WO2021227838A1 - 图像处理方法、系统及计算机可读存储介质 - Google Patents

图像处理方法、系统及计算机可读存储介质 Download PDF

Info

Publication number
WO2021227838A1
WO2021227838A1 PCT/CN2021/089489 CN2021089489W WO2021227838A1 WO 2021227838 A1 WO2021227838 A1 WO 2021227838A1 CN 2021089489 W CN2021089489 W CN 2021089489W WO 2021227838 A1 WO2021227838 A1 WO 2021227838A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
value
pixel
processed
gray value
Prior art date
Application number
PCT/CN2021/089489
Other languages
English (en)
French (fr)
Inventor
徐青松
李青
Original Assignee
杭州睿琪软件有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 杭州睿琪软件有限公司 filed Critical 杭州睿琪软件有限公司
Priority to US17/641,435 priority Critical patent/US20220301115A1/en
Publication of WO2021227838A1 publication Critical patent/WO2021227838A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/73Deblurring; Sharpening
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/70Denoising; Smoothing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformations in the plane of the image
    • G06T3/40Scaling of whole images or parts thereof, e.g. expanding or contracting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/20Image enhancement or restoration using local operators
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/90Dynamic range modification of images or parts thereof
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/13Edge detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10004Still image; Photographic image
    • G06T2207/10008Still image; Photographic image from scanner, fax or copier
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20021Dividing image into blocks, subimages or windows
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20172Image enhancement details
    • G06T2207/20192Edge enhancement; Edge preservation

Definitions

  • the present invention relates to the technical field of digital image processing, in particular to an image processing method, system and computer readable storage medium.
  • Image enhancement technology is to make the original unclear image clear or emphasize some interesting features, and suppress the uninteresting Features to improve the image quality, enrich the amount of information, and strengthen the image interpretation and recognition effect of the image processing method.
  • the captured image is not clear enough due to insufficient contrast, noise interference, etc., which will cause the image to be printed poorly and the image content is not easy to be recognized. Therefore, it is necessary to convert the captured color or unclear image to A clear and clear image with clear black and white contrast to improve the printing effect of the image.
  • the purpose of the present invention is to provide an image processing method, system, and computer readable storage medium to solve the problems of inconspicuous contrast, noise interference, and poor printing effect of images taken in the prior art.
  • the specific technical solutions are as follows:
  • an image processing method including:
  • the method further includes:
  • the black area at the edge of the target image is cleared.
  • the performing blurring processing on the to-be-processed image includes:
  • Gaussian blur is used to blur the image to be processed.
  • the performing binarization processing on the image to be processed according to the grayscale image and the first blurred image includes:
  • the pixel value of the pixel in the image to be processed is set to 255, otherwise it is set to 0;
  • the pixel value of the pixel in the image to be processed is set to 0.
  • the range of the third preset threshold is 35-75, and the range of the fourth preset threshold is 180-220.
  • the expanding the gray value of the high-value pixel in the binarized image includes:
  • the gray value of the high-value pixels in the binarized image is expanded according to a preset expansion coefficient, where the preset expansion coefficient is 1.2-1.5.
  • the first preset threshold is the sum of the mean gray value of the binarized image and the standard deviation of the gray value.
  • the clearing processing on the expanded image to obtain a clear image includes:
  • the second blurred image and the expanded image are mixed in proportion to obtain a clear image.
  • the preset mixing coefficient of the extended image is 1.5, and the preset mixing coefficient of the second blurred image is -0.5.
  • the adjusting the contrast of the clear image includes:
  • the gray value of each pixel in the clear image is adjusted.
  • the adjusting the gray value of each pixel in the clear image includes:
  • f'(i,j) is the gray value of the pixel (i,j) in the target image
  • f(i, j) is the gray value of the pixel (i, j) in the clear image
  • t is the intensity value.
  • the intensity value is 0.1-0.5.
  • the removing the black area at the edge of the target image includes:
  • the upper, lower, left, and right edges of the target image are respectively traversed to determine whether there is a black area whose width exceeds a fifth preset threshold, and if there is, the black area is removed.
  • the traversing the upper, lower, left, and right edges of the target image respectively to determine whether there is a black area whose size exceeds a fifth preset threshold includes:
  • any one of the upper, lower, left, and right edges of the target image traverse from the rows and columns to determine whether there is a black area and an edge of the black area, and then determine whether the width of the black area exceeds a fifth preset threshold.
  • the present invention also provides an image processing system.
  • the system includes a processor and a memory.
  • the memory stores instructions.
  • the image processing method is implemented. Steps, the method includes: obtaining a to-be-processed image; performing gray-scale processing on the to-be-processed image to obtain a gray-scale image, and performing blurring processing on the to-be-processed image to obtain a first blurred image;
  • the grayscale image and the first blurred image are binarized on the image to be processed to obtain a binarized image;
  • the grayscale value of high-value pixels in the binarized image is expanded, Obtain an expanded image, wherein the high-value pixels are pixels whose gray value is greater than a first preset threshold; clear the expanded image to obtain a clear image; adjust the contrast of the clear image, Obtain a contrast image; using the grayscale image as a guiding image, perform guiding filtering processing on the contrast image to obtain a target image.
  • the present invention also provides a computer-readable storage medium with instructions stored on the computer-readable storage medium.
  • the steps of the image processing method are implemented, and the method includes: Obtain a to-be-processed image; perform gray-scale processing on the to-be-processed image to obtain a gray-scale image, and perform blur-processing on the to-be-processed image to obtain a first blurred image; according to the gray-scale image and the first A blurred image, the image to be processed is binarized to obtain a binarized image; the gray value of high-value pixels in the binarized image is expanded to obtain an expanded image, wherein The high-value pixel is a pixel with a gray value greater than a first preset threshold; the expanded image is sharpened to obtain a clear image; the contrast of the clear image is adjusted to obtain a contrast image; The gray-scale image is a guided image, and guided filtering is performed on the contrast image to obtain a target image.
  • the image processing method, system and computer-readable storage medium provided by the present invention have the following advantages:
  • the image to be processed is subjected to grayscale processing and fuzzy processing respectively to obtain a grayscale image and a first blurred image, and then binarization processing is performed on the image to be processed according to the grayscale image and the first blurred image to obtain a binary image, Then expand the gray value of the high-value pixels in the binarized image to obtain the expanded image. Then, the expanded image is sharpened and the contrast is adjusted to obtain the contrast image, and the gray image is used as the guide map to compare the contrast image The guided filtering process is performed to obtain the target image.
  • the invention can convert a color image or an unclear image into a grayscale image with a clear and clear black-and-white contrast. Because the converted image has less noise interference and obvious black-and-white contrast, it can effectively improve the recognition of image content and the printing effect .
  • FIG. 1 is a schematic flowchart of an image processing method provided by an embodiment of the present invention
  • Fig. 2 is a to-be-processed image of a specific example of the present invention.
  • FIG. 3 is a grayscale image obtained after grayscale processing is performed on the image to be processed shown in FIG. 2;
  • FIG. 4 is a first blurred image obtained after the image to be processed shown in FIG. 2 is blurred
  • FIG. 5 is a binarized image obtained after binarizing the image to be processed shown in FIG. 2 according to the grayscale image shown in FIG. 3 and the first blurred image shown in FIG. 4;
  • FIG. 6 is an expanded image obtained after expansion processing is performed on the binarized image shown in FIG. 5;
  • FIG. 7 is a clear image after clearing the expanded image shown in FIG. 6;
  • FIG. 8 is a contrast image obtained after adjusting the contrast of the clear image shown in FIG. 7;
  • FIG. 9 is a target image obtained by using the grayscale image shown in FIG. 3 as a guiding diagram and performing guided filtering processing on the contrast image shown in FIG. 8;
  • FIG. 10 is an image obtained after clearing the black area at the edge of the target image shown in FIG. 9;
  • FIG. 11 is a schematic structural diagram of an image processing system provided by an embodiment of the present invention.
  • Fig. 1 shows a flowchart of an image processing method according to an exemplary embodiment of the present invention.
  • the method can be implemented in an application (app) installed on a smart terminal such as a mobile phone or a tablet computer.
  • the method may include:
  • Step S101 Obtain an image to be processed.
  • the to-be-processed image may be obtained by taking photos or scanning, and specifically may be previously stored by the user or captured by the user in real time.
  • the image to be processed may be previously stored in the mobile device by the user or captured in real time by the user using an external camera connected to the mobile device or a built-in camera of the mobile device.
  • the user can also obtain the to-be-processed image in real time via the network.
  • Figure 2 is an example of the image to be processed. The contrast in the figure is not obvious enough. If Figure 2 is printed directly, the printing effect will not be good. Therefore, follow-up processing of Figure 2 is required to make the image black and white contrast obvious, thereby improving the printing effect .
  • Step S102 Perform grayscale processing on the image to be processed to obtain a grayscale image, and perform blurring processing on the image to be processed to obtain a first blurred image.
  • R Red, G: Green, B: Blue
  • R Red, G: Green, B: Blue
  • the value range is 0 ⁇ 255.
  • the gray-scale methods include component method, maximum value method, average method and weighted average method.
  • the component method uses the brightness of the three components in the color image as the gray values of the three gray images, and a gray image can be selected according to application needs.
  • the maximum method uses the maximum value of the three-component brightness in the color image as the gray value of the gray image.
  • the average method is to average the three-component brightness in the color image to obtain a gray value.
  • the weighted average method is to weight and average the three components with different weights according to importance and other indicators. Since the human eye is the most sensitive to green and the least sensitive to blue, the weighted average of the three components of R, G, and B can be obtained by the following formula to obtain a more reasonable gray-scale image:
  • F(i,j) is the gray value of pixel (i,j) in the converted gray image
  • R(i,j) is the R component of pixel (i,j) in the color image
  • G (i,j) is the G component of the pixel (i,j) in the color image
  • B(i,j) is the B component of the pixel (i,j) in the color image.
  • any one of the above four gray-scale methods may be used to perform gray-scale processing on the image to be processed to obtain a gray-scale image.
  • FIG. 3 is a grayscale image obtained after grayscale processing is performed on the image to be processed shown in FIG. 2.
  • Blurring the image is mainly to soften the image and lighten the borders of different colors in the image, so as to cover up the defects of the image or create special effects.
  • Common blurring methods include motion blur, Gaussian blur, blur filter, further blur, radial blur, special blur, etc.
  • any one of these blurring methods may be used to perform blurring processing on the image to be processed to obtain a first blurred image.
  • FIG. 4 is a first blurred image obtained after the image to be processed shown in FIG. 2 is blurred.
  • Motion Blur refers to blurring the image along a specified direction (-360 degrees to +360 degrees) with a specified intensity (1 to 999).
  • the function of the blur filter (Blur) is to produce a slight blur effect, which can eliminate the noise in the image. If the effect is not obvious when applied only once, it can be applied repeatedly.
  • the blur effect produced by the further blur (Blur More) is better than the blur effect produced by the blur filter, and is generally 3 to 4 times the effect of the blur filter.
  • the function of Radial Blur is to simulate the blur produced by a moving or rotating camera, including two blur modes: rotation and zoom. Rotation is to blur along concentric circles at a specified rotation angle, and zoom is generated from the center of the image. The blur effect emitted by the dots.
  • Smart Blur is to produce a variety of blur effects to weaken the layering of the image, including three blur modes: normal, edge priority and superimposed edge. Normal mode only blurs the image, and edge priority mode can outline the image The color boundary, overlay edge is the overlay effect of the first two modes.
  • Gaussian blur is used to perform blurring processing on the image to be processed.
  • Gaussian Blur also called Gaussian smoothing, is a processing effect widely used in image processing software such as Adobe Photoshop, GIMP, Paint.NET, etc. It is usually used to reduce image noise and reduce the level of detail.
  • the visual effect of the image generated by this blur technology is like observing the image through a translucent screen, which is obviously different from the out-of-focus imaging effect of the lens and the effect in the shadow of ordinary lighting.
  • Gaussian smoothing is also used in the pre-processing stage of computer vision algorithms to enhance the image effect of images at different scales (see scale space representation and scale space implementation).
  • Gaussian blur refers to the convolution of an image with the probability density function of a two-dimensional Gaussian distribution.
  • the Gaussian blur process of the image is the convolution of the image and the normal distribution. Since the normal distribution is also called Gaussian distribution, this technique is called Gaussian blur. Convolution of the blurred image with the circular box will produce a more accurate out-of-focus imaging effect. Since the Fourier transform of the Gaussian function is another Gaussian function, the Gaussian blur is a low-pass filter for the image.
  • the Gaussian filter is a linear filter that can effectively suppress noise and smooth the image. Its working principle is similar to that of an average filter, and both take the average value of the pixels in the filter window as the output.
  • the coefficient of the window template is different from the average filter, and the template coefficient of the average filter is the same as 1.
  • the template coefficient of the Gaussian filter decreases as the distance from the center of the template increases. Therefore, the Gaussian filter has a smaller degree of blurring of the image compared to the average filter.
  • Gaussian filter is: Among them, ⁇ represents the neighborhood window, I p is the pixel value of p point, GF p is the output pixel value corresponding to p point,
  • the domain kernel function is defined as follows:
  • I t is the pixel value at point t
  • ⁇ s is the standard deviation of the spatial neighborhood, representing the degree of dispersion of the data. It is an important parameter of the Gaussian filter and determines the degree of blurring of the image by the Gaussian filter.
  • ⁇ s is small, the distribution of template coefficients is more concentrated, the coefficients near the center of the template are large, and the coefficients around the template are small, so the blur effect on the image is weak; when ⁇ s is large, the distribution of template coefficients is more scattered.
  • the coefficient at the center of the template is not much different from the coefficients around the template, so the blur effect on the image is more obvious.
  • Step S103 Perform binarization processing on the image to be processed according to the grayscale image and the first blurred image to obtain a binarized image.
  • Binarization is the process of setting the gray value of the pixels on the image to 0 or 255, which means that the entire image presents an obvious black and white effect.
  • the binarization of the image greatly reduces the amount of data in the image, thus Can highlight the outline of the target.
  • FIG. 5 is a binary image obtained by performing binarization processing on the image to be processed in FIG. 2 according to the grayscale image in FIG. 3 and the first blurred image in FIG. 4.
  • binarization processing is performed on the image to be processed according to the grayscale image and the first blurred image, specifically: for each pixel in the image to be processed, the following processing is performed:
  • the pixel value of the pixel in the image to be processed is set to 255, otherwise it is set to 0;
  • the pixel value of the pixel in the image to be processed is set to 0.
  • the pixel value of each pixel in the image to be processed can be set to 0 or 255, thereby obtaining a binary image.
  • the second preset threshold can be set according to actual conditions, for example, set to 10, the range of the third preset threshold is 35-75, preferably 55, and the range of the fourth preset threshold is 180-220 , Preferably 200.
  • the gray value of the pixel in the image to be processed should be set to black, if the gray value is greater than or equal to 55 (ie GrayPixel ⁇ 55), then the The gray value of this pixel is set to white.
  • GrayPixel When the gray value GrayPixel is less than the blur value BlurPixel (ie GrayPixel ⁇ BlurPixe), if the gray value is greater than 200 (ie GrayPixel>200), the gray value of the pixel in the image to be processed is set to white If the gray value is less than or equal to 200 (that is, GrayPixel ⁇ 200), the gray value of the pixel in the image to be processed is set to black.
  • the pixel value of the pixel in the image to be processed is set to black.
  • this embodiment divides all the pixels in the image to be processed into the first type of pixels, based on the gray value of the pixel in the gray image and the blur value of the pixel in the first blurred image.
  • the second type of pixels and the third type of pixels where the first type of pixels meet the following conditions: the absolute value of the difference between the gray value and the blur value is less than the second preset threshold, and the gray value is greater than or equal to Blur value, the second type of pixel points are pixels with gray values less than the blur value except for the first type of pixels, and the third type of pixels are pixels except for the first type of pixels and the Pixels other than the second type of pixels; for each of the first type of pixels, if the gray value is less than the third preset threshold, the pixel value of the pixel in the image to be processed is set to 0 , Otherwise set to 255; for each second type of pixel, if the gray value is greater than the fourth preset threshold, set the pixel value of the pixel in the image to be processed to
  • This embodiment first divides all pixels into three types of pixels, and further determines whether they should be set to black or white for the first type of pixels and the second type of pixels, so as to make the target in the obtained binary image
  • the distinction from the background is more obvious, the outline of the target is more detailed and prominent, and the black and white enhancement effect is better.
  • the grayscale image may also be binarized according to the first blurred image to obtain the same binarized image. For the specific implementation manner, refer to the above description, which will not be repeated here.
  • Step S104 performing expansion processing on the gray value of the high-value pixel in the binarized image to obtain an expanded image, wherein the high-value pixel is a pixel with a gray value greater than a first preset threshold.
  • the first preset threshold is the sum of the mean gray value of the binarized image and the standard deviation of the gray value of the binarized image. That is, the first preset threshold is equal to the average gray value of the binarized image plus the standard deviation of the gray value of the binarized image.
  • the gray value of the high-value pixel in the binarized image may be expanded according to a preset expansion coefficient, that is, the gray value of each high-value pixel is multiplied by the The expansion coefficient is preset to perform expansion processing on the gray value of the high-value pixels, so as to obtain an expanded image with more obvious black and white contrast.
  • the preset expansion coefficient is 1.2-1.5.
  • the preset expansion coefficient is 1.3.
  • the gray value of each high-value pixel in the binarized image is multiplied by 1.3 to obtain an expanded image with more obvious black and white contrast.
  • Fig. 6 is an expanded image obtained after expansion processing is performed on the binarized image shown in Fig. 5.
  • step S105 a sharpening process is performed on the expanded image to obtain a clear image.
  • FIG. 7 is a clear image after clearing the expanded image shown in FIG. 6.
  • the clearing processing of the expanded image to obtain a clear image includes:
  • f 1 (i, j) is the gray value of pixel (i, j) in the expanded image
  • f 2 (i, j) is the gray value of pixel (i, j) in the second blurred image.
  • Degree value, f 3 (i, j) is the gray value of the pixel (i, j) in the clear image
  • k 1 is the preset mixing coefficient of the extended image
  • k 2 is the second blurred image
  • the method for blurring the extended image is the same as the method for blurring the image to be processed, and will not be repeated here.
  • Gaussian blur can be used to blur the extended image.
  • Step S106 Adjust the contrast of the clear image to obtain a contrast image.
  • FIG. 8 is a contrast image obtained after adjusting the contrast of the clear image shown in FIG. 7.
  • the gray value of each pixel in the clear image can be adjusted according to the average gray value of the clear image.
  • the gray value of each pixel in the clear image is determined by the following formula Adjust the gray value: Wherein, f'(i,j) is the gray value of the pixel (i,j) in the target image, The average gray value of the clear image, f(i, j) is the gray value of the pixel (i, j) in the clear image, and t is the intensity value. Therefore, the gray value of each pixel of the clear image can be adjusted according to the above formula, so as to obtain a contrast image with more obvious black and white contrast.
  • the strength value can be 0.1-0.5, preferably 0.2.
  • the specific value of the intensity value can be selected according to the final black and white enhancement effect to be achieved.
  • Step S107 using the grayscale image as a guiding image, performing guiding filtering processing on the contrast image to obtain a target image.
  • Filters are widely used in image smoothing, denoising, and beautifying. At present, common filters include mean filter, median filter, Gaussian filter, bilateral filter and guided filter. The implementation steps of these filters are roughly the same. The specific process is as follows:
  • the pixel value of the pixel corresponding to the center position of the template in the image is the calculation result of the previous step.
  • Guided filtering is to filter the target image (input image) through a guide map, so that the final output image is roughly similar to the input image, and the edge texture is similar to the guide map.
  • the guided filter can be used as an edge-preserving smoothing operator like a bilateral filter, but it has a better processing effect on image edges and is currently one of the fastest edge-preserving filters.
  • the model includes a guiding image I, an input image p, and an output image q.
  • the guiding image I and the input image p can be the same image or different images.
  • the radius of the window ⁇ k is r, take the derivative of both sides of the above equation at the same time, and obtain Therefore, the above formula can ensure that the edge of the output image q is similar to the edge of the guide image I.
  • is a regularization parameter, minimize the cost function, and get the expressions of a k and b k:
  • ⁇ k and ⁇ k 2 are the mean value and variance of the steering image I in the window ⁇ k
  • is the number of pixels in the window ⁇ k.
  • the gray-scale image is a guide image
  • the contrast image is an input image
  • the target image is an output image. Therefore, by filtering the contrast image through the gray-scale image, the output image can be roughly the same as the contrast image.
  • FIG. 9 is a target image obtained by performing a guided filtering process on the contrast image shown in FIG. 8 with the grayscale image shown in FIG. 3 as a guide image.
  • the black area at the edge of the target image may also be cleared.
  • the upper, lower, left, and right edges of the target image may be traversed separately to determine whether there is a black area whose width exceeds the fifth preset threshold, and if there is, the black area is removed. That is, look for a continuous black area from the four edges of the target image.
  • the width of the black area exceeds the fifth preset threshold it is considered to be a black area that needs to be cleared. At this time, the black area is removed.
  • the pixel value of each pixel in the black area is set to white.
  • any one of the top, bottom, left, and right edges of the target image it can be traversed from the rows and columns to determine whether there is a black area and the boundary of the black area, and then determine whether the width of the black area exceeds the fifth Preset threshold. For example, using the scan line function, one row, one row, and one column are traversed from the edge of the image until the pixel value of the pixel is not black (that is, the boundary of the black area has been traversed at this time), so that the black area and the black area are found boundary.
  • FIG. 10 is an image obtained after clearing the black area at the edge of the target image shown in FIG. 9, in which the black area in the lower left corner area a in FIG. 9 has been removed in FIG. 10.
  • the image processing method provided by the present invention further includes the following step after acquiring the image to be processed and before performing gray-scale processing on the image to be processed: determining whether the image to be processed is a gray-scale image.
  • the image to be processed After acquiring the image to be processed, it is first determined whether the image to be processed is a grayscale image. If the image to be processed is a grayscale image, it is not necessary to perform grayscale processing on the image to be processed. Therefore, when the image to be processed is a grayscale image, the number of steps can be reduced, and the processing speed of the image can be effectively increased.
  • the image to be processed is grayed and blurred to obtain the gray image and the first blurred image, and then the image to be processed is processed according to the gray image and the first blurred image.
  • the binarization process obtains the binarized image, and then expands the gray value of the high-value pixels in the binarized image to obtain the expanded image.
  • the expanded image is sharpened and the contrast is adjusted to obtain the contrast image
  • the gray-scale image is the guiding image
  • the target image is obtained by guiding the filtering process on the contrast image.
  • the invention can convert a color image or an unclear image into a grayscale image with a clear and clear black-and-white contrast. Because the converted image has less noise interference and obvious black-and-white contrast, it can effectively improve the recognition of image content and the printing effect .
  • the present invention also provides an image processing system.
  • the image processing system 200 may include a processor 210 and a memory 220.
  • the memory 220 stores instructions. When the instructions are executed by the processor 210, the steps in the image processing method described above can be implemented.
  • the processor 210 may perform various actions and processing according to instructions stored in the memory 220.
  • the processor 210 may be an integrated circuit chip with signal processing capability.
  • the foregoing processor may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA off-the-shelf programmable gate array
  • Various methods, steps, and logical block diagrams disclosed in the embodiments of the present invention can be implemented or executed.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc., and may be an X86 architecture or an ARM architecture.
  • the memory 220 stores executable instructions, and the instructions are executed by the processor 210 in the image processing method described above.
  • the memory 220 may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be read only memory (ROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM synchronous dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • DDRSDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous connection dynamic random access memory
  • DR RAM direct memory bus random access memory
  • the present invention also provides a computer-readable storage medium with instructions stored on the computer-readable storage medium.
  • the instructions When executed, the steps in the image processing method described above can be implemented.
  • the computer-readable storage medium in the embodiment of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. It should be noted that the computer-readable storage media described herein are intended to include, but are not limited to, these and any other suitable types of memory.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more logic for implementing the specified Executable instructions for the function.
  • the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown one after another can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the various exemplary embodiments of the present invention may be implemented in hardware or special purpose circuits, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device.
  • firmware or software that can be executed by a controller, microprocessor, or other computing device.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Processing (AREA)

Abstract

一种图像处理方法、系统及计算机可读存储介质,方法包括:获取待处理图像(S101);对待处理图像进行灰度化处理,得到灰度图像,以及对待处理图像进行模糊化处理,得到第一模糊图像(S102);根据灰度图像和所述第一模糊图像,对待处理图像进行二值化处理,得到二值化图像(S103);对二值化图像中的高值像素点的灰度值进行扩充处理,得到扩充图像(S104);对扩充图像进行清晰化处理,得到清晰图像(S105);对清晰图像的对比度进行调整,得到对比度图像(S106);以灰度图像为导向图,对对比度图像进行导向滤波处理,得到目标图像(S107)。该方法可以解决现有技术中拍摄的图像对比度不明显、有噪声干扰,打印效果不好的问题。

Description

图像处理方法、系统及计算机可读存储介质 技术领域
本发明涉及数字图像处理技术领域,特别涉及一种图像处理方法、系统及计算机可读存储介质。
背景技术
近年来,随着数字图像处理技术的飞速发展,人们对图像质量的要求越来越高,图像增强技术是将原来不清晰的图像变得清晰或强调某些感兴趣的特征,抑制不感兴趣的特征,使之改善图像质量、丰富信息量,加强图像判读和识别效果的图像处理方法。
在互联网办公技术成为办公主流助力的背景下,越来越多的办公场景需要将文档等纸质资料进行传输。由于扫描仪便携性不足,而资料传输的时效性要求较高,用手机对纸质文档进行拍摄成为了便捷的首选。在采用手机拍摄纸质文档的过程中,由于人工拍摄的精确度不如扫描仪高,加上实际拍摄时环境光照不理想,拍摄得到的图像质量存在很多不足,图像光照不均和存在明暗程度不同的阴影、白底色的纸质文件成像后变成不同程度的灰色。
可见,拍摄的图像由于对比度不够明显、有噪声干扰等,导致图像不够清晰,进而会导致图像打印出来的效果不好,图像内容不易于被辨识,因此需要将拍摄的彩色或不清晰图像转换为黑白对比明显且清晰的图像,以提高图像的打印效果。
发明内容
本发明的目的在于提供一种图像处理方法、系统及计算机可读存储介质,以解决现有技术中拍摄的图像对比度不明显、有噪声干扰,打印效果不好的问题。具体技术方案如下:
为达到上述目的,本发明提供一种图像处理方法,包括:
获取待处理图像;
对所述待处理图像进行灰度化处理,得到灰度图像,以及对所述待处理 图像进行模糊化处理,得到第一模糊图像;
根据所述灰度图像和所述第一模糊图像,对所述待处理图像进行二值化处理,得到二值化图像;
对所述二值化图像中的高值像素点的灰度值进行扩充处理,得到扩充图像,其中,所述高值像素点为灰度值大于第一预设阈值的像素点;
对所述扩充图像进行清晰化处理,得到清晰图像;
对所述清晰图像的对比度进行调整,得到对比度图像;
以所述灰度图像为导向图,对所述对比度图像进行导向滤波处理,得到目标图像。
可选的,所述方法还包括:
对所述目标图像边缘的黑色区域进行清除处理。
可选的,所述对所述待处理图像进行模糊化处理,包括:
采用高斯模糊对所述待处理图像进行模糊化处理。
可选的,所述根据所述灰度图像和所述第一模糊图像,对所述待处理图像进行二值化处理,包括:
针对所述待处理图像中的每一像素点,进行如下处理:
计算所述灰度图像中相应像素点的灰度值与所述第一模糊图像中相应像素点的模糊值的差值,在所述差值的绝对值小于第二预设阈值,且灰度值大于等于模糊值的情况下,若灰度值小于第三预设阈值,则将所述待处理图像中该像素点的像素值设置为0,否则设置为255;
在灰度值小于模糊值的情况下,若灰度值大于第四预设阈值,则将所述待处理图像中该像素点的像素值设置为255,否则设置为0;
若灰度值不属于上述两种情况,则将所述待处理图像中该像素点的像素值设置为0。
可选的,所述第三预设阈值的范围为35-75,所述第四预设阈值的范围为180-220。
可选的,所述对所述二值化图像中的高值像素点的灰度值进行扩充处理,包括:
按照预设扩充系数对所述二值化图像中的高值像素点的灰度值进行扩充 处理,其中,所述预设扩充系数为1.2-1.5。
可选的,所述第一预设阈值为所述二值化图像的灰度均值与灰度值的标准差之和。
可选的,所述对所述扩充图像进行清晰化处理,得到清晰图像,包括:
对所述扩充图像进行模糊化处理,得到第二模糊图像;以及
根据预设混合系数,将所述第二模糊图像和所述扩充图像按比例进行混合,得到清晰图像。
可选的,所述扩充图像的预设混合系数为1.5,所述第二模糊图像的预设混合系数为-0.5。
可选的,所述对所述清晰图像的对比度进行调整,包括:
根据所述清晰图像的灰度均值,对所述清晰图像中每一像素点的灰度值进行调整。
可选的,所述对所述清晰图像中每一像素点的灰度值进行调整,包括:
通过如下公式对所述清晰图像中每一像素点的灰度值进行调整:
Figure PCTCN2021089489-appb-000001
其中,f'(i,j)为所述目标图像中像素点(i,j)的灰度值,
Figure PCTCN2021089489-appb-000002
为所述清晰图像的灰度均值,f(i,j)为所述清晰图像中像素点(i,j)的灰度值,t为强度值。
可选的,所述强度值为0.1-0.5。
可选的,所述对所述目标图像边缘的黑色区域进行清除处理,包括:
对所述目标图像的上下左右四个边缘分别进行遍历,判断是否存在宽度超过第五预设阈值的黑色区域,若存在,去除所述黑色区域。
可选的,所述对所述目标图像的上下左右四个边缘分别进行遍历,判断是否存在大小超过第五预设阈值的黑色区域,包括:
针对所述目标图像的上下左右四个边缘中的任一个,从行列两个方向进行遍历以确定是否存在黑色区域以及黑色区域的边缘,进而判断黑色区域的宽度是否超过第五预设阈值。
基于同一发明构思,本发明还提供了一种图像处理系统,所述系统包括处理器和存储器,所述存储器上存储有指令,当所述指令被所述处理器执行时,实现图像处理方法的步骤,所述方法包括:获取待处理图像;对所述待 处理图像进行灰度化处理,得到灰度图像,以及对所述待处理图像进行模糊化处理,得到第一模糊图像;根据所述灰度图像和所述第一模糊图像,对所述待处理图像进行二值化处理,得到二值化图像;对所述二值化图像中的高值像素点的灰度值进行扩充处理,得到扩充图像,其中,所述高值像素点为灰度值大于第一预设阈值的像素点;对所述扩充图像进行清晰化处理,得到清晰图像;对所述清晰图像的对比度进行调整,得到对比度图像;以所述灰度图像为导向图,对所述对比度图像进行导向滤波处理,得到目标图像。
基于同一发明构思,本发明还提供了一种计算机可读存储介质,所述计算机可读存储介质上存储有指令,当所述指令被执行时,实现图像处理方法的步骤,所述方法包括:获取待处理图像;对所述待处理图像进行灰度化处理,得到灰度图像,以及对所述待处理图像进行模糊化处理,得到第一模糊图像;根据所述灰度图像和所述第一模糊图像,对所述待处理图像进行二值化处理,得到二值化图像;对所述二值化图像中的高值像素点的灰度值进行扩充处理,得到扩充图像,其中,所述高值像素点为灰度值大于第一预设阈值的像素点;对所述扩充图像进行清晰化处理,得到清晰图像;对所述清晰图像的对比度进行调整,得到对比度图像;以所述灰度图像为导向图,对所述对比度图像进行导向滤波处理,得到目标图像。
与现有技术相比,本发明提供的图像处理方法、系统及计算机可读存储介质具有以下优点:
本发明对待处理图像分别进行灰度化处理和模糊化处理,得到灰度图像和第一模糊图像,再根据灰度图像和第一模糊图像对待处理图像进行二值化处理得到二值化图像,然后对二值化图像中的高值像素点的灰度值进行扩充处理得到扩充图像,接着对扩充图像进行清晰化处理以及调整对比度得到对比度图像,并以灰度图像为导向图,对对比度图像进行导向滤波处理得到目标图像。本发明可以将彩色图像或不清晰的图像转换为黑白对比较为明显且清晰的灰度图像,由于转换后的图像噪声干扰较少且黑白对比明显,从而可以有效提高图像内容的辨识度和打印效果。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本发明一实施例提供的图像处理方法的流程示意图;
图2为本发明的一具体示例的待处理图像;
图3为对图2所示的待处理图像进行灰度化处理后得到的灰度图像;
图4为对图2所示的待处理图像进行模糊化处理后得到的第一模糊图像;
图5为根据图3所示的灰度图像和图4所示的第一模糊图像对图2所示的待处理图像进行二值化处理后得到的二值化图像;
图6为对图5所示的二值化图像进行扩充处理后得到的扩充图像;
图7为对图6所示的扩充图像进行清晰化处理后的清晰图像;
图8为对图7所示的清晰图像进行对比度调整后得到的对比度图像;
图9为以图3所示的灰度图像为导向图,对图8所示的对比度图像进行导向滤波处理,得到的目标图像;
图10为对图9所示的目标图像边缘的黑色区域进行清除处理后得到的图像;
图11是本发明一实施例提供的图像处理系统的结构示意图。
具体实施方式
以下结合附图和具体实施例对本发明提出的一种图像处理方法、系统及计算机可读存储介质作进一步详细说明。根据下面说明,本发明的优点和特征将更清楚。需说明的是,附图均采用非常简化的形式且均使用非精准的比例,仅用以方便、明晰地辅助说明本发明实施例的目的。须知,本说明书所附图式所绘示的结构、比例、大小等,均仅用以配合说明书所揭示的内容,以供熟悉此技术的人士了解与阅读,并非用以限定本发明实施的限定条件,故不具技术上的实质意义,任何结构的修饰、比例关系的改变或大小的调整,在不影响本发明所能产生的功效及所能达成的目的下,均应仍落在本发明所揭示的技术内容能涵盖的范围内。
图1示出了根据本发明一示例性实施例的图像处理方法的流程图,该方法可以在例如手机、平板电脑等智能终端上安装的应用程序(app)中实现。如图1所示,该方法可以包括:
步骤S101,获取待处理图像。
所述待处理图像可通过拍照或扫描的方式取得,具体可以是用户先前存储的或者是用户实时拍摄的。例如,所述待处理图像可以是用户先前存储在移动设备中或者是用户使用连接到移动设备的外置摄像头或移动设备内置的摄像头进行实时拍摄的。在一个实施例中,用户还可以通过网络实时获取所述待处理图像。图2为一个示例的待处理图像,图中对比度不够明显,若直接对图2进行打印,则打印效果不好,因此需要对图2进行后续处理,以使图像黑白对比明显,从而改善打印效果。
步骤S102,对所述待处理图像进行灰度化处理,得到灰度图像,以及对所述待处理图像进行模糊化处理,得到第一模糊图像。
在图像处理中,用R、G、B三个分量(R:Red,G:Green,B:Blue),即红、绿、蓝三原色来表示真彩色,R分量、G分量、B分量的取值范围均为0~255。当R=G=B时,则彩色表示一种灰度颜色,其中R=G=B的值叫灰度值。
灰度化的方法有分量法、最大值法、平均值法和加权平均法。其中,分量法是将彩色图像中的三分量的亮度作为三个灰度图像的灰度值,可根据应用需要选取一种灰度图像。最大值法是将彩色图像中的三分量亮度的最大值作为灰度图的灰度值。平均值法是将彩色图像中的三分量亮度求平均得到一个灰度值。
加权平均法,是根据重要性及其它指标,将三个分量以不同的权值进行加权平均。由于,人眼对绿色的敏感最高,对蓝色敏感最低,因此,按下式对R、G、B三分量进行加权平均得到较合理的灰度图像:
F(i,j)=0.30R(i,j)+0.59G(i,j)+0.11B(i,j)
其中,F(i,j)为转换后的灰度图像中像素点(i,j)的灰度值,R(i,j)为彩色图像中像素点(i,j)的R分量,G(i,j)为彩色图像中像素点(i,j)的G分量;B(i,j)为彩色图像中在像素点(i,j)的B分量。
在本实施例中,可以采用以上四种灰度化方法中的任一种对所述待处理图像进行灰度化处理,以得到灰度图像。图3是对图2所示的待处理图像进行灰度化处理后得到的灰度图像。
对图像进行模糊化处理,主要是使图像柔和,淡化图像中不同色彩的边界,以达到掩盖图像的缺陷或创造出特殊效果的作用。常见的模糊化的方法有动感模糊、高斯模糊、模糊滤镜、进一步模糊、径向模糊、特殊模糊等。在本实施例中,可以采用这些模糊化方法中的任一种对所述待处理图像进行模糊化处理,以得到第一模糊图像。图4是对图2所示的待处理图像进行模糊化处理后得到的第一模糊图像。
其中,动感模糊(Motion Blur)是对图像沿着指定的方向(-360度至+360度),以指定的强度(1至999)进行模糊。模糊滤镜(Blur)的作用是产生轻微模糊效果,可消除图像中的杂色,如果只应用一次效果不明显,可重复应用。进一步模糊(Blur More)产生的模糊效果比模糊滤镜产生的模糊效果更好,一般为模糊滤镜效果的3至4倍。径向模糊(Radial Blur)的作用是模拟移动或旋转的相机产生的模糊,包括旋转和缩放两种模糊模式,旋转是按指定的旋转角度沿着同心圆进行模糊,缩放是产生从图像的中心点向四周发射的模糊效果。特殊模糊(Smart Blur)的作用是可以产生多种模糊效果,使图像的层次感减弱,包括正常、边缘优先和叠加边缘三种模糊模式,正常模式只将图像模糊,边缘优先模式可勾画出图像的色彩边界,叠加边缘是前两种模式的叠加效果。
优选的,采用高斯模糊对所述待处理图像进行模糊化处理。高斯模糊(Gaussian Blur),也叫高斯平滑,是在Adobe Photoshop、GIMP以及Paint.NET等图像处理软件中广泛使用的处理效果,通常用它来减少图像噪声以及降低细节层次。这种模糊技术生成的图像,其视觉效果就像是经过一个半透明屏幕在观察图像,这与镜头焦外成像效果散景以及普通照明阴影中的效果都明显不同。高斯平滑也用于计算机视觉算法中的预先处理阶段,以增强图像在不同比例大小下的图像效果(参见尺度空间表示以及尺度空间实现)。从数学的角度来看,高斯模糊是指一个图像与二维高斯分布的概率密度函数做卷积。图像的高斯模糊过程就是图像与正态分布做卷积。由于正态分布又叫作高斯 分布,所以这项技术就叫作高斯模糊。图像与圆形方框模糊做卷积将会生成更加精确的焦外成像效果。由于高斯函数的傅立叶变换是另外一个高斯函数,所以高斯模糊对于图像来说就是一个低通滤波器。
高斯滤波器是一种线性滤波器,能够有效的抑制噪声、平滑图像。其作用原理和均值滤波器类似,都是取滤波器窗口内的像素的均值作为输出。其窗口模板的系数和均值滤波器不同,均值滤波器的模板系数都是相同的为1;而高斯滤波器的模板系数,则随着距离模板中心的增大而系数减小。所以,高斯滤波器相比于均值滤波器对图像的模糊程度较小。
高斯滤波器的定义为:
Figure PCTCN2021089489-appb-000003
其中,Ω表示邻域窗口,I p为p点的像素值,GF p为p点对应的输出像素值,||p-t||表示p点和t点的欧几里得距离,G s为空间域核函数,其定义如下:
Figure PCTCN2021089489-appb-000004
其中,I t为t点的像素值,σ s为空间邻域标准差,代表着数据的离散程度,是高斯滤波器的一个重要的参数,决定了高斯滤波器对图像的模糊程度。当σ s较小时,模板系数分布较集中,模板中心附近的系数较大,而模板周围的系数较小,这样对图像的模糊效果较弱;当σ s较大时,模板系数分布较分散,模板中心的系数与模板周围的系数相差不大,这样对图像的模糊效果较明显。
步骤S103,根据所述灰度图像和所述第一模糊图像,对所述待处理图像进行二值化处理,得到二值化图像。
二值化处理是将图像上的像素点的灰度值设置为0或255,也就是将整个图像呈现出明显的黑白效果的过程,图像的二值化使图像中数据量大为减少,从而能凸显出目标的轮廓。图5是根据图3的灰度图像和图4的第一模糊图像对图2的待处理图像进行二值化处理,得到的二值化图像。
本实施例根据所述灰度图像和所述第一模糊图像,对所述待处理图像进行二值化处理,具体为:针对所述待处理图像中的每一像素点,均进行如下处理:
计算所述灰度图像中相应像素点的灰度值与所述第一模糊图像中相应像 素点的模糊值的差值,在所述差值的绝对值小于第二预设阈值,且灰度值大于等于模糊值的情况下,若灰度值小于第三预设阈值,则将所述待处理图像中该像素点的像素值设置为0,否则设置为255;
在灰度值小于模糊值的情况下,若灰度值大于第四预设阈值,则将所述待处理图像中该像素点的像素值设置为255,否则设置为0;
若灰度值不属于上述两种情况,则将所述待处理图像中该像素点的像素值设置为0。
通过上述处理可以将所述待处理图像中的每一像素点的像素值均设置为0或255,从而得到二值化图像。
所述第二预设阈值可以根据实际情况进行设置,例如设置为10,所述第三预设阈值的范围为35-75,优选为55,所述第四预设阈值的范围为180-220,优选为200。
针对任一像素点,在灰度值GrayPixel与模糊值BlurPixel的差值的绝对值小于10,且灰度值大于等于模糊值(即GrayPixel≥BlurPixe)的情况下,若灰度值小于55(即GrayPixel<55),这时应将所述待处理图像中该像素点的灰度值设置为黑色,若灰度值大于等于55(即GrayPixel≥55),这时应将所述待处理图像中该像素点的灰度值设置为白色。
在灰度值GrayPixel小于模糊值BlurPixel的情况下(即GrayPixel<BlurPixe),若灰度值大于200(即GrayPixel>200),则将所述待处理图像中该像素点的灰度值设置为白色,若灰度值小于等于200(即GrayPixel≤200),则将所述待处理图像中该像素点的灰度值设置为黑色。
若像素点的灰度值不满足上述两种情况,则将所述待处理图像中该像素点的像素值设置为黑色。
可见,本实施例通过所述灰度图像中像素点的灰度值和所述第一模糊图像中像素点的模糊值,将所述待处理图像中所有像素点分为第一类像素点、第二类像素点和第三类像素点,其中,第一类像素点满足以下条件:灰度值与模糊值的差值的绝对值小于所述第二预设阈值,且灰度值大于等于模糊值,所述第二类像素点为除所述第一类像素点以外的灰度值小于模糊值的像素点,所述第三类像素点为除所述第一类像素点和所述第二类像素点之外的像 素点;针对每一个所述第一类像素点,若灰度值小于第三预设阈值,则将所述待处理图像中该像素点的像素值设置为0,否则设置为255;针对每一个所述第二类像素点,若灰度值大于第四预设阈值,则将所述待处理图像中该像素点的像素值设置为255,否则设置为0;针对每一个所述第三类像素点,将所述待处理图像中该像素点的像素值设置为0。
本实施例首先将所有像素点分为三类像素点,并针对第一类像素点和第二类像素点进一步判断应该将其设置为黑色还是白色,从而能够使得获得的二值化图像中目标和背景的区分更明显,目标的轮廓更细致、突出,进而使黑白增强的效果更好。在其他实施例中,也可以根据所述第一模糊图像,对所述灰度图像进行二值化处理以得到同样的二值化图像,具体实现方式可参照以上描述,在此不做赘述。
步骤S104,对所述二值化图像中的高值像素点的灰度值进行扩充处理,得到扩充图像,其中,所述高值像素点为灰度值大于第一预设阈值的像素点。
优选的,所述第一预设阈值为所述二值化图像的灰度均值与所述二值化图像的灰度值的标准差之和。即,所述第一预设阈值等于所述二值化图像的灰度均值加上所述二值化图像的灰度值的标准差。
在此步骤中,可以按照预设扩充系数对所述二值化图像中的高值像素点的灰度值进行扩充处理,即,将每一个高值像素点的灰度值都乘以所述预设扩充系数,以对所述高值像素点的灰度值进行扩充处理,从而得到黑白对比更加明显的扩充图像。
其中,所述预设扩充系数为1.2-1.5。优选的,所述预设扩充系数为1.3,则此时将所述二值化图像中的每一个高值像素点的灰度值都乘以1.3,从而得到黑白对比更加明显的扩充图像。图6是对图5所示的二值化图像进行扩充处理后得到的扩充图像。
步骤S105,对所述扩充图像进行清晰化处理,得到清晰图像。
本步骤中,通过对扩充图像进行清晰化处理,可以得到相对于所述扩充图像更加清晰的清晰图像。图7是对图6所示的扩充图像进行清晰化处理后的清晰图像。
优选的,所述对所述扩充图像进行清晰化处理,得到清晰图像,包括:
对所述扩充图像进行模糊化处理,得到第二模糊图像;以及根据预设混合系数,将所述第二模糊图像和所述扩充图像按比例进行混合,得到清晰图像。
假设f 1(i,j)为所述扩充图像中像素点(i,j)的灰度值,f 2(i,j)为所述第二模糊图像中像素点(i,j)的灰度值,f 3(i,j)为所述清晰图像中像素点(i,j)的灰度值,k 1为所述扩充图像的预设混合系数,k 2为所述第二模糊图像的预设扩充系数,则f 1(i,j)、f 2(i,j)、f 3(i,j)关系如下:f 3(i,j)=k 1f 1(i,j)+k 2f 2(i,j)。
优选地,所述扩充图像的预设混合系数为1.5,所述第二模糊图像的预设混合系数为-0.5,则此时,所述清晰图像中像素点(i,j)的灰度值为:f 3(i,j)=1.5f 1(i,j)-0.5f 2(i,j)。
对所述扩充图像进行模糊化处理的方法与前述对待处理图像进行模糊化的方法相同,在此不做赘述。优选的,可采用高斯模糊对所述扩充图像进行模糊化处理。
步骤S106,对所述清晰图像的对比度进行调整,得到对比度图像。
本步骤中,通过对所述清晰图像的对比度进行调整,从而可以得到黑白对比更为明显的对比度图像。图8为对图7所示的清晰图像进行对比度调整后得到的对比度图像。
本实施例中,可以根据所述清晰图像的灰度均值,对所述清晰图像中每一像素点的灰度值进行调整,具体的,通过如下公式对所述清晰图像中每一像素点的灰度值进行调整:
Figure PCTCN2021089489-appb-000005
其中,f'(i,j)为所述目标图像中像素点(i,j)的灰度值,
Figure PCTCN2021089489-appb-000006
所述清晰图像的灰度均值,f(i,j)为所述清晰图像中像素点(i,j)的灰度值,t为强度值。由此,可以根据上述公式,对所述清晰图像的每个像素点的灰度值进行调整,从而得到黑白对比更为明显的对比度图像。
其中,强度值可为0.1-0.5,优选为0.2。强度值的具体取值可根据最终所要达到的黑白增强效果进行选取。
步骤S107,以所述灰度图像为导向图,对所述对比度图像进行导向滤波处理,得到目标图像。
滤波器在图像的平滑、去噪、美颜等方面有着广泛的应用。目前,常见 的滤波器有均值滤波器、中值滤波器、高斯滤波器、双边滤波器和导向滤波器,这些滤波器的实现步骤大体相同,其具体过程如下:
1)构建一个m×n的模板(m和n通常为奇数),然后在图像中移动该模板,使得模板中心与每个像素点依次重合(边缘像素点除外)。
2)将模板中的每个系数与对应像素点的像素值一一相差,并将所有结果相加(也可能是其他运算)。
3)图像中对应模板中心位置的像素点的像素值即为上一步的计算结果。
导向滤波是通过一张导向图,对目标图像(输入图像)进行滤波处理,使得最后输出的图像大体上与输入图像相似,而边缘纹理处与导向图相似。导向滤波器可以像双边滤波器那样,作为一个保边平滑算子使用,但是其对图像边缘的处理效果更好,是目前最快的保边滤波器之一。
导向滤波的基本原理如下:
首先引入一个局部线性模型,该模型包括一个导向图I、一个输入图像p以及一个输出图像q,导向图I和输入图像p可以是完全相同的图像,也可以是不同的图像。假设输出图像q与导向图I是下式的线性关系:q i=a kI i+b k,
Figure PCTCN2021089489-appb-000007
其中,系数a k和b k在窗口ω k中保持不变,假设窗口ω k的半径为r,对上式两边同时取导,得到
Figure PCTCN2021089489-appb-000008
所以上式可以保证输出图像q的边缘与导向图I的边缘相似。
为了确定系数a k和b k,需要引入一个约束条件,假设输出图像q是输入图像p减去不必要的纹理及噪声n得到的,则有如下公式:q i=p i-n i
为了让输出图像q与输入图像p相差最小,引入以下代价函数:
Figure PCTCN2021089489-appb-000009
其中,ε是一个正则化参数,最小化该代价函数,得到a k和b k的表达式:
Figure PCTCN2021089489-appb-000010
Figure PCTCN2021089489-appb-000011
其中,μ k和σ k 2分别是导向图I在窗口ω k中的均值和方差,|ω|是窗口ω k中像素点的个数。得到a k和b k后即可算出输出像素点q i。像素点i参与了所有包 含它的窗口的计算,所以用不同的窗口计算出来的q i不同,将其取平均,得到如下公式:
Figure PCTCN2021089489-appb-000012
由于窗口的对称性,上式可以改写为:
Figure PCTCN2021089489-appb-000013
其中,
Figure PCTCN2021089489-appb-000014
分别是窗口ω k中的平均值。
在本步骤中,所述灰度图像为导向图,所述对比度图像为输入图像,目标图像为输出图像,由此,通过灰度图像对对比度图像进行滤波处理,可以输出与所述对比度图像大体上相似且边缘纹理处与所述灰度图像相似的目标图像,经过滤波处理后,图像中的噪声明显减少。图9是以图3所示的灰度图像为导向图,对图8所示的对比度图像进行导向滤波处理,得到的目标图像。
进一步的,在步骤S107得到目标图像后,还可以对所述目标图像边缘的黑色区域进行清除处理。通过上述步骤处理得到的目标图像的边缘会存在大片的黑色区域,例如,图像的上下左右四个边缘中的至少一个存在黑色区域,因此需要将这些黑色区域去除。
本实施例中,可以对所述目标图像的上下左右四个边缘分别进行遍历,判断是否存在宽度超过第五预设阈值的黑色区域,若存在,去除所述黑色区域。即从所述目标图像的四个边缘中寻找连续的黑色区域,当黑色区域的宽度超过第五预设阈值时,则认为其是需要清除的黑色区域,此时将该黑色区域去除掉,即将该黑色区域中各个像素点的像素值设为白色。
具体而言,针对所述目标图像的上下左右四个边缘中的任一个,可以从行列两个方向进行遍历以确定是否存在黑色区域以及黑色区域的边界,进而判断黑色区域的宽度是否超过第五预设阈值。例如,采用扫描线函数,一行行、一列列从图像的边缘进行遍历,直到像素点的像素值不是黑色为止(即此时已遍历到黑色区域的边界),如此即找到黑色区域以及黑色区域的边界。
图10是对图9所示的目标图像边缘的黑色区域进行清除处理后得到的图像,其中图9左下角区域a内的黑色区域在图10中已经被去除掉。
可选的,本发明提供的图像处理方法在获取待处理图像之后且对所述待处理图像进行灰度化处理之前,还包括如下步骤:判断所述待处理图像是否为灰度图像。
在获取待处理图像之后,先判断所述待处理图像是否为灰度图像,若所述待处理图像是灰度图像,则不必再对所述待处理图像进行灰度化处理。由此,当所述待处理图像为灰度图像时,可以减少工序,有效提高图像的处理速度。
对比图2和图10可以看出,通过采用本发明提供的方法对待处理图像进行处理后,得到的目标图像相比于待处理图像黑白对比更加明显,噪声干扰明显减少,图像更加清晰,图像内容更易于辨识,图10所示的图像的打印效果要明显优于直接对图2所示的图像的打印效果。
综上所述,本发明提供的图像处理方法,对待处理图像分别进行灰度化处理和模糊化处理得到灰度图像和第一模糊图像,再根据灰度图像和第一模糊图像对待处理图像进行二值化处理得到二值化图像,然后对二值化图像中的高值像素点的灰度值进行扩充处理得到扩充图像,接着对扩充图像进行清晰化处理以及调整对比度得到对比度图像,并以灰度图像为导向图,对对比度图像进行导向滤波处理得到目标图像。本发明可以将彩色图像或不清晰的图像转换为黑白对比较为明显且清晰的灰度图像,由于转换后的图像噪声干扰较少且黑白对比明显,从而可以有效提高图像内容的辨识度和打印效果。
基于同一发明构思,本发明还提供了一种图像处理系统。如图11所示,图像处理系统200可以包括处理器210和存储器220,存储器220上存储有指令,当指令被处理器210执行时,可以实现如上文所描述的图像处理方法中的步骤。
其中,处理器210可以根据存储在存储器220中的指令执行各种动作和处理。具体地,处理器210可以是一种集成电路芯片,具有信号的处理能力。上述处理器可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(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。可以实现或者执行本发明实施例中公开的各种方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等,可以是X86架构或者是ARM架构等。
存储器220存储有可执行指令,该指令在被处理器210执行上文所述的图像处理方法。存储器220可以是易失性存储器或非易失性存储器,或可包 括易失性和非易失性存储器两者。非易失性存储器可以是只读存储器(ROM)、可编程只读存储器(PROM)、可擦除可编程只读存储器(EPROM)、电可擦除可编程只读存储器(EEPROM)或闪存。易失性存储器可以是随机存取存储器(RAM),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、同步动态随机存取存储器(SDRAM)、双倍数据速率同步动态随机存取存储器(DDRSDRAM)、增强型同步动态随机存取存储器(ESDRAM)、同步连接动态随机存取存储器(SLDRAM)和直接内存总线随机存取存储器(DR RAM)。应注意,本文描述的方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
基于同一发明构思,本发明还提供了一种计算机可读存储介质,计算机可读存储介质上存储有指令,当指令被执行时,可以实现上文所描述的图像处理方法中的步骤。
类似地,本发明实施例中的计算机可读存储介质可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。应注意,本文描述的计算机可读存储介质旨在包括但不限于这些和任意其它适合类型的存储器。
需要说明的是,附图中的流程图和框图,图示了按照本发明各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,所述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
一般而言,本发明的各种示例实施例可以在硬件或专用电路、软件、固件、逻辑,或其任何组合中实施。某些方面可以在硬件中实施,而其他方面 可以在可以由控制器、微处理器或其他计算设备执行的固件或软件中实施。当本发明的实施例的各方面被图示或描述为框图、流程图或使用某些其他图形表示时,将理解此处描述的方框、装置、系统、技术或方法可以作为非限制性的示例在硬件、软件、固件、专用电路或逻辑、通用硬件或控制器或其他计算设备,或其某些组合中实施。
需要说明的是,本说明书中的各个实施例均采用相关的方式描述,各个实施例之间相同相似的部分互相参见即可,每个实施例重点说明的都是与其他实施例的不同之处。尤其,对于系统、计算机可读存储介质而言,由于其基本相似于方法实施例,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
上述描述仅是对本发明较佳实施例的描述,并非对本发明范围的任何限定,本发明领域的普通技术人员根据上述揭示内容做的任何变更、修饰,均属于权利要求书的保护范围。

Claims (16)

  1. 一种图像处理方法,其特征在于,包括:
    获取待处理图像;
    对所述待处理图像进行灰度化处理,得到灰度图像,以及对所述待处理图像进行模糊化处理,得到第一模糊图像;
    根据所述灰度图像和所述第一模糊图像,对所述待处理图像进行二值化处理,得到二值化图像;
    对所述二值化图像中的高值像素点的灰度值进行扩充处理,得到扩充图像,其中,所述高值像素点为灰度值大于第一预设阈值的像素点;
    对所述扩充图像进行清晰化处理,得到清晰图像;
    对所述清晰图像的对比度进行调整,得到对比度图像;
    以所述灰度图像为导向图,对所述对比度图像进行导向滤波处理,得到目标图像。
  2. 如权利要求1所述的图像处理方法,其特征在于,对所述待处理图像进行模糊化处理,包括:
    采用高斯模糊对所述待处理图像进行模糊化处理。
  3. 如权利要求1所述的图像处理方法,其特征在于,根据所述灰度图像和所述第一模糊图像,对所述待处理图像进行二值化处理,包括:
    针对所述待处理图像中的每一像素点,进行如下处理:
    计算所述灰度图像中相应像素点的灰度值与所述第一模糊图像中相应像素点的模糊值的差值,在所述差值的绝对值小于第二预设阈值,且灰度值大于等于模糊值的情况下,若灰度值小于第三预设阈值,则将所述待处理图像中该像素点的像素值设置为0,否则设置为255;
    在灰度值小于模糊值的情况下,若灰度值大于第四预设阈值,则将所述待处理图像中该像素点的像素值设置为255,否则设置为0;
    若灰度值不属于上述两种情况,则将所述待处理图像中该像素点的像素值设置为0。
  4. 如权利要求3所述的图像处理方法,其特征在于,所述第三预设阈值 的范围为35-75,所述第四预设阈值的范围为180-220。
  5. 如权利要求1所述的图像处理方法,其特征在于,对所述二值化图像中的高值像素点的灰度值进行扩充处理,包括:
    按照预设扩充系数对所述二值化图像中的高值像素点的灰度值进行扩充处理,其中,所述预设扩充系数为1.2-1.5。
  6. 如权利要求1所述的图像处理方法,其特征在于,所述第一预设阈值为所述二值化图像的灰度均值与灰度值的标准差之和。
  7. 如权利要求1所述的图像处理方法,其特征在于,对所述扩充图像进行清晰化处理,得到清晰图像,包括:
    对所述扩充图像进行模糊化处理,得到第二模糊图像;以及
    根据预设混合系数,将所述第二模糊图像和所述扩充图像按比例进行混合,得到清晰图像。
  8. 如权利要求7所述的图像处理方法,其特征在于,所述扩充图像的预设混合系数为1.5,所述第二模糊图像的预设混合系数为-0.5。
  9. 如权利要求1所述的图像处理方法,其特征在于,对所述清晰图像的对比度进行调整,包括:
    根据所述清晰图像的灰度均值,对所述清晰图像中每一像素点的灰度值进行调整。
  10. 如权利要求9所述的图像处理方法,其特征在于,对所述清晰图像中每一像素点的灰度值进行调整,包括:
    通过如下公式对所述清晰图像中每一像素点的灰度值进行调整:
    Figure PCTCN2021089489-appb-100001
    其中,f'(i,j)为所述目标图像中像素点(i,j)的灰度值,
    Figure PCTCN2021089489-appb-100002
    为所述清晰图像的灰度均值,f(i,j)为所述清晰图像中像素点(i,j)的灰度值,t为强度值。
  11. 如权利要求10所述的图像处理方法,其特征在于,所述强度值为0.1-0.5。
  12. 如权利要求1所述的图像处理方法,其特征在于,还包括:
    对所述目标图像边缘的黑色区域进行清除处理。
  13. 如权利要求12所述的图像处理方法,其特征在于,对所述目标图像 边缘的黑色区域进行清除处理,包括:
    对所述目标图像的上下左右四个边缘分别进行遍历,判断是否存在宽度超过第五预设阈值的黑色区域,若存在,去除所述黑色区域。
  14. 如权利要求13所述的图像处理方法,其特征在于,对所述目标图像的上下左右四个边缘分别进行遍历,判断是否存在大小超过第五预设阈值的黑色区域,包括:
    针对所述目标图像的上下左右四个边缘中的任一个,从行列两个方向进行遍历以确定是否存在黑色区域以及黑色区域的边缘,进而判断所述黑色区域的宽度是否超过第五预设阈值。
  15. 一种图像处理系统,其特征在于,所述系统包括处理器和存储器,所述存储器上存储有指令,当所述指令被所述处理器执行时,实现如权利要求1至14中任一项所述的图像处理方法的步骤。
  16. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储有指令,当所述指令被执行时,实现如权利要求1至14中任一项所述的图像处理方法的步骤。
PCT/CN2021/089489 2020-05-13 2021-04-25 图像处理方法、系统及计算机可读存储介质 WO2021227838A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/641,435 US20220301115A1 (en) 2020-05-13 2021-04-25 Image processing method and system, and computer readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010404269.1A CN111583157B (zh) 2020-05-13 2020-05-13 图像处理方法、系统及计算机可读存储介质
CN202010404269.1 2020-05-13

Publications (1)

Publication Number Publication Date
WO2021227838A1 true WO2021227838A1 (zh) 2021-11-18

Family

ID=72126623

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/089489 WO2021227838A1 (zh) 2020-05-13 2021-04-25 图像处理方法、系统及计算机可读存储介质

Country Status (3)

Country Link
US (1) US20220301115A1 (zh)
CN (1) CN111583157B (zh)
WO (1) WO2021227838A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114582279A (zh) * 2022-05-05 2022-06-03 卡莱特云科技股份有限公司 基于误差扩散的显示屏对比度提升方法、装置及电子设备
CN114994671A (zh) * 2022-05-31 2022-09-02 南京慧尔视智能科技有限公司 基于雷达图像的目标检测方法、装置、设备及介质
CN116453029A (zh) * 2023-06-16 2023-07-18 济南东庆软件技术有限公司 基于图像数据的楼宇火灾环境检测方法
CN116596924A (zh) * 2023-07-17 2023-08-15 山东唐乐生物科技股份有限公司 基于机器视觉的甜菊糖苷质量检测方法及系统

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111583157B (zh) * 2020-05-13 2023-06-02 杭州睿琪软件有限公司 图像处理方法、系统及计算机可读存储介质
CN112132742A (zh) * 2020-08-28 2020-12-25 稿定(厦门)科技有限公司 基于粒子的自适应光晕图像生成方法及装置
CN112150394B (zh) * 2020-10-12 2024-02-20 杭州睿琪软件有限公司 图像处理方法及装置、电子设备和存储介质
CN113077399B (zh) * 2021-04-09 2023-03-14 烟台艾睿光电科技有限公司 一种图像处理方法、装置、系统及计算机可读存储介质
CN113256785B (zh) * 2021-05-31 2023-04-04 北京字跳网络技术有限公司 图像处理方法、装置、设备及介质
CN113409222A (zh) * 2021-06-30 2021-09-17 深圳市纵维立方科技有限公司 图像处理方法、打印方法、打印相关装置及可读存储介质
CN113362319A (zh) * 2021-06-30 2021-09-07 深圳市创想三维科技股份有限公司 基于图像处理的激光打印方法和装置、激光打印机、计算机可读存储介质
CN113642555B (zh) * 2021-07-29 2022-08-05 深圳市芯成像科技有限公司 一种图像处理方法、计算机可读介质和系统
CN113962907B (zh) * 2021-12-21 2022-04-19 山东信通电子股份有限公司 一种图像去噪方法、装置及设备
CN115294107B (zh) * 2022-09-29 2022-12-27 江苏三通科技有限公司 一种基于图像识别的二极管引脚表面氧化检测方法
CN115330878B (zh) * 2022-10-18 2023-01-24 山东特联信息科技有限公司 一种罐车罐口视觉定位方法
CN115700757B (zh) * 2022-11-08 2024-05-17 中信重工开诚智能装备有限公司 消防水炮的控制方法、装置及电子设备
CN116228586B (zh) * 2023-03-14 2023-09-08 深圳市合西科技有限公司 基于遍历处理的锐化算法选择系统
CN116721042A (zh) * 2023-08-10 2023-09-08 广东石油化工学院 基于多阈值二值化的摄像图像倾斜校正方法
CN117036205B (zh) * 2023-10-10 2023-12-26 深圳市悦和精密模具有限公司 基于图像增强的注塑件生产质量检测方法
CN117152135B (zh) * 2023-10-30 2024-01-23 济宁市市政园林养护中心 一种道路施工裂缝缺陷评估检测方法
CN117351001B (zh) * 2023-11-16 2024-05-28 肇庆市大正铝业有限公司 一种再生铝合金模板表面缺陷识别方法
CN117788300B (zh) * 2024-02-23 2024-05-10 中国医学科学院北京协和医院 一种输尿管镜碎石用影像增强的优化方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104715445A (zh) * 2013-12-13 2015-06-17 腾讯科技(深圳)有限公司 图像处理方法和系统
CN105303190A (zh) * 2015-11-27 2016-02-03 哈尔滨理工大学 一种基于对比度增强法的降质文档图像二值化方法
US20180157907A1 (en) * 2016-12-06 2018-06-07 Abbyy Development Llc Method and apparatus for determining a document suitability for optical character recognition (ocr) processing
CN109785264A (zh) * 2019-01-15 2019-05-21 北京旷视科技有限公司 图像增强方法、装置及电子设备
CN111583157A (zh) * 2020-05-13 2020-08-25 杭州睿琪软件有限公司 图像处理方法、系统及计算机可读存储介质

Family Cites Families (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3103387B2 (ja) * 1991-03-06 2000-10-30 グローリー工業株式会社 濃淡画像の適応2値化方法
JP3904840B2 (ja) * 2000-08-15 2007-04-11 富士通株式会社 多値画像から罫線を抽出する罫線抽出装置
JP2004266522A (ja) * 2003-02-28 2004-09-24 Ricoh Co Ltd デジタル画像読取装置
US7496237B1 (en) * 2004-01-02 2009-02-24 The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration Image processing for binarization enhancement via fuzzy reasoning
JP4099467B2 (ja) * 2004-08-04 2008-06-11 松下電器産業株式会社 部品の画像生成方法
CN101042735B (zh) * 2006-03-23 2010-11-17 株式会社理光 图像二值化方法和装置
CN101571775B (zh) * 2009-06-04 2011-04-20 广东威创视讯科技股份有限公司 一种图像触摸点的检测方法及装置
JP5960010B2 (ja) * 2012-09-26 2016-08-02 日本電産サンキョー株式会社 画像処理装置、画像処理方法、およびプログラム
JP2014110587A (ja) * 2012-12-04 2014-06-12 Fuji Xerox Co Ltd 画像処理装置、画像形成装置およびプログラム
CN106296635B (zh) * 2015-05-29 2019-11-22 厦门鹭佳生物科技有限公司 一种荧光原位杂交(fish)图像并行处理与分析方法
TWI603074B (zh) * 2015-07-03 2017-10-21 元智大學 光學薄膜缺陷辨識方法及其系統
CN105205821B (zh) * 2015-09-21 2018-09-04 江苏科技大学 一种焊接图像分割方法
CN106327442A (zh) * 2016-08-22 2017-01-11 上海奥通激光技术有限公司 多光谱显微成像的景深扩展方法及系统
CN107133929B (zh) * 2017-04-27 2019-06-11 湖北工业大学 基于背景估计和能量最小化的低质量文档图像二值化方法
RU2721188C2 (ru) * 2017-12-14 2020-05-18 Общество с ограниченной ответственностью "Аби Продакшн" Улучшение контраста и снижение шума на изображениях, полученных с камер
CN108846399A (zh) * 2018-04-10 2018-11-20 阿里巴巴集团控股有限公司 一种图像处理的方法及装置
CN109785347A (zh) * 2018-04-27 2019-05-21 京东方科技集团股份有限公司 图像处理方法、图像处理系统及存储介质
US10832085B2 (en) * 2018-09-06 2020-11-10 International Business Machines Corporation Image binarization using mean restrain
CN109523568A (zh) * 2018-10-12 2019-03-26 广东绿康源美环境科技有限公司 一种基于Canny算法的大体标本摄像系统
CN109544464A (zh) * 2018-10-19 2019-03-29 天津大学 一种基于轮廓提取的火灾视频图像分析方法
CN109754379A (zh) * 2018-12-29 2019-05-14 北京金山安全软件有限公司 一种图像处理方法及装置
CN109858373A (zh) * 2018-12-29 2019-06-07 航天信息股份有限公司 一种基于深度学习的发票识别验真方法及系统
CN110060238B (zh) * 2019-04-01 2022-04-19 桂林电子科技大学 基于深度学习的pcb板标注印刷质量检测方法
CN110119741B (zh) * 2019-04-08 2022-09-27 浙江大学宁波理工学院 一种有背景的卡证图像信息识别方法
CN110533040A (zh) * 2019-09-05 2019-12-03 哈尔滨理工大学 一种环形区域二值化图像处理方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104715445A (zh) * 2013-12-13 2015-06-17 腾讯科技(深圳)有限公司 图像处理方法和系统
CN105303190A (zh) * 2015-11-27 2016-02-03 哈尔滨理工大学 一种基于对比度增强法的降质文档图像二值化方法
US20180157907A1 (en) * 2016-12-06 2018-06-07 Abbyy Development Llc Method and apparatus for determining a document suitability for optical character recognition (ocr) processing
CN109785264A (zh) * 2019-01-15 2019-05-21 北京旷视科技有限公司 图像增强方法、装置及电子设备
CN111583157A (zh) * 2020-05-13 2020-08-25 杭州睿琪软件有限公司 图像处理方法、系统及计算机可读存储介质

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114582279A (zh) * 2022-05-05 2022-06-03 卡莱特云科技股份有限公司 基于误差扩散的显示屏对比度提升方法、装置及电子设备
CN114582279B (zh) * 2022-05-05 2022-07-22 卡莱特云科技股份有限公司 基于误差扩散的显示屏对比度提升方法、装置及电子设备
CN114994671A (zh) * 2022-05-31 2022-09-02 南京慧尔视智能科技有限公司 基于雷达图像的目标检测方法、装置、设备及介质
CN114994671B (zh) * 2022-05-31 2023-11-28 南京慧尔视智能科技有限公司 基于雷达图像的目标检测方法、装置、设备及介质
CN116453029A (zh) * 2023-06-16 2023-07-18 济南东庆软件技术有限公司 基于图像数据的楼宇火灾环境检测方法
CN116453029B (zh) * 2023-06-16 2023-08-29 济南东庆软件技术有限公司 基于图像数据的楼宇火灾环境检测方法
CN116596924A (zh) * 2023-07-17 2023-08-15 山东唐乐生物科技股份有限公司 基于机器视觉的甜菊糖苷质量检测方法及系统
CN116596924B (zh) * 2023-07-17 2023-10-20 山东唐乐生物科技股份有限公司 基于机器视觉的甜菊糖苷质量检测方法及系统

Also Published As

Publication number Publication date
CN111583157B (zh) 2023-06-02
US20220301115A1 (en) 2022-09-22
CN111583157A (zh) 2020-08-25

Similar Documents

Publication Publication Date Title
WO2021227838A1 (zh) 图像处理方法、系统及计算机可读存储介质
US9754356B2 (en) Method and system for processing an input image based on a guidance image and weights determined thereform
JP6416208B2 (ja) 近赤外ガイドイメージノイズ除去
US10410327B2 (en) Shallow depth of field rendering
Gao et al. A fast image dehazing algorithm based on negative correction
US11790499B2 (en) Certificate image extraction method and terminal device
WO2016159884A1 (en) Method and device for image haze removal
US9478004B2 (en) Method and system for analog/digital image simplification and stylization
CN111968144A (zh) 一种图像边缘点获取方法及装置
CN106934806A (zh) 一种基于结构清晰度的无参考图失焦模糊区域分割方法
US20220398698A1 (en) Image processing model generation method, processing method, storage medium, and terminal
CN113592776A (zh) 图像处理方法及装置、电子设备、存储介质
CN113379609B (zh) 一种图像处理方法、存储介质及终端设备
Chen et al. Weighted sparse representation and gradient domain guided filter pyramid image fusion based on low-light-level dual-channel camera
CN114022383A (zh) 一种文字图像的摩尔纹祛除方法、装置及电子设备
CN111028214B (zh) 一种基于云平台的皮肤检测装置
US11620763B2 (en) Method and device for recognizing fundus image, and equipment
CN113450272B (zh) 一种基于正弦曲线变化的图像增强方法及其应用
JP3860540B2 (ja) エントロピーフィルタ及び該フィルタを用いた領域抽出法
CN108647680B (zh) 图像定位框检测方法和装置
CN111915497B (zh) 一种图像黑白增强方法、装置、电子设备和可读存储介质
CN113379611B (zh) 图像处理模型的生成方法、处理方法、存储介质及终端
DE112021002288T5 (de) Inhaltsbasierte bildverarbeitung
CN113379608A (zh) 一种图像处理方法、存储介质及终端设备
CN117422656B (zh) 一种低照度模糊交通图像增强方法、装置、设备及介质

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: 21803750

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: 21803750

Country of ref document: EP

Kind code of ref document: A1