix in a method according to an embodiment of the present invention;
FIG. 4 is an exemplary diagram of a processing result of transforming a minimum circumscribed matrix A into a height matrix B in a method according to an embodiment of the present invention;
FIG. 5 is a diagram of an exemplary partial transformation of a height matrix B into an area matrix S in a method according to an embodiment of the present invention;
FIG. 6 is an exemplary diagram of a processing result of calculating an area matrix S from a height matrix B in the method according to the embodiment of the present invention;
FIG. 7 is a logic diagram illustrating the whole process of transforming the minimum circumscribed matrix A into the area matrix S in the method according to the embodiment of the present invention;
FIG. 8 is a diagram illustrating a search direction and a filling example of a quicksand filling in the method according to the embodiment of the present invention;
FIG. 9 is an exemplary diagram of data reorganization of four outermost edges of an aggregated rectangle in a method provided by an embodiment of the present invention;
fig. 10 is an example of rectangular cutting when z=0 in the method provided by the embodiment of the present invention;
fig. 11 shows an example of rectangular cutting when z=1 in the method according to the embodiment of the present invention.
Fig. 12 is a schematic structural diagram of a system for reshaping an arbitrarily shaped image area into N rectangular areas according to an embodiment of the present invention.
Detailed Description
The purpose, technical proposal and effect of the invention are more clear and clear, and the invention is further described in detail below by referring to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flowchart of a method for reshaping an arbitrarily shaped image area into N rectangular areas provided by the present invention. As shown in fig. 1, a method for reshaping an image area of arbitrary shape into N rectangular areas mainly includes the following steps:
step S01: acquiring an original image to be processed, and confirming an interested area of the original image to be processed, wherein the interested area is of any shape;
step S02: performing binarization processing on an original image to be processed, wherein the pixels of the region of interest are marked as 1, and the pixels of other regions are marked as 0;
step S03: shearing the region of interest to obtain a minimum circumscribed rectangle of the region of interest along the horizontal direction;
step S04: searching a rectangle with the largest area, namely a rectangle with the largest area, from the sheared minimum circumscribed rectangle according to a preset rule;
step S05: taking the maximum area rectangle as the center, gradually and inwards polymerizing other image pixels marked as 1 outside the maximum area rectangle and inside the minimum circumscribed rectangle into a rectangle by adopting a quicksand filling mode;
step S06: when all or part of the data of the four outermost sides of the aggregated rectangle are not filled with 1, the data of the four outermost sides are recombined, and the most sides are filled as much as possible; if the edge which is not filled with 1 still exists after the data is recombined, discarding the edge;
step S07: and cutting the processed rectangle into N rectangular areas, wherein N is a positive integer greater than 1.
Examples
Step S01: and acquiring an original image to be processed, and confirming an interested area of the original image to be processed, wherein the interested area can be in any shape.
Step S02: and carrying out binarization processing on the original image, wherein the pixels of the region of interest are marked as 1, the pixels of other regions are marked as 0, and the coordinates of the region of interest are the processing results of other algorithms or manually designated coordinates. The binarized image pixel is shown in fig. 2, in which the gray portion is the region of interest.
Step S03: shearing the region of interest to obtain a minimum circumscribed rectangle of the region of interest along the horizontal direction, wherein the steps are as follows:
starting from the left side of the four outermost sides of the binarized image, sequentially searching coordinates of the first 1 from outside to inside in a clockwise direction, and sequentially marking the coordinates as X min 、Y min 、X max 、Y max ；
The upper left and lower right corner coordinates of the region of the smallest bounding rectangle are (X min ，Y min ) And (X) max ，Y max ) I.e. the corresponding matrix of the smallest circumscribed rectangle is the smallest circumscribed matrix a= [ X ] min :X max ,Y min :Y max ]. The minimum bounding rectangle after processing is referred to as the rectangular area outlined by the dashed line in fig. 2.
Step S04: searching a rectangle with the largest area, namely a rectangle with the largest area, in the sheared minimum circumscribed matrix A according to a preset rule, wherein the method specifically comprises the following steps of:
step S041: and (5) calculating a height matrix B.
In the minimum circumscribed rectangle, traversing from top to bottom row by row, forming columns with different heights by each current row and blocks with continuous 1 of the traversed rows in the y-axis direction, and recording height values. Referring to fig. 3, fig. 3 shows a partial transformation example of the height matrix. For example, in the minimum bounding rectangle, the pixel in the third row and the third column is 1, and both pixels above it are also 1 (the dotted frame portion), i.e., at A 22 At the point of A 02 、A 12 All are 1, so that the maximum rectangular height which can be formed by the pixels of the third row and the third column upwards is 3, and the pixels of the third row and the third column in the corresponding height matrix are 3.
Specifically, the minimum circumscribed matrix A is transformed into a height matrix B, each value in the height matrix B represents the maximum rectangular height that can be formed by upwards arranging the position in the minimum circumscribed matrix A in the y-axis direction, namely
Wherein j represents the j-th row of the matrix, i represents the i-th column of the matrix, and i and j are natural numbers greater than or equal to 0; a is that ji Pixels representing the j-th row and i-th column in the minimum circumscribed matrix A; b (B) ji The j-th row and i-th column of pixels in the height matrix B are shown.
An example of a complete height matrix B transformed by the minimum circumscribed matrix a is shown in fig. 4.
Step S042: and (5) calculating an area matrix S.
According to each pixel B in the height matrix B ji The area matrix S corresponding to the height matrix B is obtained by sequentially calculating according to the following formula:
wherein S is ji Pixels representing the j-th row and i-th column in the area matrix S; n, n 1 ,n 2 ,……n n Are natural numbers of 0 or more.
Referring to fig. 5, fig. 5 shows a partial transformation example of transforming the height matrix B into the area matrix S. For example, in B 22 In the point, 1, B is taken first 22 ]The largest positive integer of (2), here 3, because B 22 The adjacent front (i.e. left side) has no value of 3 or more, i.e. n 1 =0, so S 1 = (0+1) ×3=3 (i.e., a rectangle formed by pixel points in the dashed line box in the minimum circumscribed matrix a in fig. 5); retake (B) 22 -1), i.e. 2, because of B 22 The adjacent front (i.e. left side thereof) has no value of 2 or more, i.e. n 2 =0, so S 2 = (0+1) × (3-1) =2; finally get (B) 22 -2), i.e. 1, because of B 22 The number of values of 1 or more in succession in the adjacent front (i.e. left side) is 2, i.e. n 3 =2, so S 3 = (2+1) × (3-2) =3 (i.e., corresponding to the rectangle formed by the pixels in the solid line box in the minimum circumscribed matrix a in fig. 5). Namely, each value in the area matrix S is the sum of pixels of the largest rectangle which are searched leftwards and upwards by taking the pixel points at the same position as the coordinates of the right lower corner of the rectangle in the corresponding minimum circumscribed matrix A.
An example diagram of the calculation of the full area matrix S from the height matrix B is shown with reference to fig. 6.
Step S043: the top left corner coordinates of the maximum area rectangle are recorded.
In the process of calculating the area matrix S in the last step, the coordinates of the upper left corner of the maximum area rectangle are recorded through the sparse matrix K.
Step S044: and calculating the maximum area coordinates.
Searching the maximum value, namely the maximum area coordinate S, in the calculated area matrix S ji max If there are a plurality of values, the coordinate closest to the center of the area matrix S is taken, and if there are still a plurality of values, one of the coordinates is taken at random as the maximum area coordinate S ji max . In the minimum circumscribed matrix A, corresponding to the maximum area coordinate S ji max The pixel point of the position is rectangular lower right corner coordinate and faces toThe largest rectangle found from left to right is the largest area rectangle.
Specifically, in calculating the maximum area coordinate S ji max When the maximum area coordinate S ji max There are a plurality of values, one of which is randomly taken as the maximum area coordinate S ji max The calculation formula of (2) is as follows:
S ji max ＝random(min(abs((S j -K j )/2-H/2))+abs((S i -K i )/2-W/2))))
wherein H is the height of the matrix K, W is the width of the matrix K, K j Maximum area coordinate S recorded for matrix K ji max Row coordinates of upper left corner of maximum area rectangle, K i Maximum area coordinate S recorded for matrix K ji max Column coordinates of upper left corner of corresponding maximum area rectangle, S j Is the maximum area coordinate S ji max Row coordinates of S i Is the maximum area coordinate S ji max Is a column coordinate of (c).
In the present embodiment, the maximum area coordinate S ji max For S in the area matrix S in FIG. 7 45 =9, which may correspond to a solid line box in the minimum circumscribed matrix a, where the solid line box is the maximum area rectangle found.
Step S05: taking the largest area rectangle as the center, gradually and inwards aggregating other image pixels marked as 1 outside the largest area rectangle and inside the smallest circumscribed rectangle into a rectangle by adopting a quicksand filling mode, and specifically comprising the following steps of:
referring to fig. 8, in the minimum circumscribed matrix a, starting from the left side of the outermost four sides of the maximum area rectangle, the four sides are searched and filled layer by layer outwards in a clockwise direction; when the nth side outside the maximum area rectangle is filled, n is a positive integer greater than or equal to 1, the pixel with 1 in the nth side is unchanged, and the pixel with 0 is filled by the pixel with 1 in the nearest pixel of the (n+1) th side which is the outer side adjacent to the nth side, wherein the nearest pixel is the (n+1) th side, and takes the maximum area rectangle as the center, and the left and right included angles of the nearest pixel are left and right included angles of the nearest pixel.
Specifically, the step-by-step inward polymerization of the sand-flow filling mode into a rectangle comprises the following steps: starting from the left side of the four outermost sides of the largest area rectangle, the first column outside of the rectangle is S k K is a natural number greater than or equal to 0, then S k The position of 1 in the column remains unchanged, S k The position in the column of 0 is from (S) k -1) column and filling the S-th pixel with a search value of 1 among pixels within a left-right opening range of 45 DEG included angle around the maximum area rectangle k Positions listed as 0; repeating the steps, searching all data outwards layer by side in the clockwise direction on the four outermost sides of the rectangle with the largest area.
FIG. 8 shows a search direction of a quicksand filling and a filling example, in which a solid line box indicates a maximum area rectangle, and a curved dotted arrow indicates a point (S) k -1) filling 1 in column to S k The position in the column where the pixel is 0, the curved solid arrow indicates the direction of the look-up looking up in a clockwise order, side-by-side, layer-by-layer, outwards.
Step S06: when all or part of the data of the four outermost sides of the aggregated rectangle is not filled with 1, the data of the four outermost sides are recombined, and the most sides are filled as much as possible, wherein the processing mode is as follows: referring to fig. 9, data of four outermost sides are converged to the upper left corner point of the aggregated rectangle in turn in a counterclockwise direction; and starting from the upper edge of the four outermost edges of the converged rectangle, sequentially checking the data of the four edges in a clockwise direction, reserving the edges filled with the data, and discarding the edges not filled with the data.
Step S07: cutting the processed rectangle into N rectangular areas, wherein N is a positive integer greater than 1, and specifically comprises the following steps:
calculating the length of a short side, wherein the short side is the shorter side in the processed rectangle, and the longer side is the long side; calculating the number of times of cutting the short side and the long side, wherein the number of times is X and Y respectively, and the rectangular area cut according to X, Y is closest to a square; calculating the cut coordinates according to X, Y, and performing rectangular cutting; if the processed rectangle is square, the short side and the long side are the side length of the square, and x=y.
Specifically, let the length of the short side of the processed rectangle be h, the length of the long side be w, w > =h, and the number of parts X to be cut of the short side and the number of parts Y to be cut of the long side be calculated according to the following formula, X, Y are integers greater than or equal to 1:
x Y + z=n, and X, Y, Z values satisfy the following constraints at the same time,
(1) Z is 0 or 1;
(2)Y>＝X；
(3) The absolute value of (Y-X) is the smallest;
calculating the position coordinates of short-side cutting, wherein the coordinates of the x-th part of short-side cutting are as follows: x (h/X) and rounding (e.g., round rounding), x=1, … …, X-1;
calculating the position coordinates of the long-side cutting, and when z=0, calculating the y coordinates of the long-side cutting as follows: y (w/Y) and rounding (e.g., round rounding), y=1, … …, Y-1; when z=1, the coordinates of the y' th part of the long side cut are: y '× (w/(y+1)) and rounded (e.g., round), Y' =1, … …, Y, i.e., when Z is 1, the number of cut parts of the long side is actually (y+1).
Fig. 10 shows an example of rectangular cutting when z=0, and referring to fig. 10, the length of the short side of the rectangle is h, and the length of the long side of the rectangle is w. The cutting mode is as follows: the rectangle is divided into 8 rectangular areas, i.e., n=8, wherein the short side is cut into 2 parts and the long side is cut into 4 parts, i.e., x=2, y=4.
The coordinates of the first portion of the short side cut are: x is x 1 ＝round(1*(h/2))；
The coordinates of the first part of the long side cutting are: y is 1 ＝round(1*(w/4))；
The coordinates of the second part of the long side cut are: y is 2 ＝round(2*(w/4))；
The coordinates of the third portion of the long side cut are: y is 3 ＝round(3*(w/4))。
Fig. 11 shows an example of rectangular cutting when z=1, and referring to fig. 11, the length of the short side of the rectangle is h, and the length of the long side of the rectangle is w. The cutting mode is as follows: the rectangle is divided into 7 rectangular areas, i.e., n=7, wherein the short side is cut into 2 parts and the long side is cut into 3 parts, i.e., x=2, y=3.
The coordinates of the first portion of the short side cut are: x is x 1 ＝round(1*(h/2))；
The coordinates of the first part of the long side cutting are: y is 1 ’＝round(1*(w/(3+1)))；
The coordinates of the second part of the long side cut are: y is 2 ’＝round(2*(w/(3+1)))；
The coordinates of the third portion of the long side cut are: y is 3 ’＝round(3*(w/(3+1)))。
It can be seen that when Z is 1, the number of cut parts on the long side is actually 4 parts, i.e., (Y+1) parts.
Referring to fig. 12, the present embodiment also provides a system 100 for reshaping an arbitrarily shaped image area into N rectangular areas, comprising:
the region of interest confirming module 101 is configured to obtain an original image to be processed, and obtain a region of interest of the original image, where the region of interest is in an arbitrary shape;
the original image binarization processing module 102 is used for performing binarization processing on the original image, wherein the pixels of the region of interest are marked as 1, and the pixels of other regions are marked as 0;
the minimum circumscribed rectangle searching module 103 is used for shearing the region of interest to obtain a minimum circumscribed rectangle of the region of interest along the horizontal direction;
the maximum area rectangle searching module 104 is configured to search, according to a preset rule, a rectangle with the largest area, that is, a rectangle with the largest area, in the cut minimum circumscribed rectangle;
the quicksand filling module 105 is used for gradually and inwards aggregating other image pixels marked as 1 outside the maximum area rectangle and inside the minimum circumscribed rectangle into a rectangle by adopting a quicksand filling mode by taking the maximum area rectangle as the center;
the data reorganization module 106 is configured to reorganize the data of the four outermost sides of the aggregated rectangle when all or part of the data of the four outermost sides is not fully filled with 1, where the most edges are fully filled as possible; if the edge which is not filled with 1 still exists after the data is recombined, discarding the edge;
the rectangular cutting module 107 is configured to cut the processed rectangle into N rectangular areas, where N is a positive integer greater than 1.
For the specific working process of each module, the method for reshaping an image area with any shape into N rectangular areas provided in the embodiment of the present invention may be further referred to and will not be repeated here.
In summary, the method and the system for remolding the image area with any shape into the N rectangular areas can remodel the image area with any shape of interest in the image into the N rectangular areas as the algorithm input of various image processing, so that various algorithm calculations can be conveniently carried out on the image area with any interest, the accuracy of the algorithm output of the image processing is improved, the distortion of the image processing is effectively avoided, and the development of intelligent application is accelerated.
The above description of the specific embodiments of the present invention has been given by way of example only, and the present invention is not limited to the above described specific embodiments. Any equivalent modifications and substitutions for the present invention will occur to those skilled in the art, and are also within the scope of the present invention. Accordingly, equivalent changes and modifications are intended to be included within the scope of the present invention without departing from the spirit and scope thereof.
Claims (7)
1. A method of reshaping an arbitrarily shaped image area into N rectangular areas comprising:
acquiring an original image to be processed, and confirming an interested area of the original image, wherein the interested area is in any shape;
performing binarization processing on the original image, wherein the pixels of the region of interest are marked as 1, and the pixels of other regions are marked as 0;
shearing the region of interest to obtain a minimum circumscribed rectangle of the region of interest along the horizontal direction;
searching a rectangle with the largest area from the sheared minimum circumscribed rectangle according to a preset rule, namely, the rectangle with the largest area;
taking the central point of the rectangle with the largest area as the center, gradually and inwards polymerizing other image pixels marked as 1 outside the rectangle with the largest area and inside the rectangle with the smallest circumscribed area into a rectangle by adopting a quicksand filling mode;
when all or part of the data of the four outermost sides of the aggregated rectangle are not filled with 1, the data of the four outermost sides are recombined, and the most sides are filled as much as possible; if the edge which is not filled with 1 still exists after the data is recombined, discarding the edge;
cutting the processed rectangle into N rectangular areas, wherein N is a positive integer greater than 1;
the method for searching the rectangle with the largest area, namely the rectangle with the largest area, in the sheared minimum circumscribed rectangle according to a preset rule comprises the following steps:
traversing from top to bottom in the minimum circumscribed rectangle;
each current row and the blocks with continuous 1 in the y-axis direction of the traversed rows form columns with different heights, and height values are recorded;
searching each point from left to right as a maximum rectangle which can be formed by the right lower corner coordinates in the columnar graph with different heights in the last step;
calculating the area of the largest rectangle, judging whether the area is the largest, and updating the coordinates of the largest rectangle if the area is the largest;
repeating the steps until all the rows are traversed, and obtaining the rectangular coordinates with the largest area;
the step of gradually aggregating other image pixels marked as 1 outside the largest area rectangle and inside the smallest circumscribed rectangle into a rectangle by adopting a quicksand filling mode by taking the central point of the largest area rectangle as the center comprises the following steps: starting from the left side of the four sides at the outermost side of the rectangle with the largest area, searching and filling the four sides layer by layer outwards in a clockwise direction; when the nth edge outside the maximum area rectangle is filled, n is a positive integer greater than or equal to 1, the pixel with 1 in the nth edge is unchanged, and the pixel with 0 is filled by the pixel with 1 in the nearest pixel of the (n+1) th edge which is the adjacent external edge of the nth edge, wherein the nearest pixel is the (n+1) th edge, and takes the central point of the maximum area rectangle as the center, and the left and right included angles of the pixels are left and right included angles of the pixels within the left and right opening ranges;
after the other pixels outside the rectangle with the largest area and inside the rectangle with the smallest circumscribed area are gradually and inwards aggregated into the rectangle by adopting a quicksand filling mode, the four sides at the outermost side are subjected to data recombination, the sides with the largest filling amount are filled as much as possible, and if the sides which are not filled with 1 are still present after the data recombination, the sides are discarded, and the method comprises the following steps:
sequentially converging the data of the four outermost sides of the aggregated rectangle to the left upper corner point of the rectangle according to the anticlockwise direction;
and starting from the upper edge of the four outermost edges of the converged rectangle, sequentially checking the data of the four edges in a clockwise direction, reserving the edges filled with the data, and discarding the edges not filled with the data.
2. The method of reshaping an arbitrarily shaped image area into N rectangular areas as in claim 1 wherein the clipping out the smallest bounding rectangle of the area of interest in the horizontal direction comprises the steps of:
starting from the left side of the four outermost sides of the binarized image, sequentially searching coordinates of the first 1 from outside to inside in a clockwise direction, and sequentially marking the coordinates as X min 、Y min 、X max 、Y max ；
The upper left corner of the area of the smallest bounding rectangle is marked (X) min ，Y min ) The lower right corner is marked as (X) max ，Y max )。
3. The method of reshaping an arbitrarily shaped image area into N rectangular areas as in claim 1 wherein the corresponding matrix of the smallest bounding rectangle is the smallest bounding matrix a, and a has the coordinates X min :X max ,Y min :Y max ]Wherein, (X min ，Y min ) And (X) max ，Y max ) Respectively the areas of smallest bounding rectangleThe method comprises the steps of searching a rectangle with the largest area according to a preset rule, and performing matrix transformation and area calculation; wherein,
the matrix transformation step includes:
transforming the minimum circumscribed matrix A into a height matrix B, wherein each value in the height matrix B represents the maximum rectangular height which can be formed by upwards arranging the corresponding position in the minimum circumscribed matrix A in the y-axis direction, namely
Wherein j represents the j-th row of the matrix, i represents the i-th column of the matrix, and i and j are natural numbers greater than or equal to 0; a is that ji Pixels representing the j-th row and i-th column in the minimum circumscribed matrix A; b (B) ji Pixels representing the j-th row and i-th column in the height matrix B;
the area calculation step includes:
according to each pixel B in the height matrix B ji Sequentially calculating according to the following formula to obtain an area matrix S corresponding to the height matrix B, namely summing pixels of the largest rectangle searched leftwards and upwards by taking pixel points at the same position as the right lower corner coordinates of the rectangle in the minimum circumscribed matrix A corresponding to each value in the area matrix S, and obtaining the pixels B ji The calculation formula of (2) is as follows:
wherein S is ji Pixels representing the j-th row and i-th column in the area matrix S; n, n 1 ,n 2 ,……n n Are natural numbers greater than or equal to 0;
searching the maximum value, namely the maximum area coordinate S, in the calculated area matrix S jimax If there are a plurality of values, the coordinate closest to the center of the area matrix S is taken, and if there are still a plurality of values, one of the coordinates is taken at random as the maximum area coordinate S jimax The method comprises the steps of carrying out a first treatment on the surface of the In the minimum circumscribed matrix A, corresponding to the maximum area coordinate S jimax The pixel point of the position is the right lower corner coordinate of the rectangle, and the largest rectangle searched leftwards and upwards is the rectangle with the largest area.
4. A method of reshaping an arbitrarily shaped image area into N rectangular areas as in claim 3 wherein the coordinates of the top left corner of the largest area rectangle are recorded by a sparse matrix K during the calculation of the area matrix S; in calculating the maximum area coordinate S jimax When the maximum area coordinate S jimax There are a plurality of values, one of which is randomly taken as the maximum area coordinate S jimax The calculation formula of (2) is as follows:
S jimax ＝random(min(abs((S j -K j )/2-H/2))+abs((S i -K i )/2-W/2))))
wherein H is the height of the matrix K, W is the width of the matrix K, K j Maximum area coordinate S recorded for matrix K jimax Row coordinates of upper left corner of maximum area rectangle, K i Maximum area coordinate S recorded for matrix K jimax Column coordinates of upper left corner of corresponding maximum area rectangle, S j Is the maximum area coordinate S jimax Row coordinates of S i Is the maximum area coordinate S jimax Is a column coordinate of (c).
5. The method of reshaping an arbitrarily shaped image area into N rectangular areas as in claim 1 wherein the cutting the processed rectangle into N rectangular areas comprises the steps of:
calculating the length of a short side, wherein the short side is the shorter side in the processed rectangle, and the longer side is the long side;
calculating the number of times of cutting the short side and the long side, wherein the number of times is X and Y respectively, and the rectangular area cut according to X, Y is closest to a square;
calculating the cut coordinates according to X, Y, and performing rectangular cutting;
if the processed rectangle is square, the short side and the long side are the side length of the square, and x=y.
6. The method for reshaping an arbitrarily shaped image area into N rectangular areas according to claim 5, wherein the length of the short side of the processed rectangle is h, the length of the long side is w, w > = h, the number of times X the short side needs to be cut and the number of times Y the long side needs to be cut are each a positive integer of 1 or more calculated according to the following formula:
x Y + z=n, and X, Y, Z values satisfy the following constraints at the same time,
(1) Z is 0 or 1;
(2)Y>＝X；
(3) The absolute value of (Y-X) is the smallest;
calculating the position coordinates of short-side cutting, wherein the coordinates of the x-th part of short-side cutting are as follows: x (h/X) and rounding, x=1, … …, X-1;
calculating the position coordinates of the long-side cutting, and when z=0, calculating the y coordinates of the long-side cutting as follows: y (w/Y) and rounding, y=1, … …, Y-1; when z=1, the coordinates of the y' th part of the long side cut are: y '× (w/(y+1)) and rounded, Y' =1, … …, Y, i.e., when Z is 1, the number of cut parts of the long side is actually (y+1).
7. A system for reshaping an arbitrarily shaped image area into N rectangular areas comprising:
the device comprises an interested region confirming module, a processing module and a processing module, wherein the interested region confirming module is used for acquiring an original image to be processed and acquiring an interested region of the original image, and the interested region is in any shape;
the original image binarization processing module is used for performing binarization processing on the original image, wherein the pixels of the region of interest are marked as 1, and the pixels of other regions are marked as 0;
the minimum circumscribed rectangle searching module is used for shearing the region of interest and shearing a minimum circumscribed rectangle of the region of interest along the horizontal direction;
the maximum area rectangle searching module is used for searching the rectangle with the largest area in the sheared minimum circumscribed rectangle according to a preset rule, namely the rectangle with the largest area;
the quicksand type filling module is used for gradually and inwards polymerizing other image pixels marked as 1 outside the maximum area rectangle and inside the minimum circumscribed rectangle into a rectangle by adopting a quicksand type filling mode by taking the central point of the maximum area rectangle as the center;
the data reorganization module is used for reorganizing the data of the four outermost sides of the aggregated rectangle when all or part of the data of the four outermost sides are not filled with 1, and filling the edges with the most as much as possible; if the edge which is not filled with 1 still exists after the data is recombined, discarding the edge;
the rectangular cutting module is used for cutting the processed rectangle into N rectangular areas, wherein N is a positive integer greater than 1;
in the maximum area rectangle searching module, the preset rule comprises:
traversing from top to bottom in the minimum circumscribed rectangle;
each current row and the blocks with continuous 1 in the y-axis direction of the traversed rows form columns with different heights, and height values are recorded;
searching each point from left to right as a maximum rectangle which can be formed by the right lower corner coordinates in the columnar graph with different heights in the last step;
calculating the area of the largest rectangle, judging whether the area is the largest, and updating the coordinates of the largest rectangle if the area is the largest;
repeating the steps until all the rows are traversed, and obtaining the rectangular coordinates with the largest area;
wherein the quicksand filling module is configured to:
starting from the left side of the four sides at the outermost side of the rectangle with the largest area, searching and filling the four sides layer by layer outwards in a clockwise direction; when the nth edge outside the maximum area rectangle is filled, n is a positive integer greater than or equal to 1, the pixel with 1 in the nth edge is unchanged, and the pixel with 0 is filled by the pixel with 1 in the nearest pixel of the (n+1) th edge which is the adjacent external edge of the nth edge, wherein the nearest pixel is the (n+1) th edge, and takes the central point of the maximum area rectangle as the center, and the left and right included angles of the pixels are left and right included angles of the pixels within the left and right opening ranges;
wherein the data reorganization module is configured to:
sequentially converging the data of the four outermost sides of the aggregated rectangle to the left upper corner point of the rectangle according to the anticlockwise direction;
and starting from the upper edge of the four outermost edges of the converged rectangle, sequentially checking the data of the four edges in a clockwise direction, reserving the edges filled with the data, and discarding the edges not filled with the data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110186850.5A CN112991375B (en) | 2021-02-08 | 2021-02-08 | Method and system for remolding image area with arbitrary shape into N rectangular areas |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110186850.5A CN112991375B (en) | 2021-02-08 | 2021-02-08 | Method and system for remolding image area with arbitrary shape into N rectangular areas |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112991375A CN112991375A (en) | 2021-06-18 |
| CN112991375B true CN112991375B (en) | 2024-01-23 |
Family
ID=76393366
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110186850.5A Active CN112991375B (en) | 2021-02-08 | 2021-02-08 | Method and system for remolding image area with arbitrary shape into N rectangular areas |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112991375B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116934774B (en) * | 2023-06-30 | 2024-03-22 | 安徽大学 | Quick and high-precision panoramic image clipping method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957077A (en) * | 2015-04-29 | 2016-09-21 | 国网河南省电力公司电力科学研究院 | Detection method for foreign body in transmission lines based on visual saliency analysis |
| CN106898004A (en) * | 2017-01-04 | 2017-06-27 | 努比亚技术有限公司 | A kind of preprocess method for realizing interactive image segmentation, device and terminal |
| CN108205811A (en) * | 2016-12-16 | 2018-06-26 | 广东技术师范学院 | A kind of plant leaf blade minimum enclosed rectangle computational methods |
| CN108734131A (en) * | 2018-05-22 | 2018-11-02 | 杭州电子科技大学 | A kind of traffic sign symmetry detection methods in image |
| CN110782470A (en) * | 2019-11-04 | 2020-02-11 | 浙江工业大学 | Carpal bone region segmentation method based on shape information |
| CN111145261A (en) * | 2019-08-30 | 2020-05-12 | 广东星舆科技有限公司 | Method for identifying index point and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4162633B2 (en) * | 2004-06-30 | 2008-10-08 | 株式会社リコー | Image distortion correction apparatus, image reading apparatus, image forming apparatus, program, and storage medium |
| JP6600356B2 (en) * | 2015-06-24 | 2019-10-30 | オリンパス株式会社 | Image processing apparatus, endoscope apparatus, and program |
| CN109960988A (en) * | 2017-12-26 | 2019-07-02 | 浙江宇视科技有限公司 | Image analysis method, device, electronic equipment and readable storage medium storing program for executing |
-
2021
- 2021-02-08 CN CN202110186850.5A patent/CN112991375B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105957077A (en) * | 2015-04-29 | 2016-09-21 | 国网河南省电力公司电力科学研究院 | Detection method for foreign body in transmission lines based on visual saliency analysis |
| CN108205811A (en) * | 2016-12-16 | 2018-06-26 | 广东技术师范学院 | A kind of plant leaf blade minimum enclosed rectangle computational methods |
| CN106898004A (en) * | 2017-01-04 | 2017-06-27 | 努比亚技术有限公司 | A kind of preprocess method for realizing interactive image segmentation, device and terminal |
| CN108734131A (en) * | 2018-05-22 | 2018-11-02 | 杭州电子科技大学 | A kind of traffic sign symmetry detection methods in image |
| CN111145261A (en) * | 2019-08-30 | 2020-05-12 | 广东星舆科技有限公司 | Method for identifying index point and storage medium |
| CN110782470A (en) * | 2019-11-04 | 2020-02-11 | 浙江工业大学 | Carpal bone region segmentation method based on shape information |
Non-Patent Citations (2)
| Title |
|---|
| Mammogram classification using sparse-ROI: A novel representation to arbitrary shaped masses;Karteeka Pavan Kanadam等;《Expert Systems with Applications》;204–213 * |
| 基于图像分割的目标尺寸特征测量;王颖;王鹏飞;杨余旺;;计算机技术与发展(02);197-201 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112991375A (en) | 2021-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107045634B (en) | Text positioning method based on maximum stable extremum region and stroke width | |
| US20090016608A1 (en) | Character recognition method | |
| CN110503610B (en) | GAN network-based image rain and snow trace removing method | |
| KR20130016213A (en) | Text enhancement of a textual image undergoing optical character recognition | |
| CN112991375B (en) | Method and system for remolding image area with arbitrary shape into N rectangular areas | |
| CN110060260B (en) | Image processing method and system | |
| CN103402042A (en) | Halftone image generation method based on sectioned error diffusion | |
| CN114529925A (en) | Method for identifying table structure of whole line table | |
| CN111062331A (en) | Mosaic detection method and device for image, electronic equipment and storage medium | |
| CN112883983A (en) | Feature extraction method and device and electronic system | |
| KR100988380B1 (en) | Image retargeting method using importance diffusion, storage medium of storing program for executing the same and apparatus performing the same | |
| CN115909353A (en) | Image binarization processing method and device | |
| US20170195520A1 (en) | Image processing method, apparatus, and image forming device | |
| CN113963009A (en) | Local self-attention image processing method and model based on deformable blocks | |
| CN113077477B (en) | Image vectorization method and device and terminal equipment | |
| US20100008599A1 (en) | Resolution Converting Method | |
| JPH0830787A (en) | Image area dividing method and image area integrating method | |
| JP2012070269A (en) | Image processing apparatus and image processing method | |
| CN117058338A (en) | CAD-based three-dimensional building model construction method, system, equipment and medium | |
| CN116883441A (en) | Point cloud building contour line extraction method capable of guaranteeing fitting precision | |
| CN114511862B (en) | Form identification method and device and electronic equipment | |
| CN111178371B (en) | Target detection method, device and computer storage medium | |
| JP6116271B2 (en) | Feature amount calculation apparatus, method, and program | |
| CN111260723A (en) | Barycenter positioning method of bar and terminal equipment | |
| CN113487624B (en) | Human body instance segmentation method, terminal equipment and storage 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 | ||
| CB02 | Change of applicant information |
Address after: 200435 11th Floor, Building 27, Lane 99, Shouyang Road, Jing'an District, Shanghai Applicant after: Shanghai Tongban Information Service Co.,Ltd. Address before: 709, building a, Harui center, 555 Shouyang Road, Jing'an District, Shanghai 200072 Applicant before: Shanghai Tongban Information Service Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |