CN116132824B - Image partition conversion method, system, electronic equipment and storage medium - Google Patents
Image partition conversion method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116132824B CN116132824B CN202310393846.5A CN202310393846A CN116132824B CN 116132824 B CN116132824 B CN 116132824B CN 202310393846 A CN202310393846 A CN 202310393846A CN 116132824 B CN116132824 B CN 116132824B
- Authority
- CN
- China
- Prior art keywords
- image
- gradient
- partition
- channel
- raw image
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/01—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level
- H04N7/0117—Conversion of standards, e.g. involving analogue television standards or digital television standards processed at pixel level involving conversion of the spatial resolution of the incoming video signal
Abstract
The invention provides an image partition conversion method, a system, an electronic device and a storage medium, wherein the acquired RAW image is processed to obtain a gradient image of the RAW image, then the gradient image is scanned from top to bottom in a progressive mode, the pixel number with the pixel value larger than a set pixel threshold value is obtained through superposition, the RAW image is partitioned according to the proportion of the scanned line number to the total line number of the gradient image when the pixel number is larger than the set pixel number threshold value, a complex partition and a simple partition are obtained, and finally the simple partition is converted by adopting a nearest neighbor interpolation method and the complex partition is converted by adopting a cubic spline interpolation method to obtain an RGB format image.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to an image partition conversion method, an image partition conversion system, an electronic device, and a storage medium.
Background
The demosaicing algorithm is a very important ring in the processing of images by a digital camera and an image signal processor, and has the main function of converting an image file (such as Bayer Pattern and the like) coming out of a photoelectric image sensor into a complete RGB data format which can be directly watched by human eyes so as to be directly displayed and output on a display device, so that the quality of the image display is directly determined by the demosaicing algorithm; since the demosaicing algorithm technology was proposed, researchers have researched various demosaicing algorithms, in general, a simple demosaicing algorithm is used, the output image quality is poor, but the operation complexity is low, and a complex demosaicing algorithm is used, the output image quality is very high, but the operation complexity is higher, so that in the actual process, how to consider the image quality and the operation efficiency becomes a hotspot and a difficult problem in the industry.
For high resolution images of 8K and above, the same demosaicing algorithm is used to represent a great disadvantage, mainly because: firstly, since the 8K image has ultra-high resolution, if a complex algorithm is globally used for pursuing imaging quality, a huge amount of calculation is brought; secondly, the 8K scene has typical scene characteristics of large picture, is quite wide, the upper part is mostly sky area background, the lower part is detail area scene which is more focused by human eyes, and a complex algorithm is unnecessary in an area which is not focused by human eyes, so that quality and efficiency cannot be considered.
Accordingly, there is a need to provide an image partition conversion method, system, electronic device, and storage medium that solve the above-mentioned technical problems.
Disclosure of Invention
In order to solve the technical problems, the invention provides an image partition conversion method, an image partition conversion system, electronic equipment and a storage medium, which are used for reducing the image resolution through a sampling method, then carrying out gradient judgment on a sampled low-resolution image to obtain an image edge, carrying out region-of-interest partition on the image, and using demosaicing algorithms with different complexity in different regions, thereby reducing the operation complexity and improving the algorithm efficiency while ensuring the image quality.
The invention provides an image partition conversion method, which comprises the following steps:
processing the acquired RAW image to obtain a gradient map of the RAW image;
scanning the gradient map line by line from top to bottom and superposing to obtain the number of pixels with pixel values larger than a set pixel threshold value;
calculating the proportion of the scanned line number to the total line number of the gradient graph when the pixel number is larger than a set pixel number threshold;
partitioning the RAW image based on the scale;
and performing image conversion by adopting a demosaicing algorithm corresponding to the complexity degree of the partition.
Preferably, the processing the acquired RAW image to obtain a gradient map of the RAW image includes:
extracting channels of the RAW image, wherein the channels are divided into an R channel, a Gr channel, a Gb channel and a B channel;
sampling all the channel data in the same proportion to obtain four image matrixes corresponding to an R channel, a Gr channel, a Gb channel and a B channel;
and merging gradient images of the image matrix in the vertical direction to obtain a gradient map of the RAW image.
Preferably, the merging gradient images of the image matrix in the vertical direction includes:
convolving the airspace Prewitt gradient operator with the image matrixes to calculate gradients of the four image matrixes in the vertical direction so as to obtain corresponding gradient images;
taking an absolute value of the gradient image;
and merging the gradient images to obtain a gradient map of the RAW image.
Preferably, the partitioning the RAW image based on the ratio includes:
the RAW image is divided into a simple partition located at an upper portion and a complex partition located at a lower portion in the scale.
Preferably, the image conversion using a demosaicing algorithm corresponding to the complexity of the partition includes:
converting the simple partition by adopting a nearest neighbor interpolation method;
the complex partitions are transformed using cubic spline interpolation.
The invention also provides an image partition conversion system, which comprises:
the original image processing module is used for processing the acquired RAW image to obtain a gradient map of the RAW image;
the pixel number calculation module is used for scanning the gradient map line by line from top to bottom and superposing to obtain the number of pixels with pixel values larger than a set pixel threshold value;
the proportion calculating module is used for calculating the proportion of the scanned line number to the total line number of the gradient graph when the pixel number is larger than a set pixel number threshold value;
the partitioning module is used for partitioning the RAW image based on the proportion;
an image conversion module for performing image conversion by using demosaicing algorithm corresponding to the complexity of the partition
Preferably, the raw image processing module further includes:
an extraction submodule for extracting channels of the RAW image, wherein the channels are divided into an R channel, a Gr channel, a Gb channel and a B channel;
the sampling submodule is used for sampling all the channel data in the same proportion to obtain four image matrixes corresponding to the R channel, the Gr channel, the Gb channel and the B channel;
and the gradient map acquisition sub-module is used for merging gradient images of the image matrix in the vertical direction to obtain a gradient map of the RAW image.
Preferably, the gradient map obtaining sub-module further includes:
the gradient calculation sub-module is used for carrying out convolution calculation on gradients of the four image matrixes in the vertical direction by utilizing a airspace Prewitt gradient operator and the image matrixes so as to obtain corresponding gradient images;
the value taking sub-module is used for taking absolute values of the gradient images;
and the merging submodule is used for merging the gradient images to obtain a gradient map of the RAW image.
The invention also provides an electronic device, comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the one image partition conversion method.
The present invention also provides a computer-readable storage medium having stored therein executable program code that is called by the processor to perform the image partition conversion method.
Compared with the related art, the image partition conversion method, the system, the electronic equipment and the storage medium provided by the invention have the following beneficial effects:
the invention obtains a gradient image of an RAW image by processing the acquired RAW image, then scans the gradient image from top to bottom in a progressive way and superimposes the gradient image to obtain the pixel number with the pixel value larger than a set pixel threshold, partitions the RAW image according to the proportion of the scanned line number to the total line number of the gradient image when the pixel number is larger than the set pixel number threshold to obtain a complex partition and a simple partition, and finally converts the simple partition by adopting a nearest neighbor interpolation method and converts the complex partition by adopting a cubic spline interpolation method to obtain an RGB format image.
Drawings
FIG. 1 is a schematic flow chart of an image partition conversion method provided by the invention;
fig. 2 is a schematic flow chart of a RAW image processing method according to the present invention;
FIG. 3 is a schematic diagram of a gradient map acquisition flow chart of an image partition conversion method according to the present invention;
FIG. 4 is a flowchart illustrating another image partition conversion method according to the present invention;
fig. 5 is a schematic diagram of a system structure of an image partition conversion system according to the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to the present invention.
Fig. 7 is a schematic diagram of sampling of an image partition conversion method according to the present invention.
Detailed Description
The invention will be further described with reference to the drawings and embodiments.
Firstly, the invention aims at a high-resolution RAW image, and meanwhile, the RAW image needs to be acquired before the RAW image is converted, specifically, an 8K resolution camera capable of outputting a RAW format file is used, the format of a color filter array of an image sensor is BGGR, the data bit depth is 10 bits, a physical scene is shot by the camera, an output image in the RAW format is obtained, the size is 7680 x 4320, and the space position of the output image is provided with digital image data containing red, green, blue color channels at intervals.
The invention provides an image partition conversion method, as shown in fig. 1 and fig. 4, which comprises the following steps:
step S100: processing the acquired RAW image to obtain a gradient map of the RAW image;
specifically, as shown in fig. 2, step S100 includes the following operation steps:
step S101: extracting channels of the RAW image, wherein the channels are divided into an R channel, a Gr channel, a Gb channel and a B channel; more specifically, four channel data of R, gr, gb, and B of the RAW image are extracted, which are all obtained by extracting data of corresponding positions in three matrices red, green, blue, and resolution of R, gr, gb, and B is 3840×2160.
Step S102: sampling all the channel data in the same proportion to obtain four image matrixes corresponding to an R channel, a Gr channel, a Gb channel and a B channel; more specifically, since the 8K resolution is too large, the calculation of the partition by using the original resolution results in too large calculation amount, the invention uses the equal interval sampling method to sample the R, gr, gb, B channel data in the same proportion, so as to reduce the calculation amount, and obtain four image matrixes corresponding to the four channel data, for example, as shown in fig. 7, the four image matrixes are sampled by taking the interval as one pixel point, and the resolution is changed from 3840×2160 to 1920×1080 after the sampling.
Step S103: combining the gradient images of the image matrix in the vertical direction to obtain a gradient image of the RAW image
Specifically, as shown in fig. 3, step S103 includes the following operation steps:
step S1031: convolving the airspace Prewitt gradient operator with the image matrixes to calculate gradients of the four image matrixes in the vertical direction so as to obtain corresponding gradient images; more specifically, the computation of the gradient adopts a airspace Prewitt gradient operator to convolve the gradient operator with an image matrix, wherein when the centre of the Prewitt gradient operator template moves to an image boundary, the operator coverage area exceeds the image boundary, and the boundary processing method of filling is needed to be adopted at the periphery of the image in a mode of copying pixels of the image boundary, so that four gradient images corresponding to R, gr, gb and B are finally obtained.
Step S1032: taking an absolute value of the gradient image; more specifically, if there is a negative value in the gradient image, it is necessary to take an absolute value for the gradient image.
Step S1033: combining the gradient images to obtain a gradient map of the RAW image; specifically, the vertical gradient map of the image reflects the rate of change of the pixels of the image in the vertical direction, and the larger the rate of change, the higher the pixel value of the gradient map, so that the vertical gradient map can show the horizontal edge of the original image.
Step S200: scanning the gradient map line by line from top to bottom and superposing to obtain the number of pixels with pixel values larger than a set pixel threshold value; more specifically, two threshold empirical parameters t and k need to be set, wherein, the t can take a value of 100, the k can take a value of 0.02, of course, the values of the parameters t and k can be adjusted according to the actual situation, the rows and columns of the gradient map are respectively m and n, the gradient map is scanned line by line from top to bottom, the number of pixels with the pixel value larger than the set pixel threshold t in the scanned line is accumulated, for example, two pixels with the pixel value larger than the set pixel threshold t appear in the first line, two pixels with the pixel value larger than the set pixel threshold t appear in the second line, the number of pixels with the pixel value larger than the set pixel threshold t is four at the moment, and the like after progressive scanning.
Step S300: calculating the proportion of the scanned line number to the total line number of the gradient graph when the pixel number is larger than a set pixel number threshold; more specifically, if the ith row is scanned, the number of pixels with values greater than t is greater than k×n, which indicates that a more obvious edge appears on the ith row, the line is not scanned downward any more, and the scaling factor q=i/m of the scanned upper half of the full gradient map is obtained.
In addition, when setting the threshold parameters t and k, decreasing either value will weaken the condition of edge determination (i.e., the easier it is to determine this line as a more distinct edge), the value of the scaling factor Q will decrease, and the partition boundary will be raised; if either one of the threshold parameters t and k is increased, the condition for edge determination is enhanced, the value of the scaling factor Q is increased, and the partition boundary is decreased.
Step S400: partitioning the RAW image based on the scale; more specifically, the RAW image is divided into a simple partition located at the upper part and a complex partition located at the lower part according to the ratio Q, for example, the original 8K image (resolution 7680×4320) is divided into a simple partition located at the upper part and a complex partition located at the lower part from the region according to the ratio Q, the simple partition resolution is 7680×4320, and the complex partition resolution is 7680× ((1-Q) ×4320).
In addition, when the areas are divided, the color filter array format of the simple partition and the complex partition is guaranteed to be BGGR, and the simple partition and the complex partition are convenient to input as a subsequent algorithm.
Step S500: performing image conversion by adopting a demosaicing algorithm corresponding to the complexity of the partition; more specifically, a nearest neighbor interpolation method suitable for a simple partition is selected, the gray value of a pixel after transformation is equal to the gray value of an input pixel nearest to the nearest neighbor interpolation method, the simple partition is processed, an output image is obtained, the operation complexity of the nearest neighbor interpolation method is low, image details can be lost in a complex scene, and adverse effects are small in the simple scene.
And selecting a cubic spline interpolation method suitable for the complex subarea, and processing the complex subarea to obtain an output image, wherein the cubic spline interpolation method is to divide an interpolation interval into a plurality of cells, then interpolate by adopting a cubic polynomial in each cell, and the polynomials in the cells meet some additional conditions, such as equality of first derivative or second derivative, so as to ensure smoothness and continuity of an interpolation curve, and the cubic spline interpolation method has higher operation complexity, but has high retention degree of details and good interpolation effect, and is suitable for processing the complex subarea.
And finally combining images respectively obtained by a nearest neighbor interpolation method and a cubic spline interpolation method, namely, finally outputting an 8K full-resolution size image, and rapidly and completely retaining flat and detail area information.
As shown in Table 1, the global nearest-neighbor interpolation method and the global cubic spline interpolation method are compared with Matlab operation results of the method, and the results show that the peak signal-to-noise ratio of the global nearest-neighbor interpolation method is the lowest, namely the effect is the worst and the operation time is the shortest; the peak signal-to-noise ratio is higher by using a cubic spline interpolation method globally, but the running time is longest; the peak signal-to-noise ratio of the method of the invention is close to that of the cubic spline interpolation method, but the running time is greatly shortened.
TABLE 1
According to the image partition conversion method, the acquired RAW image is processed to obtain the gradient image of the RAW image, then the gradient image is scanned from top to bottom in a progressive mode, the pixel number with the pixel value larger than the set pixel threshold value is obtained through superposition, the RAW image is partitioned according to the proportion of the scanned line number to the total line number of the gradient image when the pixel number is larger than the set pixel number threshold value, the complex partition and the simple partition are obtained, and finally the nearest neighbor interpolation method is adopted to convert the simple partition and the cubic spline interpolation method is adopted to convert the complex partition to obtain the RGB format image.
In this embodiment, the present invention further provides an image partition conversion system, as shown in fig. 5, where the conversion system includes:
the original image processing module is used for processing the acquired RAW image to obtain a gradient map of the RAW image;
specifically, the original image processing module includes:
an extraction submodule for extracting channels of the RAW image, wherein the channels are divided into an R channel, a Gr channel, a Gb channel and a B channel;
the sampling submodule is used for sampling all the channel data in the same proportion to obtain four image matrixes corresponding to the R channel, the Gr channel, the Gb channel and the B channel;
and the gradient map acquisition sub-module is used for merging gradient images of the image matrix in the vertical direction to obtain a gradient map of the RAW image.
Meanwhile, the gradient map acquisition submodule comprises:
the gradient calculation sub-module is used for carrying out convolution calculation on gradients of the four image matrixes in the vertical direction by utilizing a airspace Prewitt gradient operator and the image matrixes so as to obtain corresponding gradient images;
the value taking sub-module is used for taking absolute values of the gradient images;
and the merging submodule is used for merging the gradient images to obtain a gradient map of the RAW image.
The pixel number calculation module is used for scanning the gradient map line by line from top to bottom and superposing to obtain the number of pixels with pixel values larger than a set pixel threshold value;
the proportion calculating module is used for calculating the proportion of the scanned line number to the total line number of the gradient graph when the pixel number is larger than a set pixel number threshold value;
the partitioning module is used for partitioning the RAW image based on the proportion;
and the image conversion module is used for carrying out image conversion by adopting a demosaicing algorithm corresponding to the complexity degree of the partition.
The image partition conversion system provided by the invention is realized based on the image partition conversion method, and is not described herein.
The invention provides an image partition conversion system, which is characterized in that an original image processing module is used for processing an acquired RAW image to obtain a gradient image of the RAW image, a pixel number calculation module is used for scanning the gradient image from top to bottom line by line and overlapping to obtain the pixel number with the pixel value larger than a set pixel threshold value, then a proportion calculation module is used for calculating the proportion of the scanned line number to the total line number of the gradient image when the pixel number is larger than the set pixel number threshold value, a partition module is used for partitioning the RAW image to obtain a complex partition and a simple partition, and finally the conversion module is used for converting the simple partition by adopting a nearest neighbor interpolation method and converting the complex partition by adopting a cubic spline interpolation method to obtain an RGB format image.
In this embodiment, the present invention further provides an electronic device, as shown in fig. 6, including:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the steps of:
step 100: processing the acquired RAW image to obtain a gradient map of the RAW image;
step 200: scanning the gradient map line by line from top to bottom and superposing to obtain the number of pixels with pixel values larger than a set pixel threshold value;
step 300: calculating the proportion of the scanned line number to the total line number of the gradient graph when the pixel number is larger than a set pixel number threshold;
step 400: partitioning the RAW image based on the scale;
step 500: and performing image conversion by adopting a demosaicing algorithm corresponding to the complexity degree of the partition.
According to the electronic equipment provided by the invention, on the premise of ensuring the output image effect, the corresponding partitions in the RAW image are processed by adopting the demosaicing algorithms with different complexity, so that the operation amount of the system is reduced, and the efficiency of processing the RAW image by the image signal processor is improved.
The present invention also provides a computer-readable storage medium having stored therein executable program code that is called by the processor to perform the image partition conversion method.
Those of ordinary skill in the art will appreciate that all or part of the steps of the various methods of the above embodiments may be implemented by hardware associated with a program stored in a computer-readable storage medium, including Read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), erasable programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), one-time programmable Read-Only Memory (OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (CD-ROM), or any other medium capable of being used to carry or store data.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, systems, and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description of the present invention, it should be noted that the azimuth or positional relationship indicated by the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc. are based on the azimuth or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific azimuth, be constructed and operated in a specific azimuth, and thus should not be construed as limiting the present invention.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (9)
1. An image partition conversion method, characterized in that the conversion method comprises:
processing the acquired RAW image to obtain a gradient map of the RAW image;
scanning the gradient map line by line from top to bottom and superposing to obtain the number of pixels with pixel values larger than a set pixel threshold value;
calculating the proportion of the scanned line number to the total line number of the gradient graph when the pixel number is larger than a set pixel number threshold;
partitioning the RAW image based on the scale; dividing the RAW image into a simple partition positioned at an upper part and a complex partition positioned at a lower part according to the proportion;
and performing image conversion by adopting a demosaicing algorithm corresponding to the complexity degree of the partition.
2. The method for image partition transformation according to claim 1, wherein the processing the acquired RAW image to obtain a gradient map of the RAW image comprises:
extracting channels of the RAW image, wherein the channels are divided into an R channel, a Gr channel, a Gb channel and a B channel;
sampling all the channel data in the same proportion to obtain four image matrixes corresponding to an R channel, a Gr channel, a Gb channel and a B channel;
and merging gradient images of the image matrix in the vertical direction to obtain a gradient map of the RAW image.
3. The method of claim 2, wherein said merging gradient images of said image matrix in a vertical direction comprises:
convolving the airspace Prewitt gradient operator with the image matrixes to calculate gradients of the four image matrixes in the vertical direction so as to obtain corresponding gradient images;
taking an absolute value of the gradient image;
and merging the gradient images to obtain a gradient map of the RAW image.
4. A method of image partition transformation according to claim 3, wherein said performing image transformation using a demosaicing algorithm corresponding to the complexity of the partition comprises:
converting the simple partition by adopting a nearest neighbor interpolation method;
the complex partitions are transformed using cubic spline interpolation.
5. An image partition transformation system, the transformation system comprising:
the original image processing module is used for processing the acquired RAW image to obtain a gradient map of the RAW image;
the pixel number calculation module is used for scanning the gradient map line by line from top to bottom and superposing to obtain the number of pixels with pixel values larger than a set pixel threshold value;
the proportion calculating module is used for calculating the proportion of the scanned line number to the total line number of the gradient graph when the pixel number is larger than a set pixel number threshold value;
the partitioning module is used for partitioning the RAW image based on the proportion; dividing the RAW image into a simple partition positioned at an upper part and a complex partition positioned at a lower part according to the proportion;
and the image conversion module is used for carrying out image conversion by adopting a demosaicing algorithm corresponding to the complexity degree of the partition.
6. The image partition transformation system of claim 5, wherein the raw image processing module further comprises:
an extraction submodule for extracting channels of the RAW image, wherein the channels are divided into an R channel, a Gr channel, a Gb channel and a B channel;
the sampling submodule is used for sampling all the channel data in the same proportion to obtain four image matrixes corresponding to the R channel, the Gr channel, the Gb channel and the B channel;
and the gradient map acquisition sub-module is used for merging gradient images of the image matrix in the vertical direction to obtain a gradient map of the RAW image.
7. The image partition transformation system of claim 6, wherein the gradient map acquisition sub-module further comprises:
the gradient calculation sub-module is used for carrying out convolution calculation on gradients of the four image matrixes in the vertical direction by utilizing a airspace Prewitt gradient operator and the image matrixes so as to obtain corresponding gradient images;
the value taking sub-module is used for taking absolute values of the gradient images;
and the merging submodule is used for merging the gradient images to obtain a gradient map of the RAW image.
8. An electronic device, comprising:
a memory storing executable program code;
a processor coupled to the memory;
the processor invokes the executable program code stored in the memory to perform the image partition conversion method of any one of claims 1-4.
9. A computer readable storage medium having stored therein executable program code which is invoked by a processor to perform the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310393846.5A CN116132824B (en) | 2023-04-13 | 2023-04-13 | Image partition conversion method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310393846.5A CN116132824B (en) | 2023-04-13 | 2023-04-13 | Image partition conversion method, system, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116132824A CN116132824A (en) | 2023-05-16 |
| CN116132824B true CN116132824B (en) | 2023-06-16 |
Family
ID=86299419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310393846.5A Active CN116132824B (en) | 2023-04-13 | 2023-04-13 | Image partition conversion method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116132824B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105830424A (en) * | 2013-10-18 | 2016-08-03 | 泽莱特科股份有限公司 | Image capture control methods and apparatus |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8184928B2 (en) * | 2009-10-20 | 2012-05-22 | Eastman Kodak Company | Combining seam carving an image resizing |
| CN105282529B (en) * | 2015-10-22 | 2018-01-16 | 浙江宇视科技有限公司 | A kind of digital wide dynamic approach and device based on RAW spaces |
| CN109389110B (en) * | 2018-10-11 | 2021-03-19 | 北京奇艺世纪科技有限公司 | Region determination method and device |
| CN111062331B (en) * | 2019-12-18 | 2023-09-05 | 银河互联网电视有限公司 | Image mosaic detection method and device, electronic equipment and storage medium |
| US11334961B2 (en) * | 2020-08-06 | 2022-05-17 | Apple Inc. | Multi-scale warping circuit for image fusion architecture |
| CN115424017B (en) * | 2022-08-23 | 2023-10-17 | 河海大学 | Building inner and outer contour segmentation method, device and storage medium |
-
2023
- 2023-04-13 CN CN202310393846.5A patent/CN116132824B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105830424A (en) * | 2013-10-18 | 2016-08-03 | 泽莱特科股份有限公司 | Image capture control methods and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116132824A (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4116649B2 (en) | High resolution device and method | |
| US20090073277A1 (en) | Image processing apparatus, image processing method and image pickup apparatus | |
| US8891866B2 (en) | Image processing apparatus, image processing method, and program | |
| CN103155567B (en) | Image processing apparatus and image processing method | |
| CN103403758B (en) | Image processing apparatus, image processing method, computer program and recording medium for image procossing | |
| US7760967B2 (en) | Image processing apparatus capable of carrying out magnification change process of image | |
| KR100873880B1 (en) | Image processing apparatus and image processing method | |
| CN111510691B (en) | Color interpolation method and device, equipment and storage medium | |
| US20060177152A1 (en) | Apparatus and method for producing thumbnail images and for improving image quality of re-sized images | |
| CN111225135B (en) | Image sensor, imaging device, electronic apparatus, image processing system, and signal processing method | |
| CN110992246B (en) | Pyramid layered slicing method for image | |
| KR20190087017A (en) | Image sensing device | |
| CN111402139A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| US11244431B2 (en) | Image processing | |
| KR101009108B1 (en) | Image processing apparatus and image processing method | |
| CN110650346B (en) | 3D-HEVC depth map motion estimation parallel implementation method and structure | |
| US20110141321A1 (en) | Method and apparatus for transforming a lens-distorted image to a perspective image in bayer space | |
| CN116132824B (en) | Image partition conversion method, system, electronic equipment and storage medium | |
| JP2010016812A (en) | Image processing apparatus and method, and computer-readable medium | |
| JP6014349B2 (en) | Imaging apparatus, control method, and program | |
| CN113068011B (en) | Image sensor, image processing method and system | |
| US20110032269A1 (en) | Automatically Resizing Demosaicked Full-Color Images Using Edge-Orientation Maps Formed In The Demosaicking Process | |
| CN109993693B (en) | Method and apparatus for interpolating an image | |
| CN102779335A (en) | Processing device and processing method for digital image | |
| CN110602410B (en) | Image processing method and device, aerial camera 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |