CN113298790B - Image filtering method, device, terminal and computer readable storage medium - Google Patents
Image filtering method, device, terminal and computer readable storage medium Download PDFInfo
- Publication number
- CN113298790B CN113298790B CN202110598742.9A CN202110598742A CN113298790B CN 113298790 B CN113298790 B CN 113298790B CN 202110598742 A CN202110598742 A CN 202110598742A CN 113298790 B CN113298790 B CN 113298790B
- Authority
- CN
- China
- Prior art keywords
- pixel
- matrix
- pixels
- pixel matrix
- column
- 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 58
- 238000001914 filtration Methods 0.000 title claims abstract description 46
- 239000011159 matrix material Substances 0.000 claims description 360
- 238000012163 sequencing technique Methods 0.000 claims description 51
- 238000004590 computer program Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 abstract description 10
- 230000008569 process Effects 0.000 description 15
- 238000004364 calculation method Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 235000002566 Capsicum Nutrition 0.000 description 3
- 239000006002 Pepper Substances 0.000 description 3
- 241000722363 Piper Species 0.000 description 3
- 235000016761 Piper aduncum Nutrition 0.000 description 3
- 235000017804 Piper guineense Nutrition 0.000 description 3
- 235000008184 Piper nigrum Nutrition 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 150000003839 salts Chemical class 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The application belongs to the technical field of image processing and mainly provides an image filtering method, an image filtering device, a terminal and a computer readable storage medium.
Description
Technical Field
The application belongs to the technical field of image processing, and particularly relates to an image filtering method, an image filtering device, a terminal and a computer readable storage medium.
Background
Noise is very common in the image field, impulse noise being one of the common types of noise. Impulse noise is also known as salt and pepper noise, because it is thought that impulse noise is caused by the fact that a digital image signal is strongly disturbed for a short period of time, so that some pixels of an image become white or black, and as the pixels which are disturbed with strong disturbance become more and more large, the bright spots on the image appear as if salt particles are scattered on the image, and the dark spots appear as pepper particles.
In the prior art, median filtering is generally used for filtering salt and pepper noise, however, when an image is filtered by adopting a median filtering method, the problem of low filtering efficiency often exists.
Disclosure of Invention
An object of the present application is to provide an image filtering method, apparatus, terminal, and computer-readable storage medium, which can improve the efficiency of image filtering.
A first aspect of an embodiment of the present application provides an image filtering method, including:
acquiring a first pixel matrix obtained by sliding the sliding window on an image to be filtered each time; the sliding window comprises a current pixel and a neighborhood pixel of the current pixel in the image to be filtered;
removing redundant pixels in each first pixel matrix to obtain second pixel matrixes corresponding to the first pixel matrixes;
determining pixel values of target pixels in the first pixel matrixes corresponding to the second pixel matrixes according to the pixel values of the pixels in the second pixel matrixes, and obtaining target images corresponding to the images to be filtered; wherein the target pixel in the first pixel matrix is equivalent to the current pixel of the sliding window.
Optionally, based on the image filtering method provided in the first aspect, in a first possible implementation manner of the present application, the removing redundant pixels in each first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix includes:
sorting pixels in each first pixel matrix to obtain sorted first pixel matrixes corresponding to each first pixel matrix;
and removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix.
Optionally, based on the first possible implementation manner, in a second possible implementation manner of the present application, the sorting pixels in each first pixel matrix to obtain a sorted first pixel matrix corresponding to each first pixel matrix includes:
sequencing each row of pixels in each first pixel matrix, and sequencing each column of pixels in each first pixel matrix to obtain sequenced first pixel matrixes corresponding to each first pixel matrix;
or,
and sequencing each column of pixels in each first pixel matrix respectively, and sequencing each row of pixels in each first pixel matrix to obtain sequenced first pixel matrixes corresponding to the first pixel matrixes.
Optionally, based on the first possible implementation manner and the second possible implementation manner, in a third possible implementation manner of the present application, the redundant pixel includes: the pixel of the column of the maximum pixel value in the first pixel matrix after sequencing is except the first pixel, the pixel of the column of the middle pixel value in the first pixel matrix after sequencing is except the second pixel, and the pixel of the column of the minimum pixel value in the first pixel matrix after sequencing is except the third pixel; wherein, the first pixel is the pixel corresponding to the minimum pixel value of the column where the maximum pixel value is located in the first pixel matrix after sequencing; the second pixels are pixels corresponding to intermediate pixel values of columns where the intermediate pixel values are located in the first pixel matrix after sequencing; the third pixel is a pixel corresponding to the maximum pixel value of the column where the minimum pixel value is located in the first pixel matrix after sequencing;
removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix, wherein the method comprises the following steps:
removing pixels except the first pixels in a column of the maximum pixel value in each ordered first pixel matrix; removing pixels except the second pixels in the columns of the intermediate pixel values in each ordered first pixel matrix; and removing the pixels except the third pixels in the column of the minimum pixel value in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix.
Optionally, based on the first possible implementation manner and the second possible implementation manner, in a fourth possible implementation manner of the present application, the redundant pixel includes: based on the ordered diagonal symmetric partial pixels of the first pixel matrix;
removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix, wherein the method comprises the following steps:
and removing partial pixels which are symmetrical based on the diagonal lines of the first pixel matrixes in each ordered first pixel matrix, and obtaining second pixel matrixes corresponding to the first pixel matrixes.
Optionally, based on the first possible implementation manner and the second possible implementation manner, in a fifth possible implementation manner of the present application, the redundant pixel includes: based on the ordered diagonal symmetric partial pixels of the first pixel matrix;
removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix, wherein the method comprises the following steps:
removing partial pixels which are symmetrical based on a diagonal line of the first pixel matrix in each ordered first pixel matrix, and carrying out average grouping on pixels except the partial pixels in each ordered first pixel matrix to obtain a matrix which is corresponding to each ordered first pixel matrix and is preliminarily removed with redundant pixels;
Sequencing the matrixes of each primary redundancy pixel removal to obtain a third pixel matrix corresponding to each matrix of each primary redundancy pixel removal;
removing the pixels except the fourth pixel in the column of the maximum pixel value in each third pixel matrix; removing pixels except for a fifth pixel in a column where the middle pixel value in each third pixel matrix is located; removing pixels except the sixth pixel in the column of the minimum pixel value in each third pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix; the fourth pixel is a pixel corresponding to a minimum pixel value of a column where a maximum pixel value in the third pixel matrix is located; the fifth pixel is a pixel corresponding to the middle pixel value of the column where the middle pixel value is located in the third pixel matrix; the sixth pixel is a pixel corresponding to the maximum pixel value of the column where the minimum pixel value is located in the third pixel matrix.
Optionally, based on the fourth and fifth possible embodiments, in a sixth possible implementation of the present application, the first pixel matrix after being ordered is a matrix containing h×h pixel values;
The obtaining of the partial pixels based on the diagonal symmetry of the first pixel matrix after sequencing includes:
taking a connecting line of the position of the first pixel matrix after sequencing and the position of the last pixel as a diagonal line of the first pixel matrix after sequencing;
taking the diagonal line as a symmetry axis, respectively taking the first pixel and the last pixel as starting points, extending to edge pixels of the first pixel matrix after sequencing, and sequentially obtaining the partial pixels which comprise the first pixel, the last pixel and (H-1)/2 edge pixels which are symmetrical about the symmetry axis in the first pixel matrix after sequencing;
wherein the edge pixels are the first row pixels, the last row pixels, the first column pixels and the last column pixels of the first pixel matrix after being ordered, and (H-1)/2 edge pixels do not contain the first pixels and the last pixels.
The second aspect of the embodiments of the present application further provides an image filtering apparatus, including:
the acquisition unit is used for acquiring a first pixel matrix obtained by sliding the sliding window on the image to be filtered every time; the sliding window comprises a current pixel and a neighborhood pixel of the current pixel in the image to be filtered;
The removing unit is used for removing redundant pixels in each first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix;
the determining unit is used for determining the pixel value of the target pixel in each first pixel matrix corresponding to the second pixel matrix according to the pixel value of the pixel in the second pixel matrix to obtain a target image corresponding to the image to be filtered; wherein the target pixel in the first pixel matrix is equivalent to the current pixel of the sliding window.
A third aspect of the embodiments of the present application provides a terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the computer program implements the steps of the image filtering method described in the first aspect.
A fourth aspect of the embodiments of the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the steps of the image filtering method described in the first aspect.
In the embodiment of the application, the redundant pixels in each first pixel matrix are removed to obtain the second pixel matrix corresponding to each first pixel matrix, so that the number of ordered data is reduced in the process of taking the median of the pixel value of the pixel in the second pixel matrix as the pixel value of the target pixel in the first pixel matrix corresponding to the second pixel matrix, and the efficiency of filtering the image to be filtered is effectively improved.
Drawings
Fig. 1 is a schematic implementation flow chart of an image filtering method according to an embodiment of the present application.
Fig. 2 is a schematic flowchart of a specific implementation of the image filtering method step 102 provided in the embodiment of the present application.
Fig. 3 is a schematic flowchart of a specific implementation of the image filtering method step 202 provided in the embodiment of the present application.
Fig. 4 is a schematic structural diagram of an image filtering device according to an embodiment of the present application.
Fig. 5 is a schematic diagram of a terminal provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference 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 present application.
Fig. 1 is a schematic flow chart of an implementation of an image filtering method according to an embodiment of the present application, where the method may be executed by an image filtering device configured on a terminal. The terminal may be a device that needs to perform image filtering, for example, the terminal may be a terminal device such as a mobile phone, a tablet computer, or the like.
Specifically, the image filtering method provided in the embodiment of the present application may include steps 101 to 103, which are described in detail below:
In the embodiment of the application, the size of the sliding window is smaller than or equal to the size of the image to be filtered; the step length of each sliding of the sliding window on the image to be filtered can be one pixel; the pixel located in the center of the first pixel matrix (i.e., the current pixel) is the target pixel in the first pixel matrix, which corresponds to the pixel at the corresponding position in the image to be filtered.
According to the method, the first pixel matrixes obtained by sliding the sliding window with the preset size on the image to be filtered each time are obtained, and the pixel value of the target pixel in each first pixel matrix is calculated, so that the target image corresponding to the image to be filtered is obtained.
The size of the sliding window can determine the blurring degree of the target image, and the larger the size of the sliding window is, the higher the blurring degree of the target image is, so that the preset size can be determined according to the actual application scene of the target image.
Optionally, in some embodiments of the present application, in step 103, in a process of determining a pixel value of a target pixel in the first pixel matrix corresponding to the second pixel matrix according to a pixel value of each pixel in the second pixel matrix, a median of the pixel values of the pixels in the second pixel matrix may be calculated, and the median is taken as the pixel value of the target pixel in the first pixel matrix corresponding to the second pixel matrix, so as to obtain the target image corresponding to the image to be filtered.
At present, when median filtering is performed on an image, as all pixels in each sliding window of the whole image are required to be fetched, then the pixel values of all the pixels are ordered one by one, and then the median of the pixel values is taken as the pixel value of the target pixel of the sliding window, the efficiency is very low, the output frame rate of the image is seriously affected, and the power consumption is also greatly increased.
According to the method and the device, the redundant pixels in each first pixel matrix are removed, so that the second pixel matrix corresponding to each first pixel matrix is obtained, the number of median of pixel values of pixels in each second pixel matrix is reduced, and the efficiency of filtering the image to be filtered is effectively improved in the process of taking the median of pixel values of pixels in each second pixel matrix as the pixel value of the target pixel in the first pixel matrix corresponding to the second pixel matrix.
Alternatively, as shown in fig. 2, in some embodiments of the present application, the foregoing step 102 of removing redundant pixels in each first pixel matrix may be implemented in the following manner from step 201 to step 202, which is described in detail below:
In the process of sorting pixels in each first pixel matrix, sorting pixels in each row in each first pixel matrix, and sorting pixels in each column in each first pixel matrix to obtain sorted first pixel matrixes corresponding to each first pixel matrix; or, each column of pixels in each first pixel matrix may be first ordered, and then each row of pixels in each first pixel matrix may be ordered, so as to obtain an ordered first pixel matrix corresponding to each first pixel matrix.
That is, the first pixel matrix may be an ordered first pixel matrix obtained by first performing row ordering and then performing column ordering, or an ordered first pixel matrix obtained by first performing column ordering and then performing row ordering.
The row sorting and the column sorting may be performed in order from small to large or in order from large to small, depending on the size of the pixel values.
For example, in the first pixel matrix shown in table 1 below, when the pixels in each of the first pixel matrices are ordered, each pixel in each row where the a0 position, the a1 position, the a2 position, the a3 position, and the a4 position are located may be ordered first, and then each pixel in each column where the a0 position, the b0 position, the c0 position, the d0 position, and the e0 position are located may be ordered, so as to obtain an ordered first pixel matrix obtained by first performing row ordering and then performing column ordering.
For example, in the first pixel matrix shown in table 1 below, in the process of sorting pixels in each of the first pixel matrices to obtain a sorted first pixel matrix corresponding to each of the first pixel matrices, each pixel in each column where the a0 position, the b0 position, the c0 position, the d0 position, and the e0 position are located may be sorted first, and then each pixel in each row where the a0 position, the a1 position, the a2 position, the a3 position, and the a4 position are located may be sorted first, to obtain a sorted first pixel matrix obtained by sorting columns and then sorting rows.
Table 1:
it should be noted that, since the first pixel matrix includes pixel values of multiple rows and multiple columns, in the process of sorting pixels in each first pixel matrix, when sorting pixels in each row in each first pixel matrix and sorting pixels in each column in each first pixel matrix, parallel processing can be implemented, that is, sorting pixels in each row in each first pixel matrix in a parallel processing manner, and then sorting pixels in each column in each first pixel matrix in a parallel processing manner, so as to further improve filtering efficiency of an image, and the problem of low filtering efficiency of an image caused by sequential sorting of all data in a traditional median filtering method is broken through.
It should be further noted that, in the step 201, in the process of sorting the pixels in each first pixel matrix to obtain the sorted first pixel matrix corresponding to each first pixel matrix, except for the sorted first pixel matrix obtained by first sorting by row and then sorting by column and the sorted first pixel matrix obtained by first sorting by column and then sorting by row, in some embodiments of the present application, the pixels in each first pixel matrix may be equally divided into multiple groups, then the pixel values of each group of pixels may be sorted, and the number of each group of pixels may be greater than or less than the number of each row of pixels of the first pixel matrix, which is not limited in this application.
In this embodiment of the present application, in the process of removing the redundant pixels in each first pixel matrix in the above step 202, the removing may be implemented in various manners.
Optionally, in a first implementation manner of the present application, the redundant pixel may include: the method comprises the steps of sorting pixels except a first pixel in a column of a maximum pixel value in a first pixel matrix, sorting pixels except a second pixel in a column of an intermediate pixel value in the first pixel matrix, and sorting pixels except a third pixel in a column of a minimum pixel value in the first pixel matrix.
Wherein, the first pixel is the pixel corresponding to the minimum pixel value of the column where the maximum pixel value is located in the first pixel matrix after sequencing; the second pixels are pixels corresponding to intermediate pixel values of columns where the intermediate pixel values are located in the first pixel matrix after sequencing; the third pixel is the pixel corresponding to the maximum pixel value of the column where the minimum pixel value is located in the first pixel matrix after sequencing.
Correspondingly, in step 202 above, removing redundant pixels in each of the ordered first pixel matrices to obtain a second pixel matrix corresponding to each first pixel matrix may include: removing pixels except the first pixels in the column of the maximum pixel value in each ordered first pixel matrix; removing pixels except the second pixels in the columns of the intermediate pixel values in the first pixel matrix after each sequencing; and removing the pixels except the third pixels in the column of the minimum pixel value in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix.
Specifically, assuming that the first pixel matrix is a matrix including h×h pixel values, and H is an odd number, the first pixel matrix after sorting is a pixel matrix obtained by sorting rows according to the order of the pixel values from small to large and then sorting columns, where the maximum pixel value is located, is an H column, and the first pixel is the first pixel of the H column; the column where the intermediate pixel value in the first pixel matrix after sequencing is located is the (H+1)/2 th column, and the second pixel is the (H+1)/2 th pixel of the (H+1)/2 th column; the column of the minimum pixel value in the first pixel matrix after sequencing is the 1 st column, and the third pixel is the last pixel in the first column.
For example, the first pixel matrix is a pixel matrix of 5*5 shown in the above table 1, the first pixel matrix after sorting is a pixel matrix obtained by sorting rows according to the order of the pixel values from small to large and then sorting columns, where the column where the maximum pixel value of the first pixel matrix after sorting is located is the 5 th column, and the first pixel of the 5 th column of the first pixel, that is, the pixel where e0 is located; the column of the intermediate pixel value in the ordered first pixel matrix is the 3 rd column, and the second pixel is the 3 rd pixel of the 3 rd column, namely, the pixel at the position of c 2; the column where the minimum pixel value is located in the first pixel matrix after sequencing is the 1 st column, and the third pixel is the last pixel in the 1 st column, namely, the pixel where a4 is located.
Based on the above, removing the pixels except the first pixels in the column where the maximum pixel value in each ordered first pixel matrix is located; removing pixels except the second pixels in the columns of the intermediate pixel values in the first pixel matrix after each sequencing; and removing the pixels except the third pixel in the column of the minimum pixel value in each ordered first pixel matrix, wherein the pixel matrix containing 25 pixel values of 5*5 is simplified to be a matrix with only 13 pixel values, so that the data volume ordered in the process of taking the median of the pixel values of each pixel in the second pixel matrix as the pixel value of the target pixel in the first pixel matrix corresponding to the second pixel matrix is effectively reduced, and the filtering efficiency of the image can be improved.
Optionally, in a second implementation manner of the present application, the redundant pixel may further include: based on diagonally symmetric partial pixels of the ordered first pixel matrix.
Accordingly, in some embodiments of the present application, the removing redundant pixels in each of the ordered first pixel matrices to obtain a second pixel matrix corresponding to each first pixel matrix in step 202 may include: and removing partial pixels which are symmetrical based on the diagonal lines of the first pixel matrixes in each ordered first pixel matrix, and obtaining second pixel matrixes corresponding to the first pixel matrixes. That is, in the present embodiment, the pixels in the second pixel matrix are composed of pixels other than the partial pixels in the first pixel matrix.
Optionally, when the first ordered pixel matrix is a matrix containing h×h pixel values and H is an odd number, the obtaining the partial pixels based on diagonal symmetry of the first ordered pixel matrix may include: taking a connecting line of the position of the first pixel matrix after sequencing and the position of the last pixel as a diagonal line of the first pixel matrix after sequencing; and extending to the edge pixels of the first pixel matrix after sequencing by taking the diagonal line as a symmetry axis and taking the first pixel and the last pixel as starting points respectively to sequentially obtain the partial pixels which comprise the first pixel, the last pixel and (H-1)/2 edge pixels which are symmetrical about the symmetry axis in the first pixel matrix after sequencing.
Wherein the edge pixels are the first row pixels, the last row pixels, the first column pixels and the last column pixels of the first pixel matrix after being ordered, and (H-1)/2 edge pixels do not contain the first pixels and the last pixels.
For example, in a first pixel matrix of 7*7 shown in the following table two, acquiring a part of pixels symmetric based on a diagonal line of the first pixel matrix includes: taking a connecting line of the position of the first pixel a0 of the first pixel matrix after sequencing and the position of the last pixel g6 as a diagonal line of the first pixel matrix after sequencing; and extending the edge pixels of the first pixel matrix after sequencing by taking the diagonal line as a symmetry axis and taking the first pixel a0 and the last pixel g6 as starting points respectively, so as to sequentially obtain the partial pixels a0, b0, c0, d0, a1, a2, a3, g4, g5, g6, f6, e5 and d6 which comprise the first pixel, the last pixel and (H-1)/2 edge pixels symmetrical about the symmetry axis in the first pixel matrix after sequencing.
And (II) table:
optionally, when the number of pixels in the first pixel matrix is greater, after removing the part of pixels in each ordered first pixel matrix that are symmetric based on the diagonal of the first pixel matrix, the number of pixels in the second pixel matrix corresponding to each obtained first pixel matrix is still greater, so in order to further improve the efficiency of image filtering, in some embodiments of the present application, as shown in fig. 3, when the redundant pixels include: based on the ordered diagonally symmetrical partial pixels of the first pixel matrix, the above step 202 may be further implemented in the following manner shown in steps 301 to 303, which is described in detail below:
Optionally, in some embodiments of the present application, when the first ordered pixel matrix is a matrix including h×h pixel values, and H is an odd number, the average grouping the pixels in each first ordered pixel matrix except for the partial pixels includes: and equally dividing the pixels except the partial pixels in the first pixel matrix after each sequencing into H-2 groups, wherein each group contains H elements.
Specifically, when the pixels except the partial pixels in each ordered first pixel matrix are equally divided into H-2 groups, the first edge pixel of the first column of pixels in the ordered first pixel matrix may be taken as a starting point, the counterclockwise direction is taken as a reference direction, n=h-2, i is less than or equal to n, where the grouping more specifically includes: when i > (n+1)/2, the i-th group includes the i-th edge pixel, the second pixel, the third pixel, … …, the n+1th pixel and the n+2th column in the i+1th column 
A pixel; … …; the n-th group includes the n-th edge pixel, the second pixel, the third pixel, … …, the n+1th pixel and the (n+1)/2-th pixel of the n+2th column in the n+1th column; when i is less than or equal to (n+1)/2, the pixels included in the ith group are the ith edge pixel, the first pixel, the second pixel, … …, the nth pixel and the (th) in the (i+1) th column>
First pixel of column, +.>
The group comprises pixels of +.>
Edge pixels, the first
The first pixel in the column, the second pixel, … …, the nth pixel and the first pixel in the n+2th column, and so on.
In other embodiments of the present application, the pixels except for the partial pixels in the first pixel matrix after each sorting may be further grouped in other manners, so as to obtain a matrix with preliminarily removed redundant pixels corresponding to the first pixel matrix after each sorting, which is not limited in the present application.
And step 302, sorting the matrix of each primary redundant pixel removal to obtain a third pixel matrix.
Optionally, the sorting the matrix of each of the preliminary redundant pixels includes sorting each of the pixel values in each of the groups to obtain a third pixel matrix.
The fourth pixel is a pixel corresponding to a minimum pixel value of a column where a maximum pixel value in the third pixel matrix is located; the fifth pixel is a pixel corresponding to the middle pixel value of the column where the middle pixel value is located in the third pixel matrix; the sixth pixel is a pixel corresponding to the maximum pixel value of the column where the minimum pixel value is located in the third pixel matrix.
Specifically, when the third pixel matrix is a matrix including (H-2) H pixels, and H is an odd number, in step 302, when the matrix of each of the preliminary redundancy-removed pixels is ordered, in order from the smaller pixel value to the larger pixel value, each row of pixels in the matrix of each of the preliminary redundancy-removed pixels is ordered, and the column where the largest pixel value in the third pixel matrix is located is the last column of the third pixel matrix, the column where the middle pixel value in the third pixel matrix is located is the (h+1)/2 column of the third pixel matrix, and the column where the smallest pixel value in the third pixel matrix is located is the first column of the third pixel matrix.
Optionally, in some embodiments of the present application, after the step 302, the method may further include: acquiring a seventh pixel, an eighth pixel and a ninth pixel in each third pixel matrix; and sequencing the pixel values of the seventh pixel, the eighth pixel and the ninth pixel to obtain the median of the pixel values of the seventh pixel, the eighth pixel and the ninth pixel, and taking the median of the pixel values of the seventh pixel, the eighth pixel and the ninth pixel as the pixel value of the target pixel in the first pixel matrix corresponding to each third pixel matrix.
The seventh pixel is a pixel corresponding to a minimum pixel value in a column where a maximum pixel value in the third pixel matrix is located, and the eighth pixel is a pixel corresponding to an intermediate pixel value in a column where an intermediate pixel value in the third pixel matrix is located; and the ninth pixel is a pixel corresponding to the maximum pixel value in the column where the minimum pixel value is located in the third pixel matrix.
In the embodiment of the application, the redundant pixels in each first pixel matrix are removed to obtain the second pixel matrix corresponding to each first pixel matrix, so that the number of ordered data is reduced in the process of taking the median of the pixel values of each pixel in the second pixel matrix as the pixel value of the target pixel in the first pixel matrix corresponding to the second pixel matrix, and the efficiency of filtering the image to be filtered is effectively improved.
In addition, the method can be realized in a parallel processing mode when each row of pixels in the matrix are ordered or each column of pixels in the matrix are ordered, so that the time spent on ordering the pixels can be saved, the filtering efficiency of the image is improved, and the output frame rate of the image is ensured.
In this embodiment of the present application, the image to be filtered may be an image that needs to be filtered, such as a depth image, an infrared image, or a color image, which is not limited in this application.
When the image to be filtered is a depth image, the depth image may be a depth image acquired in the following manner.
Mode (1): the projection module projects a structured light beam to the target area, and the acquisition module receives the beam reflected back through the target area and forms an electrical signal. The electric signal is transmitted to a depth calculation module, the depth calculation module processes the electric signal, intensity information reflecting the light beam is calculated to form a structured light pattern, and finally matching calculation or trigonometry calculation is carried out based on the structured light pattern to obtain depth values of a plurality of pixel points so as to obtain a depth image of the target area.
Mode (2): the projection module projects an infrared beam to the target area, and the acquisition module receives the beam reflected back by the target area and forms an electric signal. The electric signals are transmitted to a depth calculation module, the depth calculation module processes the electric signals to calculate a phase difference, the flight time for light beams to be transmitted to an acquisition module by a projection module to be received is indirectly calculated based on the phase difference, and depth values of a plurality of pixel points are further calculated based on the flight time to obtain a depth image of a target area. It should be understood that the infrared beam may include both pulsed and continuous wave modes, and is not limited herein.
Mode (3): the projection module projects an infrared pulse beam to the target object, and the acquisition module receives the beam reflected by the target object and forms an electric signal. The electric signals are transmitted to a depth calculation module, the depth calculation module counts the electric signals to obtain a waveform histogram, the flight time used for being transmitted to an acquisition module by a projection module to be received is directly calculated according to the histogram, and the depth values of a plurality of pixel points are further calculated based on the flight time to obtain a depth image of a target area.
It should be understood that for the foregoing method embodiments, for simplicity of description, all of them are represented as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may occur in other orders in accordance with the application.
As shown in fig. 4, a schematic structural diagram of an image filtering device according to an embodiment of the present application may include: an acquisition unit 401, a removal unit 402, and a determination unit 403.
An obtaining unit 401, configured to obtain a first pixel matrix obtained by sliding on an image to be filtered each time using a sliding window; the sliding window comprises a current pixel and a neighborhood pixel of the current pixel in the image to be filtered;
A removing unit 402, configured to remove redundant pixels in each first pixel matrix, so as to obtain a second pixel matrix corresponding to each first pixel matrix;
a determining unit 403, configured to determine, according to pixel values of each pixel in the second pixel matrix, pixel values of target pixels in each first pixel matrix corresponding to the second pixel matrix, so as to obtain a target image corresponding to the image to be filtered; wherein the target pixel in the first pixel matrix is equivalent to the current pixel of the sliding window.
It should be noted that, for convenience and brevity of description, the specific working process of the image filtering apparatus described above may refer to the description of the image filtering method in fig. 1 to 3, and will not be repeated here. In addition, it should be noted that the foregoing embodiments may be combined with each other to obtain a plurality of different embodiments, which all fall within the scope of the present application.
As shown in fig. 5, the embodiment of the application further provides a terminal. The terminal may be provided with the image filtering means shown in the respective embodiments described above.
As shown in fig. 5, the terminal 5 may include: a processor 50, a memory 51 and a computer program 52 stored in the memory 51 and executable on the processor 50. The steps of the various image filtering method embodiments described above, e.g., steps 101 through 103 shown in fig. 1, are implemented when the processor 50 executes the computer program 52.
The processor 50 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor, but in the alternative, it may be any conventional processor or the like.
The storage 51 may be an internal storage unit of the terminal 5, for example, a hard disk or a memory. The memory 51 may also be an external storage device for the terminal 5, such as a plug-in hard disk provided on the terminal 5, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like. Further, the memory 51 may also include both an internal storage unit and an external storage device of the terminal 5. The memory 51 is used to store the above-mentioned computer programs and other programs and data required for the terminal.
The computer program may be divided into one or more modules/units, which are stored in the memory 51 and executed by the processor 50 to complete the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program in the terminal for user care. For example, the above-described computer program may be divided into: the specific functions of the acquisition unit, the removal unit and the determination unit are as follows:
The acquisition unit is used for acquiring a first pixel matrix obtained by sliding the sliding window on the image to be filtered every time; the sliding window comprises a current pixel and a neighborhood pixel of the current pixel in the image to be filtered;
the removing unit is used for removing redundant pixels in each first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix;
the determining unit is used for determining the pixel value of the target pixel in each first pixel matrix corresponding to the second pixel matrix according to the pixel value of each pixel in the second pixel matrix to obtain a target image corresponding to the image to be filtered; wherein the target pixel in the first pixel matrix is equivalent to the current pixel of the sliding window.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed terminal and method may be implemented in other manners. For example, the terminal embodiments described above are merely illustrative. For example, the division of a module or unit is merely a logical function division, and there may be another division manner when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (8)
1. An image filtering method, comprising:
acquiring a first pixel matrix obtained by sliding the sliding window on an image to be filtered each time; the sliding window comprises a current pixel and a neighborhood pixel of the current pixel in the image to be filtered;
removing redundant pixels in each first pixel matrix to obtain second pixel matrixes corresponding to the first pixel matrixes;
determining pixel values of target pixels in the first pixel matrixes corresponding to the second pixel matrixes according to the pixel values of the pixels in the second pixel matrixes, and obtaining target images corresponding to the images to be filtered; wherein the target pixel in the first pixel matrix is equivalent to the current pixel of the sliding window;
The removing redundant pixels in each first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix includes:
sorting pixels in each first pixel matrix to obtain sorted first pixel matrixes corresponding to each first pixel matrix;
removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix;
the redundant pixel includes: based on the ordered diagonal symmetric partial pixels of the first pixel matrix;
removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix, wherein the method comprises the following steps:
removing partial pixels which are symmetrical based on a diagonal line of the first pixel matrix in each ordered first pixel matrix, and carrying out average grouping on pixels except the partial pixels in each ordered first pixel matrix to obtain a matrix which is corresponding to each ordered first pixel matrix and is preliminarily removed with redundant pixels;
sequencing the matrixes of each primary redundancy pixel removal to obtain a third pixel matrix corresponding to each matrix of each primary redundancy pixel removal;
Removing the pixels except the fourth pixel in the column of the maximum pixel value in each third pixel matrix; removing pixels except for a fifth pixel in a column where the middle pixel value in each third pixel matrix is located; removing pixels except the sixth pixel in the column of the minimum pixel value in each third pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix; the fourth pixel is a pixel corresponding to a minimum pixel value of a column where a maximum pixel value in the third pixel matrix is located; the fifth pixel is a pixel corresponding to the middle pixel value of the column where the middle pixel value is located in the third pixel matrix;
the sixth pixel is a pixel corresponding to the maximum pixel value of the column where the minimum pixel value is located in the third pixel matrix.
2. The method of image filtering according to claim 1, wherein said sorting pixels in each of said first pixel matrices to obtain a sorted first pixel matrix corresponding to each of said first pixel matrices, comprises:
sequencing each row of pixels in each first pixel matrix, and sequencing each column of pixels in each first pixel matrix to obtain sequenced first pixel matrixes corresponding to each first pixel matrix;
Or,
and sequencing each column of pixels in each first pixel matrix respectively, and sequencing each row of pixels in each first pixel matrix to obtain sequenced first pixel matrixes corresponding to the first pixel matrixes.
3. The image filtering method according to claim 1 or 2, wherein the redundant pixel includes: the pixel of the column of the maximum pixel value in the first pixel matrix after sequencing is except the first pixel, the pixel of the column of the middle pixel value in the first pixel matrix after sequencing is except the second pixel, and the pixel of the column of the minimum pixel value in the first pixel matrix after sequencing is except the third pixel; wherein, the first pixel is the pixel corresponding to the minimum pixel value of the column where the maximum pixel value is located in the first pixel matrix after sequencing; the second pixels are pixels corresponding to intermediate pixel values of columns where the intermediate pixel values are located in the first pixel matrix after sequencing; the third pixel is a pixel corresponding to the maximum pixel value of the column where the minimum pixel value is located in the first pixel matrix after sequencing;
removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix, wherein the method comprises the following steps:
Removing pixels except the first pixels in a column of the maximum pixel value in each ordered first pixel matrix; removing pixels except the second pixels in the columns of the intermediate pixel values in each ordered first pixel matrix; and removing the pixels except the third pixels in the column of the minimum pixel value in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix.
4. The image filtering method of claim 1, wherein the redundant pixels comprise: based on the ordered diagonal symmetric partial pixels of the first pixel matrix;
removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix, wherein the method comprises the following steps:
and removing partial pixels which are symmetrical based on the diagonal lines of the first pixel matrixes in each ordered first pixel matrix, and obtaining second pixel matrixes corresponding to the first pixel matrixes.
5. The image filtering method of claim 4, wherein the first matrix of ordered pixels is a matrix comprising H x H pixel values;
The obtaining of the partial pixels based on the diagonal symmetry of the first pixel matrix after sequencing includes:
taking a connecting line of the position of the first pixel matrix after sequencing and the position of the last pixel as a diagonal line of the first pixel matrix after sequencing;
taking the diagonal line as a symmetry axis, respectively taking the first pixel and the last pixel as starting points, extending to edge pixels of the first pixel matrix after sequencing, and sequentially obtaining the partial pixels which comprise the first pixel, the last pixel and (H-1)/2 edge pixels which are symmetrical about the symmetry axis in the first pixel matrix after sequencing;
wherein the edge pixels are the first row pixels, the last row pixels, the first column pixels and the last column pixels of the first pixel matrix after being ordered, and (H-1)/2 edge pixels do not contain the first pixels and the last pixels.
6. An image filtering apparatus, comprising:
the acquisition unit is used for acquiring a first pixel matrix obtained by sliding the sliding window on the image to be filtered every time; the sliding window comprises a current pixel and a neighborhood pixel of the current pixel in the image to be filtered;
The removing unit is used for removing redundant pixels in each first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix;
the determining unit is used for determining the pixel value of the target pixel in each first pixel matrix corresponding to each second pixel matrix according to the pixel value of the pixel in each second pixel matrix to obtain a target image corresponding to the image to be filtered; wherein the target pixel in the first pixel matrix is equivalent to the current pixel of the sliding window;
the removing redundant pixels in each first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix includes:
sorting pixels in each first pixel matrix to obtain sorted first pixel matrixes corresponding to each first pixel matrix;
removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix;
the redundant pixel includes: based on the ordered diagonal symmetric partial pixels of the first pixel matrix;
removing redundant pixels in each sequenced first pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix, wherein the method comprises the following steps:
Removing partial pixels which are symmetrical based on a diagonal line of the first pixel matrix in each ordered first pixel matrix, and carrying out average grouping on pixels except the partial pixels in each ordered first pixel matrix to obtain a matrix which is corresponding to each ordered first pixel matrix and is preliminarily removed with redundant pixels;
sequencing the matrixes of each primary redundancy pixel removal to obtain a third pixel matrix corresponding to each matrix of each primary redundancy pixel removal;
removing the pixels except the fourth pixel in the column of the maximum pixel value in each third pixel matrix; removing pixels except for a fifth pixel in a column where the middle pixel value in each third pixel matrix is located; removing pixels except the sixth pixel in the column of the minimum pixel value in each third pixel matrix to obtain a second pixel matrix corresponding to each first pixel matrix; the fourth pixel is a pixel corresponding to a minimum pixel value of a column where a maximum pixel value in the third pixel matrix is located; the fifth pixel is a pixel corresponding to the middle pixel value of the column where the middle pixel value is located in the third pixel matrix;
The sixth pixel is a pixel corresponding to the maximum pixel value of the column where the minimum pixel value is located in the third pixel matrix.
7. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1-5 when the computer program is executed.
8. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1-5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110598742.9A CN113298790B (en) | 2021-05-31 | 2021-05-31 | Image filtering method, device, terminal and computer readable storage medium |
| PCT/CN2022/080526 WO2022252739A1 (en) | 2021-05-31 | 2022-03-13 | Image filtering method and apparatus, terminal, and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110598742.9A CN113298790B (en) | 2021-05-31 | 2021-05-31 | Image filtering method, device, terminal and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113298790A CN113298790A (en) | 2021-08-24 |
| CN113298790B true CN113298790B (en) | 2023-05-05 |
Family
ID=77326157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110598742.9A Active CN113298790B (en) | 2021-05-31 | 2021-05-31 | Image filtering method, device, terminal and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113298790B (en) |
| WO (1) | WO2022252739A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113298790B (en) * | 2021-05-31 | 2023-05-05 | 奥比中光科技集团股份有限公司 | Image filtering method, device, terminal and computer readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1341246A (en) * | 1999-02-05 | 2002-03-20 | 三星电子株式会社 | Color image processing method and apparatus thereof |
| CN110264482A (en) * | 2019-05-10 | 2019-09-20 | 河南科技大学 | Active contour dividing method based on middle intelligence set transformation matrix factorisation |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3204562B2 (en) * | 1993-03-18 | 2001-09-04 | 富士通株式会社 | Median filter processing method |
| US7912311B2 (en) * | 2005-03-21 | 2011-03-22 | Intel Corporation | Techniques to filter media signals |
| US8098913B2 (en) * | 2007-01-23 | 2012-01-17 | Kabushiki Kaisha Toshiba | Ultrasonic diagnostic apparatus and image filtering method of the same |
| CN102932661A (en) * | 2012-11-29 | 2013-02-13 | 重庆大学 | Median filtering matching error correction method for disparity map, and circuit for implementing method |
| US9898805B2 (en) * | 2015-02-11 | 2018-02-20 | Texas Instruments Incorporated | Method for efficient median filtering |
| CN104899842B (en) * | 2015-06-29 | 2018-08-10 | 济南大学 | The adaptive extreme value median filter method of sequence for remote line-structured light image |
| CN105335943A (en) * | 2015-09-24 | 2016-02-17 | 上海斐讯数据通信技术有限公司 | Image median filtering method and system |
| CN113298790B (en) * | 2021-05-31 | 2023-05-05 | 奥比中光科技集团股份有限公司 | Image filtering method, device, terminal and computer readable storage medium |
-
2021
- 2021-05-31 CN CN202110598742.9A patent/CN113298790B/en active Active
-
2022
- 2022-03-13 WO PCT/CN2022/080526 patent/WO2022252739A1/en active Application Filing
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1341246A (en) * | 1999-02-05 | 2002-03-20 | 三星电子株式会社 | Color image processing method and apparatus thereof |
| CN110264482A (en) * | 2019-05-10 | 2019-09-20 | 河南科技大学 | Active contour dividing method based on middle intelligence set transformation matrix factorisation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113298790A (en) | 2021-08-24 |
| WO2022252739A1 (en) | 2022-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3514735B1 (en) | A device and a method for image classification using a convolutional neural network | |
| CN110555847B (en) | Image processing method and device based on convolutional neural network | |
| CN111507909A (en) | Method and device for clearing fog image and storage medium | |
| CN107908998B (en) | Two-dimensional code decoding method and device, terminal equipment and computer readable storage medium | |
| CN110490204B (en) | Image processing method, image processing device and terminal | |
| US11244426B2 (en) | Method for image super resolution imitating optical zoom implemented on a resource-constrained mobile device, and a mobile device implementing the same | |
| CN113298790B (en) | Image filtering method, device, terminal and computer readable storage medium | |
| CN113298761B (en) | Image filtering method, device, terminal and computer readable storage medium | |
| CN110838088B (en) | Multi-frame noise reduction method and device based on deep learning and terminal equipment | |
| CN115937794B (en) | Small target object detection method and device, electronic equipment and storage medium | |
| CN111882565B (en) | Image binarization method, device, equipment and storage medium | |
| CN111738969A (en) | Image fusion method and device and computer readable storage medium | |
| EP0069542A2 (en) | Data processing arrangement | |
| CN114677319A (en) | Stem cell distribution determination method and device, electronic equipment and storage medium | |
| CN112489103A (en) | High-resolution depth map acquisition method and system | |
| EP0547881B1 (en) | Method and apparatus for implementing two-dimensional digital filters | |
| CN115587943B (en) | Denoising method and device for point cloud data, electronic equipment and storage medium | |
| Vasicek et al. | An area-efficient alternative to adaptive median filtering in fpgas | |
| CN110971837B (en) | ConvNet-based dim light image processing method and terminal equipment | |
| JP4621944B2 (en) | Image filter device, method and computer program | |
| CN112508065B (en) | Robot and positioning method and device thereof | |
| CN116107450A (en) | Touch point identification method and device of infrared touch screen and infrared touch screen | |
| CN111383171B (en) | Picture processing method, system and terminal equipment | |
| CN110012195B (en) | Method and device for reducing interference on depth camera, terminal equipment and storage medium | |
| Camunas-Mesa et al. | Fully digital AER convolution chip for vision processing |
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 |