CN113379607B - Method and device for adaptively adjusting image - Google Patents
Method and device for adaptively adjusting image Download PDFInfo
- Publication number
- CN113379607B CN113379607B CN202010115757.0A CN202010115757A CN113379607B CN 113379607 B CN113379607 B CN 113379607B CN 202010115757 A CN202010115757 A CN 202010115757A CN 113379607 B CN113379607 B CN 113379607B
- Authority
- CN
- China
- Prior art keywords
- image
- frequency sub
- enhanced
- enhancement
- max
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000009466 transformation Effects 0.000 claims abstract description 65
- 238000011156 evaluation Methods 0.000 claims abstract description 53
- 230000002708 enhancing effect Effects 0.000 claims abstract description 14
- 230000001105 regulatory effect Effects 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 48
- 238000003708 edge detection Methods 0.000 claims description 15
- 230000033228 biological regulation Effects 0.000 abstract description 3
- 238000001914 filtration Methods 0.000 description 7
- 238000013139 quantization Methods 0.000 description 5
- 238000013441 quality evaluation Methods 0.000 description 4
- 235000002566 Capsicum Nutrition 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The application discloses a method and a device for adaptively adjusting images, comprising the following steps: performing wavelet transformation on the original image to obtain a multi-scale and multi-directional sub-image; respectively enhancing the multi-scale and multi-directional sub-images; performing wavelet inverse transformation on the enhanced sub-image to obtain an enhanced image; and (3) evaluating the image subjected to the wavelet inverse transformation by using an evaluation function, if the evaluation result meets the requirement, outputting the enhanced image, otherwise, continuing to perform the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement. The application carries out self-adaptive parameter adjustment on the basis of artificial regulation, further improves the quality of the ultrasonic image, and solves the problem that the enhanced parameters cannot be regulated and controlled accurately.
Description
Technical Field
The present application relates to image processing, and more particularly, to a method and apparatus for adaptively adjusting an image.
Background
The medical ultrasonic image is inevitably influenced by various factors such as sensor sensitivity, noise interference, quantization problem during analog-to-digital conversion and the like in the acquisition process, so that the image cannot achieve a satisfactory visual effect, and in order to realize the problem that a doctor requires a high-quality ultrasonic image, the improvement action on the original image is called image enhancement. The image is enhanced, and new regulation parameters are introduced. Because the related parameters can be manually adjusted only according to experience and doctors, the effect is not ideal, and the enhancement parameters cannot be accurately regulated.
Disclosure of Invention
The application provides a method and a device for adaptively adjusting images.
According to a first aspect of the present application, there is provided a method of adaptively adjusting an image, comprising:
A wavelet transformation step: performing wavelet transformation on the original image to obtain a multi-scale and multi-directional sub-image;
An image enhancement step: respectively enhancing the multi-scale and multi-directional sub-images;
a wavelet inverse transformation step: performing wavelet inverse transformation on the enhanced sub-image to obtain an enhanced image;
Self-adjusting: and (3) evaluating the image subjected to the wavelet inverse transformation by using an evaluation function, if the evaluation result meets the requirement, outputting the enhanced image, otherwise, continuing to perform the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement.
Further, the multi-scale, multi-directional sub-image comprises: a low frequency sub-image, a horizontal high frequency sub-image, a vertical high frequency sub-image, and a diagonal high frequency sub-image.
Further, the enhancing the multi-scale, multi-directional sub-image includes:
Performing linear threshold enhancement on the low-frequency sub-image;
Respectively carrying out blurring enhancement on the horizontal high-frequency sub-image, the vertical high-frequency sub-image and the diagonal high-frequency sub-image;
the performing the inverse wavelet transform on the enhanced sub-image includes:
And performing wavelet inverse transformation on the enhanced low-frequency sub-image, the enhanced horizontal high-frequency sub-image, the enhanced vertical high-frequency sub-image and the enhanced diagonal high-frequency sub-image.
Further, the performing linear threshold enhancement on the low frequency sub-image includes:
selecting a single threshold value a, performing zero setting operation if the image pixel point is smaller than Shan Yuzhi a, and enhancing b times if the image pixel point is larger than Shan Yuzhi a, wherein b is larger than 1;
Respectively blurring-enhancing the horizontal high-frequency sub-image, the vertical high-frequency sub-image, and the diagonal high-frequency sub-image, including:
And respectively carrying out fuzzy enhancement on the horizontal high-frequency sub-image, the vertical high-frequency sub-image and the diagonal high-frequency sub-image, carrying out edge detection by using a first-order differential edge detection operator, carrying out enhancement c times on the detected edge part, and carrying out enhancement d times on data of other parts which are not edges, wherein c >1, d <1, a, b, c and d are parameters which are regulated by ultrasonic equipment.
Further, the evaluation function is:
s.tmin1＜a＜max1 min1,max1∈R
min2＜b＜max2 min2,max2∈R
min3＜c＜max3 min3,max3∈R
min4＜d＜max4 min4,max4∈R
Wherein a, b, c, D are parameters which have been adjusted by the ultrasonic device, min 1,min2,min3,min4 are defined lower limits, max 1,max2,max3,max4 are defined upper limits, D (f (a, b, c, D)) are variance functions, and PSNR (f (a, b, c, D)) are peak signal-to-noise ratios.
According to a second aspect of the present application, there is provided an apparatus for adaptively adjusting an image, comprising:
the wavelet transformation module is used for carrying out wavelet transformation on the original image to obtain a multi-scale and multi-directional sub-image;
The image enhancement module is used for enhancing the multi-scale and multi-directional sub-images respectively;
The wavelet inverse transformation module is used for carrying out wavelet inverse transformation on the enhanced sub-image to obtain an enhanced image;
And the self-adjusting module is used for evaluating the image after the wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, otherwise, continuing the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement.
Further, the multi-scale, multi-directional sub-image comprises: a low frequency sub-image, a horizontal high frequency sub-image, a vertical high frequency sub-image, and a diagonal high frequency sub-image;
the image enhancement module comprises:
A low-frequency enhancement unit, configured to perform linear threshold enhancement on the low-frequency sub-image;
a high-frequency enhancement unit for performing blurring enhancement on the horizontal high-frequency sub-image, the vertical high-frequency sub-image, and the diagonal high-frequency sub-image, respectively;
The inverse wavelet transform module comprises:
And the wavelet inverse transformation unit is used for carrying out wavelet inverse transformation on the enhanced low-frequency sub-image, the enhanced horizontal high-frequency sub-image, the enhanced vertical high-frequency sub-image and the enhanced diagonal high-frequency sub-image.
Further, the low-frequency enhancement unit is further configured to select a single threshold value a, perform a zero setting operation if the image pixel point is smaller than Shan Yuzhi a, and enhance b times if the image pixel point is larger than Shan Yuzhi a, where b >1;
The high-frequency enhancement unit is further configured to perform blur enhancement on the horizontal high-frequency sub-image, the vertical high-frequency sub-image, and the diagonal high-frequency sub-image, perform edge detection by using a first-order differential edge detection operator, enhance the detected edge by c times, and enhance data of other parts other than the edge by d times, where c >1, d <1, a, b, c, d are parameters adjusted by the ultrasonic device.
Further, the evaluation function is:
s.tmin1＜a＜max1 min1,max1∈R
min2＜b＜max2 min2,max2∈R
min3＜c＜max3 min3,max3∈R
min4＜d＜max4 min4,max4∈R
Wherein a, b, c, D are parameters which have been adjusted by the ultrasonic device, min 1,min2,min3,min4 are defined lower limits, max 1,max2,max3,max4 are defined upper limits, D (f (a, b, c, D)) are variance functions, and PSNR (f (a, b, c, D)) are peak signal-to-noise ratios.
According to a third aspect of the present application, there is provided an apparatus for adaptively adjusting an image, comprising:
a memory for storing a program;
And the processor is used for executing the program stored in the memory to realize the method.
Due to the adoption of the technical scheme, the application has the beneficial effects that:
In a specific embodiment of the application, the enhancement is performed on the multi-scale and multi-directional sub-images respectively; performing wavelet inverse transformation on the enhanced sub-image to obtain an enhanced image; and (3) evaluating the image subjected to the wavelet inverse transformation by using an evaluation function, if the evaluation result meets the requirement, outputting the enhanced image, otherwise, continuing to perform the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement. The application carries out self-adaptive parameter adjustment on the basis of artificial regulation, further improves the quality of the ultrasonic image and solves the problem that the enhanced parameters cannot be regulated and controlled accurately.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the application in one implementation;
FIG. 2 is a flow chart of a method according to an embodiment of the present application in another implementation;
FIG. 3 is a schematic diagram of a program module of an apparatus according to a second embodiment of the present application;
fig. 4 is a schematic diagram of a program module of an apparatus according to a second embodiment of the present application.
Detailed Description
The application will be described in further detail below with reference to the drawings by means of specific embodiments. This application may be embodied in many different forms and is not limited to the implementations described in this example. The following detailed description is provided to facilitate a more thorough understanding of the present disclosure, in which words of upper, lower, left, right, etc., indicating orientations are used solely for the illustrated structure in the corresponding figures.
However, one skilled in the relevant art will recognize that the detailed description of one or more of the specific details may be omitted, or that other methods, components, or materials may be used. In some instances, some embodiments are not described or described in detail.
The numbering of the components itself, e.g. "first", "second", etc., is used herein merely to distinguish between the described objects and does not have any sequential or technical meaning.
Furthermore, the features and aspects described herein may be combined in any suitable manner in one or more embodiments. It will be readily understood by those skilled in the art that the steps or order of operation of the methods associated with the embodiments provided herein may also be varied. Thus, any order in the figures and examples is for illustrative purposes only and does not imply that a certain order is required unless explicitly stated that a certain order is required.
In the algorithm of wavelet threshold enhancement, the wavelet filtering method covers the following four key characteristics for coefficients obtained after the image signal is subjected to wavelet transformation processing: the coefficient of the noise signal obtained after the wavelet transform processing does not have the above properties. According to different properties of the transformation coefficients of the image signals and the noise signals on different scales after wavelet transformation, the wavelet filtering method can effectively filter noise and better retain signals.
The threshold function filtering method is a relatively simple wavelet domain filtering method, mainly makes the amplitude of the wavelet transformation coefficient of the noise-containing image compared with a set threshold value, and when the amplitude is smaller than the threshold value, the wavelet transformation coefficient is set to zero or reduced to be inhibited to a certain extent, and when the amplitude is larger than the threshold value, the wavelet transformation coefficient is reserved or amplified to be enhanced, so that the effects of noise inhibition and image enhancement are achieved. Threshold filtering is generally divided into soft threshold filtering and hard threshold filtering. The soft threshold filter function is changed to zero when the absolute value of the wavelet transform coefficient is smaller than the set threshold value, and the soft threshold filter function is subtracted from the threshold value when the absolute value of the wavelet transform coefficient is larger than the set threshold value. The hard threshold filter function is changed to zero when the absolute value of the transformation coefficient is smaller than the set threshold value, and is not changed when the absolute value of the transformation coefficient is larger than the set threshold value.
Embodiment one:
as shown in fig. 1, an embodiment of a method for adaptively adjusting an image according to the present application includes the following steps:
Step 102: a wavelet transformation step: and carrying out wavelet transformation on the original image to obtain multi-scale and multi-directional sub-images. In one embodiment, a multi-scale, multi-directional sub-image includes: a low frequency sub-image, a horizontal high frequency sub-image, a vertical high frequency sub-image, and a diagonal high frequency sub-image.
Step 104: an image enhancement step: and respectively enhancing the multi-scale and multi-directional sub-images.
Further, step 104 may include the steps of:
performing linear threshold enhancement on the low-frequency sub-image;
Blur enhancement is performed on the horizontal high frequency sub-image, the vertical high frequency sub-image, and the diagonal high frequency sub-image, respectively.
Step 106: a wavelet inverse transformation step: and carrying out wavelet inverse transformation on the enhanced sub-image to obtain the enhanced image.
Further, step 106 may include the steps of:
And performing wavelet inverse transformation on the enhanced low-frequency sub-image, the enhanced horizontal high-frequency sub-image, the enhanced vertical high-frequency sub-image and the enhanced diagonal high-frequency sub-image.
Step 108: self-adjusting: and (3) evaluating the image subjected to the wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, otherwise, turning to step 104, and continuing to perform the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement.
Further, the evaluation function is:
s.tmin1＜a＜max1 min1,max1∈R
min2＜b＜max2 min2,max2∈R
min3＜c＜max3 min3,max3∈R
min4＜d＜max4 min4,max4∈R
Wherein a, b, c, D are parameters which have been adjusted by the ultrasonic device, min 1,min2,min3,min4 are defined lower limits, max 1,max2,max3,max4 are defined upper limits, D (f (a, b, c, D)) are variance functions, and PSNR (f (a, b, c, D)) are peak signal-to-noise ratios.
The application introduces an image quality quantization evaluation criterion, evaluates and feeds back an image in the face of a non-reference output image, and introduces an image definition evaluation criterion: the variance function, because the clearly focused image has larger gray scale difference than the blurred image, can regard the variance function as the evaluation function, D (f) = Σ y∑x|f(x,y)-μ|2, wherein μ is the average gray scale value of the whole image, the function is more sensitive to noise, the purer the image picture is, the smaller the function value is, and the larger D (f) is the more abundant the detail information of the image, the more clear the image, but in order to prevent the salt and pepper noise influence, the peak signal to noise (PSNR) is needed to be introduced and compared with the quality evaluation, the more the peak signal to noise ratio is generally used in the evaluation of the image, the formula is: where MN is the size of the graphic, f is the output enhanced image,/> Is the image input to be enhanced. The definition and image quality evaluation function are combined to form a final evaluation function, the evaluation function is used as an objective function, doctor/software limiting parameters are limiting equations, and the problem of self-adaptive adjustment parameters is converted into a quadratic programming problem:
s.tmin1＜a＜max1 min1,max1∈R
min2＜b＜max2 min2,max2∈R
min3＜c＜max3 min3,max3∈R
min4＜d＜max4 min4,max4∈R
Wherein a, b, c and d are parameters which are regulated by doctors, and min and max are adjustable ranges which are limited up and down. Meanwhile, for timeliness, the step length and the adjustment times are further limited, so that a multi-limit equation set is formed. By solving the linear equation set, the optimal parameters are adaptively adjusted around the doctor adjusting parameters.
The application converts the problem into linear equation solution, introduces clear quality quantization standard to the medical image, and adjusts the medical image by using the quantization standard.
As shown in fig. 2, another embodiment of the method for adaptively adjusting an image according to the present application includes the steps of:
Step 202: and carrying out wavelet transformation on the original image to obtain multi-scale and multi-directional sub-images. In one embodiment, a multi-scale, multi-directional sub-image includes: a low frequency sub-image, a horizontal high frequency sub-image, a vertical high frequency sub-image, and a diagonal high frequency sub-image.
Step 204: linear threshold enhancement is performed on the low frequency sub-image. And selecting a single threshold value a, carrying out zero setting operation if the image pixel point is smaller than Shan Yuzhi a, and enhancing b times if the image pixel point is larger than Shan Yuzhi a, wherein b is larger than 1.
Step 206: blur enhancement is performed on the horizontal high frequency sub-image, the vertical high frequency sub-image, and the diagonal high frequency sub-image, respectively. And respectively selecting a first-order differential edge detection operator for edge detection (for example, selecting a first-order differential edge detection operator Sobel for edge detection) for the horizontal high-frequency sub-image, the vertical high-frequency sub-image and the diagonal high-frequency sub-image, and enhancing the detected edge part by c times and enhancing data of other parts which are not edges by d times, wherein c is more than 1, d is less than 1, a, b, c and d are parameters which are regulated by ultrasonic equipment.
Step 208: and performing wavelet inverse transformation on the enhanced low-frequency sub-image, the enhanced horizontal high-frequency sub-image, the enhanced vertical high-frequency sub-image and the enhanced diagonal high-frequency sub-image.
Step 210: and (3) evaluating the image subjected to the wavelet inverse transformation by using an evaluation function, if the evaluation result meets the requirement, outputting the enhanced image, otherwise, continuing to perform the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement.
The evaluation function is:
s.tmin1＜a＜max1 min1,max1∈R
min2＜b＜max2 min2,max2∈R
min3＜c＜max3 min3,max3∈R
min4＜d＜max4 min4,max4∈R
Wherein a, b, c, D are parameters which have been adjusted by the ultrasonic device, min 1,min2,min3,min4 are defined lower limits, max 1,max2,max3,max4 are defined upper limits, D (f (a, b, c, D)) are variance functions, and PSNR (f (a, b, c, D)) are peak signal-to-noise ratios.
If the parameters a, b, c, d, the 1 st level a=0.7, b=1.2, c=1.5, d=0.8, the enhanced image 1 is obtained after wavelet transformation, image enhancement and wavelet inverse transformation according to the parameters, the output result of the enhanced image 1 is solved according to the evaluation function, if the result is 0.9, the secondary planning idea is as follows: when the solution satisfies st limitation, the value of a, b, c and d is 0.9 when the evaluation function is minimum, the current result is adjusted in the limitation condition by a quadratic programming algorithm, wavelet transformation, enhancement processing and inverse transformation are carried out again to obtain an enhanced image solution evaluation value, if the value is smaller than 0.9, the new value of a, b, c and d replaces the original value of a, b, c and d to be an optimized parameter, the solution process does not always keep dead circulation, the upper part has description, the circulation solution times and a, b, c, d range sizes are limited, the solution is stopped when the solution is carried out to the minimum value in the circulation times, and if the solution is not carried out to the minimum value in the circulation times, the minimum value in the circulation times is the minimum value of the evaluation function.
Embodiment two:
As shown in fig. 3, an apparatus for adaptively adjusting an image according to an embodiment of the present application may include a wavelet transform module 310, an image enhancement module 320, an inverse wavelet transform module 330, and a self-adjustment module 340.
The wavelet transform module 310 is configured to perform wavelet transform on the original image to obtain a multi-scale and multi-directional sub-image.
The image enhancement module 320 is configured to enhance the multi-scale and multi-directional sub-images respectively. In one embodiment, a multi-scale, multi-directional sub-image includes: a low frequency sub-image, a horizontal high frequency sub-image, a vertical high frequency sub-image, and a diagonal high frequency sub-image.
The inverse wavelet transform module 330 is configured to perform inverse wavelet transform on the enhanced sub-image to obtain an enhanced image;
The self-adjusting module 340 is configured to evaluate the image after the wavelet inverse transformation using an evaluation function, if the evaluation result meets the requirement, output the enhanced image, otherwise continue the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement.
As shown in fig. 4, another embodiment of the apparatus for adaptively adjusting an image according to the present application may include a wavelet transform module 410, an image enhancement module 420, an inverse wavelet transform module 430, and a self-adjustment module 440.
The wavelet transform module 410 is configured to perform wavelet transform on the original image to obtain a multi-scale and multi-directional sub-image.
The image enhancement module 420 is configured to enhance the multi-scale and multi-directional sub-images respectively. In one embodiment, a multi-scale, multi-directional sub-image includes: a low frequency sub-image, a horizontal high frequency sub-image, a vertical high frequency sub-image, and a diagonal high frequency sub-image.
A wavelet inverse transformation module 430, configured to perform wavelet inverse transformation on the enhanced sub-image to obtain an enhanced image;
The self-adjusting module 440 is configured to evaluate the image after the wavelet inverse transformation using an evaluation function, if the evaluation result meets the requirement, output the enhanced image, otherwise, continue the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement.
Further, the image enhancement module 420 may include a low frequency enhancement unit 421 and a high frequency enhancement unit 422; the inverse wavelet transform module 430 may include an inverse wavelet transform unit 431.
A low frequency enhancement unit 421, configured to perform linear threshold enhancement on the low frequency sub-image;
a high frequency enhancement unit 422 for blurring-enhancing the horizontal high frequency sub-image, the vertical high frequency sub-image, and the diagonal high frequency sub-image, respectively;
the inverse wavelet transform unit 431 performs inverse wavelet transform on the enhanced low-frequency sub-image, the enhanced horizontal high-frequency sub-image, the enhanced vertical high-frequency sub-image, and the enhanced diagonal high-frequency sub-image.
Further, the low frequency enhancing unit 421 is further configured to select a single threshold a, perform a zero setting operation if the image pixel is smaller than Shan Yuzhi a, and enhance b times if the image pixel is larger than Shan Yuzhi a, where b >1;
The high-frequency enhancement unit 422 is further configured to perform edge detection on the horizontal high-frequency sub-image, the vertical high-frequency sub-image, and the diagonal high-frequency sub-image by using a first-order differential edge detection operator, enhance the detected edge by c times, and enhance the data of other parts other than the edge by d times, where c >1, d <1, a, b, c, d are parameters that have been adjusted by the ultrasonic device.
Further, the evaluation function is:
s.tmin1＜a＜max1 min1,max1∈R
min2＜b＜max2 min2,max2∈R
min3＜c＜max3 min3,max3∈R
min4＜d＜max4 min4,max4∈R
Wherein a, b, c, D are parameters which have been adjusted by the ultrasonic device, min 1,min2,min3,min4 are defined lower limits, max 1,max2,max3,max4 are defined upper limits, D (f (a, b, c, D)) are variance functions, and PSNR (f (a, b, c, D)) are peak signal-to-noise ratios.
The application introduces an image quality quantization evaluation criterion, evaluates and feeds back an image in the face of a non-reference output image, and introduces an image definition evaluation criterion: the variance function, because the clearly focused image has larger gray scale difference than the blurred image, can regard the variance function as the evaluation function, D (f) = Σ y∑x|f(x,y)-μ|2, wherein μ is the average gray scale value of the whole image, the function is more sensitive to noise, the purer the image picture is, the smaller the function value is, and the larger D (f) is the more abundant the detail information of the image, the more clear the image, but in order to prevent the salt and pepper noise influence, the peak signal to noise (PSNR) is needed to be introduced and compared with the quality evaluation, the more the peak signal to noise ratio is generally used in the evaluation of the image, the formula is: where MN is the size of the graphic, f is the output enhanced image,/> Is the image input to be enhanced. The definition and image quality evaluation function are combined to form a final evaluation function, the evaluation function is used as an objective function, doctor/software limiting parameters are limiting equations, and the problem of self-adaptive adjustment parameters is converted into a quadratic programming problem:
min3＜c＜max3 min3,max3∈R
min4＜d＜max4 min4,max4∈R
Wherein a, b, c and d are parameters which are regulated by doctors, and min and max are adjustable ranges which are limited up and down. Meanwhile, for timeliness, the step length and the adjustment times are further limited, so that a multi-limit equation set is formed. By solving the linear equation set, the optimal parameters are adaptively adjusted around the doctor adjusting parameters.
Embodiment III:
The embodiment of the application provides a device for adaptively adjusting images, which comprises a memory and a processor.
A memory for storing a program;
A processor configured to implement the method in the first embodiment by executing a program stored in the memory.
Those skilled in the art will appreciate that all or part of the steps of the various methods in the above embodiments may be implemented by a program to instruct related hardware, and the program may be stored in a computer readable storage medium, where the storage medium may include: read-only memory, random access memory, magnetic or optical disk, etc.
The foregoing is a further detailed description of the application in connection with specific embodiments, and it is not intended that the application be limited to such description. It will be apparent to those skilled in the art that several simple deductions or substitutions can be made without departing from the spirit of the application.
Claims (3)
1. A method of adaptively adjusting an image, comprising:
A wavelet transformation step: performing wavelet transformation on the original image to obtain a multi-scale and multi-directional sub-image, including: a low frequency sub-image, a horizontal high frequency sub-image, a vertical high frequency sub-image, and a diagonal high frequency sub-image;
An image enhancement step: the low-frequency sub-image is subjected to linear threshold enhancement, which comprises the steps of selecting a single threshold value a, carrying out zero setting operation if an image pixel point is smaller than Shan Yuzhi a, and enhancing b times if the image pixel point is larger than Shan Yuzhi a, wherein b is larger than 1; and respectively carrying out fuzzy enhancement on the horizontal high-frequency sub-image, the vertical high-frequency sub-image and the diagonal high-frequency sub-image, wherein the fuzzy enhancement comprises the steps of selecting a first-order differential edge detection operator to carry out edge detection, carrying out enhancement c times on the detected edge part and carrying out enhancement d times on other part data which are not the edge, wherein c is more than 1, d is less than 1, a, b, c and d are parameters which are regulated by ultrasonic equipment;
A wavelet inverse transformation step: performing wavelet inverse transformation on the enhanced low-frequency sub-image, the enhanced horizontal high-frequency sub-image, the enhanced vertical high-frequency sub-image and the enhanced diagonal high-frequency sub-image to obtain an enhanced image;
Self-adjusting: evaluating the image after the wavelet inverse transformation by using an evaluation function, if the evaluation result meets the requirement, outputting the enhanced image, otherwise, continuing to perform the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement;
wherein the evaluation function is:
，
Wherein a, b, c, D are parameters which have been adjusted by the ultrasonic device, min 1,min2,min3,min4 are defined lower limits, max 1,max2,max3,max4 are defined upper limits, D (f (a, b, c, D)) are variance functions, and PSNR (f (a, b, c, D)) are peak signal-to-noise ratios.
2. An apparatus for adaptively adjusting an image, comprising:
the wavelet transformation module is used for carrying out wavelet transformation on the original image to obtain a multi-scale and multi-directional sub-image, and comprises the following steps: a low frequency sub-image, a horizontal high frequency sub-image, a vertical high frequency sub-image, and a diagonal high frequency sub-image;
The image enhancement module is used for enhancing the multi-scale and multi-directional sub-images respectively;
The wavelet inverse transformation module is used for carrying out wavelet inverse transformation on the enhanced sub-image to obtain an enhanced image;
The self-adjusting module is used for evaluating the image after the wavelet inverse transformation by using an evaluation function, if the evaluation result meets the requirement, the enhanced image is output, otherwise, the image enhancement step and the wavelet inverse transformation step are continuously carried out until the evaluation result meets the requirement;
the image enhancement module comprises:
the low-frequency enhancement unit is used for carrying out linear threshold enhancement on the low-frequency sub-image and comprises a single threshold value a, zero setting operation is carried out if the pixel point of the image is smaller than Shan Yuzhi a, b times enhancement is carried out if the pixel point of the image is larger than Shan Yuzhi a, and b is larger than 1;
The high-frequency enhancement unit is used for respectively carrying out fuzzy enhancement on the horizontal high-frequency sub-image, the vertical high-frequency sub-image and the diagonal high-frequency sub-image, and comprises an edge detection unit for selecting a first-order differential edge detection operator to carry out edge detection, enhancing the detected edge part by c times and enhancing data of other parts which are not edges by d times, wherein c >1, d <1, a, b, c and d are parameters which are regulated by ultrasonic equipment;
The inverse wavelet transform module comprises:
A wavelet inverse transformation unit for performing wavelet inverse transformation on the enhanced low-frequency sub-image, the enhanced horizontal high-frequency sub-image, the enhanced vertical high-frequency sub-image, and the enhanced diagonal high-frequency sub-image;
The evaluation function is:
，
Wherein a, b, c, D are parameters which have been adjusted by the ultrasonic device, min 1,min2,min3,min4 are defined lower limits, max 1,max2,max3,max4 are defined upper limits, D (f (a, b, c, D)) are variance functions, and PSNR (f (a, b, c, D)) are peak signal-to-noise ratios.
3. An apparatus for adaptively adjusting an image, comprising:
a memory for storing a program;
A processor for implementing the method of claim 1 by executing a program stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010115757.0A CN113379607B (en) | 2020-02-25 | 2020-02-25 | Method and device for adaptively adjusting image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010115757.0A CN113379607B (en) | 2020-02-25 | 2020-02-25 | Method and device for adaptively adjusting image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113379607A CN113379607A (en) | 2021-09-10 |
| CN113379607B true CN113379607B (en) | 2024-05-10 |
Family
ID=77569166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010115757.0A Active CN113379607B (en) | 2020-02-25 | 2020-02-25 | Method and device for adaptively adjusting image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113379607B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117649357B (en) * | 2024-01-29 | 2024-04-12 | 深圳市恩普电子技术有限公司 | Ultrasonic image processing method based on image enhancement |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1794300A (en) * | 2005-12-20 | 2006-06-28 | 上海电力学院 | Multisensor image fusion method based on optimized small wave filter set |
| US7206455B1 (en) * | 2003-08-20 | 2007-04-17 | Eastman Kodak Company | Adaptive setting of wavelet sub-band thresholds for low-light image denoising |
| CN101882304A (en) * | 2010-06-24 | 2010-11-10 | 西北工业大学 | Self-adaptive de-noising and characteristic enhancing method of SAR (Synthetic Aperture Radar) image |
| CN108648174A (en) * | 2018-04-04 | 2018-10-12 | 上海交通大学 | A kind of fusion method of multilayer images and system based on Autofocus Technology |
| CN109507623A (en) * | 2018-09-17 | 2019-03-22 | 上海理工大学 | A kind of low-field nuclear magnetic resonance signal antinoise method that adaptive threshold is chosen |
| CN109872289A (en) * | 2019-02-19 | 2019-06-11 | 重庆邮电大学 | Image enchancing method based on improved non-downsampling Contourlet conversion |
-
2020
- 2020-02-25 CN CN202010115757.0A patent/CN113379607B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7206455B1 (en) * | 2003-08-20 | 2007-04-17 | Eastman Kodak Company | Adaptive setting of wavelet sub-band thresholds for low-light image denoising |
| CN1794300A (en) * | 2005-12-20 | 2006-06-28 | 上海电力学院 | Multisensor image fusion method based on optimized small wave filter set |
| CN101882304A (en) * | 2010-06-24 | 2010-11-10 | 西北工业大学 | Self-adaptive de-noising and characteristic enhancing method of SAR (Synthetic Aperture Radar) image |
| CN108648174A (en) * | 2018-04-04 | 2018-10-12 | 上海交通大学 | A kind of fusion method of multilayer images and system based on Autofocus Technology |
| CN109507623A (en) * | 2018-09-17 | 2019-03-22 | 上海理工大学 | A kind of low-field nuclear magnetic resonance signal antinoise method that adaptive threshold is chosen |
| CN109872289A (en) * | 2019-02-19 | 2019-06-11 | 重庆邮电大学 | Image enchancing method based on improved non-downsampling Contourlet conversion |
Non-Patent Citations (4)
| Title |
|---|
| A novel medical image enhancement algorithm based improvement correction strategy in wavelet transform domain;Kai-jian Xia 等;《Cluster Computing》;20171020;10969-10977 * |
| 基于复合评价值的小波去噪参数选定方法;焦志浩 等;《重庆理工大学学报（自然科学）》;20190831;第33卷(第8期);178-184 * |
| 基于自适应遗传算法的变电站红外图像模糊增强;崔昊杨 等;《高电压技术》;20150331;第41卷(第3期);902-908 * |
| 基于自适应阈值的小波增强方法;王景中 等;《信息技术》;20150930;36-39 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113379607A (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107527333B (en) | Quick image enhancement method based on gamma transformation | |
| US6628842B1 (en) | Image processing method and apparatus | |
| US8064718B2 (en) | Filter for adaptive noise reduction and sharpness enhancement for electronically displayed pictures | |
| US20100142790A1 (en) | Image processing method capable of enhancing contrast and reducing noise of digital image and image processing device using same | |
| KR101674078B1 (en) | Method and apparatus for block-based image denoising | |
| US8532428B2 (en) | Noise reducing apparatus, noise reducing method, and noise reducing program for improving image quality | |
| EP1909227A1 (en) | method of and apparatus for minimizing ringing artifacts in an input image | |
| CN109584198B (en) | Method and device for evaluating quality of face image and computer readable storage medium | |
| RU2342701C1 (en) | Method of complexing digital multispectral half-tone images | |
| Sun et al. | Scanned image descreening with image redundancy and adaptive filtering | |
| Knaus et al. | Dual-domain filtering | |
| CN113379607B (en) | Method and device for adaptively adjusting image | |
| CN103489168A (en) | Enhancing method and system for infrared image being converted to pseudo color image in self-adaptive mode | |
| CN112215764A (en) | Image processing method based on median filtering improved algorithm | |
| Zlokolica et al. | Video denoising using multiple class averaging with multiresolution | |
| CN109064413B (en) | Image contrast enhancement method and image acquisition medical equipment adopting same | |
| Singh et al. | Image enhancement by adaptive power-law transformations | |
| Zhan et al. | Nonlocal means image denoising with minimum MSE-based decay parameter adaptation | |
| Ghazal et al. | Structure-oriented multidirectional wiener filter for denoising of image and video signals | |
| Sun et al. | Adaptive bilateral filter considering local characteristics | |
| Cvetkovic et al. | Non-linear locally-adaptive video contrast enhancement algorithm without artifacts | |
| KR100821939B1 (en) | Apparatus and method for image noise reduction | |
| US7773824B2 (en) | Signal processing device and method, recording medium, and program | |
| Priyadharsini et al. | The new robust adaptive median filter for denoising cancer images using image processing techniques | |
| Adamu et al. | Enhanced Adaptive Threshold Median Filter For Medical Image Filtering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |