CN113379607A - Method and device for adaptively adjusting image - Google Patents
Method and device for adaptively adjusting image Download PDFInfo
- Publication number
- CN113379607A CN113379607A CN202010115757.0A CN202010115757A CN113379607A CN 113379607 A CN113379607 A CN 113379607A CN 202010115757 A CN202010115757 A CN 202010115757A CN 113379607 A CN113379607 A CN 113379607A
- Authority
- CN
- China
- Prior art keywords
- image
- frequency sub
- max
- enhanced
- sub
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 230000009466 transformation Effects 0.000 claims abstract description 60
- 238000011156 evaluation Methods 0.000 claims abstract description 45
- 230000002708 enhancing effect Effects 0.000 claims abstract description 26
- 230000006870 function Effects 0.000 claims description 45
- 238000003708 edge detection Methods 0.000 claims description 14
- 238000002604 ultrasonography Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 description 8
- 238000013441 quality evaluation Methods 0.000 description 3
- 238000013139 quantization Methods 0.000 description 3
- 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
- 238000011158 quantitative evaluation Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000002401 inhibitory effect 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
- 238000005457 optimization Methods 0.000 description 1
- 230000000717 retained 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
Images
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 an image, which comprise the following steps: performing wavelet transformation on the original image to obtain multi-scale and multi-directional sub-images; respectively enhancing the multi-scale and multi-directional sub-images; performing wavelet inverse transformation on the enhanced sub-images to obtain enhanced images; and evaluating the image subjected to wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, and otherwise, continuing the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement. According to the method and the device, parameters are adjusted in a self-adaptive mode on the basis of artificial adjustment, the quality of the ultrasonic image is further improved, and the problem that the enhanced parameters cannot be adjusted and controlled accurately is solved.
Description
Technical Field
The present application relates to image processing, and in particular, to a method and an apparatus for adaptively adjusting an image.
Background
The medical ultrasound image is inevitably affected 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 enhancing the image and introducing new regulation and control parameters. Because the related parameters can only be adjusted manually according to experience and doctors, the effect is not ideal, and the enhanced parameters cannot be accurately adjusted and controlled.
Disclosure of Invention
The application provides a method and a device for adaptively adjusting an image.
According to a first aspect of the present application, there is provided a method for adaptively adjusting an image, comprising:
wavelet transformation: performing wavelet transformation on the original image to obtain multi-scale and multi-directional sub-images;
an image enhancement step: respectively enhancing the multi-scale and multi-directional sub-images;
wavelet inverse transformation: performing wavelet inverse transformation on the enhanced sub-images to obtain enhanced images;
self-regulation step: and evaluating the image subjected to wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, and 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.
Further, the enhancing the multi-scale, multi-directional sub-image comprises:
performing linear threshold enhancement on the low-frequency sub-image;
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;
the wavelet inverse transformation of the enhanced sub-image comprises:
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, if the image pixel point is smaller than the single threshold value a, carrying out zero setting operation, and if the image pixel point is larger than the single threshold value a, enhancing b times, wherein b is larger than 1;
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 the fuzzy enhancement comprises the following steps:
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, selecting a first-order differential edge detection operator for edge detection, enhancing the detected edge part by c times, and enhancing the 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 well-adjusted parameters of ultrasonic equipment.
Further, the merit 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 and d are parameters which are adjusted by ultrasonic equipment, and min is1,min2,min3,min4Respectively, a defined lower limit, max1,max2,max3,max4D (f (a, b, c, D)) is the variance function and PSNR (f (a, b, c, D)) is the peak signal-to-noise ratio, respectively.
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 multi-scale and multi-direction sub-images;
the image enhancement module is used for respectively enhancing the multi-scale and multi-direction sub-images;
the wavelet inverse transformation module is used for carrying out wavelet inverse transformation on the enhanced sub-images to obtain enhanced images;
and the self-adjusting module is used for evaluating the image subjected to wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, and 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:
the low-frequency enhancement unit is used for performing linear threshold enhancement on the low-frequency sub-image;
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;
the inverse wavelet transform module comprises:
and the wavelet inverse transformation unit is used 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.
Further, the low-frequency enhancement unit is further configured to select a single threshold a, perform a zeroing operation if an image pixel point is smaller than the single threshold a, and enhance b times if the image pixel point is larger than the single threshold a, where b is greater than 1;
the high-frequency enhancing unit is further configured to perform fuzzy enhancement on the horizontal high-frequency sub-image, the vertical high-frequency sub-image, and the diagonal high-frequency sub-image, respectively, select a first-order differential edge detection operator to perform edge detection, perform c-fold enhancement on a detected edge portion, and perform d-fold enhancement on data of other portions other than the edge, where c is greater than 1, and d is less than 1, a, b, c, and d are parameters that have been adjusted by the ultrasound device.
Further, the merit 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 and d are parameters which are adjusted by ultrasonic equipment, and min is1,min2,min3,min4The lower limits, respectively, of the limits defined,max1,max2,max3,max4d (f (a, b, c, D)) is the variance function and PSNR (f (a, b, c, D)) is the peak signal-to-noise ratio, respectively.
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;
a processor for implementing the above method by executing the program stored in the memory.
Due to the adoption of the technical scheme, the beneficial effects of the application are as follows:
in the specific embodiment of the application, the multi-scale and multi-directional sub-images are enhanced respectively; performing wavelet inverse transformation on the enhanced sub-images to obtain enhanced images; and evaluating the image subjected to wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, and otherwise, continuing the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement. According to the method and the device, parameters are adjusted in a self-adaptive mode on the basis of artificial adjustment, the quality of the ultrasonic image is further improved, and the problem that the enhanced parameters cannot be adjusted and controlled accurately is solved.
Drawings
FIG. 1 is a flow chart of a method in one embodiment of the present application;
FIG. 2 is a flow chart of a method in another embodiment according to the first embodiment of the present application;
FIG. 3 is a schematic diagram of program modules of an apparatus according to a second embodiment of the present application;
fig. 4 is a schematic diagram of program modules of an apparatus in an embodiment two of the present application in another implementation manner.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. The present application may be embodied in many different forms and is not limited to the embodiments described in the present embodiment. The following detailed description is provided to facilitate a more thorough understanding of the present disclosure, and the words used to indicate orientation, top, bottom, left, right, etc. are used solely to describe the illustrated structure in connection with the accompanying figures.
One skilled in the relevant art will recognize, however, that one or more of the specific details can be omitted, or other methods, components, or materials can be used. In some instances, some embodiments are not described or not described in detail.
The numbering of the components as such, e.g., "first", "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning.
Furthermore, the technical features, aspects or characteristics described herein may be combined in any suitable manner in one or more embodiments. It will be readily appreciated by those of skill in the art that the order of the steps or operations of the methods associated with the embodiments provided herein may be varied. Thus, any sequence in the figures and examples is for illustrative purposes only and does not imply a requirement in a certain order unless explicitly stated to require a certain order.
In the wavelet threshold enhancement algorithm, the wavelet filtering method covers the following four key characteristics for the coefficients obtained after the image signal is subjected to wavelet transform processing: the propagation property, the sparse property, the aggregation property and the directional property, and the coefficient obtained after the noise signal is subjected to wavelet transform processing does not have the properties. According to different properties of the transformation coefficients of the image signal and the noise signal on different scales after wavelet transformation, the wavelet filtering method can effectively filter out noise and better retain the signal.
The threshold function filtering method is a simple wavelet domain filtering method, mainly makes the amplitude of the wavelet transform coefficient of the noisy image compare with the set threshold, when the amplitude is smaller than the threshold, the wavelet transform coefficient is set to zero or reduced for certain inhibition, and when the amplitude is larger than the threshold, the wavelet transform coefficient is retained or amplified and enhanced, thus achieving the effect of inhibiting noise and enhancing image. The threshold filtering is generally divided into soft threshold filtering and hard threshold filtering. The soft threshold filtering function is changed to zero when the absolute value of the wavelet transform coefficient is smaller than the set threshold, and the threshold is subtracted when the absolute value of the wavelet transform coefficient is larger than the set threshold. The hard threshold filter function is changed to zero when the absolute value of the transform coefficient is smaller than a set threshold, and is not changed when the absolute value of the transform coefficient is larger than the set threshold.
The first embodiment is as follows:
as shown in fig. 1, one implementation of the method for adaptively adjusting an image provided in the application example includes the following steps:
step 102: wavelet transformation: and performing 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, 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.
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;
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.
Step 106: wavelet inverse transformation: and performing wavelet inverse transformation on the enhanced sub-images to obtain enhanced images.
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-regulation step: and (5) evaluating the image subjected to wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, otherwise, turning to the step 104, and continuing the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement.
Further, the merit 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 and d are parameters which are adjusted by ultrasonic equipment, and min is1,min2,min3,min4Respectively, a defined lower limit, max1,max2,max3,max4D (f (a, b, c, D)) is the variance function and PSNR (f (a, b, c, D)) is the peak signal-to-noise ratio, respectively.
The method introduces an image quality quantitative evaluation standard, evaluates and feeds back the image in the face of outputting the image without reference, and then introduces an image definition evaluation criterion: variance function, which can be used as an evaluation function, d (f) Σ, because sharply focused images have a greater difference in gray than blurred imagesy∑x|f(x,y)-μ|2Wherein mu is an average gray value of the whole image, the function is sensitive to noise, the purer the image is, the smaller the function value is, and the larger D (f) is, the richer the image detail information is, the clearer the image is, but in order to prevent the influence of salt and pepper noise, a peak signal-to-noise ratio (PSNR) is required to be introduced for comparing the quality evaluation, and the general peak signal-to-noise ratio is more used in the evaluation of the image, and the formula is as follows:where MN is the size of the graph, f is the output enhancement image,is the one that is input to be enhanced. The definition and the image quality evaluation function are combined into a final evaluation function, the evaluation function is used as a target function, the doctor/software defines parameters as a defined equation, and the self-adaptive parameter adjusting problem 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 adjusted by a doctor, min and max are upper and lower limited adjustable ranges. Meanwhile, for timeliness, the adjustment stepping length and the adjustment times of the stepping length and the adjustment times are further limited to form a multi-limit equation set. By solving the linear equation system, the more optimal parameters are adaptively adjusted around the adjustment parameters of the doctor.
The medical image quality optimization method converts the problem into a linear equation to be solved, introduces a clear quality quantization standard for the medical image, and utilizes the quantization standard to optimize the medical image.
As shown in fig. 2, another embodiment of the method for adaptively adjusting an image according to the present application includes the following steps:
step 202: and performing 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, 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.
Step 204: and performing linear threshold enhancement on the low-frequency sub-image. And selecting a single threshold value a, if the image pixel point is smaller than the single threshold value a, carrying out zero setting operation, and if the image pixel point is larger than the single threshold value a, enhancing b times, wherein b is larger than 1.
Step 206: 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. 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, enhancing the detected edge part by c times, and enhancing the data of other parts, which are not edges, by d times, wherein c is greater than 1, d is less than 1, a, b, c and d are well-adjusted parameters of the 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 evaluating the image subjected to wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, and otherwise, continuing 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 and d are parameters which are adjusted by ultrasonic equipment, and min is1,min2,min3,min4Respectively, a defined lower limit, max1,max2,max3,max4D (f (a, b, c, D)) is a variance function, PSNR (f (a, b, c, D)) isPeak signal-to-noise ratio.
If parameters a, b, c and d are 0.7 at level 1, 1.2 at level b, 1.5 at level c and 0.8 at level d, wavelet transform, image enhancement and wavelet inverse transform are performed according to the parameters to obtain an enhanced image 1, the enhanced image 1 is solved according to an evaluation function, and an output result is obtained, and if the result is 0.9, the quadratic programming idea is as follows: when st limitation is met, the value of a, b, c and d when the evaluation function is minimum is solved, the result is 0.9, the quadratic programming algorithm adjusts the value of a, b, c and d in the limitation condition, wavelet transformation, enhancement processing and inverse transformation are carried out again, the enhanced image solution evaluation value is obtained, if the value is less than 0.9, the new value of a, b, c and d replaces the original value of a, b, c and d as the optimized parameter, of course, the solving process can not be continued all the time, the above part shows that the loop solving times are limited, the range sizes of a, b, c and d are all limited, if the solution is carried out to the minimum value in the loop times, the minimum value in the loop times is the minimum value of the evaluation function if the minimum value is not solved in the loop times.
Example two:
as shown in fig. 3, an implementation manner of the apparatus for adaptively adjusting an image according to the 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.
An image enhancement module 320 for enhancing the multi-scale and multi-directional sub-images, respectively. In one embodiment, a 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.
A wavelet inverse transformation module 330, configured to perform wavelet inverse transformation on the enhanced sub-image to obtain an enhanced image;
and the self-adjusting module 340 is configured to evaluate the wavelet inverse-transformed image by using an evaluation function, output the enhanced image if the evaluation result meets the requirement, and 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 implementation of the apparatus for adaptively adjusting an image according to the embodiment of 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.
And an image enhancement module 420 for enhancing the multi-scale and multi-directional sub-images, respectively. In one embodiment, a 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.
A wavelet inverse transformation module 430, configured to perform wavelet inverse transformation on the enhanced sub-image to obtain an enhanced image;
and the self-adjusting module 440 is configured to evaluate the wavelet inverse-transformed image by using an evaluation function, output the enhanced image if the evaluation result meets the requirement, and 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 enhancing unit 422, 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, respectively;
and a wavelet inverse transformation unit 431, configured to perform 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 enhancing unit 421 is further configured to select a single threshold a, perform a zeroing operation if the image pixel point is smaller than the single threshold a, and enhance b times if the image pixel point is larger than the single threshold a, where b is greater than 1;
the high-frequency enhancing unit 422 is further configured to select a first-order differential edge detection operator for the horizontal high-frequency sub-image, the vertical high-frequency sub-image, and the diagonal high-frequency sub-image to perform edge detection, enhance the detected edge portion by c times, and enhance the data of the other portions other than the edge by d times, where c is greater than 1, and d is less than 1, a, b, c, and d are parameters that have been adjusted by the ultrasound device.
Further, the merit 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 and d are parameters which are adjusted by ultrasonic equipment, and min is1,min2,min3,min4Respectively, a defined lower limit, max1,max2,max3,max4D (f (a, b, c, D)) is the variance function and PSNR (f (a, b, c, D)) is the peak signal-to-noise ratio, respectively.
The method introduces an image quality quantitative evaluation standard, evaluates and feeds back the image in the face of outputting the image without reference, and then introduces an image definition evaluation criterion: variance function, which can be used as an evaluation function, d (f) Σ, because sharply focused images have a greater difference in gray than blurred imagesy∑x|f(x,y)-μ|2Where μ is the average gray value of the whole image, the function is sensitive to noise, the purer the image, the smaller the function value, and the larger D (f) indicates the imageThe detailed information is richer, the image is clearer, but in order to prevent the influence of salt and pepper noise, a peak signal-to-noise ratio (PSNR) is introduced to evaluate the quality of the image, and the peak signal-to-noise ratio is more used in the evaluation of the image, and the formula is as follows:where MN is the size of the graph, f is the output enhancement image,is the one that is input to be enhanced. The definition and the image quality evaluation function are combined into a final evaluation function, the evaluation function is used as a target function, the doctor/software defines parameters as a defined equation, and the self-adaptive parameter adjusting problem 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 adjusted by a doctor, min and max are upper and lower limited adjustable ranges. Meanwhile, for timeliness, the adjustment stepping length and the adjustment times of the stepping length and the adjustment times are further limited to form a multi-limit equation set. By solving the linear equation system, the more optimal parameters are adaptively adjusted around the adjustment parameters of the doctor.
Example three:
the device for adaptively adjusting the image comprises a memory and a processor.
A memory for storing a program;
and the processor is used for executing the program stored in the memory to realize the method in the first embodiment.
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 instructions associated with hardware via a program, which may be stored in a computer-readable storage medium, and the storage medium may include: read-only memory, random access memory, magnetic or optical disk, and the like.
The foregoing is a more detailed description of the present application in connection with specific embodiments thereof, and it is not intended that the present application be limited to the specific embodiments thereof. It will be apparent to those skilled in the art from this disclosure that many more simple derivations or substitutions can be made without departing from the spirit of the disclosure.
Claims (10)
1. A method for adaptively adjusting an image, comprising:
wavelet transformation: performing wavelet transformation on the original image to obtain multi-scale and multi-directional sub-images;
an image enhancement step: respectively enhancing the multi-scale and multi-directional sub-images;
wavelet inverse transformation: performing wavelet inverse transformation on the enhanced sub-images to obtain enhanced images;
self-regulation step: and evaluating the image subjected to wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, and otherwise, continuing the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement.
2. The method of claim 1, wherein the multi-scale, multi-directional sub-images comprise: a low frequency sub-image, a horizontal high frequency sub-image, a vertical high frequency sub-image, and a diagonal high frequency sub-image.
3. The method of claim 2, wherein the enhancing the multi-scale, multi-directional sub-image comprises:
performing linear threshold enhancement on the low-frequency sub-image;
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;
the wavelet inverse transformation of the enhanced sub-image comprises:
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.
4. The method of claim 3, wherein the linearly thresholding the low frequency sub-image comprises:
selecting a single threshold value a, if the image pixel point is smaller than the single threshold value a, carrying out zero setting operation, and if the image pixel point is larger than the single threshold value a, enhancing b times, wherein b is larger than 1;
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 the fuzzy enhancement comprises the following steps:
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, selecting a first-order differential edge detection operator for edge detection, enhancing the detected edge part by c times, and enhancing the 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 well-adjusted parameters of ultrasonic equipment.
5. The method of claim 4, wherein the merit function is:
s.t min1<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 adjusted by ultrasonic equipment, and min is1,min2,min3,min4Respectively, a defined lower limit, max1,max2,max3,max4D (f (a, b, c, D)) is the variance function and PSNR (f (a, b, c, D)) is the peak signal-to-noise ratio, respectively.
6. 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 multi-scale and multi-direction sub-images;
the image enhancement module is used for respectively enhancing the multi-scale and multi-direction sub-images;
the wavelet inverse transformation module is used for carrying out wavelet inverse transformation on the enhanced sub-images to obtain enhanced images;
and the self-adjusting module is used for evaluating the image subjected to wavelet inverse transformation by using an evaluation function, outputting the enhanced image if the evaluation result meets the requirement, and otherwise, continuing the image enhancement step and the wavelet inverse transformation step until the evaluation result meets the requirement.
7. The apparatus of claim 6, wherein the multi-scale, multi-directional sub-images comprise: 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:
the low-frequency enhancement unit is used for performing linear threshold enhancement on the low-frequency sub-image;
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;
the inverse wavelet transform module comprises:
and the wavelet inverse transformation unit is used 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.
8. The apparatus of claim 7,
the low-frequency enhancement unit is also used for selecting a single threshold a, if the image pixel point is smaller than the single threshold a, the zero setting operation is carried out, and if the image pixel point is larger than the single threshold a, b times of the image pixel point is enhanced, wherein b is larger than 1;
the high-frequency enhancing unit is further configured to perform fuzzy enhancement on the horizontal high-frequency sub-image, the vertical high-frequency sub-image, and the diagonal high-frequency sub-image, respectively, select a first-order differential edge detection operator to perform edge detection, perform c-fold enhancement on a detected edge portion, and perform d-fold enhancement on data of other portions other than the edge, where c is greater than 1, and d is less than 1, a, b, c, and d are parameters that have been adjusted by the ultrasound device.
9. The apparatus of claim 8, wherein the merit function is:
s.t min1<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 adjusted by ultrasonic equipment, and min is1,min2,min3,min4Respectively, a defined lower limit, max1,max2,max3,max4D (f (a, b, c, D)) is the variance function and PSNR (f (a, b, c, D)) is the peak signal-to-noise ratio, respectively.
10. An apparatus for adaptively adjusting an image, comprising:
a memory for storing a program;
a processor for implementing the method of any one of claims 1-5 by executing a program stored by 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 true CN113379607A (en) | 2021-09-10 |
CN113379607B 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) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117649357A (en) * | 2024-01-29 | 2024-03-05 | 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 |
---|
KAI-JIAN XIA 等: "A novel medical image enhancement algorithm based improvement correction strategy in wavelet transform domain", 《CLUSTER COMPUTING》, 20 October 2017 (2017-10-20), pages 10969 - 10977, XP036949693, DOI: 10.1007/s10586-017-1264-y * |
崔昊杨 等: "基于自适应遗传算法的变电站红外图像模糊增强", 《高电压技术》, vol. 41, no. 3, 31 March 2015 (2015-03-31), pages 902 - 908 * |
焦志浩 等: "基于复合评价值的小波去噪参数选定方法", 《重庆理工大学学报(自然科学)》, vol. 33, no. 8, 31 August 2019 (2019-08-31), pages 178 - 184 * |
王景中 等: "基于自适应阈值的小波增强方法", 《信息技术》, 30 September 2015 (2015-09-30), pages 36 - 39 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117649357A (en) * | 2024-01-29 | 2024-03-05 | 深圳市恩普电子技术有限公司 | Ultrasonic image processing method based on image enhancement |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN113379607B (en) | 2024-05-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chen et al. | Aggressive region growing for speckle reduction in ultrasound images | |
Sun et al. | Postprocessing of low bit-rate block DCT coded images based on a fields of experts prior | |
US7570829B2 (en) | Selection of alternative image processing operations to maintain high image quality | |
US8131104B2 (en) | Method and apparatus for adjusting the contrast of an input image | |
US20110280494A1 (en) | Method and apparatus for generating enhanced images | |
Hossain et al. | Image enhancement based on logarithmic transform coefficient and adaptive histogram equalization | |
RU2342701C1 (en) | Method of complexing digital multispectral half-tone images | |
Sun et al. | Scanned image descreening with image redundancy and adaptive filtering | |
Khan et al. | Contrast enhancement of low-contrast medical images using modified contrast limited adaptive histogram equalization | |
Nevriyanto et al. | Image enhancement using the image sharpening, contrast enhancement, and Standard Median Filter (Noise Removal) with pixel-based and human visual system-based measurements | |
Lee et al. | Two-stage false contour detection using directional contrast and its application to adaptive false contour reduction | |
CN103489168A (en) | Enhancing method and system for infrared image being converted to pseudo color image in self-adaptive mode | |
CN113379607A (en) | Method and device for adaptively adjusting image | |
Shedbalkar et al. | A comparative analysis of filters for noise reduction and smoothening of brain MRI images | |
Singh et al. | Image enhancement by adaptive power-law transformations | |
Li et al. | Saliency guided naturalness enhancement in color images | |
Zhan et al. | Nonlocal means image denoising with minimum MSE-based decay parameter adaptation | |
Mai et al. | A modified unsharp masking method using particle swarm optimization | |
Khellah | Textured image denoising using dominant neighborhood structure | |
Ghazal et al. | Structure-oriented multidirectional wiener filter for denoising of image and video signals | |
Kavya | Performance Analysis of Different Filters for Digital Image Processing | |
Storozhilova et al. | 2.5 D extension of neighborhood filters for noise reduction in 3D medical CT images | |
Chang et al. | Rician noise removal in MR images using an adaptive trilateral filter | |
Kadmin | Enhancement of Digital Stereo Vision Images based on Histogram and Gamma Correction Strategy | |
Pawana et al. | Image Enhancement using CLAHE and Noise Removal for Shoreline Detection Framework |
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 |