WO2022233185A1 - 一种图像滤波方法、装置、终端和计算机可读存储介质 - Google Patents
一种图像滤波方法、装置、终端和计算机可读存储介质 Download PDFInfo
- Publication number
- WO2022233185A1 WO2022233185A1 PCT/CN2022/080527 CN2022080527W WO2022233185A1 WO 2022233185 A1 WO2022233185 A1 WO 2022233185A1 CN 2022080527 W CN2022080527 W CN 2022080527W WO 2022233185 A1 WO2022233185 A1 WO 2022233185A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- filtered
- pixel
- target
- filtering
- Prior art date
Links
- 238000001914 filtration Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000009499 grossing Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000005070 sampling Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 abstract description 12
- 238000004321 preservation Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 12
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000002146 bilateral effect Effects 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
- 230000009471 action Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001559 infrared map 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
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000007704 transition Effects 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
Definitions
- the present application belongs to the technical field of image processing, and in particular, relates to an image filtering method, device, terminal and computer-readable storage medium.
- guided filtering In the image filtering algorithm, guided filtering, bilateral filtering and least square filtering are called the three major edge preserving filters, which belong to anisotropic filters. smooth. Compared with bilateral filtering and least squares filtering, guided filtering can be used to process images with more image noise, and the edge optimization effect is better.
- the amount of calculation of guided filtering is large. Even if the down-sampled image is used for fast guided filtering (Fast Guided Filter), the amount of calculation is still very large, especially in the calculation process, in addition to a large number of additions and multiplications, it is necessary to do division. Operation, its realization cost is high, it is difficult to realize with general processor CPU or DSP, even if it can be realized with ASIC special circuit, its cost is also very high.
- the value of the filtered image and the initially input floating-point data image will be at the edge of the object. , the junction of front and back background and other transition areas will produce flying spots, reducing the quality of smoothing filtering of the image.
- the purpose of the present application is to provide an image filtering method, device, terminal and computer-readable storage medium, which can avoid the problem of flying spots appearing in a target filtered image obtained by filtering an image to be filtered.
- a first aspect of the embodiments of the present application provides an image filtering method, where the image filtering method includes:
- the acquisition of the error threshold value includes:
- the error threshold value of each pixel in the image to be filtered is determined according to the preset smoothing scale parameter.
- the acquisition of the error threshold value may further include:
- the error threshold value of each pixel in the image to be filtered is determined according to the preset smoothing scale parameter and the auxiliary image.
- the third possible implementation manner of the present application obtain the image to be filtered and perform filtering processing.
- the initial filtered image obtained after including:
- Up-sampling processing is performed on the initial processed image to obtain the initial filtered image.
- performing filtering processing on the down-sampled image to obtain an initially processed image includes:
- the pixel difference value corresponding to each pixel in the to-be-filtered image is compared with that in the to-be-filtered image.
- the error threshold values of the corresponding pixels are compared, and according to the comparison result, the target pixel value corresponding to each pixel in the image to be filtered in the target filtered image is determined, and the target filtered image corresponding to the image to be filtered is obtained, including:
- the target pixel value corresponding to the pixel whose value is less than or equal to the error threshold value is determined as its corresponding pixel value in the initial filtered image, and the target filtered image corresponding to the to-be-filtered image is obtained.
- a second aspect of the embodiments of the present application further provides an image filtering apparatus, including:
- an acquisition unit used for acquiring an initial filtered image obtained after filtering the image to be filtered
- a calculation unit configured to separately calculate the pixel difference between each pixel in the image to be filtered and the corresponding pixel in the initial filtered image, and obtain the pixel difference corresponding to each pixel in the image to be filtered;
- a comparison unit configured to compare the pixel difference value corresponding to each pixel in the image to be filtered with the error threshold value of the corresponding pixel in the image to be filtered, and determine each pixel in the image to be filtered according to the comparison result
- the target pixel value corresponding to the pixel in the target filtered image is obtained, and the target filtered image corresponding to the to-be-filtered image is obtained.
- a third aspect of an embodiment 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 is executed by the processor to implement the above-mentioned first The steps of the image filtering method described in the aspect.
- a fourth aspect of the embodiments of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements the steps of the image filtering method described in the first aspect.
- the error threshold value of each pixel in the image to be filtered is introduced, and the pixel difference value corresponding to each pixel in the image to be filtered is compared with the error threshold value of the corresponding pixel in the image to be filtered method, select the corresponding pixel value from the initial filtered image and the to-be-filtered image as the target pixel value corresponding to each pixel in the to-be-filtered image in the target filtered image, which effectively avoids the target pixel value obtained after the to-be-filtered image is filtered.
- the problem of flying spots in the filtered image is beneficial to obtain the target filtered image with better edge preservation effect and filtering effect.
- it compared with the guided filtering method, it has a smaller amount of calculation and lower hardware requirements, which is convenient for various applications.
- FIG. 1 is a schematic flowchart of a first implementation of an image filtering method provided by an embodiment of the present application.
- FIG. 2 is a schematic diagram of a first specific implementation flow of obtaining an error threshold value in an image filtering method provided by an embodiment of the present application.
- FIG. 3 is a schematic flowchart of a second specific implementation of obtaining an error threshold value in an image filtering method provided by an embodiment of the present application.
- FIG. 4 is a schematic structural diagram of an image filtering apparatus provided by an embodiment of the present application.
- FIG. 5 is a schematic diagram of a terminal provided by an embodiment of the present application.
- FIG. 1 is a schematic flowchart of an implementation of an image filtering method provided by an embodiment of the present application, and the method may be executed by an image filtering apparatus configured on a terminal.
- the terminal may need a device for performing image filtering, for example, the terminal may be a terminal device such as a mobile phone and a tablet computer.
- the image filtering method provided in this embodiment of the present application may include steps 101 to 103, which are described in detail as follows:
- Step 101 Obtain an initial filtered image obtained after filtering the image to be filtered.
- the above-mentioned 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 the present application.
- a smoothing filtering processing method such as mean filtering, bilateral filtering, median filtering, and Gaussian filtering can be adopted.
- mean filtering is preferred, which has the advantages of low implementation cost and easy implementation.
- the process may include: acquiring pixel values of adjacent pixels corresponding to each target pixel in the image to be filtered; calculating the pixel value of each target pixel The pixel average value between the pixel values of its corresponding adjacent pixels, and the pixel average value is used as the pixel value corresponding to each target pixel to obtain the initial filtered image.
- the above-mentioned target pixel is any pixel in the image to be filtered.
- Step 102 respectively calculating the pixel difference value of each pixel in the to-be-filtered image and the corresponding pixel in the initial filtered image, to obtain the pixel difference value corresponding to each pixel in the to-be-filtered image;
- the initial filtered image and the to-be-filtered image may be calculated first. Alignment is performed to obtain the pixels corresponding to each pixel in the initial filtered image and each pixel in the to-be-filtered image, and then calculate the pixel difference between each pixel in the to-be-filtered image and the corresponding pixel in the initial filtered image. .
- Step 103 Compare the pixel difference value corresponding to each pixel in the image to be filtered with the error threshold value of the corresponding pixel in the image to be filtered, and determine the corresponding pixel in the image to be filtered according to the comparison result. to obtain the target filtered image corresponding to the to-be-filtered image.
- the acquisition of the above-mentioned error threshold value may be achieved through the following steps 201 to 203, which are described in detail as follows:
- Step 201 Acquire a preset smoothing scale parameter.
- the above-mentioned preset smoothing ratio parameter is a parameter used to reflect the trade-off between edge preservation and smoothness in the filtering process.
- the value range of the preset smoothing ratio parameter is 0 to 1.
- the preset smoothing ratio parameter when the preset smoothing ratio parameter is 0, the edge preservation effect is the best, and at this time, no smoothing operation is performed;
- the smoothing scale parameter is set to 1, the smoothing effect is the best, and the edge preservation effect is the worst.
- the user can select the processing effect to be achieved by setting the above-mentioned preset smoothing ratio parameter, which improves the flexibility of image filtering processing.
- Step 202 Determine the error threshold value of each pixel in the image to be filtered according to the preset smoothing scale parameter.
- the following steps 301 to 301 can also be used. 302.
- the method of introducing an auxiliary image to determine the specific value of the above-mentioned error threshold value is described in detail as follows:
- Step 301 obtaining a preset smoothing scale parameter and an auxiliary image corresponding to the image to be filtered
- the type of the auxiliary image may be related to the type of the image to be filtered.
- the auxiliary image may be an IR map of structured light, a matching cost map, or a confidence map.
- the auxiliary image when the image to be filtered is a depth image collected by a TOF camera, the auxiliary image may be a pulse phase image, an infrared image, or an amplitude image, which is not limited in this application.
- Step 302 Determine the error threshold value of each pixel in the image to be filtered according to the preset smoothing scale parameter and the auxiliary image.
- the pixel difference value corresponding to each pixel in the image to be filtered is compared with the error threshold value of the corresponding pixel in the image to be filtered, and the In the process of the target pixel value corresponding to each pixel in the image to be filtered, it can be first determined whether the pixel difference value corresponding to each pixel in the image to be filtered is greater than the error threshold value of the corresponding pixel in the image to be filtered, and the The target pixel value corresponding to the pixel whose corresponding pixel difference value in the to-be-filtered image is greater than the error threshold value is determined as its corresponding pixel value in the to-be-filtered image; the corresponding pixel difference value in the to-be-filtered image is determined The target pixel value corresponding to the pixel less than or equal to the error threshold value is determined as its corresponding pixel value in the initial filtered image, and then the target filtered image corresponding to the to-be-filtered image is obtained.
- the error threshold value of each pixel in the image to be filtered is introduced, and the pixel difference value corresponding to each pixel in the image to be filtered is compared with the error threshold value of the corresponding pixel in the image to be filtered method, select the corresponding pixel value from the initial filtered image and the to-be-filtered image as the target pixel value corresponding to each pixel in the to-be-filtered image in the target filtered image, which effectively avoids the target pixel value obtained after the to-be-filtered image is filtered.
- the problem of flying spots in the filtered image is beneficial to obtain the target filtered image with better edge preservation effect and filtering effect.
- the amount of calculation is smaller and the hardware requirements are lower, which is convenient for various calculations. implemented on the platform.
- the image to be filtered in the above step 101, in the process of acquiring the initial filtered image obtained after filtering the image to be filtered, the image to be filtered may be down-sampled first. processing to obtain a down-sampled image, and then performing filtering processing on the down-sampled image to obtain an initial processed image; then, performing up-sampling processing on the initial processed image to obtain the initial filtered image, so as to reduce the need for filtering the image The amount of computation processed.
- down-sampling processing Before performing down-sampling processing on the image to be filtered, it can be determined whether the image to be filtered needs to be down-sampled, and after determining that the image to be filtered needs down-sampling processing, down-sampling processing is performed on the image to be filtered to obtain a down-sampled image.
- the process of judging whether the image to be filtered needs to be subjected to downsampling processing it can be determined whether the number of pixels of the image to be filtered is greater than the quantity threshold, and if the number of pixels of the image to be filtered is greater than the quantity threshold, it is determined that the image to be filtered needs to be downsampled. Sampling processing, and then reduce the number of pixels of the image to be filtered through downsampling, and reduce the calculation amount of the image filtering processing.
- the number of pixels of the image to be filtered is less than or equal to the number threshold, it is determined that the image to be filtered does not need down-sampling processing.
- the image filtering apparatus may include: an acquisition unit 401 , a calculation unit 402 , and a comparison unit 403 .
- an acquisition unit 401 configured to acquire an initial filtered image obtained after filtering the image to be filtered
- a calculation unit 402 configured to calculate the pixel difference value of each pixel in the image to be filtered and the corresponding pixel in the initial filtered image, respectively, to obtain the pixel difference value corresponding to each pixel in the image to be filtered;
- the comparison unit 403 is configured to compare the pixel difference value corresponding to each pixel in the image to be filtered with the error threshold value of the corresponding pixel in the image to be filtered, and determine the difference in the image to be filtered according to the comparison result.
- the target pixel value corresponding to each pixel in the target filtered image is obtained, and the target filtered image corresponding to the to-be-filtered image is obtained.
- an embodiment of the present application further provides a terminal.
- the terminal may be configured with the image filtering apparatus shown in each of the foregoing embodiments.
- 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 processor 50 executes the computer program 52, the steps in each of the above image filtering method embodiments are implemented, for example, steps 101 to 103 shown in FIG. 1 .
- the so-called processor 50 may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processors, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
- a general-purpose processor may be a microprocessor, or any conventional processor, or the like.
- the memory 51 may be an internal storage unit of the terminal 5, eg, a hard disk or a memory.
- the memory 51 can also be an external storage device for the terminal 5, for example, a plug-in hard disk equipped on the terminal 5, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card ( Flash Card), etc.
- the memory 51 may also include both an internal storage unit of the terminal 5 and an external storage device.
- the memory 51 is used to store the above-mentioned computer programs and other programs and data required by the terminal.
- the above-mentioned computer program can be divided into one or more modules/units, and the above-mentioned one or more modules/units are stored in the above-mentioned memory 51 and executed by the above-mentioned processor 50 to complete the present application.
- the above-mentioned one or more modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the above-mentioned computer program in the above-mentioned terminal for user care.
- the above computer program can be divided into: an acquisition unit, a calculation unit and a comparison unit, and the specific functions are as follows:
- an acquisition unit used for acquiring an initial filtered image obtained after filtering the image to be filtered
- a calculation unit configured to separately calculate the pixel difference between each pixel in the image to be filtered and the corresponding pixel in the initial filtered image, and obtain the pixel difference corresponding to each pixel in the image to be filtered;
- a comparison unit configured to compare the pixel difference value corresponding to each pixel in the image to be filtered with the error threshold value of the corresponding pixel in the image to be filtered, and determine each pixel in the image to be filtered according to the comparison result
- the target pixel value corresponding to the pixel in the target filtered image is obtained, and the target filtered image corresponding to the to-be-filtered image is obtained.
- Module completion means dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.
- Each functional unit and module in the embodiment may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit, and the above-mentioned integrated units may adopt hardware. It can also be realized in the form of software functional units.
- the specific names of the functional units and modules are only for the convenience of distinguishing from each other, and are not used to limit the protection scope of the present application. For the specific working processes of the units and modules in the above-mentioned system, reference may be made to the corresponding processes in the foregoing method embodiments, which will not be repeated here.
- the disclosed terminal and method may be implemented in other manners.
- the terminal embodiments described above are merely illustrative.
- the division of modules or units is only for one logical function. In actual implementation, there may be other divisions.
- multiple units or components may be combined or integrated into another system, or some features may be ignored or not implement.
- the shown or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
- Units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
- each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
- the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of 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.
- the present application realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program is in When executed by the processor, the steps of the foregoing method embodiments can be implemented.
- the computer program includes computer program code
- the computer program code may be in the form of source code, object code, executable file or some intermediate forms, and the like.
- the computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM), random access Memory (Random Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in computer-readable media may be appropriately increased or decreased in accordance with the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include Electrical carrier signals and telecommunication signals.
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
本申请属于图像处理技术领域，主要提供了一种图像滤波方法、装置、终端和计算机可读存储介质，本申请通过引入待滤波图像中各个像素的误差门限值，并将待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较的方式，从初始滤波图像与待滤波图像中选择相应的像素值作为所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，有效避免了待滤波图像经过滤波后得到的目标滤波图像中出现飞点的问题，有利于获取边缘保持效果和滤波效果较佳的目标滤波图像，并且，与导向滤波方式相比，具有计算量较小，对硬件要求较低，便于在各种计算平台上实现的特点。
Description
本申请要求于2021年5月7日提交中国专利局，申请号为202110495403.8，发明名称为“一种图像滤波方法、装置、终端和计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本申请属于图像处理技术领域，尤其涉及一种图像滤波方法、装置、终端和计算机可读存储介质。
在图像滤波算法中，导向滤波、双边滤波及最小二乘滤波并称为三大边缘保持滤波器，属于各向异性滤波器，最大的特点是在去除噪声的同时，能最大限度保持边缘不被平滑。与双边滤波及最小二乘滤波相比，导向滤波可用于处理图像噪点较多的图像，且边缘优化效果更好。
然而，导向滤波的计算量大，即使是采用降采样后的图像进行快速导向滤波(Fast Guided Filter)，其计算量仍然很大，特别是计算过程中除了大量的加法和乘法外，需要做除法操作，其实现成本高，难以用一般的处理器CPU或DSP实现，即使能用ASIC专用电路实现，其成本亦非常高。尤其是针对浮点数据时，如果采用快速导向滤波，对降采样后的图像进行方差和均值计算的方式实现滤波，则其滤波得到的图像与最初输入的浮点数据图像的数值在物体的边缘、前后景的交界处等过渡区域会产生飞点，降低了对图像进行平滑滤波的质量。
发明内容
本申请的目的在于提供一种图像滤波方法、装置、终端和计算机可读存储介质，可以避免待滤波图像经过滤波后得到的目标滤波图像中出现飞点的问题。
本申请实施例第一方面提供一种图像滤波方法，所述图像滤波方法包括：
获取对待滤波图像进行滤波处理后得到的初始滤波图像；
分别计算所述待滤波图像中的各个像素与所述初始滤波图像中对应像素的像素差值，得到所述待滤波图像中的各个像素对应的像素差值；
将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，得到所述待滤波图像对应的目标滤波图像。
可选的，基于上述第一方面提供的图像滤波方法，在本申请的第一种可能的实现方式中，误差门限值的获取，包括：
获取预设平滑比例参数；
根据所述预设平滑比例参数确定所述待滤波图像中各个像素的误差门限值。
可选的，基于上述第一方面提供的图像滤波方法，在本申请的第二种可能的实现方式中，误差门限值的获取，还可以包括：
获取预设平滑比例参数，以及所述待滤波图像对应的辅助图像；
根据所述预设平滑比例参数以及所述辅助图像确定所述待滤波图像中各个像素的误差门限值。
可选的，基于上述第一方面提供的图像滤波方法，以及上述第一种和上述第二种可能的实施方式，在本申请的第三种可能的实现方式中，获取对待滤波图像进行滤波处理后得到的初始滤波图像，包括：
对待滤波图像进行降采样处理，得到降采样图像；
对所述降采样图像进行滤波处理，得到初始处理图像；
对所述初始处理图像进行升采样处理，得到所述初始滤波图像。
可选的，基于上述第三种可能的实施方式，在本申请的第四种可能的实现方式中，所述对所述降采样图像进行滤波处理，得到初始处理图像，包括：
对所述降采样图像进行均值滤波处理，得到所述初始处理图像。
可选的，基于上述各种可能的实施方式，在本申请的第五种可能的实现方式中，所述将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，得到所述待滤波图像对应的目标滤波图像，包括：
判断所述待滤波图像中的各个像素对应的像素差值是否大于所述待滤波图像中对应像素的误差门限值；
将所述待滤波图像中对应的像素差值大于误差门限值的像素对应的目标像素值确定为其在所述待滤波图像中对应的像素值；将所述待滤波图像中对应的像素差值小于或等于误差门限值的像素对应的目标像素值确定为其在所述初始滤波图像中对应的像素值，得到所述待滤波图像对应目标滤波图像。
本申请实施例第二方面还提供一种图像滤波装置，包括：
获取单元，用于获取对待滤波图像进行滤波处理后得到的初始滤波图像；
计算单元，用于分别计算所述待滤波图像中的各个像素与所述初始滤波图像中对应像素的像素差值，得到所述待滤波图像中的各个像素对应的像素差值；
比较单元，用于将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，得到所述待滤波图像对应的目标滤波图像。
本申请实施例第三方面提供一种终端，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，所述计算机程序被处理器执行时实现上述第一方面所述的图像滤波方法的步骤。
本申请实施例第四方面提供一种计算机可读存储介质，计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现上述第一方面所述的图像滤波方法的步骤。
本申请实施例中，通过引入待滤波图像中各个像素的误差门限值，并将待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较的方式，从初始滤波图像与待滤波图像中选择相应的像素值作为所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，有效避免了待滤波图像经过滤波后得到的目标滤波图像中出现飞点的问题，有利于获取边缘保持效果和滤波效果较佳的目标滤波图像，并且，与导向滤波方式相比，具有计算量较小，对硬件要求较低，便于在各种计算平台上实现的特点。
图1为本申请实施例提供的图像滤波方法的第一实现流程示意图。
图2为本申请实施例提供的图像滤波方法中获取误差门限值的第一具体实现流程示意图。
图3为本申请实施例提供的图像滤波方法中获取误差门限值的第二具体实现流程示意图。
图4为本申请的实施例提供的图像滤波装置的结构示意图。
图5为本申请的实施例提供的终端的示意图。
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
图1为本申请实施例提供的一种图像滤波方法的实现流程示意图，该方法可以由终端上配置的图像滤波装置执行。并且，该终端可以需要进行图像滤波的设备，例如，该终端可以为手机、平板电脑等终端设备。
具体的，本申请实施例提供的图像滤波方法可以包括步骤101至步骤103，详述如下：
步骤101，获取对待滤波图像进行滤波处理后得到的初始滤波图像。
本申请实施例中，上述待滤波图像可以为深度图像、红外图像或彩色图像等需要进行滤波处理的图像，本申请对此不作限制。
上述对待滤波图像进行滤波处理时，可以采用均值滤波、双边滤波、中值滤波、高斯滤波等平滑滤波处理方法实现。其中，优选为均值滤波，其具有实现代价低，且易于实现的优点。
在一个实施例中，在通过对待滤波图像进行均值滤波处理，得到初始滤波图像时可以包括：获取待滤波图像中每个目标像素对应的相邻像素的像素值；计算每个目标像素的像素值与其对应的相邻像素的像素值之间像素平均值，并将该像素平均值作为各个目标像素对应的像素值，得到所述初始滤波图像。其中，上述目标像素为待滤波图像中的任意一个像素。
更具体地，获取待滤波图像中的目标像素x
i对应的8个相邻像素x
2、x
3、x
4、x
5、x
6、x
7、x
8的像素值，计算目标像素x
i的像素值与其对应的相邻像素的像素值之间像素平均值
并将该像素平均值
作为目标像素x
i对应的像素值，依此，遍历待滤波图像中的每个目标像素，得到待滤波图像中的每个目标像素对应的像素平均值，并将该像素平均值作为各个目标像素对应的像素值，得到所述初始滤波图像。
步骤102，分别计算所述待滤波图像中的各个像素与所述初始滤波图像中对应像素的像素差值，得到所述待滤波图像中的各个像素对应的像素差值；
可选的，在本申请的一些实施方式中，上述分别计算所述待滤波图像中的各个像素与所述初始滤波图像中对应像素的像素差值时，可以先将初始滤波图像与待滤波图像进行对齐，得到所述初始滤波图像中与所述待滤波图像中的各个像素分别对应的像素，再分别计算所述待滤波图像中的各个像素与所述初始滤波图像中对应像素的像素差值。
步骤103，将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待滤波图像 中的各个像素对应的目标像素值，得到所述待滤波图像对应的目标滤波图像。
可选的，在本申请的一些实施方式中，如图2所示，上述误差门限值的获取可以通过下述步骤201至步骤203实现，详述如下：
步骤201，获取预设平滑比例参数。
本申请实施例中，上述预设平滑比例参数是用于体现滤波处理过程中保持边缘和平滑之间的权衡的参数。可选的，预设平滑比例参数的取值范围为0～1，本申请实施例中，当预设平滑比例参数为0时，边缘保持效果最佳，此时，不进行平滑操作；当预设平滑比例参数为1时，平滑效果最佳，边缘保持效果最差。
本申请实施例中，用户可以通过设置上述预设平滑比例参数，选择需要达到的处理效果，提高了图像滤波处理的灵活性。
步骤202，根据所述预设平滑比例参数确定所述待滤波图像中各个像素的误差门限值。
可选的，在本申请的一些实施方式中，上述根据所述预设平滑比例参数确定所述待滤波图像中各个像素的误差门限值可以包括：根据公式t(x
i,η)＝ηf(x
i)确定所述待滤波图像中各个像素x
i的误差门限值t(x
i,η)。其中，η为预设平滑比例参数，f(x
i)＝x
i，或者f(x
i)＝x
i
2，或者f(x
i)＝filter(x
i)，或者f(x
i)＝filter(x
i
2)，其中，filter可以为高斯滤波器、均值滤波器、中值滤波器等空间平滑滤波器。
基于上述图2所示的误差门限值的获取方法，为了进一步优化待滤波图像的滤波处理效果，如图3所示，在本申请的一些实施方式中，还可以通过下述步骤301至步骤302，引入辅助图像的方式，确定上述误差门限值的具体取值，详述如下：
步骤301，获取预设平滑比例参数，以及所述待滤波图像对应的辅助图像；
可选的，本申请实施例中，辅助图像的类型可以与待滤波图像的类型相关。
在一个实施例中，当待滤波图像为通过结构光采集的深度图像，则该辅助 图像可以为结构光的IR图、匹配代价图或者为置信图。
在另一个实施例中，当待滤波图像为通过TOF摄像头采集的深度图像，则该辅助图像可以为脉冲相位图、红外图像或者为幅值图像，本申请对此不作限制。
步骤302，根据所述预设平滑比例参数以及所述辅助图像确定所述待滤波图像中各个像素的误差门限值。
具体的，可以根据公式t(x
i,η,a
i)＝ηf(x
i)h(a
i)确定所述待滤波图像中各个像素x
i的误差门限值t(x
i,η,a
i)。其中，η为预设平滑比例参数，f(x
i)＝x
i，或者f(x
i)＝x
i
2；h(a
i)＝a
i，或者h(a
i)＝filter(a
i)，其中，filter可以为高斯滤波器、均值滤波器、中值滤波器等空间平滑滤波器，x
i待滤波图像中的像素。
本申请实施例中，上述步骤103，在将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待滤波图像中各个像素对应的目标像素值的过程中，可以先判断所述待滤波图像中的各个像素对应的像素差值是否大于所述待滤波图像中对应像素的误差门限值，并将所述待滤波图像中对应的像素差值大于误差门限值的像素对应的目标像素值确定为其在所述待滤波图像中对应的像素值；将所述待滤波图像中对应的像素差值小于或等于误差门限值的像素对应的目标像素值确定为其在所述初始滤波图像中对应的像素值，进而得到所述待滤波图像对应目标滤波图像。
本申请实施例中，通过引入待滤波图像中各个像素的误差门限值，并将待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较的方式，从初始滤波图像与待滤波图像中选择相应的像素值作为所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，有效避免了待滤波图像经过滤波后得到的目标滤波图像中出现飞点的问题，有利于获取边缘保持效果和滤波效果较佳的目标滤波图像，并且，与导向滤波方式相比，计算量较小，对硬件要求较低，便于在各种计算平台上实现。
可选的，为了进一步减小计算量，在本申请的一些实施方式中，在上述步骤101，获取对待滤波图像进行滤波处理后得到的初始滤波图像的过程中，可以先对待滤波图像进行降采样处理，得到降采样图像，接着，对所述降采样图像进行滤波处理，得到初始处理图像；然后，对所述初始处理图像进行升采样处理，得到所述初始滤波图像，以减少对图像进行滤波处理的计算量。
其中，在对待滤波图像进行降采样处理之前，可以判断待滤波图像是否需要进行降采样处理，并在确定待滤波图像需要进行降采样处理之后，对待滤波图像进行降采样处理，得到降采样图像。
其中，在判断待滤波图像是否需要进行降采样处理的过程中，可以通过判断待滤波图像的像素数量是否大于数量阈值，若待滤波图像的像素数量大于数量阈值，则确定待滤波图像需要进行降采样处理，进而通过降采样减少待滤波图像的像素数量，减少图像滤波处理的计算量。
需要说明的是，本申请的一些实施例中，若待滤波图像的像素数量小于或等于数量阈值，则确定待滤波图像不需要进行降采样处理。
应理解的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为根据本申请，某些步骤可以采用其它顺序进行。
如图4所示，为本申请实施例提供的图像滤波装置的结构示意图，该图像滤波装置可以包括：获取单元401、计算单元402和比较单元403。
获取单元401，用于获取对待滤波图像进行滤波处理后得到的初始滤波图像；
计算单元402，用于分别计算所述待滤波图像中的各个像素与所述初始滤波图像中对应像素的像素差值，得到所述待滤波图像中的各个像素对应的像素差值；
比较单元403，用于将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待 滤波图像中的各个像素在目标滤波图像中对应的目标像素值，得到所述待滤波图像对应的目标滤波图像。
需要说明的是，为描述的方便和简洁，上述描述的图像滤波装置的具体工作过程，可以参考上述图1至图4中图像滤波方法的描述，在此不再赘述。并且，还需要说明的是，上述各个实施方式可以进行相互组合，得到多种不同的实施方式，均属于本申请的保护范围。
如图5所示，本申请实施例还提供一种终端。该终端可以配置有上述各个实施方式所示的图像滤波装置。
如图5所示，终端5可以包括：处理器50、存储器51以及存储在存储器51中并可在处理器50上运行的计算机程序52。处理器50执行计算机程序52时实现上述各个图像滤波方法实施例中的步骤，例如，图1所示的步骤101至步骤103。
所称处理器50可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器，也可以是任何常规的处理器等。
存储器51可以是终端5的内部存储单元，例如，硬盘或内存。存储器51也可以是用于终端5的外部存储设备，例如，终端5上配备的插接式硬盘，智能存储卡(Smart Media Card，SMC)，安全数字(Secure Digital，SD)卡，闪存卡(Flash Card)等。进一步地，存储器51还可以既包括终端5的内部存储单元也包括外部存储设备。存储器51用于存储上述计算机程序以及终端所需的其他程序和数据。
上述计算机程序可以被分割成一个或多个模块/单元，上述一个或者多个模块/单元被存储在上述存储器51中，并由上述处理器50执行，以完成本申请。 上述一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述上述计算机程序在上述进行用户关怀的终端中的执行过程。例如，上述计算机程序可以被分割成：获取单元、计算单元和比较单元，具体功能如下：
获取单元，用于获取对待滤波图像进行滤波处理后得到的初始滤波图像；
计算单元，用于分别计算所述待滤波图像中的各个像素与所述初始滤波图像中对应像素的像素差值，得到所述待滤波图像中的各个像素对应的像素差值；
比较单元，用于将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，得到所述待滤波图像对应的目标滤波图像。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述***中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用 和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的实施例中，应该理解到，所揭露的终端和方法，可以通过其它的方式实现。例如，以上所描述的终端实施例仅仅是示意性的。例如，模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口、装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，计算机程序包括计算机程序代码，计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。计算机可读介质可以包括：能够携带计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、电载波信号、电信信号以及软件分发介质等。需要说明的是，计算机可读介质包含的内容可以根据司法管辖区内立法和专利实践的要求进行适当的增减，例如在某些司法管辖区，根据立法和专利实践，计算机可读介质不包括电载波信号和电信信号。
以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。
Claims (10)
- 一种图像滤波方法，其特征在于，包括：获取对待滤波图像进行滤波处理后得到的初始滤波图像；分别计算所述待滤波图像中的各个像素与所述初始滤波图像中对应像素的像素差值，得到所述待滤波图像中的各个像素对应的像素差值；将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，得到所述待滤波图像对应的目标滤波图像。
- 如权利要求1所述的图像滤波方法，其特征在于，所述误差门限值的获取，包括：获取预设平滑比例参数；根据所述预设平滑比例参数确定所述待滤波图像中各个像素的误差门限值。
- 如权利要求1所述的图像滤波方法，其特征在于，所述误差门限值的获取，包括：获取预设平滑比例参数，以及所述待滤波图像对应的辅助图像；根据所述预设平滑比例参数以及所述辅助图像确定所述待滤波图像中各个像素的误差门限值。
- 如权利要求1-3任意一项所述的图像滤波方法，其特征在于，所述获取对待滤波图像进行滤波处理后得到的初始滤波图像，包括：对待滤波图像进行降采样处理，得到降采样图像；对所述降采样图像进行滤波处理，得到初始处理图像；对所述初始处理图像进行升采样处理，得到所述初始滤波图像。
- 如权利要求4所述的图像滤波方法，其特征在于，所述对所述降采样图 像进行滤波处理，得到初始处理图像，包括：对所述降采样图像进行均值滤波处理，得到所述初始处理图像。
- 如权利要求1-3任意一项所述的图像滤波方法，其特征在于，所述将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，得到所述待滤波图像对应的目标滤波图像，包括：判断所述待滤波图像中的各个像素对应的像素差值是否大于所述待滤波图像中对应像素的误差门限值；将所述待滤波图像中对应的像素差值大于误差门限值的像素对应的目标像素值确定为其在所述待滤波图像中对应的像素值；将所述待滤波图像中对应的像素差值小于或等于误差门限值的像素对应的目标像素值确定为其在所述初始滤波图像中对应的像素值，得到所述待滤波图像对应目标滤波图像。
- 一种图像滤波装置，其特征在于，包括：获取单元，用于获取对待滤波图像进行滤波处理后得到的初始滤波图像；计算单元，用于分别计算所述待滤波图像中的各个像素与所述初始滤波图像中对应像素的像素差值，得到所述待滤波图像中的各个像素对应的像素差值；比较单元，用于将所述待滤波图像中的各个像素对应的像素差值与所述待滤波图像中对应像素的误差门限值进行比较，并根据比较结果确定所述待滤波图像中的各个像素在目标滤波图像中对应的目标像素值，得到所述待滤波图像对应的目标滤波图像。
- 如权利要求7所述的图像滤波装置，其特征在于，所述获取单元，还用于：获取预设平滑比例参数；根据所述预设平滑比例参数确定所述待滤波图像中各个像素的误差门限值。
- 一种终端，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1-6任意一项所述方法的步骤。
- 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1-6中任意一项所述方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110495403.8A CN113298761B (zh) | 2021-05-07 | 2021-05-07 | 一种图像滤波方法、装置、终端和计算机可读存储介质 |
| CN202110495403.8 | 2021-05-07 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2022233185A1 true WO2022233185A1 (zh) | 2022-11-10 |
Family
ID=77321085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/080527 WO2022233185A1 (zh) | 2021-05-07 | 2022-03-13 | 一种图像滤波方法、装置、终端和计算机可读存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113298761B (zh) |
| WO (1) | WO2022233185A1 (zh) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115689378A (zh) * | 2022-11-15 | 2023-02-03 | 湖北中烟工业有限责任公司 | 一种用于爆珠滤棒质量溯源的数据处理方法及装置 |
| CN116703958A (zh) * | 2023-08-03 | 2023-09-05 | 山东仕达思医疗科技有限公司 | 显微图像的边缘轮廓检测方法、***、设备和存储介质 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113298761B (zh) * | 2021-05-07 | 2023-07-04 | 奥比中光科技集团股份有限公司 | 一种图像滤波方法、装置、终端和计算机可读存储介质 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130084004A1 (en) * | 2011-09-30 | 2013-04-04 | Konica Minolta Laboratory U.S.A., Inc. | Image processing of data from scanned display |
| CN110298805A (zh) * | 2019-07-03 | 2019-10-01 | 云南电网有限责任公司电力科学研究院 | 一种多光谱图像的去噪和滤波方法及装置 |
| CN112488910A (zh) * | 2020-11-16 | 2021-03-12 | 广州视源电子科技股份有限公司 | 点云优化方法、装置及设备 |
| CN113298761A (zh) * | 2021-05-07 | 2021-08-24 | 奥比中光科技集团股份有限公司 | 一种图像滤波方法、装置、终端和计算机可读存储介质 |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6937365B2 (en) * | 2001-05-30 | 2005-08-30 | Polaroid Corporation | Rendering images utilizing adaptive error diffusion |
| CN101316321B (zh) * | 2007-05-30 | 2010-04-07 | 展讯通信（上海）有限公司 | 一种基于中值滤波器的图像噪声去除方法和装置 |
| JP4585602B1 (ja) * | 2009-09-18 | 2010-11-24 | 株式会社東芝 | 画像処理装置、表示装置及び画像処理方法 |
| TWI608447B (zh) * | 2015-09-25 | 2017-12-11 | 台達電子工業股份有限公司 | 立體影像深度圖產生裝置及方法 |
| CN114979634B (zh) * | 2017-10-09 | 2023-10-27 | 佳能株式会社 | 用于对样本块进行滤波的方法、装置和存储介质 |
| CN109584204B (zh) * | 2018-10-15 | 2021-01-26 | 上海途擎微电子有限公司 | 一种图像噪声强度估计方法、存储介质、处理及识别装置 |
| CN111383178A (zh) * | 2018-12-29 | 2020-07-07 | Tcl集团股份有限公司 | 一种图像增强方法、装置及终端设备 |
| CN110517201B (zh) * | 2019-08-29 | 2021-11-16 | 北京迈格威科技有限公司 | 循环保边平滑滤波的方法、装置和电子设备 |
| CN112215768A (zh) * | 2020-09-30 | 2021-01-12 | 广州虎牙科技有限公司 | 图像清晰度提升方法、装置、电子设备及可读存储介质 |
-
2021
- 2021-05-07 CN CN202110495403.8A patent/CN113298761B/zh active Active
-
2022
- 2022-03-13 WO PCT/CN2022/080527 patent/WO2022233185A1/zh active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130084004A1 (en) * | 2011-09-30 | 2013-04-04 | Konica Minolta Laboratory U.S.A., Inc. | Image processing of data from scanned display |
| CN110298805A (zh) * | 2019-07-03 | 2019-10-01 | 云南电网有限责任公司电力科学研究院 | 一种多光谱图像的去噪和滤波方法及装置 |
| CN112488910A (zh) * | 2020-11-16 | 2021-03-12 | 广州视源电子科技股份有限公司 | 点云优化方法、装置及设备 |
| CN113298761A (zh) * | 2021-05-07 | 2021-08-24 | 奥比中光科技集团股份有限公司 | 一种图像滤波方法、装置、终端和计算机可读存储介质 |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115689378A (zh) * | 2022-11-15 | 2023-02-03 | 湖北中烟工业有限责任公司 | 一种用于爆珠滤棒质量溯源的数据处理方法及装置 |
| CN116703958A (zh) * | 2023-08-03 | 2023-09-05 | 山东仕达思医疗科技有限公司 | 显微图像的边缘轮廓检测方法、***、设备和存储介质 |
| CN116703958B (zh) * | 2023-08-03 | 2023-11-17 | 山东仕达思医疗科技有限公司 | 显微图像的边缘轮廓检测方法、***、设备和存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113298761B (zh) | 2023-07-04 |
| CN113298761A (zh) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022233185A1 (zh) | 一种图像滤波方法、装置、终端和计算机可读存储介质 | |
| EP3614334B1 (en) | Method for image processing and electronic device | |
| WO2021004180A1 (zh) | 一种纹理特征提取方法、纹理特征提取装置及终端设备 | |
| US10547871B2 (en) | Edge-aware spatio-temporal filtering and optical flow estimation in real time | |
| US10262401B2 (en) | Noise reduction using sequential use of multiple noise models | |
| US20160253787A1 (en) | Methods and systems for denoising images | |
| CN109064504B (zh) | 图像处理方法、装置和计算机存储介质 | |
| CN110335216B (zh) | 图像处理方法、图像处理装置、终端设备及可读存储介质 | |
| CN111402170A (zh) | 图像增强方法、装置、终端及计算机可读存储介质 | |
| CN109214996B (zh) | 一种图像处理方法及装置 | |
| WO2020232910A1 (zh) | 基于图像处理的目标物统计方法、装置、设备及存储介质 | |
| CN111131688B (zh) | 一种图像处理方法、装置及移动终端 | |
| CN112508816B (zh) | 一种红外图像锐化方法、锐化处理***及终端设备 | |
| WO2019210707A1 (zh) | 一种图像清晰度评测方法、装置及电子设备 | |
| WO2017128646A1 (zh) | 一种图像处理的方法及装置 | |
| WO2019200785A1 (zh) | 快速手部跟踪方法、装置、终端及存储介质 | |
| CN113744294A (zh) | 图像处理方法及相关装置 | |
| CN111222446B (zh) | 人脸识别方法、人脸识别装置及移动终端 | |
| US11354925B2 (en) | Method, apparatus and device for identifying body representation information in image, and computer readable storage medium | |
| WO2022252739A1 (zh) | 一种图像滤波方法、装置、终端和计算机可读存储介质 | |
| WO2023019681A1 (zh) | 一种图像内容的提取方法、装置、终端和存储介质 | |
| WO2019148894A1 (zh) | 一种利用图像斑块追踪测量偏移的方法、装置及存储介质 | |
| KR102585573B1 (ko) | 콘텐츠 기반 이미지 프로세싱 | |
| CN114025089A (zh) | 一种视频图像采集抖动处理方法及*** | |
| CN113628148A (zh) | 红外图像降噪方法和装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22798527 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 22798527 Country of ref document: EP Kind code of ref document: A1 |