CN113240606A - Traditional Chinese medicine inspection image color correction method and system - Google Patents
Traditional Chinese medicine inspection image color correction method and system Download PDFInfo
- Publication number
- CN113240606A CN113240606A CN202110566849.5A CN202110566849A CN113240606A CN 113240606 A CN113240606 A CN 113240606A CN 202110566849 A CN202110566849 A CN 202110566849A CN 113240606 A CN113240606 A CN 113240606A
- Authority
- CN
- China
- Prior art keywords
- image
- corrected
- frequency information
- inspection
- low
- 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
- 238000012937 correction Methods 0.000 title claims abstract description 136
- 238000007689 inspection Methods 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000003814 drug Substances 0.000 title claims abstract description 25
- 230000004927 fusion Effects 0.000 claims abstract description 14
- 238000007499 fusion processing Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 11
- 238000000354 decomposition reaction Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 7
- 238000012552 review Methods 0.000 claims 1
- 238000003745 diagnosis Methods 0.000 abstract description 11
- 230000015654 memory Effects 0.000 description 13
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000002558 medical inspection Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003042 antagnostic effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 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
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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 using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/90—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to alternative medicines, e.g. homeopathy or oriental medicines
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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]
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Radiology & Medical Imaging (AREA)
- Epidemiology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Alternative & Traditional Medicine (AREA)
- Pharmacology & Pharmacy (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a color correction method and a system for traditional Chinese medicine inspection images, which comprises the steps of obtaining an inspection image to be corrected; inputting the inspection image to be corrected into a color correction model to obtain an initial correction image; respectively extracting high-frequency information and low-frequency information of the inspection image to be corrected and the initial correction image; and carrying out fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image. The invention realizes the fusion correction between the image to be corrected and the image generated by the model by using information fusion on the basis of the image generated by the color correction model, and the obtained corrected image can meet the requirements of traditional Chinese medicine inspection diagnosis on the precision and color content, thereby improving the precision of the corrected image.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a color correction method and system for a traditional Chinese medicine inspection image.
Background
The inspection of traditional Chinese medicine has been developed for a long time, and the rationality and effectiveness of the inspection have been verified through abundant practice cases. With the development of intelligent traditional Chinese medicine inspection, the types of inspection image acquisition equipment are more and more, however, the acquired inspection images have color distortions of different degrees due to the differences between the optical lens and the photoelectric sensor of different inspection image acquisition equipment and the differences between different acquisition environments, and the color distortions finally affect the accuracy of the inspection result.
At present, based on a traditional color correction algorithm, for example, a mapping-based color correction algorithm, such an algorithm often needs a large amount of standard color block data or reference data with consistent matching results, otherwise, a high-precision color reduction effect is difficult to achieve; although the color correction method based on image analysis is simple in calculation, there is a certain limitation, for example, a gray world algorithm often cannot complete a task of color correction when a large area of a single color appears in an image.
Therefore, the conventional color correction methods have certain limitations, and if the color correction methods are directly applied to the correction processing process of the inspection image, the accuracy of the corrected image is reduced.
Disclosure of Invention
In order to solve the problems, the invention provides a color correction method and a color correction system for a traditional Chinese medicine inspection image, which improve the accuracy of the inspection image after color correction.
In order to achieve the purpose, the invention provides the following technical scheme:
a color correction method for traditional Chinese medicine inspection images comprises the following steps:
acquiring a to-be-corrected inspection image;
inputting the inspection image to be corrected into a color correction model to obtain an initial correction image;
respectively extracting high-frequency information and low-frequency information of the inspection image to be corrected and the initial correction image;
and carrying out fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image.
Optionally, the color correction model includes a generative confrontation network, wherein the generative confrontation network is trained by the following steps:
inputting a first sample image set into a first generation network to obtain a first sample output image, wherein the first sample image set is an image data set to be corrected;
inputting the first sample output image into a first judgment network to obtain a first judgment result;
correcting the first generated network according to the first judgment result to obtain a corrected first generated network;
inputting a second sample image set into a second generation network to obtain a second sample output image, wherein the second sample image set is a standard image data set;
inputting the second sample output image into a second judgment network to obtain a second judgment result;
correcting the second generation network according to the second judgment result to obtain a corrected second generation network;
and fusing the modified first generation network and the modified second generation network to obtain the generation countermeasure network.
Optionally, the extracting high frequency information and low frequency information of the inspection image to be corrected and the initial correction image respectively includes:
and performing wavelet decomposition on the inspection image to be corrected and the initial correction image to respectively obtain high-frequency information and low-frequency information of the image to be corrected and the initial correction image.
Optionally, the performing fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image includes:
respectively traversing the inspection image to be corrected and the initial correction image based on the low-frequency information, and extracting a fused low-frequency component obtained from the minimum value in the low-frequency components in the image;
traversing the high-frequency information of the inspection image to be corrected and the initial correction image, and determining a definition parameter based on the low-frequency component;
fusing the high-frequency information based on the definition parameters to obtain fused high-frequency components;
and generating a target correction image based on the fused low-frequency component and the fused high-frequency component.
Optionally, the acquiring the inspection image to be corrected includes:
acquiring a visiting image acquired by image acquisition equipment;
and extracting images meeting image distortion conditions in the inspection images, and determining the images as the inspection images to be corrected.
A color correction system for traditional Chinese medicine inspection images comprises:
an acquisition unit for acquiring a prospective image to be corrected;
the model processing unit is used for inputting the inspection image to be corrected into the color correction model to obtain an initial correction image;
an extraction unit, configured to extract high-frequency information and low-frequency information of the inspection image to be corrected and the initial correction image, respectively;
and the processing unit is used for carrying out fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image.
Optionally, the color correction model includes generating a confrontation network, wherein the system further includes a model training unit, and the model training unit is specifically configured to:
inputting a first sample image set into a first generation network to obtain a first sample output image, wherein the first sample image set is an image data set to be corrected;
inputting the first sample output image into a first judgment network to obtain a first judgment result;
correcting the first generated network according to the first judgment result to obtain a corrected first generated network;
inputting a second sample image set into a second generation network to obtain a second sample output image, wherein the second sample image set is a standard image data set;
inputting the second sample output image into a second judgment network to obtain a second judgment result;
correcting the second generation network according to the second judgment result to obtain a corrected second generation network;
and fusing the modified first generation network and the modified second generation network to obtain the generation countermeasure network.
Optionally, the extracting unit is specifically configured to:
and performing wavelet decomposition on the inspection image to be corrected and the initial correction image to respectively obtain high-frequency information and low-frequency information of the image to be corrected and the initial correction image.
Optionally, the processing unit comprises:
the first traversal subunit is used for respectively traversing the inspection image to be corrected and the initial correction image based on the low-frequency information, and extracting a fused low-frequency component obtained from the minimum value in the low-frequency components in the image;
the second traversal subunit is used for traversing the high-frequency information of the inspection image to be corrected and the initial correction image and determining a definition parameter based on the low-frequency component;
the fusion subunit is configured to fuse the high-frequency information based on the definition parameter to obtain a fused high-frequency component;
and the generating subunit is used for generating a target correction image based on the fused low-frequency component and the fused high-frequency component.
Optionally, the obtaining unit includes:
the acquisition subunit is used for acquiring the inspection image acquired by the image acquisition equipment;
and the image extraction subunit is used for extracting the image which meets the image distortion condition in the inspection image and determining the image as the inspection image to be corrected.
Compared with the prior art, the invention provides a color correction method and a system for traditional Chinese medicine inspection images, which comprises the steps of obtaining an inspection image to be corrected; inputting the inspection image to be corrected into a color correction model to obtain an initial correction image; respectively extracting high-frequency information and low-frequency information of the inspection image to be corrected and the initial correction image; and carrying out fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image. The invention realizes the fusion correction between the image to be corrected and the image generated by the model by using information fusion on the basis of the image generated by the color correction model, and the obtained corrected image can meet the requirements of traditional Chinese medicine inspection diagnosis on the precision and color content, thereby improving the precision of the corrected image.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic flow chart of a color correction method for inspection images in traditional Chinese medicine according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an eye image color correction result according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a color correction system for inspection images in traditional Chinese medicine 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 terms "first" and "second," and the like in the description and claims of the present invention and the above-described drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not set forth for a listed step or element but may include steps or elements not listed.
The embodiment of the invention provides a color correction method for a traditional Chinese medicine inspection image, which can be applied to a processing device for the traditional Chinese medicine inspection image and an acquisition device for the traditional Chinese medicine inspection image, namely, the color correction is carried out on the acquired inspection image which does not meet the requirements. Referring to fig. 1, a schematic flow chart of a color correction method for a traditional Chinese medical inspection image according to an embodiment of the present invention is shown, where the method may include the following steps:
s101, acquiring a to-be-corrected inspection image.
The inspection image to be corrected may be an image that does not satisfy the requirements of the traditional Chinese medicine diagnosis, such as an image with color distortion, and may mainly include an inspection image generated under the conditions of light leakage, color cast, and the like. Or, the image which satisfies the image distortion and is obtained by automatically screening the image acquired by the inspection image acquisition device, that is, the acquiring of the inspection image to be corrected includes: acquiring a visiting image acquired by image acquisition equipment; and extracting images meeting image distortion conditions in the inspection images, and determining the images as the inspection images to be corrected. The inspection image may be different depending on the diagnosis site, and may be a face image, a tongue image, an eye image, or the like. Since the precision required for the inspection diagnosis is high, the inspection image to be corrected in the embodiment of the present application is described as the inspection image data to be corrected for convenience of description.
And S102, inputting the inspection image to be corrected into a color correction model to obtain an initial correction image.
In the embodiment of the invention, the color correction of the inspection image to be corrected is realized based on the deep learning spirit network. However, since the conventional regression prediction of color correction coefficients using a machine learning algorithm or the fitting generation of an image to be corrected using a deep learning neural network is limited by the scale of the amount of training data. Therefore, in the embodiment of the present invention, the color correction model is preferably implemented by generating a confrontation network, the image data set to be corrected and the color normal image set are learned by fitting the generated confrontation network, and a corrected image with correct color information is generated.
S103, respectively extracting the high-frequency information and the low-frequency information of the inspection image to be corrected and the initial correction image.
And S104, carrying out fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image.
Based on the image generated by the network, namely after the initial correction image output by the color correction model is obtained, the fusion correction between the inspection image to be corrected and the initial correction image is carried out by utilizing a wavelet image fusion algorithm, so that the finally obtained target correction image can meet the requirements of the traditional Chinese medicine inspection diagnosis on the precision and the color content, and the correct implementation of the traditional Chinese medicine inspection diagnosis is ensured. The frequency of the image is an index of the intensity of change in the gray scale value, and is the gradient of the gray scale in the plane space. The low frequency is that the color changes slowly, that is, the gray scale changes slowly, and represents that the area is a continuously changing area, and the part is the low frequency information of the image. The high frequency information is an area with fast frequency change in the image, namely the high frequency information is an area with rich details in the image, and the low frequency information is an area with less details in the image. The wavelet transform is characterized in that the characteristics of some aspects of problems can be fully highlighted through transformation, the time (space) frequency can be locally analyzed, signals (functions) are gradually subjected to multi-scale refinement through telescopic translation, and finally the requirements of time subdivision at high frequency and frequency subdivision at low frequency can be met automatically.
In a possible implementation of the invention, the generation of the set of training data of the antagonistic network is first performed. Taking a specific operation as an example, a color-distorted image may be screened from 10 eye images of a single person, and a color-normal image with a relatively consistent structure may be screened from the color-distorted image, so as to generate an image data set to be corrected and a standard image data set required by the anti-network training, for example, 3960 image data sets to be corrected and 6176 image data sets. And then, the data sets are sent to an examination and various line countermeasure network for color correction model training, wherein the data ensures that the standard image data set contains structural information of a certain image in the image data to be corrected, but the image structural information does not need to be completely consistent. The two generators and the two discriminators are adopted, so that the image data set to be corrected can be converted again after being converted to generate the standard image data set, the situation that the image data set to be corrected can only generate the error of the same picture in the standard data set finally is avoided, and the color correction model is finally obtained.
For convenience of description, the generated countermeasure network includes two generators and two discriminators, wherein the two generators are represented by a first generation network and a second generation network, the two discriminators are represented by a first discrimination network and a second discrimination network, the first sample image set is an image data set to be corrected, and the second sample image set is a standard image data set, and the generated countermeasure network is trained by the following steps:
inputting the first sample image set into a first generation network to obtain a first sample output image;
inputting the first sample output image into a first judgment network to obtain a first judgment result;
correcting the first generated network according to the first judgment result to obtain a corrected first generated network;
inputting the second sample image set into a second generation network to obtain a second sample output image;
inputting the second sample output image into a second judgment network to obtain a second judgment result;
correcting the second generation network according to the second judgment result to obtain a corrected second generation network;
and fusing the modified first generation network and the modified second generation network to obtain the generation countermeasure network.
It should be noted that, when the style of the first sample output image is the style of the second sample, the first discrimination result corresponds to the first discrimination value; when the style of the first sample output image is not the second sample style, the first judgment result corresponds to the second judgment value. Correspondingly, the first discrimination network is further configured to compare the first sample output image with a preset output image to obtain a first loss result, where the preset output image may be obtained after the user performs manual correction processing on the sample image. That is, the first discrimination network is a permanent key network for determining whether the output image of the first sample is a real output image, and then the generated output image of the first sample and the original real output image are both input into the first discrimination network. When the first discrimination result is the first discrimination value, the fourth degree of the character between the first sample output image and the preset output image is higher, and when the first discrimination result is the second discrimination value, the similarity between the first sample output image and the preset output image is lower. The first generation network may be modified according to the similarity until the similarity between the first sample output image output by the first generation network and the preset output image meets the preset condition, and the corresponding first generation network is determined as the trained first generation network. For the processing of the second generation network, reference may be made to the processing of the first generation network described above.
Aiming at the conditions that the generation of the countermeasure network influences the correction effect caused by the scale of the training data set and the accuracy of the image finally generated by the network possibly cannot restore the accuracy of the original image, the image to be corrected and the initial corrected image processed by the model are subjected to secondary fusion correction by using wavelet change in the embodiment of the invention, and certainly, fusion correction can be realized by using other processing modes. Specifically, in the embodiment of the present invention, wavelet decomposition is performed on the inspection image to be corrected and the initial correction image, so as to obtain high frequency information and low frequency information of the image to be corrected and the initial correction image, respectively. Correspondingly, the performing the fusion processing on the high-frequency information and the low-frequency information to obtain the target correction image includes: respectively traversing the inspection image to be corrected and the initial correction image based on the low-frequency information, and extracting a fused low-frequency component obtained from the minimum value in the low-frequency components in the image; traversing the high-frequency information of the inspection image to be corrected and the initial correction image, and determining a definition parameter based on the low-frequency component; fusing the high-frequency information based on the definition parameters to obtain fused high-frequency components; and generating a target correction image based on the fused low-frequency component and the fused high-frequency component.
For example, after acquiring the inspection image to be corrected, and obtaining the initial correction image through the color correction model, the wavelet decomposition is performed on the image to be corrected and the initial correction image by using 4-layer wavelet transform, so as to generate a low-frequency component layer and a high-frequency component layer. And traversing the images aiming at the low-frequency components of the images to be corrected and the initial corrected images, and obtaining the fused low-frequency components by obtaining the minimum value in the low-frequency components. Aiming at the high-frequency components of the image to be corrected and the initial corrected image, firstly, calculating a definition matrix of the image truth problem, wherein the definition calculating method is based on the image contrast concept and is shown as the formula (1):
C＝(LP-LB)/LB＝LH/LBformula (1)
Wherein L isPIs the local gray scale of the image, LBThe local background gray scale of the image is equivalent to the low frequency component of the image after wavelet decomposition, and therefore, L is knownHThe image is subjected to wavelet decomposition to obtain high-frequency components, namely, the residual image edge, texture and other detail information after the low-frequency components of the image are subtracted, and C is the contrast. In the embodiment of the invention, the local gray scale is defined as a matrix window with the size of 9 x 9, the image to be corrected and the high-frequency component of the image after model correction are traversed, and the square sum of the ratio of the high-frequency component to the low-frequency component in the window is obtained to be the final definition measurement index, namely the definition parameter. And then on the basis of the generated definition matrix, comparing the definition of the image to be corrected with that of the image after model correction, and taking the high-frequency component of the image with higher definition to perform high-frequency component fusion. And finally, fusing the fused low-frequency component and the high-frequency component through inverse wavelet transform to generate a final target correction image.
Referring to fig. 2, which is a schematic diagram illustrating a color correction result of an eye image according to an embodiment of the present invention, in fig. 2, a first row of images is an image to be corrected, and a second row of images is a target correction image. As can be seen from FIG. 2, the invention realizes a general color correction algorithm for multi-color distortion images for the sighting diagnosis by generating a countermeasure network and wavelet transform combination method on the premise of ensuring the accuracy of the corrected images, the method does not need preprocessing such as image registration, and has better color correction effect on the conditions of multi-color distortion, such as image color cast, brightness, light leakage, and the like, and the finally generated color correction images meet the requirements of Chinese medical experts on the sighting diagnosis, thereby ensuring the correct implementation of the sighting diagnosis.
Referring to fig. 3, in an embodiment of the present invention, a color correction system for a traditional Chinese medical inspection image is provided, including:
an acquisition unit 10 for acquiring a prospective image to be corrected;
a model processing unit 20, configured to input the inspection image to be corrected to a color correction model, so as to obtain an initial correction image;
an extracting unit 30 for extracting high frequency information and low frequency information of the inspection image to be corrected and the initial correction image, respectively;
and the processing unit 40 is configured to perform fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image.
On the basis of the above embodiment, the color correction model includes generating a confrontation network, wherein the system further includes a model training unit, and the model training unit is specifically configured to:
inputting a first sample image set into a first generation network to obtain a first sample output image, wherein the first sample image set is an image data set to be corrected;
inputting the first sample output image into a first judgment network to obtain a first judgment result;
correcting the first generated network according to the first judgment result to obtain a corrected first generated network;
inputting a second sample image set into a second generation network to obtain a second sample output image, wherein the second sample image set is a standard image data set;
inputting the second sample output image into a second judgment network to obtain a second judgment result;
correcting the second generation network according to the second judgment result to obtain a corrected second generation network;
and fusing the modified first generation network and the modified second generation network to obtain the generation countermeasure network.
On the basis of the foregoing embodiment, the extraction unit is specifically configured to:
and performing wavelet decomposition on the inspection image to be corrected and the initial correction image to respectively obtain high-frequency information and low-frequency information of the image to be corrected and the initial correction image.
Optionally, the processing unit comprises:
the first traversal subunit is used for respectively traversing the inspection image to be corrected and the initial correction image based on the low-frequency information, and extracting a fused low-frequency component obtained from the minimum value in the low-frequency components in the image;
the second traversal subunit is used for traversing the high-frequency information of the inspection image to be corrected and the initial correction image and determining a definition parameter based on the low-frequency component;
the fusion subunit is configured to fuse the high-frequency information based on the definition parameter to obtain a fused high-frequency component;
and the generating subunit is used for generating a target correction image based on the fused low-frequency component and the fused high-frequency component.
On the basis of the above embodiment, the acquiring unit includes:
the acquisition subunit is used for acquiring the inspection image acquired by the image acquisition equipment;
and the image extraction subunit is used for extracting the image which meets the image distortion condition in the inspection image and determining the image as the inspection image to be corrected.
The invention provides a color correction system for traditional Chinese medicine inspection images, which comprises the steps of obtaining an inspection image to be corrected; inputting the inspection image to be corrected into a color correction model to obtain an initial correction image; respectively extracting high-frequency information and low-frequency information of the inspection image to be corrected and the initial correction image; and carrying out fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image. The invention realizes the fusion correction between the image to be corrected and the image generated by the model by using information fusion on the basis of the image generated by the color correction model, and the obtained corrected image can meet the requirements of traditional Chinese medicine inspection diagnosis on the precision and color content, thereby improving the precision of the corrected image.
Based on the foregoing embodiments, embodiments of the present application provide a computer-readable storage medium storing one or more programs, which are executable by one or more processors, to implement the steps of the color correction method for a chinese medical inspection image as described in any one of the above.
The embodiment of the invention also provides electronic equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the steps of the traditional Chinese medicine inspection image color correction method realized when the processor executes the program.
The Processor or the CPU may be at least one of an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Central Processing Unit (CPU), a controller, a microcontroller, and a microprocessor. It is understood that the electronic device implementing the above-mentioned processor function may be other electronic devices, and the embodiments of the present application are not particularly limited.
The computer storage medium/Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a magnetic Random Access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read-Only Memory (CD-ROM); but may also be various terminals such as mobile phones, computers, tablet devices, personal digital assistants, etc., that include one or any combination of the above-mentioned memories.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all functional units in the embodiments of the present application may be integrated into one processing module, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit. Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: various media capable of storing program codes, such as a removable Memory device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, and an optical disk.
The methods disclosed in the several method embodiments provided in the present application may be combined arbitrarily without conflict to obtain new method embodiments.
Features disclosed in several of the product embodiments provided in the present application may be combined in any combination to yield new product embodiments without conflict.
The features disclosed in the several method or apparatus embodiments provided in the present application may be combined arbitrarily, without conflict, to arrive at new method embodiments or apparatus embodiments.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
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. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A color correction method for traditional Chinese medicine inspection images is characterized by comprising the following steps:
acquiring a to-be-corrected inspection image;
inputting the inspection image to be corrected into a color correction model to obtain an initial correction image;
respectively extracting high-frequency information and low-frequency information of the inspection image to be corrected and the initial correction image;
and carrying out fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image.
2. The method of claim 1, wherein the color correction model comprises a generative confrontation network, wherein the generative confrontation network is trained by:
inputting a first sample image set into a first generation network to obtain a first sample output image, wherein the first sample image set is an image data set to be corrected;
inputting the first sample output image into a first judgment network to obtain a first judgment result;
correcting the first generated network according to the first judgment result to obtain a corrected first generated network;
inputting a second sample image set into a second generation network to obtain a second sample output image, wherein the second sample image set is a standard image data set;
inputting the second sample output image into a second judgment network to obtain a second judgment result;
correcting the second generation network according to the second judgment result to obtain a corrected second generation network;
and fusing the modified first generation network and the modified second generation network to obtain the generation countermeasure network.
3. The method according to claim 1, wherein said extracting high frequency information and low frequency information of said inspection image to be corrected and said initial correction image, respectively, comprises:
and performing wavelet decomposition on the inspection image to be corrected and the initial correction image to respectively obtain high-frequency information and low-frequency information of the image to be corrected and the initial correction image.
4. The method according to claim 3, wherein the fusing the high frequency information and the low frequency information to obtain a target correction image comprises:
respectively traversing the inspection image to be corrected and the initial correction image based on the low-frequency information, and extracting a fused low-frequency component obtained from the minimum value in the low-frequency components in the image;
traversing the high-frequency information of the inspection image to be corrected and the initial correction image, and determining a definition parameter based on the low-frequency component;
fusing the high-frequency information based on the definition parameters to obtain fused high-frequency components;
and generating a target correction image based on the fused low-frequency component and the fused high-frequency component.
5. The method of claim 1, wherein said acquiring a review image to be corrected comprises:
acquiring a visiting image acquired by image acquisition equipment;
and extracting images meeting image distortion conditions in the inspection images, and determining the images as the inspection images to be corrected.
6. A color correction system for traditional Chinese medicine inspection images is characterized by comprising:
an acquisition unit for acquiring a prospective image to be corrected;
the model processing unit is used for inputting the inspection image to be corrected into the color correction model to obtain an initial correction image;
an extraction unit, configured to extract high-frequency information and low-frequency information of the inspection image to be corrected and the initial correction image, respectively;
and the processing unit is used for carrying out fusion processing on the high-frequency information and the low-frequency information to obtain a target correction image.
7. The system of claim 6, wherein the color correction model comprises a generative confrontation network, wherein the system further comprises a model training unit, the model training unit being configured to:
inputting a first sample image set into a first generation network to obtain a first sample output image, wherein the first sample image set is an image data set to be corrected;
inputting the first sample output image into a first judgment network to obtain a first judgment result;
correcting the first generated network according to the first judgment result to obtain a corrected first generated network;
inputting a second sample image set into a second generation network to obtain a second sample output image, wherein the second sample image set is a standard image data set;
inputting the second sample output image into a second judgment network to obtain a second judgment result;
correcting the second generation network according to the second judgment result to obtain a corrected second generation network;
and fusing the modified first generation network and the modified second generation network to obtain the generation countermeasure network.
8. The system according to claim 6, wherein the extraction unit is specifically configured to:
and performing wavelet decomposition on the inspection image to be corrected and the initial correction image to respectively obtain high-frequency information and low-frequency information of the image to be corrected and the initial correction image.
9. The system of claim 8, wherein the processing unit comprises:
the first traversal subunit is used for respectively traversing the inspection image to be corrected and the initial correction image based on the low-frequency information, and extracting a fused low-frequency component obtained from the minimum value in the low-frequency components in the image;
the second traversal subunit is used for traversing the high-frequency information of the inspection image to be corrected and the initial correction image and determining a definition parameter based on the low-frequency component;
the fusion subunit is configured to fuse the high-frequency information based on the definition parameter to obtain a fused high-frequency component;
and the generating subunit is used for generating a target correction image based on the fused low-frequency component and the fused high-frequency component.
10. The system of claim 6, wherein the obtaining unit comprises:
the acquisition subunit is used for acquiring the inspection image acquired by the image acquisition equipment;
and the image extraction subunit is used for extracting the image which meets the image distortion condition in the inspection image and determining the image as the inspection image to be corrected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110566849.5A CN113240606B (en) | 2021-05-24 | 2021-05-24 | Traditional Chinese medicine inspection image color correction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110566849.5A CN113240606B (en) | 2021-05-24 | 2021-05-24 | Traditional Chinese medicine inspection image color correction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113240606A true CN113240606A (en) | 2021-08-10 |
| CN113240606B CN113240606B (en) | 2024-06-21 |
Family
ID=77138499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110566849.5A Active CN113240606B (en) | 2021-05-24 | 2021-05-24 | Traditional Chinese medicine inspection image color correction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113240606B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114157815A (en) * | 2022-02-10 | 2022-03-08 | 博奥生物集团有限公司 | Inspection imaging system and inspection image acquisition method |
| CN115314604A (en) * | 2022-10-12 | 2022-11-08 | 杭州魔点科技有限公司 | Method and system for generating color correction matrix, electronic device and storage medium |
| CN118037609A (en) * | 2024-04-11 | 2024-05-14 | 康亲(厦门)控股有限公司 | Color correction method, device and equipment for facial image and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004153473A (en) * | 2002-10-30 | 2004-05-27 | Fuji Photo Film Co Ltd | Picture data correction device and method therefor |
| US20110043603A1 (en) * | 2006-01-18 | 2011-02-24 | Technion Research & Development Foundation Ltd. | System And Method For Dehazing |
| US20110206289A1 (en) * | 2010-02-22 | 2011-08-25 | Salih Dikbas | Guaranteed-Rate Tiled Image Data Compression |
| CN110148095A (en) * | 2019-05-14 | 2019-08-20 | 北京科技大学 | A kind of underwater picture Enhancement Method and enhancement device |
| CN110660038A (en) * | 2019-09-09 | 2020-01-07 | 山东工商学院 | Multispectral image and panchromatic image fusion method based on generation countermeasure network |
| CN111383299A (en) * | 2018-12-28 | 2020-07-07 | Tcl集团股份有限公司 | Image processing method and device and computer readable storage medium |
| CN111739077A (en) * | 2020-06-15 | 2020-10-02 | 大连理工大学 | Monocular underwater image depth estimation and color correction method based on depth neural network |
| WO2020258668A1 (en) * | 2019-06-26 | 2020-12-30 | 平安科技（深圳）有限公司 | Facial image generation method and apparatus based on adversarial network model, and nonvolatile readable storage medium and computer device |
| CN112164005A (en) * | 2020-09-24 | 2021-01-01 | Oppo（重庆）智能科技有限公司 | Image color correction method, device, equipment and storage medium |
| CN112488971A (en) * | 2020-11-23 | 2021-03-12 | 石家庄铁路职业技术学院 | Medical image fusion method for generating countermeasure network based on spatial attention mechanism and depth convolution |
| CN112598582A (en) * | 2020-05-28 | 2021-04-02 | 西安诺瓦星云科技股份有限公司 | Image correction and correction data generation method, device and system and display method |
| CN112750531A (en) * | 2021-01-21 | 2021-05-04 | 广东工业大学 | Automatic inspection system, method, equipment and medium for traditional Chinese medicine |
| CN112767279A (en) * | 2021-02-01 | 2021-05-07 | 福州大学 | Underwater image enhancement method for generating countermeasure network based on discrete wavelet integration |
-
2021
- 2021-05-24 CN CN202110566849.5A patent/CN113240606B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004153473A (en) * | 2002-10-30 | 2004-05-27 | Fuji Photo Film Co Ltd | Picture data correction device and method therefor |
| US20110043603A1 (en) * | 2006-01-18 | 2011-02-24 | Technion Research & Development Foundation Ltd. | System And Method For Dehazing |
| US20110206289A1 (en) * | 2010-02-22 | 2011-08-25 | Salih Dikbas | Guaranteed-Rate Tiled Image Data Compression |
| CN111383299A (en) * | 2018-12-28 | 2020-07-07 | Tcl集团股份有限公司 | Image processing method and device and computer readable storage medium |
| CN110148095A (en) * | 2019-05-14 | 2019-08-20 | 北京科技大学 | A kind of underwater picture Enhancement Method and enhancement device |
| WO2020258668A1 (en) * | 2019-06-26 | 2020-12-30 | 平安科技（深圳）有限公司 | Facial image generation method and apparatus based on adversarial network model, and nonvolatile readable storage medium and computer device |
| CN110660038A (en) * | 2019-09-09 | 2020-01-07 | 山东工商学院 | Multispectral image and panchromatic image fusion method based on generation countermeasure network |
| CN112598582A (en) * | 2020-05-28 | 2021-04-02 | 西安诺瓦星云科技股份有限公司 | Image correction and correction data generation method, device and system and display method |
| CN111739077A (en) * | 2020-06-15 | 2020-10-02 | 大连理工大学 | Monocular underwater image depth estimation and color correction method based on depth neural network |
| CN112164005A (en) * | 2020-09-24 | 2021-01-01 | Oppo（重庆）智能科技有限公司 | Image color correction method, device, equipment and storage medium |
| CN112488971A (en) * | 2020-11-23 | 2021-03-12 | 石家庄铁路职业技术学院 | Medical image fusion method for generating countermeasure network based on spatial attention mechanism and depth convolution |
| CN112750531A (en) * | 2021-01-21 | 2021-05-04 | 广东工业大学 | Automatic inspection system, method, equipment and medium for traditional Chinese medicine |
| CN112767279A (en) * | 2021-02-01 | 2021-05-07 | 福州大学 | Underwater image enhancement method for generating countermeasure network based on discrete wavelet integration |
Non-Patent Citations (1)
| Title |
|---|
| 陈梦竹;岑翼刚;许家佗;崔龙涛;王文强;屠立平;黄景斌;荆聪聪;张建峰;: "基于图像处理的望诊面色自动识别研究", 中国中医药信息杂志, no. 12 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114157815A (en) * | 2022-02-10 | 2022-03-08 | 博奥生物集团有限公司 | Inspection imaging system and inspection image acquisition method |
| CN115314604A (en) * | 2022-10-12 | 2022-11-08 | 杭州魔点科技有限公司 | Method and system for generating color correction matrix, electronic device and storage medium |
| CN118037609A (en) * | 2024-04-11 | 2024-05-14 | 康亲(厦门)控股有限公司 | Color correction method, device and equipment for facial image and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113240606B (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113240606A (en) | Traditional Chinese medicine inspection image color correction method and system | |
| CN112017198B (en) | Right ventricle segmentation method and device based on self-attention mechanism multi-scale features | |
| CN105917353B (en) | Feature extraction and matching for biological identification and template renewal | |
| CN111667459B (en) | Medical sign detection method, system, terminal and storage medium based on 3D variable convolution and time sequence feature fusion | |
| CN115311186B (en) | Cross-scale attention confrontation fusion method and terminal for infrared and visible light images | |
| CN109146891B (en) | Hippocampus segmentation method and device applied to MRI and electronic equipment | |
| CN111784665B (en) | OCT image quality evaluation method, system and device based on Fourier transform | |
| CN111738265A (en) | Semantic segmentation method, system, medium, and electronic device for RGB-D image | |
| Zhang et al. | Pixel‐wise dense detector for image inpainting | |
| Ma et al. | Dynamic gesture contour feature extraction method using residual network transfer learning | |
| CN117191816B (en) | Method and device for detecting surface defects of electronic component based on multispectral fusion | |
| CN105574844B (en) | Rdaiation response Function Estimation method and apparatus | |
| CN118015190A (en) | Autonomous construction method and device of digital twin model | |
| He et al. | Image processing design and algorithm research based on cloud computing | |
| Belhedi et al. | Adaptive scene‐text binarisation on images captured by smartphones | |
| CN116958539A (en) | Model training and image processing method, device and equipment for vessel tree segmentation | |
| CN109190506A (en) | It is a kind of based on core is sparse and the EO-1 hyperion object detection method of space constraint | |
| CN115115900A (en) | Training method, device, equipment, medium and program product of image reconstruction model | |
| Yang et al. | Progressive image dehazing network based on dual feature extraction modules | |
| CN103955610B (en) | Medical image computer-aided analysis method | |
| Lei et al. | A monocular image depth estimation method based on weighted fusion and point‐wise convolution | |
| CN116129206B (en) | Processing method and device for image decoupling characterization learning and electronic equipment | |
| Xu | Image Fusion and Stylization Processing Based on Multiscale Transformation and Convolutional Neural Network | |
| CN107341799A (en) | Diagnostic data acquisition methods and device | |
| Wei et al. | NMPE: a normalized metric for measuring generalized spatial distortion of multispectral panshapening fusion |
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 |