CN108898581A - A kind of ear nose larynx check image screening control system, method and application - Google Patents
A kind of ear nose larynx check image screening control system, method and application Download PDFInfo
- Publication number
- CN108898581A CN108898581A CN201810580982.4A CN201810580982A CN108898581A CN 108898581 A CN108898581 A CN 108898581A CN 201810580982 A CN201810580982 A CN 201810580982A CN 108898581 A CN108898581 A CN 108898581A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- value
- region
- pure tone
- 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.)
- Pending
Links
- 210000000867 larynx Anatomy 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012216 screening Methods 0.000 title claims abstract description 30
- 238000012076 audiometry Methods 0.000 claims abstract description 59
- 210000001331 nose Anatomy 0.000 claims abstract description 35
- 208000009205 Tinnitus Diseases 0.000 claims abstract description 29
- 231100000886 tinnitus Toxicity 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000003745 diagnosis Methods 0.000 claims abstract description 25
- 210000003928 nasal cavity Anatomy 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 210000005069 ears Anatomy 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000003780 insertion Methods 0.000 claims description 6
- 230000037431 insertion Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000013316 zoning Methods 0.000 claims description 6
- 238000005286 illumination Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 101100177269 Arabidopsis thaliana HCAR gene Proteins 0.000 claims description 3
- 230000003190 augmentative effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 230000007115 recruitment Effects 0.000 claims description 3
- 230000008901 benefit Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 claims description 2
- 238000002474 experimental method Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 4
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 229920000742 Cotton Polymers 0.000 description 1
- 238000005054 agglomeration Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 210000002939 cerumen Anatomy 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- 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
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to field of medical technology, discloses a kind of ear nose larynx check image screening control system method and application, control system include：Photographing module, lighting module, main control module, image processing module, tinnitus diagnosis module, nasal cavity diagnostic module, throat diagnostic module, display module；Method includes：The noise image of ear, nasal cavity, throat check point image is acquired using the basic model of the fully differential restructing algorithm based on non-local mean regular terms by photographing module；By image processing module, the image of photographing module acquisition is handled；By tinnitus diagnosis module using pure tone audiometry detection method to the pure tone audiometry detection of ears.The present invention greatly improves the reliability of check image, and advantageous doctor accurately diagnoses；The match time for substantially reducing tinnitus frequency by tinnitus diagnosis module simultaneously, fault-tolerant ability is increased, solves the possibility that tinnitus frequency existing in the prior art is missed；Improve diagnosis effect.
Description
Technical field
The invention belongs to field of medical technology more particularly to a kind of ear nose larynx check image screening control system, method and
Using.
Background technique
Currently, the prior art commonly used in the trade is such：
Ear nose larynx inspection must be careful because ear,nose & throat be all it is deep tiny chamber hole, it is special to you must use
Lighting device and examination apparatus are checked that there are commonly the inspecting lamp of 100 watts of agglomeration optical lens, frontal mirror, otoscope, air-blowing ears
Mirror, gun-shaped forceps, cotton applicator, cerumen hook, spatula, nasal endoscope, posterior rhinoscope, indirect laryngoscope, tuning fork, sprayer etc..However, existing
Ear nose larynx check image obtains unintelligible, poor reliability, influences the diagnosis of doctor；It is existing low to the diagnosis efficiency of tinnitus simultaneously,
Tinnitus frequency is easy to be missed, and causes diagnosis effect poor.
In conclusion problem of the existing technology is：
Existing ear nose larynx check image obtains unintelligible, poor reliability, influences the diagnosis of doctor；It is existing simultaneously to tinnitus
Diagnosis efficiency is low, and tinnitus frequency is easy to be missed, and causes diagnosis effect poor.
In the prior art, the image of ear nose larynx inspection, the diagnosis of tinnitus data existence and unique solution Absolute Value Equation, provide
Algorithm simultaneously carries out corresponding convergence.All solutions can not be found out；For there are the Absolute Value Equation of multiple solutions how
All solutions are found out, this is a relatively difficult problem.To influence detection effect.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of ear nose larynx check image screening control system methods
And application.
The invention is realized in this way a kind of ear nose larynx check image screening control method, the ear nose larynx check image
Screening control method includes：
Ear is acquired using the basic model of the fully differential restructing algorithm based on non-local mean regular terms by photographing module
Piece, the noise image of nasal cavity, throat check point image；Fully differential restructing algorithm based on non-local mean regular terms it is basic
Model is expressed as：Wherein α is the weight of non-local mean regular terms, and Du is
The gradient of image；
By image processing module, wherein one page text image is taken out from text image set P, size M*N, into
Row binary conversion treatment, is denoted as X, handles the image of photographing module acquisition；
By tinnitus diagnosis module using pure tone audiometry detection method to the pure tone audiometry detection of ears；
By display module, the text coverage rate in each region, finally obtains the company in the region in the set of zoning
Logical area matrix, and carry out image information display.
Further, photographing module is reconstructed using the noise image of acquisition image based on the fully differential of non-local mean regular terms
Algorithm specifically includes：
1) basic model of the fully differential restructing algorithm based on non-local mean regular terms is expressed as：
Wherein α is the weight of non-local mean regular terms, and Du is the gradient of image, by introducing auxiliary variable Du=w, u
=x, and can be obtained using Augmented Lagrange method：
Wherein α, β and θ respectively indicate the coefficient of corresponding penalty term, and v, γ and λ indicate corresponding Lagrange multiplier,
By being divided into w, u, tri- subproblems of x are iterated solution；
2) by the solution to u subproblem, to obtain the new iterative reconstruction value of image u, concrete model is represented by：
uk+1=uk-ηd；
Wherein η=abs (dTd/dTGd optimal step size, G=(β D) are indicatedTD+θI+μATA), I is unit matrix, d=DT(β
Du-v)-γ+θ(u-x)-βDTw+AT(μ (Au-y)-λ) is gradient direction, and k obtains current iteration knot for indexing the number of iterations
Fruit uk+1Afterwards, subsequent processes are sent to, for judging whether iterated conditional meets and assume to handle more.
Further, the image processing method of image processing module includes：
Step 1, takes out wherein one page text image from text image set P, and size M*N is carried out at binaryzation
Reason, is denoted as X；
Two-value text image X is divided into the region of M1*N1, X by step 2i(i=1,2,3 ..., Nmax) indicate subregion after
Image some region, NmaxIndicate the maximum number of original image subregion, NmaxIt is calculated by following formula：
Step 3 calculates text coverage rate k for each region after picture portion；Text coverage rate refers to this
The number of black pixel point accounts for the ratio of pixel total number in region, the text coverage rate k in some region be less than previously according to
Test the threshold value t of setting, then it is assumed that the block text character number is less, and Texture complication is lower, is not suitable for embedding in this region
Enter watermark information, to the block without any processing；K is greater than preset threshold value t, then the region is as an insertion water
The effective coverage of print, and the region is added in the set WX of effective coverage；Enable WXi(i=1,2,3 ..., Mmax) indicate some
Effective coverage, MmaxIndicate the total quantity of effective coverage in text image；
Step 4 enables Z indicate the maximum watermark capacity that can be embedded in text image, then Z is calculate by the following formula
It arrives：
Z=Mmax*z；
Wherein, z indicates the watermark capacity that each region can be embedded in, MmaxIndicate the number of effective coverage；Watermark data
Capacity is Z '=m*n, and updating remaining watermark capacity dz, dz=dz-Z, the dz initial value for needing to be embedded in is Z '：
Step 5 successively takes out a region WX from the set of effective coveragei, by WXiCarry out piecemeal operation.
Further, the method for display module display acquisition image information, including：
Zoning set XiIn each region text coverage rate k, the text coverage rate k in some region is greater than scheduled
Threshold value t, then it is assumed that include watermark information in the region, which is added to the regional ensemble WX comprising watermark informationi(i
=1,2,3 ..., Mmax) in, MmaxIndicate the number of effective coverage in two-value text image；The text coverage rate k in the region is less than
Threshold value t, then it is assumed that the region does not include watermark information, does not carry out any processing to the region；The calculation of text coverage rate k
Calculation when being embedded in watermark is identical；Obtain the regional ensemble WX comprising watermark informationi(i=1,2,3 ..., Mmax), it is right
Set WXiIn a region be divided into identical 64 sub-blocks of size, calculate the connection area of each piecemeal, finally obtain the area
The connected surface product matrix M in domain.
Further, pure tone audiometry detection method includes：
The first step, problem definition and parameter value：Assuming that problem is to minimize, and the following minf (x) of form, s.t. xi∈xi,
I=1,2 ..., N, f (x) are objective functions, and x is by decision variable xiThe solution vector (i=1,2 ..., N) of composition, each change
The codomain of amount is Xi：xi L≤Xi≤xi U, N is decision variable number；
Parameter has：The size of pure tone audiometry value data base, study pure tone audiometry value data base probability, each parameter is in the first step
It is intended to be initialised；
Second step initializes pure tone audiometry value data base：
HMS pure tone audiometry value x is generated at random1, x2..., xHMSIt is put into pure tone audiometry value data base, the memory of pure tone audiometry value
Library is analogous to the population in genetic algorithm；
Third step generates a new pure tone audiometry value：
Generate new pure tone audiometry value xi'=(x '1, x '2..., x 'N), generating new pure tone audiometry value XnewWhen, setting one
A probability WSR generates a random number R and, if Rand < WSR, to the worst solution in current pure tone audiometry value library HM
It is updated；Otherwise, the preferably solution in current pure tone audiometry value library HM is updated, meanwhile, it is general during population recruitment
Rate is chosen in feasible zone, remembers that improved algorithm is HSWB, each tone x of new pure tone audiometry valuei' (i=1,2 ...,
N it) is generated by following mechanism：Learn pure tone audiometry value data base；
First variable x ' of new explanation1There is the probability of HMCR (x ' in HM1~x1 HMS) any one value, have 1-
The probability of HCMR is selected from any one value of HM outer (and in range of variables), likewise, the generating mode of other variables is as follows：
Rand indicates the equally distributed random number on [0,1]；
Secondly, if new pure tone audiometry value xi' come from pure tone audiometry value data base, row tone fine tuning, concrete operations
It is as follows：
4th step updates pure tone audiometry value data base
New explanation in third step is assessed, if one worst better than the functional value in HM, new explanation is updated
Into HM, concrete operations are as follows：
5th step, checks whether and reaches termination condition；
Third step and the 4th step are repeated, until detection the number of iterations reaches Tmax.
Another object of the present invention is to provide a kind of computer for realizing the ear nose larynx check image screening control method
Program.
Another object of the present invention is to provide a kind of Information Number for realizing the ear nose larynx check image screening control method
According to processing terminal.
Another object of the present invention is to provide a kind of computer readable storage medium, including instruction, when its on computers
When operation, so that computer executes the ear nose larynx check image screening control method.
Another object of the present invention is to provide a kind of ear nose larynx check image screening control system：
Photographing module is connect with main control module, for passing through miniature webcam to patient's ear, nasal cavity, throat insertion section
Position is acquired image data；
Lighting module is connect with main control module, for providing illumination functions to miniature webcam by miniature lighting lamp；
Main control module, with photographing module, lighting module, image processing module, tinnitus diagnosis module, nasal cavity diagnostic module,
Throat diagnostic module, display module connection, work normally for dispatching modules；
Image processing module is connect with main control module, for handling the image that photographing module acquires；
Tinnitus diagnosis module, connect with main control module, for being diagnosed by pure tone test to tinnitus；
Nasal cavity diagnostic module, connect with main control module, diagnoses for the nasal cavity image by acquiring to nasal cavity；
Throat diagnostic module, connect with main control module, diagnoses for the throat image by acquiring to throat；
Display module is connect with main control module, for showing the image information of acquisition.
Another object of the present invention is to provide a kind of ear nose for being equipped with the ear nose larynx check image screening control system
Larynx check image screening controls equipment.
Advantages of the present invention and good effect are：
The present invention improves clarity, precision, the integrality of image by image processing module, greatly improves check image
Reliability, advantageous doctor accurately diagnoses；The match time of tinnitus frequency is substantially reduced by tinnitus diagnosis module simultaneously,
Fault-tolerant ability is increased, solves the possibility that tinnitus frequency existing in the prior art is missed；Improve diagnosis effect.
Algorithm after application enhancements of the present invention has solved Non-Linear Programming and Absolute Value Equation, improve numerical stability,
Arithmetic speed and precision, and there is faster convergence rate；For Absolute Value Equation, improved algorithm can find former problem
Solution as much as possible.Realize the accuracy of detection data.
Detailed description of the invention
Fig. 1 is ear nose larynx check image screening Control system architecture block diagram provided in an embodiment of the present invention.
In figure：1, photographing module；2, lighting module；3, main control module；4, image processing module；5, tinnitus diagnosis module；
6, nasal cavity diagnostic module；7, throat diagnostic module；8, display module.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1, ear nose larynx check image screening control system provided by the invention includes：Photographing module 1, illumination mould
Block 2, main control module 3, image processing module 4, tinnitus diagnosis module 5, nasal cavity diagnostic module 6, throat diagnostic module 7, display mould
Block 8.
Photographing module 1 is connect with main control module 3, for being inserted by miniature webcam to patient's ear, nasal cavity, throat
Acquire image data；
Lighting module 2 is connect with main control module 3, for providing illumination functions to miniature webcam by miniature lighting lamp；
Main control module 3 is diagnosed with photographing module 1, lighting module 2, image processing module 4, tinnitus diagnosis module 5, nasal cavity
Module 6, throat diagnostic module 7, display module 8 connect, and work normally for dispatching modules；
Image processing module 4 is connect with main control module 3, and the image for acquiring to photographing module 1 is handled；
Tinnitus diagnosis module 5 is connect with main control module 3, for being diagnosed by pure tone test to tinnitus；
Nasal cavity diagnostic module 6 is connect with main control module 3, is diagnosed for the nasal cavity image by acquiring to nasal cavity；
Throat diagnostic module 7 is connect with main control module 3, is diagnosed for the throat image by acquiring to throat；
Display module 8 is connect with main control module 3, for showing the image information of acquisition.
Below with reference to concrete analysis, the invention will be further described.
Ear nose larynx check image screening control method provided in an embodiment of the present invention includes：
Ear is acquired using the basic model of the fully differential restructing algorithm based on non-local mean regular terms by photographing module
Piece, the noise image of nasal cavity, throat check point image；Fully differential restructing algorithm based on non-local mean regular terms it is basic
Model is expressed as：Wherein α is the weight of non-local mean regular terms, and Du is
The gradient of image；
By image processing module, wherein one page text image is taken out from text image set P, size M*N, into
Row binary conversion treatment, is denoted as X, handles the image of photographing module acquisition；
By tinnitus diagnosis module using pure tone audiometry detection method to the pure tone audiometry detection of ears；
By display module, the text coverage rate in each region, finally obtains the company in the region in the set of zoning
Logical area matrix, and carry out image information display.
Photographing module is had using the noise image of acquisition image based on the fully differential restructing algorithm of non-local mean regular terms
Body includes：
1) basic model of the fully differential restructing algorithm based on non-local mean regular terms is expressed as：
Wherein α is the weight of non-local mean regular terms, and Du is the gradient of image, by introducing auxiliary variable Du=w, u
=x, and can be obtained using Augmented Lagrange method：
Wherein α, β and θ respectively indicate the coefficient of corresponding penalty term, and v, γ and λ indicate corresponding Lagrange multiplier,
By being divided into w, u, tri- subproblems of x are iterated solution；
2) by the solution to u subproblem, to obtain the new iterative reconstruction value of image u, concrete model is represented by：
uk+1=uk-ηd；
Wherein η=abs (dTd/dTGd optimal step size, G=(β D) are indicatedTD+θI+μATA), I is unit matrix, d=DT(β
Du-v)-γ+θ(u-x)-βDTw+AT(μ (Au-y)-λ) is gradient direction, and k obtains current iteration knot for indexing the number of iterations
Fruit uk+1Afterwards, subsequent processes are sent to, for judging whether iterated conditional meets and assume to handle more.
The image processing method of image processing module includes：
Step 1, takes out wherein one page text image from text image set P, and size M*N is carried out at binaryzation
Reason, is denoted as X；
Two-value text image X is divided into the region of M1*N1, X by step 2i(i=1,2,3 ..., Nmax) indicate subregion after
Image some region, NmaxIndicate the maximum number of original image subregion, NmaxIt is calculated by following formula：
Step 3 calculates text coverage rate k for each region after picture portion；Text coverage rate refers to this
The number of black pixel point accounts for the ratio of pixel total number in region, the text coverage rate k in some region be less than previously according to
Test the threshold value t of setting, then it is assumed that the block text character number is less, and Texture complication is lower, is not suitable for embedding in this region
Enter watermark information, to the block without any processing；K is greater than preset threshold value t, then the region is as an insertion water
The effective coverage of print, and the region is added in the set WX of effective coverage；Enable WXi(i=1,2,3 ..., Mmax) indicate some
Effective coverage, MmaxIndicate the total quantity of effective coverage in text image；
Step 4 enables Z indicate the maximum watermark capacity that can be embedded in text image, then Z is calculate by the following formula
It arrives：
Z=Mmax*z；
Wherein, z indicates the watermark capacity that each region can be embedded in, MmaxIndicate the number of effective coverage；Watermark data
Capacity is Z '=m*n, and updating remaining watermark capacity dz, dz=dz-Z, the dz initial value for needing to be embedded in is Z '：
Step 5 successively takes out a region WX from the set of effective coveragei, by WXiCarry out piecemeal operation.
The method of display module display acquisition image information, including：
Zoning set XiIn each region text coverage rate k, the text coverage rate k in some region is greater than scheduled
Threshold value t, then it is assumed that include watermark information in the region, which is added to the regional ensemble WX comprising watermark informationi(i
=1,2,3 ..., Mmax) in, MmaxIndicate the number of effective coverage in two-value text image；The text coverage rate k in the region is less than
Threshold value t, then it is assumed that the region does not include watermark information, does not carry out any processing to the region；The calculation of text coverage rate k
Calculation when being embedded in watermark is identical；Obtain the regional ensemble WX comprising watermark informationi(i=1,2,3 ..., Mmax), it is right
Set WXiIn a region be divided into identical 64 sub-blocks of size, calculate the connection area of each piecemeal, finally obtain the area
The connected surface product matrix M in domain.
Pure tone audiometry detection method includes：
The first step, problem definition and parameter value：Assuming that problem is to minimize, and the following min f (x) of form, s.t. xi∈
Xi, i=1,2 ..., N, f (x) is objective function, and x is by decision variable xiThe solution vector (i=1,2 ..., N) of composition, each
The codomain of variable is Xi：xi L≤Xi≤xi U, N is decision variable number；
Parameter has：The size of pure tone audiometry value data base, study pure tone audiometry value data base probability, each parameter is in the first step
It is intended to be initialised；
Second step initializes pure tone audiometry value data base：
HMS pure tone audiometry value x is generated at random1, x2..., xHMSIt is put into pure tone audiometry value data base, the memory of pure tone audiometry value
Library is analogous to the population in genetic algorithm；
Third step generates a new pure tone audiometry value：
Generate new pure tone audiometry value xi'=(x '1, x '2..., x 'N), generating new pure tone audiometry value XnewWhen, setting one
A probability WSR generates a random number R and, if Rand < WSR, to the worst solution in current pure tone audiometry value library HM
It is updated；Otherwise, the preferably solution in current pure tone audiometry value library HM is updated, meanwhile, it is general during population recruitment
Rate is chosen in feasible zone, remembers that improved algorithm is HSWB, each tone x of new pure tone audiometry valuei' (i=1,2 ...,
N it) is generated by following mechanism：Learn pure tone audiometry value data base；
First variable x of new explanation1' there is the probability of HMCR (x in HM1'~x1 HMS) any one value, have 1-
The probability of HCMR is selected from any one value of HM outer (and in range of variables), likewise, the generating mode of other variables is as follows：
Rand indicates the equally distributed random number on [0,1]；
Secondly, if new pure tone audiometry value x 'iFrom pure tone audiometry value data base, the fine tuning of row tone, concrete operations
It is as follows：
4th step updates pure tone audiometry value data base
New explanation in third step is assessed, if one worst better than the functional value in HM, new explanation is updated
Into HM, concrete operations are as follows：
5th step, checks whether and reaches termination condition；
Third step and the 4th step are repeated, until detection the number of iterations reaches Tmax.
When the present invention checks, by photographing module 1 using miniature webcam to patient's ear, nasal cavity, throat insertion acquisition
Image data；And it is equipped with lighting module 2 and provides illumination functions to miniature webcam；Main control module 3 dispatches image processing module 4
The image acquired to photographing module 1 is handled；Then, tinnitus is examined using pure tone test by tinnitus diagnosis module 5
It is disconnected；Nasal cavity is diagnosed according to the nasal cavity image of acquisition by nasal cavity diagnostic module 6；By throat diagnostic module 7 according to adopting
The throat image of collection diagnoses throat；Finally, passing through the image information of the display acquisition of display module 8.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or
Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to
Process described in the embodiment of the present invention or function.The computer can be general purpose computer, special purpose computer, computer network
Network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or from one
Computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from one
A web-site, computer, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)
Or wireless (such as infrared, wireless, microwave etc.) mode is carried out to another web-site, computer, server or data center
Transmission).The computer-readable storage medium can be any usable medium or include one that computer can access
The data storage devices such as a or multiple usable mediums integrated server, data center.The usable medium can be magnetic Jie
Matter, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid
State Disk (SSD)) etc..
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (10)
1. a kind of ear nose larynx check image screening control method, which is characterized in that the ear nose larynx check image screening controlling party
Method includes：
Ear, nose are acquired using the basic model of the fully differential restructing algorithm based on non-local mean regular terms by photographing module
The noise image of chamber, throat check point image；The basic model of fully differential restructing algorithm based on non-local mean regular terms
It is expressed as：Wherein α is the weight of non-local mean regular terms, and Du is image
Gradient；
By image processing module, wherein one page text image is taken out from text image set P, size M*N carries out two-value
Change processing, is denoted as X, handles the image of photographing module acquisition；
By tinnitus diagnosis module using pure tone audiometry detection method to the pure tone audiometry detection of ears；
By display module, the text coverage rate in each region, finally obtains the connected surface in the region in the set of zoning
Product matrix, and carry out image information display.
2. ear nose larynx check image screening control method as described in claim 1, which is characterized in that
Photographing module is specifically wrapped using the noise image of acquisition image based on the fully differential restructing algorithm of non-local mean regular terms
It includes：
1) basic model of the fully differential restructing algorithm based on non-local mean regular terms is expressed as：
Wherein α is the weight of non-local mean regular terms, and Du is the gradient of image, by introducing auxiliary variable Du=w, u=x,
And it can be obtained using Augmented Lagrange method：
Wherein α, β and θ respectively indicate the coefficient of corresponding penalty term, and v, γ and λ indicate corresponding Lagrange multiplier, pass through
It is divided into w, u, tri- subproblems of x are iterated solution；
2) by the solution to u subproblem, to obtain the new iterative reconstruction value of image u, concrete model is represented by：
uk+1=uk-ηd；
Wherein η=abs (dTd/dTGd optimal step size, G=(β D) are indicatedTD+θΙ+μATA), Ι is unit matrix, d=DT(βDu-
v)-γ+θ(u-x)-βDTw+AT(μ (Au-y)-λ) is gradient direction, and k obtains current iteration result u for indexing the number of iterationsk +1Afterwards, subsequent processes are sent to, for judging whether iterated conditional meets and assume to handle more.
3. ear nose larynx check image screening control method as described in claim 1, which is characterized in that
The image processing method of image processing module includes:
Step 1, takes out wherein one page text image from text image set P, and size M*N carries out binary conversion treatment, note
For X；
Two-value text image X is divided into the region of M1*N1, X by step 2i(i=1,2,3 ..., Nmax) indicate the image after subregion
Some region, NmaxIndicate the maximum number of original image subregion, NmaxIt is calculated by following formula：
Step 3 calculates text coverage rate k for each region after picture portion；Text coverage rate refers to the region
The number of middle black pixel point accounts for the ratio of pixel total number, and the text coverage rate k in some region is less than previously according to experiment
The threshold value t of setting, then it is assumed that the block text character number is less, and Texture complication is lower, is not suitable for being embedded in water in this region
Official seal breath, to the block without any processing；K is greater than preset threshold value t, then the region is embedded in watermark as one
Effective coverage, and the region is added in the set WX of effective coverage；Enable WXi(i=1,2,3 ..., Mmax) indicate some effectively
Region, MmaxIndicate the total quantity of effective coverage in text image；
Step 4 enables Z indicate the maximum watermark capacity that can be embedded in text image, then Z is calculate by the following formula to obtain：
Z=Mmax*z；
Wherein, z indicates the watermark capacity that each region can be embedded in, MmaxIndicate the number of effective coverage；The capacity of watermark data
For Z'=m*n, updating remaining watermark capacity dz, dz=dz-Z, the dz initial value for needing to be embedded in is Z '；
Step 5 successively takes out a region WX from the set of effective coveragei, by WXiCarry out piecemeal operation.
4. ear nose larynx check image screening control method as described in claim 1, which is characterized in that
The method of display module display acquisition image information, including：
Zoning set XiIn each region text coverage rate k, the text coverage rate k in some region is greater than scheduled threshold value
T, then it is assumed that include watermark information in the region, which is added to the regional ensemble WX comprising watermark informationi(i=1,
2,3,…,Mmax) in, MmaxIndicate the number of effective coverage in two-value text image；The text coverage rate k in the region is less than threshold value
T, then it is assumed that the region does not include watermark information, does not carry out any processing to the region；The calculation and water of text coverage rate k
Calculation when print insertion is identical；Obtain the regional ensemble WX comprising watermark informationi(i=1,2,3 ..., Mmax), to set
WXiIn a region be divided into identical 64 sub-blocks of size, calculate the connection area of each piecemeal, finally obtain the region
Connected surface product matrix M.
5. ear nose larynx check image screening control method as described in claim 1, which is characterized in that
Pure tone audiometry detection method includes：
The first step, problem definition and parameter value：Assuming that problem is to minimize, and the following minf (x) of form, s.t.xi∈Xi, i=1,
2 ..., N, f (x) are objective functions, and x is by decision variable xiThe value of solution vector (i=1,2 ..., N) of composition each variable
Domain is Xi:xi L≤Xi≤xi U, N is decision variable number；
Parameter has：The size of pure tone audiometry value data base, study pure tone audiometry value data base probability, each parameter are intended in the first step
It is initialised；
Second step initializes pure tone audiometry value data base：
HMS pure tone audiometry value x is generated at random1,x2,…,xHMSIt is put into pure tone audiometry value data base, pure tone audiometry value data base class
Than the population in genetic algorithm；
Third step generates a new pure tone audiometry value：
Generate new pure tone audiometry value xi'=(x1',x'2,…,x'N), generating new pure tone audiometry value XnewWhen, set one generally
Rate WSR generates a random number R and, if Rand<WSR then carries out the more worst solution in current pure tone audiometry value library HM
Newly；Otherwise, the preferably solution in current pure tone audiometry value library HM is updated, meanwhile, probability is can during population recruitment
It is chosen in row domain, remembers that improved algorithm is HSWB, each tone x of new pure tone audiometry valuei' (i=1,2 ..., N) pass through
Following mechanism generates:Learn pure tone audiometry value data base；
First variable x of new explanation1' there is the probability of HMCR (x in HM1'~x1 HMS) any one value, have 1-HCMR's
Probability is selected from any one value of HM outer (and in range of variables), likewise, the generating mode of other variables is as follows：
Rand indicates the equally distributed random number on [0,1]；
Secondly, if new pure tone audiometry value xi' come from pure tone audiometry value data base, the fine tuning of row tone, concrete operations are as follows：
4th step updates pure tone audiometry value data base
New explanation in third step is assessed, if one worst better than the functional value in HM, new explanation is updated to HM
In, concrete operations are as follows：
5th step, checks whether and reaches termination condition；
Third step and the 4th step are repeated, until detection the number of iterations reaches Tmax.
6. a kind of computer program for realizing ear nose larynx check image screening control method described in Claims 1 to 5 any one.
7. a kind of realize at the information data of ear nose larynx check image screening control method described in Claims 1 to 5 any one
Manage terminal.
8. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer is executed as weighed
Benefit requires ear nose larynx check image screening control method described in 1-5 any one.
9. a kind of ear nose larynx check image screening of ear nose larynx check image screening control method as described in claim 1 controls system
System, which is characterized in that ear nose larynx check image screening control system includes：
Photographing module is connect with main control module, for by miniature webcam to patient's ear, nasal cavity, throat insertion site into
Row acquisition image data；
Lighting module is connect with main control module, for providing illumination functions to miniature webcam by miniature lighting lamp；
Main control module, with photographing module, lighting module, image processing module, tinnitus diagnosis module, nasal cavity diagnostic module, throat
Diagnostic module, display module connection, work normally for dispatching modules；
Image processing module is connect with main control module, for handling the image that photographing module acquires；
Tinnitus diagnosis module, connect with main control module, for being diagnosed by pure tone test to tinnitus；
Nasal cavity diagnostic module, connect with main control module, diagnoses for the nasal cavity image by acquiring to nasal cavity；
Throat diagnostic module, connect with main control module, diagnoses for the throat image by acquiring to throat；
Display module is connect with main control module, for showing the image information of acquisition.
10. a kind of ear nose larynx check image screening for being equipped with ear nose larynx check image screening control system described in claim 9
Control equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810580982.4A CN108898581A (en) | 2018-06-07 | 2018-06-07 | A kind of ear nose larynx check image screening control system, method and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810580982.4A CN108898581A (en) | 2018-06-07 | 2018-06-07 | A kind of ear nose larynx check image screening control system, method and application |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108898581A true CN108898581A (en) | 2018-11-27 |
Family
ID=64344211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810580982.4A Pending CN108898581A (en) | 2018-06-07 | 2018-06-07 | A kind of ear nose larynx check image screening control system, method and application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108898581A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110244009A (en) * | 2019-06-18 | 2019-09-17 | 六盘水市食品药品检验检测所 | A kind of quick identification detection system and method for honey quality |
| CN111584065A (en) * | 2020-04-07 | 2020-08-25 | 上海交通大学医学院附属第九人民医院 | Noise hearing loss prediction and susceptible population screening method, device, terminal and medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013173574A1 (en) * | 2012-05-16 | 2013-11-21 | The Johns Hopkins University | Imaging system and method for use of same to determine metric scale of imaged bodily anatomy |
| CN103631758A (en) * | 2013-11-21 | 2014-03-12 | 陕西理工学院 | Method for solving non-linear programming and absolute value equation through improved harmony search algorithm |
| CN104637026A (en) * | 2015-02-10 | 2015-05-20 | 西安电子科技大学 | Watermark embedding and extracting method based on continuous multi-page document image |
| CN104771179A (en) * | 2015-03-20 | 2015-07-15 | 运城市康丽声医疗器械有限公司 | Intelligent diagnosis and treatment system for tinnitus and deafness |
| CN105469093A (en) * | 2015-12-07 | 2016-04-06 | 周升峰 | Intelligent electronic ear-nose-throat examining device and image processing method |
| CN205234439U (en) * | 2015-12-18 | 2016-05-18 | 威海东舟医疗器械股份有限公司 | Otolaryngology passes a sentence checkout system entirely |
| CN107481293A (en) * | 2017-06-16 | 2017-12-15 | 西安电子科技大学 | Based on the difference image compressed sensing reconstructing methods and intelligent terminal for assuming weighting more |
| CN107705257A (en) * | 2017-09-15 | 2018-02-16 | 重庆科技学院 | One kind is based on partial fractional differential graph of equation image contrast method |
| CN107720552A (en) * | 2017-10-16 | 2018-02-23 | 西华大学 | A kind of assembled architecture intelligence hanging method based on computer machine vision |
| US20180085002A1 (en) * | 2013-03-11 | 2018-03-29 | Carestream Dental Technology Topco Limited | Method and System For Three-Dimensional Imaging |
| CN108010003A (en) * | 2018-01-29 | 2018-05-08 | 佳木斯大学附属第医院 | A kind of computer based ear nose larynx auxiliary treatment checks control system |
-
2018
- 2018-06-07 CN CN201810580982.4A patent/CN108898581A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013173574A1 (en) * | 2012-05-16 | 2013-11-21 | The Johns Hopkins University | Imaging system and method for use of same to determine metric scale of imaged bodily anatomy |
| US20180085002A1 (en) * | 2013-03-11 | 2018-03-29 | Carestream Dental Technology Topco Limited | Method and System For Three-Dimensional Imaging |
| CN103631758A (en) * | 2013-11-21 | 2014-03-12 | 陕西理工学院 | Method for solving non-linear programming and absolute value equation through improved harmony search algorithm |
| CN104637026A (en) * | 2015-02-10 | 2015-05-20 | 西安电子科技大学 | Watermark embedding and extracting method based on continuous multi-page document image |
| CN104771179A (en) * | 2015-03-20 | 2015-07-15 | 运城市康丽声医疗器械有限公司 | Intelligent diagnosis and treatment system for tinnitus and deafness |
| CN105469093A (en) * | 2015-12-07 | 2016-04-06 | 周升峰 | Intelligent electronic ear-nose-throat examining device and image processing method |
| CN205234439U (en) * | 2015-12-18 | 2016-05-18 | 威海东舟医疗器械股份有限公司 | Otolaryngology passes a sentence checkout system entirely |
| CN107481293A (en) * | 2017-06-16 | 2017-12-15 | 西安电子科技大学 | Based on the difference image compressed sensing reconstructing methods and intelligent terminal for assuming weighting more |
| CN107705257A (en) * | 2017-09-15 | 2018-02-16 | 重庆科技学院 | One kind is based on partial fractional differential graph of equation image contrast method |
| CN107720552A (en) * | 2017-10-16 | 2018-02-23 | 西华大学 | A kind of assembled architecture intelligence hanging method based on computer machine vision |
| CN108010003A (en) * | 2018-01-29 | 2018-05-08 | 佳木斯大学附属第医院 | A kind of computer based ear nose larynx auxiliary treatment checks control system |
Non-Patent Citations (2)
| Title |
|---|
| BHAT NALINI M.S 等: "Tuberculosis in ear，nose，and throat practice：its presentation and diagnosis", 《AMERICAN JOURNAL OF OTOLARYNGOLOGY》 * |
| 雍龙泉: "带有聚类的和声搜索算法求解具有2n个解的绝对值方程", 《第27届中国控制与决策会议论文集（下册）》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110244009A (en) * | 2019-06-18 | 2019-09-17 | 六盘水市食品药品检验检测所 | A kind of quick identification detection system and method for honey quality |
| CN111584065A (en) * | 2020-04-07 | 2020-08-25 | 上海交通大学医学院附属第九人民医院 | Noise hearing loss prediction and susceptible population screening method, device, terminal and medium |
| CN111584065B (en) * | 2020-04-07 | 2023-09-19 | 上海交通大学医学院附属第九人民医院 | Noise hearing loss prediction and susceptible crowd screening method, device, terminal and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Heo et al. | Artificial intelligence in oral and maxillofacial radiology: what is currently possible? | |
| CN109166130B (en) | Image processing method and image processing device | |
| CN109697741A (en) | A kind of PET image reconstruction method, device, equipment and medium | |
| Gan et al. | Toward accurate tooth segmentation from computed tomography images using a hybrid level set model | |
| US20200372301A1 (en) | Adversarial Defense Platform For Automated Dental Image Classification | |
| Saghiri et al. | A new approach for locating the minor apical foramen using an artificial neural network | |
| Padma et al. | Deep learning based chest x-ray image as a diagnostic tool for covid-19 | |
| Al Arif et al. | Shape-aware deep convolutional neural network for vertebrae segmentation | |
| Okada et al. | Noninvasive differential diagnosis of dental periapical lesions in cone‐beam CT scans | |
| WO2020083298A1 (en) | Medical image identification method and apparatus, storage medium and electronic device | |
| JP6768620B2 (en) | Learning support device, operation method of learning support device, learning support program, learning support system, terminal device and program | |
| US10726948B2 (en) | Medical imaging device- and display-invariant segmentation and measurement | |
| CN107481254A (en) | Processing method, device, medium and the electronic equipment of medical image | |
| US11308664B2 (en) | Method for reconstructing a three-dimensional image data set | |
| CN108898581A (en) | A kind of ear nose larynx check image screening control system, method and application | |
| Karobari et al. | Evaluation of the diagnostic and prognostic accuracy of artificial intelligence in endodontic dentistry: A comprehensive review of literature | |
| Ren et al. | Investigation of a novel deep learning-based computed tomography perfusion mapping framework for functional lung avoidance radiotherapy | |
| CN111403029A (en) | Information processing method and device for improving evaluation quality | |
| Subbotin | Applying machine learning in fog computing environments for panoramic teeth imaging | |
| CN105125228B (en) | The image processing method that a kind of Chest X-rays DR images rib suppresses | |
| EP4140433A2 (en) | Blood parameter assessment systems and methods | |
| CN114974579B (en) | Auxiliary judging system and equipment for prognosis of digestive tract submucosal tumor endoscopic treatment | |
| EP3651117A1 (en) | Methods, systems and use for detecting irregularities in medical images by means of a machine learning model | |
| JP2020025730A (en) | Image processing device, image processing method, and program | |
| CN113284132A (en) | Directional treatment method and system for endoscope cleaning fluid |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181127 |