CN109978794B - Method and system for processing mammary gland dual-energy image - Google Patents
Method and system for processing mammary gland dual-energy image Download PDFInfo
- Publication number
- CN109978794B CN109978794B CN201910248001.0A CN201910248001A CN109978794B CN 109978794 B CN109978794 B CN 109978794B CN 201910248001 A CN201910248001 A CN 201910248001A CN 109978794 B CN109978794 B CN 109978794B
- Authority
- CN
- China
- Prior art keywords
- dual
- image
- energy
- energy image
- processing
- 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 30
- 210000005075 mammary gland Anatomy 0.000 title claims abstract description 26
- 210000000481 breast Anatomy 0.000 claims description 20
- 230000009977 dual effect Effects 0.000 claims description 8
- 208000004434 Calcinosis Diseases 0.000 abstract description 15
- 230000002308 calcification Effects 0.000 abstract description 15
- 210000004872 soft tissue Anatomy 0.000 abstract description 6
- 210000004907 gland Anatomy 0.000 abstract description 5
- 210000001519 tissue Anatomy 0.000 abstract description 4
- 210000004204 blood vessel Anatomy 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 16
- 230000000694 effects Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 238000009607 mammography Methods 0.000 description 2
- 230000035807 sensation Effects 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000000762 glandular Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000000126 substance Substances 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
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G06T5/73—
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30068—Mammography; Breast
Abstract
The invention discloses a method and a system for processing a mammary gland dual-energy image, wherein the method comprises the following steps: acquiring a high-energy level image and a low-energy level image of a mammary gland; superposing the high-energy-level image and the low-energy-level image to obtain a first dual-energy image; carrying out reverse color processing on the first dual-energy image to obtain a second dual-energy image; correcting the background gray value of the second dual-energy image to obtain a third dual-energy image; and sharpening the third dual-energy image by adopting an improved Laplace of Gaussian algorithm. The invention can reduce the influence of mammary gland ducts, blood vessels, gland tissues and the like on the calcifications under the background of the mammary gland soft tissues, thereby improving the detection capability of the calcifications.
Description
Technical Field
The invention belongs to the field of medical imaging, and particularly relates to a method and a system for processing a dual-energy image of a mammary gland.
Background
Mammography is the most effective method for diagnosing breast lesions in early stages, and since calcification is the main feature of breast lesions, mammography can detect calcification in the breast. However, the breast duct, the blood vessel, the glandular tissue and the like in the breast can make the background imaging of the soft tissue of the breast uneven, thereby possibly influencing the probability of detecting the calcification points. The breast edge in the breast image processed by the traditional dual-energy subtraction technique is not clear, and the calcifications are not obvious.
Disclosure of Invention
The invention aims to provide a method and a system for processing a mammary gland dual-energy image, which are used for reducing the influence of mammary gland ducts, blood vessels, gland tissues and the like on calcifications under the background of mammary gland soft tissues so as to improve the detection capability of the calcifications.
In order to achieve the purpose, the invention provides the following scheme:
a processing method of a mammary gland dual-energy image comprises the following steps:
acquiring a high-energy level image and a low-energy level image of a mammary gland;
superposing the high-energy-level image and the low-energy-level image to obtain a first dual-energy image;
carrying out reverse color processing on the first dual-energy image to obtain a second dual-energy image;
correcting the background gray value of the second dual-energy image to obtain a third dual-energy image;
sharpening the third dual-energy image by using an improved laplacian of gaussian algorithm, wherein the improved laplacian of gaussian algorithm comprises:
wherein f is3' (x, y) is a modified portion representing the modified third dual energy image gray scale value function, f3And (x, y) is a part before improvement and represents a gray value function of the third dual-energy image, x is an abscissa of the pixel point in the third dual-energy image, y is an ordinate of the pixel point in the third dual-energy image, a is a minimum gray value of the third dual-energy image, and b is a maximum gray value of the third dual-energy image.
Optionally, the superimposing processing of the high-energy level image and the low-energy level image specifically includes:
according to ln (I)Dual)=ln(IH)+ωln(IL) Performing superposition processing on the high-energy level image and the low-energy level image, wherein IDualRepresenting the gray value of the first dual-energy image, IHFor high-level image grey values, ILAnd omega is a superposition coefficient.
Optionally, the performing the inverse color processing on the first dual-energy image specifically includes:
according to f2(x,y)=M-f1(x, y) performing reverse color processing on a first dual-energy image, wherein x is the abscissa of a pixel point in the first dual-energy image, and y is the first dual-energy image of the pixel pointOrdinate, f, in the image2(x, y) is a gray value function of the second dual-energy image, M is the maximum value of the gray scale range of the image generated by the detector, f1(x, y) is a function of the gray scale values of the first bi-energy image.
Optionally, the correcting the background gray value of the second dual-energy image specifically includes:
respectively calculating gray values of four corners of the second dual-energy image;
calculating the average value of the four corner gray values as a background gray value threshold;
and setting the gray value of the point of which the gray value is smaller than the background gray value threshold value in the second dual-energy image to be zero.
Optionally, the sharpening process is performed on the third dual-energy image by using an improved laplacian of gaussian algorithm, and specifically includes:
according toCarrying out sharpening processing on the third dual-energy image, wherein g (x, y) is a function of the gray value of the sharpened image, f3' (x, y) is the part of the algorithm that is improved, f3(x, y) is a function of the gray values of the third dual energy image, alpha is a scaling factor,in order to be the laplacian operator,is a differential operator symbol.
Optionally, the respectively calculating the gray values of the four corners of the second dual-energy image includes: the sum of the four corner pixel points accounts for 10% of the total number of the pixel points.
Optionally, 300 × 300 pixel points are taken from each corner.
Optionally, the shooting conditions used when acquiring the low-level image of the breast are 28KV and 100 mA.
Optionally, the shooting conditions used when acquiring the high-energy level image of the breast are 40KV and 100 mA.
A system for processing dual-energy images of the breast, comprising:
the image acquisition module is used for acquiring a high-energy-level image and a low-energy-level image of the mammary gland;
the image superposition module is used for carrying out superposition processing on the high-energy-level image and the low-energy-level image to obtain a first dual-energy image;
the reverse color processing module is used for performing reverse color processing on the first dual-energy image to obtain a second dual-energy image;
the data correction module is used for correcting the background gray value of the second dual-energy image to obtain a third dual-energy image;
the operation module is used for improving the gray value function of the third dual-energy image;
and the sharpening processing module is used for sharpening the image according to the improved third dual-energy image gray value function.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: firstly, performing superposition processing on a high-energy-level image and a low-energy-level image by using a dual-energy superposition algorithm; and then, correcting the grey value of the reverse color and the background, and finally sharpening to ensure that the outline edge of the gland can be observed to be clear and the existence of calcification can be observed obviously in the result image.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flowchart illustrating a method for processing a dual-energy breast image according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a breast dual-energy image processing system according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for processing a mammary gland dual-energy image, so that the obtained dual-energy image can have a good edge effect of a low-energy image and a calcification point effect in a high-energy image.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flowchart of a method for processing a dual-energy mammary gland image according to an embodiment of the present invention, and as shown in fig. 1, the method for processing a dual-energy mammary gland image provided by the present invention includes the following steps:
step 101: acquiring a high-energy level image and a low-energy level image of a mammary gland;
step 102: superposing the high-energy-level image and the low-energy-level image to obtain a first dual-energy image;
step 103: carrying out reverse color processing on the first dual-energy image to obtain a second dual-energy image;
step 104: correcting the background gray value of the second dual-energy image to obtain a third dual-energy image;
step 105: and sharpening the third dual-energy image by adopting an improved Laplace of Gaussian algorithm.
Wherein, the step 101 specifically comprises: the method comprises the steps of collecting low-level images and high-level images of a mammary gland phantom in a grading mode (the energy level is determined by tube voltage when an X-ray source shoots), wherein shooting conditions (X-ray tube voltage and tube current used when the X-ray source shoots) used for shooting the low-level images are 28KV and 100mA, and shooting conditions (X-ray tube voltage and tube current used when the X-ray source shoots) used for shooting the high-level images are 40KV and 100 mA.
the specific superposition algorithm is as follows:
ln(IDual)=ln(IH)+ωln(IL)
wherein IDualRepresenting the gray value of the first dual-energy image, IHFor high-level image grey values, ILThe gray value of the low-level image is obtained, omega is a superposition coefficient, and the numerical value of omega is obtained according to the attenuation coefficient of the substance and experiments.
In order to better observe soft tissues and calcifications, the image needs to be processed in reverse color. In the field of digital X-ray imaging, since the detector detects X-rays that should reach the detector surface, the X-rays are converted into visible light, and then the photosensor converts the optical signal into an electrical signal, resulting in a digital image. Therefore, where the subject is not being photographed, the X-ray should not be attenuated, the X-ray should produce the most visible photons, so its electrical signal should be the largest, its gray value should be the largest for the entire picture, and the greater the attenuation coefficient, the greater the X-ray attenuation, and ultimately the lower the gray value should be. The background color should be close to white and the soft tissue and calcifications should be dark. After the reverse color, the background color is near black, while the soft tissue and calcifications are near white.
Therefore, step 103 is specifically: according to f2(x,y)=M-f1(x, y) performing reverse color processing on a first dual-energy image, wherein x is an abscissa of a pixel point in the first dual-energy image, y is an ordinate of the pixel point in the first dual-energy image, and f2(x, y) is a gray value function of the second dual-energy image, M is the maximum value of the gray scale range of the image generated by the detector, f1(x, y) is a function of the gray scale values of the first bi-energy image.
When the image is reversed, the gray level value of the area where no object is captured should be the minimum value, which should be 0. In practice, however, the background of the picture generated by the detector is not 0 after the reverse color, because the detector has a dark current and also a noisy image, resulting in a background gray value of not 0. So in order to better perform image processing we need to determine the background for the image.
Since the X-ray image is usually taken with the object in the center and four corners left empty, step 104 is specifically: respectively calculating gray values of four corners of the second dual-energy image; 300 pixel points are taken from each corner, and 360000 pixel points account for about 10% of the total number of the pixels;
calculating the average value of the four corner gray values as a background gray value threshold;
and setting the gray value of the point of which the gray value is smaller than the background gray value threshold value in the second dual-energy image to be zero.
In order to reduce noise in the picture as much as possible and weaken granular sensation as much as possible, the image needs to be sharpened, but due to the precision and complexity of the human organ, the thicknesses and attenuation coefficients of tissues represented by adjacent pixel points may be greatly different, so that the gray values of the adjacent pixel points are greatly different, and further, when a laplacian gaussian operator and a laplacian gaussian operator are used according to a traditional sharpening method, the granular sensation of the image is serious. We therefore propose a new and improved process.
Namely, step 105 specifically comprises: the laplacian of gaussian algorithm is improved:
wherein f is3' (x, y) is a modified portion representing the modified third dual energy image gray scale value function, f3(x, y) is a part before improvement and represents a gray value function of the third dual-energy image, x is an abscissa of a pixel point in the third dual-energy image, y is an ordinate of the pixel point in the third dual-energy image, a is a minimum gray value of the third dual-energy image, and b is a gray value of the third dual-energy imageA maximum value of degree;
the sharpening process of the third dual-energy image by using the improved laplacian of gaussian algorithm specifically includes:
according toCarrying out sharpening processing on the third dual-energy image, wherein g (x, y) is a function of the gray value of the sharpened image, f3' (x, y) is the part of the algorithm that is improved, f3(x, y) is a function of the gray values of the third dual energy image, alpha is a scaling factor,in order to be the laplacian operator,is a differential operator symbol.
Firstly, performing superposition processing on a high-energy-level image and a low-energy-level image by using a dual-energy superposition algorithm; and then, correcting the grey value of the reverse color and the background, and finally sharpening to ensure that the outline edge of the gland can be observed to be clear and the existence of calcification can be observed obviously in the result image.
Fig. 2 is a schematic structural diagram of a dual-energy breast image processing system according to an embodiment of the present invention, and as shown in fig. 2, the dual-energy breast image processing system provided by the present invention includes:
an image acquisition module 201, configured to acquire a high-level image and a low-level image of a breast;
an image overlaying module 202, configured to perform an overlay process on the high-energy level image and the low-energy level image to obtain a first dual-energy image;
the reverse color processing module 203 is configured to perform reverse color processing on the first dual-energy image to obtain a second dual-energy image;
the data correction module 204 is used for correcting the background gray value of the second dual-energy image to obtain a third dual-energy image;
an operation module 205, configured to improve a gray-scale function of the third dual-energy image;
and a sharpening module 206, configured to perform sharpening on the image according to the improved third dual-energy image gray-value function.
The system is applied to processing the mammary gland image, so that the contour edge of the gland in the result image is clear, and the existence of calcification can be obviously observed.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (7)
1. A method for processing a dual-energy image of a breast is characterized by comprising the following steps:
acquiring a high-energy level image and a low-energy level image of a mammary gland;
superposing the high-energy-level image and the low-energy-level image to obtain a first dual-energy image;
carrying out reverse color processing on the first dual-energy image to obtain a second dual-energy image;
correcting the background gray value of the second dual-energy image to obtain a third dual-energy image;
sharpening the third dual-energy image by adopting an improved Laplace of Gaussian algorithm; wherein, the improved laplacian of gaussian algorithm comprises:
wherein f is3' (x, y) is a modified portion representing the modified third dual energy image gray scale value function, f3(x, y) is a part before improvement and represents a third dual-energy image gray value function, x is an abscissa of a pixel point in the third dual-energy image, y is an ordinate of the pixel point in the third dual-energy image, a is a third dual-energy image gray minimum value, and b is a third dual-energy image gray maximum value;
the superimposing process of the high-energy-level image and the low-energy-level image specifically includes:
according to ln (I)Dual)=ln(IH)+ωln(IL) Performing superposition processing on the high-energy level image and the low-energy level image, wherein IDualRepresenting the gray value of the first dual-energy image, IHFor high-level image grey values, ILThe gray value of the low-level image is obtained, and omega is a superposition coefficient;
the correcting the background gray value of the second dual-energy image specifically includes:
respectively calculating gray values of four corners of the second dual-energy image;
calculating the average value of the four corner gray values as a background gray value threshold;
and setting the gray value of the point of which the gray value is smaller than the background gray value threshold value in the second dual-energy image to be zero.
2. The method for processing the dual-energy image of the breast according to claim 1, wherein the performing the inverse color processing on the first dual-energy image specifically comprises:
according to f2(x,y)=M-f1(x, y) performing reverse color processing on a first dual-energy image, wherein x is an abscissa of a pixel point in the first dual-energy image, y is an ordinate of the pixel point in the first dual-energy image, and f2(x, y) is a gray value function of the second dual-energy image, M is the maximum value of the gray scale range of the image generated by the detector, f1(x, y) is a function of the gray scale values of the first bi-energy image。
3. The method for processing the dual-energy image of the breast according to claim 1, wherein the sharpening process on the third dual-energy image by using the improved laplacian of gaussian algorithm specifically includes:
according toCarrying out sharpening processing on the third dual-energy image, wherein g (x, y) is a function of the gray value of the sharpened image, f3' (x, y) is the part of the algorithm that is improved, f3(x, y) is a function of the gray values of the third dual energy image, alpha is a scaling factor,in order to be the laplacian operator,is a differential operator symbol.
4. The method for processing the dual-energy image of the breast as claimed in claim 1, wherein the calculating the gray values of the four corners of the second dual-energy image respectively comprises: the sum of the four corner pixel points accounts for 10% of the total number of the pixel points.
5. The method of claim 4, wherein each corner has 300 x 300 pixels.
6. The method for processing the dual-energy image of the mammary gland as claimed in claim 1, wherein the capturing conditions used for acquiring the low-level image of the mammary gland are 28KV and 100 mA.
7. The method for processing the dual-energy image of the mammary gland according to claim 1, wherein the shooting conditions used for acquiring the high-energy level image of the mammary gland are 40KV and 100 mA.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910248001.0A CN109978794B (en) | 2019-03-29 | 2019-03-29 | Method and system for processing mammary gland dual-energy image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910248001.0A CN109978794B (en) | 2019-03-29 | 2019-03-29 | Method and system for processing mammary gland dual-energy image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109978794A CN109978794A (en) | 2019-07-05 |
CN109978794B true CN109978794B (en) | 2021-03-23 |
Family
ID=67081537
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910248001.0A Active CN109978794B (en) | 2019-03-29 | 2019-03-29 | Method and system for processing mammary gland dual-energy image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109978794B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111904445B (en) * | 2020-08-18 | 2023-03-31 | 深圳蓝影医学科技股份有限公司 | Method and device for acquiring and processing contrast enhanced image of mammary gland |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE3322705A1 (en) * | 1983-06-24 | 1985-01-10 | Fa. Carl Zeiss, 7920 Heidenheim | METHOD AND CIRCUIT FOR THE VIDEO-QUICK DETERMINATION OF THE MEDIAN VALUE OF AN EVALUATION WINDOW |
CN101169868A (en) * | 2006-10-25 | 2008-04-30 | 爱克发医疗保健公司 | Method for segmenting a digital medical image |
CN101822545A (en) * | 2010-05-11 | 2010-09-08 | 河南大学 | Method for eliminating motion artifacts in digital subtraction angiography and system thereof |
CN102496161A (en) * | 2011-12-13 | 2012-06-13 | 浙江欧威科技有限公司 | Method for extracting contour of image of printed circuit board (PCB) |
CN103729630A (en) * | 2014-01-14 | 2014-04-16 | 浙江正泰电器股份有限公司 | System and method for identification surface recognition |
CN104809452A (en) * | 2015-05-19 | 2015-07-29 | 成都英力拓信息技术有限公司 | Fingerprint identification method |
CN105046658A (en) * | 2015-06-26 | 2015-11-11 | 北京大学深圳研究生院 | Low-illumination image processing method and device |
CN105054954A (en) * | 2015-07-17 | 2015-11-18 | 王东良 | Method and system for acquiring and processing multi-energy X-ray fluoroscopic images in real time |
CN104651462B (en) * | 2015-01-29 | 2017-02-22 | 华南农业大学 | Method for detecting magnaporthe grisea spore based on microscopic image analysis |
CN106859677A (en) * | 2017-01-16 | 2017-06-20 | 沈阳东软医疗系统有限公司 | Dual intensity CT scan image rebuilding method and device |
CN107864337A (en) * | 2017-11-30 | 2018-03-30 | 广东欧珀移动通信有限公司 | Sketch image processing method, device and equipment |
CN108230417A (en) * | 2016-12-16 | 2018-06-29 | 通用电气公司 | Synthesize the multilayer color displays in 2D images |
CN109523472A (en) * | 2018-10-12 | 2019-03-26 | 海南大学 | Retinex colour-image reinforcing method, computer vision processing system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101027323B1 (en) * | 2010-01-20 | 2011-04-06 | 고려대학교 산학협력단 | Apparatus and method for image interpolation using anisotropic gaussian filter |
WO2016205419A1 (en) * | 2015-06-15 | 2016-12-22 | Flir Systems Ab | Contrast-enhanced combined image generation systems and methods |
CN105894459A (en) * | 2015-12-10 | 2016-08-24 | 乐视云计算有限公司 | Gradient value and direction based image sharpening method and device |
CN106780447B (en) * | 2016-12-02 | 2019-07-16 | 北京航星机器制造有限公司 | A kind of intelligent selection image enchancing method |
-
2019
- 2019-03-29 CN CN201910248001.0A patent/CN109978794B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE3322705A1 (en) * | 1983-06-24 | 1985-01-10 | Fa. Carl Zeiss, 7920 Heidenheim | METHOD AND CIRCUIT FOR THE VIDEO-QUICK DETERMINATION OF THE MEDIAN VALUE OF AN EVALUATION WINDOW |
CN101169868A (en) * | 2006-10-25 | 2008-04-30 | 爱克发医疗保健公司 | Method for segmenting a digital medical image |
CN101822545A (en) * | 2010-05-11 | 2010-09-08 | 河南大学 | Method for eliminating motion artifacts in digital subtraction angiography and system thereof |
CN102496161A (en) * | 2011-12-13 | 2012-06-13 | 浙江欧威科技有限公司 | Method for extracting contour of image of printed circuit board (PCB) |
CN103729630A (en) * | 2014-01-14 | 2014-04-16 | 浙江正泰电器股份有限公司 | System and method for identification surface recognition |
CN104651462B (en) * | 2015-01-29 | 2017-02-22 | 华南农业大学 | Method for detecting magnaporthe grisea spore based on microscopic image analysis |
CN104809452A (en) * | 2015-05-19 | 2015-07-29 | 成都英力拓信息技术有限公司 | Fingerprint identification method |
CN105046658A (en) * | 2015-06-26 | 2015-11-11 | 北京大学深圳研究生院 | Low-illumination image processing method and device |
CN105054954A (en) * | 2015-07-17 | 2015-11-18 | 王东良 | Method and system for acquiring and processing multi-energy X-ray fluoroscopic images in real time |
CN108230417A (en) * | 2016-12-16 | 2018-06-29 | 通用电气公司 | Synthesize the multilayer color displays in 2D images |
CN106859677A (en) * | 2017-01-16 | 2017-06-20 | 沈阳东软医疗系统有限公司 | Dual intensity CT scan image rebuilding method and device |
CN107864337A (en) * | 2017-11-30 | 2018-03-30 | 广东欧珀移动通信有限公司 | Sketch image processing method, device and equipment |
CN109523472A (en) * | 2018-10-12 | 2019-03-26 | 海南大学 | Retinex colour-image reinforcing method, computer vision processing system |
Also Published As
Publication number | Publication date |
---|---|
CN109978794A (en) | 2019-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Dhawan et al. | Mammographic feature enhancement by computerized image processing | |
US5594767A (en) | Methods and apparatus for enhancing image sharpness | |
JP2007014759A (en) | Method for reducing image-based artifact in pet/ct imaging | |
CN110458827B (en) | Method, device, equipment and medium for detecting medical image dead pixels | |
CN110047055B (en) | Infrared image detail enhancement and denoising method | |
JP6284898B2 (en) | Noise suppression processing apparatus and method, and program | |
JP6071444B2 (en) | Image processing apparatus, operation method thereof, and program | |
JP6678541B2 (en) | Image processing apparatus, method and program | |
WO2014050045A1 (en) | Body movement detection device and method | |
CN111353958A (en) | Image processing method, device and system | |
CN109978794B (en) | Method and system for processing mammary gland dual-energy image | |
JP6492553B2 (en) | Image processing apparatus and program | |
CN103822932A (en) | X-ray real-time image weld defect detection method based on multi-scale filtering operator | |
JP2017018339A (en) | Method for making pulmonary nodule clear in chest x-ray image | |
US20110280463A1 (en) | Image processing method and radiographic apparatus using the same | |
EP1520255A2 (en) | Methods of anisotropic diffusion and foveal segmentation of digital images | |
CN107507169B (en) | Method for estimating dual-energy subtraction parameters and computer-readable storage medium | |
US20100061656A1 (en) | Noise reduction of an image signal | |
CN115511726A (en) | X-ray image unsharp double-mask image enhancement method and system | |
US6956977B2 (en) | Methods for improving contrast based dynamic range management | |
Ishida | Image processing | |
KR101970989B1 (en) | Method and system for applying filters for dental CT imaging | |
CN111489314A (en) | Image enhancement method and device and terminal equipment | |
JP4607476B2 (en) | Radiographic image diagnostic apparatus and data processing method of radiographic image diagnostic apparatus | |
KR20100121273A (en) | Apparatus and method for processing x-ray image |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Qi Yihong Inventor after: Sang Juncheng Inventor before: Wang Kai Inventor before: Qi Yihong Inventor before: Sang Juncheng |
|
PP01 | Preservation of patent right | ||
PP01 | Preservation of patent right |
Effective date of registration: 20231211 Granted publication date: 20210323 |