CN107423736A - A kind of noise-reduction method and device for detecting skin symptom - Google Patents
A kind of noise-reduction method and device for detecting skin symptom Download PDFInfo
- Publication number
- CN107423736A CN107423736A CN201710264107.0A CN201710264107A CN107423736A CN 107423736 A CN107423736 A CN 107423736A CN 201710264107 A CN201710264107 A CN 201710264107A CN 107423736 A CN107423736 A CN 107423736A
- Authority
- CN
- China
- Prior art keywords
- skin
- image
- white
- module
- gray
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/44—Detecting, measuring or recording for evaluating the integumentary system, e.g. skin, hair or nails
- A61B5/441—Skin evaluation, e.g. for skin disorder diagnosis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Dermatology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present invention provides a kind of noise-reduction method for detecting skin symptom, including：After the White-light image of skin to be detected is obtained, gray processing processing is carried out to the White-light image, obtains gray-scale map；The hair area in gray-scale map is extracted, as the first mask images；The hair area of former White-light image is marked according to the first mask images, generation mark image；The hair area in mark image is eliminated, generates the second mask images；According to the second mask images, the region that hair blocks in the White-light image is rebuild.The present invention also provides a kind of denoising device for detecting skin symptom.The present invention passes through the noise reduction to skin picture to be measured, greatly reduce interference of the hair to skin picture during diagnosis, improve the precision to skin symptom detection, the problem of eliminating and the influence that hair blocks be highly susceptible to during skin to be tested is identified, and then serious interference is caused to the identification of skin symptom inspection.
Description
Technical field
The present invention relates to the technical field of image procossing, in particular to a kind of noise-reduction method for detecting skin symptom
And device.
Background technology
Skin disease (dermatosis) is occurred in skin and the general name of skin accessory organ's disease.Skin is human body maximum
Organ, dermopathic species is not only various, and the disease that a variety of internal organ occur can also have performance on skin.Cause skin disease
The reason for it is a lot, for example skin disease caused by infective agent, such as leprosy, scabies, nosomycosis, bacterial skin infections usually have one
Fixed infectiousness, health is not only influenceed, and raised fear and social discrimination, but with the improvement of people ' s living standards
And the infectious disease such as scientific and technological progress, leprosy has been obviously controlled in the whole world.Other cause it is dermopathic it is inside and outside because
Element, such as mechanicalness, it is physical, chemically, biological, incretion, immunity, be increasingly valued by people at present.
Skin participates in the functional activity of body as first of physiology defence line of human body and maximum organ, moment, ties up
The unity of opposites of body and natural environment is hold, the abnormal conditions of body can also reflect in skin surface.Skin possesses
The Physiological protection function of almost Perfect：Such as barrier action, sensation, regulation body temperature, absorption, secretion and Excretion
Deng in the health for safeguarding body, playing highly important effect.The physiological function of skin suffers damage, and causes skin disease.
In skin disease it is most common to pathogenic factor be infection disease and allergic dermatitis, but with the degeneration of aging
Change, senile dermatosis, cutaneum carcinoma etc. are also important skin disease, it is furthermore noted that causing secondary work because of drug therapy disease
Various skin barriers.Specifically it is summarized as following a few classes：
1. chemical factors：
The factors such as pressure and friction, local temperature change are too fast, radiation, illumination, heat radiation, chemical reagent can cause skin
Skin disease occurs.Some factors can aggravate skin disease.Such as excessively scratching scabies secondary infection；Hot water is scalded, soap is washed, inappropriate medication aggravates
Eczema lesion；Exposure can aggravate photosensitive diseases.
2. biological factor：
Insect bites, contact certain plants, parasite and microorganism infection are common causative factors, and such as virus infection is drawn
The various virus dermatopathies risen.
3. food and other diseases：
Some foods such as shrimp etc. easily causes anaphylactia.Viscera, local infection, blood and disturbances of lymph circulation
Etc. can cause Related Skin Diseases, as diabetic is susceptible to suffer from pruritus, local infection causes dermatitis infectiosa eczematoides, circulation barrier
Cyanosis, elephantiasis etc. can be caused by hindering.
4. heredity：
Some diseases have obvious family history, such as ichthyosis, albinism.
5. psychoneural factor：
Neurotrosis can cause trophic ulcer；The close phases of morbidity such as pressure and nervous and alopecia areata, lichen simplex chronicus
Close.
6. metabolism and endocrine factors：
Dysbolism can cause skin amyloidosis, xanthoma etc., and acne, crinosity then easily occur for Cushing ' s syndromes
Deng.
Dermopathic diagnosis is as other diseases, it is necessary to is integrated according to medical history, physical examination and laboratory examination
Analysis：
1. inquire medical history
Dept. of dermatology answer emphasis inquiry patient have no conscious sympton and duration, degree how, the predilection site of skin lesion and
Other illness or which kind of used medicine are whether there is before the sequencing of generation, distribution situation, form, color and luster and onset, whether there is whole body
Symptom, it is whether relevant with season, weather, life and working environment, diet etc., similar skin disease is whether there is in family, is examined after morbidity
How are treatment situation and curative effect.
2. physical examination
(1) emphasis checks the Germ distribution of skin lesion, the species of skin lesion, number, size, form, surface and substrate situation, face
Whether color, blister content and its color, arrangement feature and border are clear.
(2) Aided Physical inspection：
1) slide is firmly pressed in upper 10~20 seconds of infringement by diascopy, and inflammatory erythema and hemangioma color can disappear
Lose.Available for discriminating erythema and purple plague purpura, and observation lupoma.
2) dermographism draws skin with blunt, and wheal is such as produced at the place of streaking, and referred to as dermographism is positive.Nettle rash
Patient often gives the anemicus reaction for occurring ochrodermia color during mechanical stimulus for the positive, atopic dermatitis, the skin of erythroderma.
3) feel to check and include temperature sensation, tactile and pain sensation etc..
4) wood's light examination such as favus disease hair is in dirty-green fluorescence, and tinea alba is in bright green fluorescence.Other diseases, such as
Tinea versicolor, porpharia etc. can send the fluorescent of different colours.
5) acantholysis cell loosens sign (nikolsky's sign) passage blister to surrounding diffusion, and normal skin is by outward appearance between promotion and blister
Normal skin is rubbed off as the positive.
3. laboratory examination：
(1) skin histopathology checks that partial skin disease has its distinctive pathological change, can make a definite diagnosis according to this and antidiastole.
(2) 1. patch test is used to check contactant for Skin-test.2. scratch test or intracutaneous test are used to examine
Allergic reaction type at once is looked into, determines whether certain material has allergic reaction (I type).3. lepromin test is used to judge leprosy
Patient's Immunity.4. achoricine tests the diagnosis for contributing to dermatophytids.
(3) microorganism checking dermatophyte, Mycobacterium leprae scabies rash worm, which check, contributes to corresponding dermopathic diagnosis.
And dermopathic diagnosis at present relies primarily on the mode that artificial observation and laboratory physical and chemical inspection are combined, wherein people
Work is observed, and is the observation directly perceived by medical worker, and the mode contrasted with relative patient picture, this diagnostic mode are past
Toward can only be judged with doctors experience and lower doctor's advice is treated, it sometimes appear that certain Misdiagnosis.
With the continuous development of vision technique, image processing techniques is commonly used by people in various fields.Computer is diagnosed a disease just
It is one of wherein important application case, it is automatic, quick due to having the characteristics that, efficiency of diagnosing a disease can be greatly improved, is considered as not
Carry out the developing direction that medical science is diagnosed a disease.But skin surface has a large amount of pores, and the diameter of pore is about 0.02~0.05 milli
Meter, 100~120 pores are there are about on each square centimeter of skin, the face of people shares individual pore more than 20,000, so just having
A large amount of hairs are disturbed the picture of skin.It is highly susceptible to what hair blocked during skin to be tested is identified
Influence, and then examine identification to cause serious interference skin symptom.
The content of the invention
In view of this, the technical problem to be solved in the present invention is to overcome in the prior art, is carried out to skin to be tested
The influence that hair blocks is highly susceptible in identification process, and then the identification examined to skin symptom causes serious interference
Defect.
To solve the above problems, the present invention provides a kind of noise-reduction method for being used to detect skin symptom, comprise the following steps：
After the White-light image of skin to be detected is obtained, gray processing processing is carried out to the White-light image, obtains gray-scale map；
The hair area in the gray-scale map is extracted, as the first mask images；
The hair area of former White-light image is marked according to first mask images, generation mark image；
The hair area in the mark image is eliminated, generates the second mask images；
According to the second mask images, the region that hair blocks in the White-light image is rebuild.
Preferably, it is described after the White-light image of skin to be detected is obtained, gray processing processing is carried out to the White-light image,
After obtaining gray-scale map, in addition to：
Calculus of differences will be carried out with former gray-scale map after gray-scale map progress closed operation operation, obtain difference image；
The difference image is subjected to noise reduction process.
Preferably, it is described that the difference image is subjected to noise reduction process, including：
The difference image is subjected to binary conversion treatment；
After the binary conversion treatment to the difference image, Threshold segmentation is fixed.
Preferably, the hair area eliminated in the mark image, generates the second mask images, including：
Medium filtering is carried out so as to eliminate hair area to the mark image, generates the second mask images.
Preferably, it is described after the White-light image of skin to be detected is obtained, gray processing processing is carried out to the White-light image,
Before obtaining gray-scale map, in addition to：
Skin area to be measured is selected, and skin area to be measured is shot；
Obtain the White-light image of the skin area to be measured.
In addition, to solve the above problems, the present invention also provide it is a kind of be used to detect the denoising device of skin symptom, including：
It is ashed module, extraction module, mark module, cancellation module and rebuilds module；
The ashing module, for after the White-light image of skin to be detected is obtained, gray scale to be carried out to the White-light image
Change is handled, and obtains gray-scale map；
The extraction module, for extracting the hair area in the gray-scale map, as the first mask images；
The mark module, for the hair area of former White-light image to be marked according to first mask images,
Generation mark image；
The cancellation module, for eliminating the hair area in the mark image, generate the second mask images；
The reconstruction module, for according to the second mask images, rebuilding the region that hair blocks in the White-light image.
Preferably, in addition to：Computing module and noise reduction module；
The computing module, for calculus of differences will to be carried out with former gray-scale map after gray-scale map progress closed operation operation,
Obtain difference image；
The noise reduction module, for the difference image to be carried out into noise reduction process.
Preferably, the noise reduction module, including：Binarization unit and cutting unit
The binarization unit, for the difference image to be carried out into binary conversion treatment；
The cutting unit, for after the binary conversion treatment to the difference image, Threshold segmentation to be fixed.
Preferably, the cancellation module, including：
Filter unit, for carrying out medium filtering to the mark image so as to eliminate hair area, generate the second mask
Image.
Preferably, in addition to：Taking module and acquisition module；
The taking module, shot for selecting skin area to be measured, and to skin area to be measured；
The acquisition module, for obtaining the White-light image of the skin area to be measured.
After the White-light image of skin to be detected is obtained, gray processing processing is carried out to the White-light image, obtains gray-scale map；
The hair area in the gray-scale map is extracted, as the first mask images；
The hair area of former White-light image is marked according to first mask images, generation mark image；
The hair area in the mark image is eliminated, generates the second mask images；
According to the second mask images, the region that hair blocks in the White-light image is rebuild.
The present invention provides a kind of noise-reduction method for detecting skin symptom, by being obtained to the White-light image of skin, ash
The mark image of generation mark hair area after change, and then mark image is eliminated, then the weight to White-light image is carried out by mask
Build, so as to complete the noise reduction process of the White-light image to skin to be detected.The present invention by the noise reduction to skin picture to be measured,
Interference of the hair to skin picture during diagnosis is greatly reduced, the precision to skin symptom detection is substantially increased, exempts from
Go during skin to be tested is identified to be highly susceptible to the influence that hair blocks, and then skin symptom is examined and known
The problem of not causing serious interference.
Brief description of the drawings
It should be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore it is not construed as to model
The restriction enclosed, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to these
Accompanying drawing obtains other related accompanying drawings.
Fig. 1 is the schematic flow sheet of an embodiment of the noise-reduction method of present invention detection skin symptom；
Fig. 2 is the schematic flow sheet of two embodiments of the noise-reduction method of present invention detection skin symptom；
Fig. 3 is that the difference image is carried out noise reduction process step by the described of noise-reduction method of present invention detection skin symptom
Refinement schematic flow sheet；
Fig. 4 is the schematic flow sheet of three embodiments of the noise-reduction method of present invention detection skin symptom；
Fig. 5 is the schematic flow sheet of four embodiments of the noise-reduction method of present invention detection skin symptom；
Fig. 6 is the high-level schematic functional block diagram of the embodiment of the denoising device of present invention detection skin symptom；
Fig. 7 is the high-level schematic functional block diagram of the refinement of the cancellation module of the denoising device of present invention detection skin symptom；
Fig. 8 is the high-level schematic functional block diagram of the refinement of the noise reduction module of the denoising device of present invention detection skin symptom；
Embodiment
Hereinafter, the various embodiments of the disclosure will be described more fully.The disclosure can have various embodiments, and
It can adjust and change wherein.It should be understood, however, that：It is limited to spy disclosed herein in the absence of by the various embodiments of the disclosure
Determine the intention of embodiment, but the disclosure should be interpreted as covering in the spirit and scope for the various embodiments for falling into the disclosure
All adjustment, equivalent and/or alternatives.
Hereinafter, disclosed in the term " comprising " that can be used in the various embodiments of the disclosure or " may include " instruction
Function, operation or the presence of element, and do not limit the increase of one or more functions, operation or element.In addition, such as exist
Used in the various embodiments of the disclosure, term " comprising ", " having " and its cognate are meant only to represent special characteristic, number
Word, step, operation, the combination of element, component or foregoing item, and be understood not to exclude first one or more other
Feature, numeral, step, operation, element, component or foregoing item combination presence or one or more features of increase, numeral,
Step, operation, element, component or foregoing item combination possibility.
In the various embodiments of the disclosure, stating "or" or " at least one in A or/and B " includes what is listed file names with
Any combinations of word or all combinations.For example, " A or B " or " at least one in A or/and B " may include A, may include for statement
B may include A and B both.
The statement (" first ", " second " etc.) used in the various embodiments of the disclosure can be modified in various implementations
Various element in example, but respective sets can not be limited into element.For example, presented above be not intended to limit the suitable of the element
Sequence and/or importance.The purpose presented above for being only used for differentiating an element and other elements.For example, the first user fills
Put and indicate different user device with second user device, although the two is all user's set.For example, each of the disclosure is not being departed from
In the case of the scope of kind embodiment, the first element is referred to alternatively as the second element, and similarly, the second element is also referred to as first
Element.
It should be noted that：, can be by the first composition member if an element ' attach ' to another element by description
Part is directly connected to the second element, and " connection " the 3rd can be formed between the first element and the second element
Element.On the contrary, when an element " being directly connected to " is arrived into another element, it will be appreciated that be in the first element
And second be not present the 3rd element between element.
The term " user " used in the various embodiments of the disclosure, which may indicate that, to be used the people of electronic installation or uses electricity
The device (for example, artificial intelligence electronic installation) of sub-device.
The term used in the various embodiments of the disclosure is only used for describing the purpose of specific embodiment and not anticipated
In the various embodiments of the limitation disclosure.As used herein, singulative is intended to also include plural form, unless context is clear
Chu it is indicated otherwise.Unless otherwise defined, all terms (including the technical term and scientific terminology) tool being otherwise used herein
There is the implication identical implication that the various embodiment one skilled in the art with the disclosure are generally understood that.The term
(term such as limited in the dictionary typically used) is to be interpreted as having and the situational meaning in correlative technology field
Identical implication and the implication with Utopian implication or overly formal will be not construed as, unless in the various of the disclosure
It is clearly defined in embodiment.
The present invention provides a kind of noise-reduction method for detecting skin symptom.
Reference picture 1, Fig. 1 are the schematic flow sheet of an embodiment of the noise-reduction method of present invention detection skin symptom.
In one embodiment, the noise-reduction method of the detection skin symptom includes：
Step S10, after the White-light image of skin to be detected is obtained, gray processing processing is carried out to the White-light image, obtained
To gray-scale map；
It is to be appreciated that the process that coloured image is transformed into gray level image is handled as the gray processing of image.It is color
The color of each pixel in color image has tri- components of R, G, B to determine, and each component has 255 intermediate values can use, such a
Pixel can have the excursion of more than 1,600 ten thousand (255*255*255) color.And gray level image is tri- component phases of R, G, B
A kind of same special coloured image, the excursion of one pixel is 255 kinds, so general in Digital Image Processing kind
The image of various forms is first transformed into gray level image so that the amount of calculation of follow-up image becomes few.Gray level image is retouched
State the entirety that entire image is still reflected as coloured image and the colourity of part and distribution and the feature of brightness degree.
Step S20, the hair area in the gray-scale map is extracted, as the first mask images；
It is to be appreciated that pattern mask be with selected image, figure or object, to pending image (all or
It is local) blocked to control the region of image procossing or processing procedure.With selected image, figure or object, to pending
Image (all or local) blocked, to control the region of image procossing or processing procedure.Specific image for covering
Or object is referred to as mask or template.In optical image security, mask can be film, optical filter etc..In Digital Image Processing, cover
Mould is two-dimensional matrix array, also uses multivalue image sometimes.In Digital Image Processing, pattern mask is mainly used in：First, extraction sense
Region of interest, it is multiplied with the region of interest mask of pre-production with pending image, obtains Image with Region of Interest, scheme in region of interest
Picture value keeps constant, and image value is all 0 outside area.Second, shielding action, some regions on image are shielded with mask, made
Its calculating do not participated in processing or do not participate in processing parameter, or only blind zone is dealt with or counted.3rd, architectural feature carries
Take, detect and extract architectural feature similar to mask in image with similitude variable or image matching method.4th, special form
The making of shape image.
Step S30, the hair area of former White-light image is marked according to first mask images, generation mark figure
Picture；
Step S40, the hair area in the mark image is eliminated, generates the second mask images；
Step S50, according to the second mask images, rebuild the region that hair blocks in the White-light image.
In the present embodiment, by being obtained to the White-light image of skin, the mark of generation mark hair area after ashing
Remember image, and then eliminate mark image, then the reconstruction to White-light image is carried out by mask, so as to complete to skin to be detected
White-light image noise reduction process.The present invention greatly reduces the hair during diagnosis by the noise reduction to skin picture to be measured
The interference to skin picture is sent out, the precision to skin symptom detection is substantially increased, eliminates and skin to be tested is identified
During be highly susceptible to the influence that hair blocks, and then the problem of examine identification to cause serious interference skin symptom.
Reference picture 2, Fig. 2 are the schematic flow sheet of two embodiments of the noise-reduction method of present invention detection skin symptom.
Based on an above-mentioned embodiment, after the step S10, in addition to：
Step S60, calculus of differences will be carried out with former gray-scale map after gray-scale map progress closed operation operation, obtain difference diagram
Picture；
Above-mentioned, calculus of differences, i.e. difference, also known as difference function, the result of difference reflect a kind of change between discrete magnitude
Change, be a kind of instrument for studying discrete mathematics.Original function f (x) is mapped to f (x+a)-f (x+b) by it.Calculus of differences, correspond to
Differentiate, be a concept important in calculus.Sum it up, differential pair should be discrete, differential corresponds to continuous.Difference is divided again
For two kinds of forward difference and reverse difference.
Step S70, the difference image is subjected to noise reduction process.
Step S71, the difference image is subjected to binary conversion treatment；
Step S72, after the binary conversion treatment to the difference image, Threshold segmentation is fixed.
With reference to figure 3, the binaryzation of image, the gray value of the pixel on image is exactly arranged to 0 or 255, that is,
Whole image is showed into obvious black and white visual effect.Piece image includes target object, background also has noise, wants
Target object is directly extracted from the digital picture of multivalue, the most frequently used method is exactly to set a threshold value T, with T by image
Data be divided into two parts：Pixel group more than T and the pixel group less than T.This is the most special method for studying greyscale transformation,
The referred to as binaryzation of image.
In the present embodiment, the gray-scale map of white light picture is subjected to calculus of differences, and then dropped by binary conversion treatment
Make an uproar, so as to which Threshold segmentation be fixed, the hair interference noise of picture is marked and split, the identification to skin symptom is more
It is accurate to add.
With reference to the schematic flow sheet of three embodiments of the noise-reduction method that 4, Fig. 4 is present invention detection skin symptom.
Based on an above-mentioned embodiment, the step S40, including：
Step S41, medium filtering is carried out so as to eliminate hair area to the mark image, generates the second mask images.
Median filtering method is a kind of nonlinear smoothing technology, and the gray value of each pixel is arranged to the point neighborhood by it
The intermediate value of all pixels point gray value in window.
It is to be appreciated that medium filtering is based on a kind of theoretical non-linear letter that can effectively suppress noise of sequencing statistical
Number treatment technology, the general principle of medium filtering are a neighborhood with the point the value of any in digital picture or Serial No.
In the Mesophyticum of each point value replace, the close actual value of the pixel value of surrounding is allowed, so as to eliminate isolated noise spot.Method is to use certain
The two-dimentional sleiding form of kind structure, pixel in plate is ranked up according to the size of pixel value, generation monotone increasing (or decline)
For 2-D data sequence.
In the present embodiment, by carrying out median filtering algorithm to mark image, so as to which hair area be removed
Filter, and then further noise reduction process is carried out, the identification to skin symptom is more accurate.
Reference picture 5, Fig. 5 are the schematic flow sheet of four embodiments of the noise-reduction method of present invention detection skin symptom.
Based on an above-mentioned embodiment, before the step S10, including：
Step S80, skin area to be measured is selected, and skin area to be measured is shot；
Step S90, obtain the White-light image of the skin area to be measured.
In the present embodiment, by being shot to the skin to be detected of patient, so as to obtain White-light image, and then carry out
Diagnose identification process.White-light image, visible images are specifically can be described as, the skin image after being shot by white light is advantageous to
Further to skin noise reduction process.
The present invention further provides a kind of denoising device for detecting skin symptom.
Reference picture 6, Fig. 6 are the high-level schematic functional block diagram of the embodiment of skin symptom detection means of the present invention, including：Ashing
Module, extraction module, mark module, cancellation module, reconstruction module, computing module and noise reduction module；The cancellation module includes：
Filter unit；The noise reduction module includes：Binarization unit and cutting unit；
The ashing module, for after the White-light image of skin to be detected is obtained, gray scale to be carried out to the White-light image
Change is handled, and obtains gray-scale map；
The extraction module, for extracting the hair area in the gray-scale map, as the first mask images；
The mark module, for the hair area of former White-light image to be marked according to first mask images,
Generation mark image；
The cancellation module, for eliminating the hair area in the mark image, generate the second mask images；
The reconstruction module, for according to the second mask images, rebuilding the region that hair blocks in the White-light image.
The computing module, for calculus of differences will to be carried out with former gray-scale map after gray-scale map progress closed operation operation,
Obtain difference image；
The noise reduction module, for the difference image to be carried out into noise reduction process.
The binarization unit, for the difference image to be carried out into binary conversion treatment；
The cutting unit, for after the binary conversion treatment to the difference image, Threshold segmentation to be fixed.
Filter unit, for carrying out medium filtering to the mark image so as to eliminate hair area, generate the second mask
Image.
Preferably, in addition to：Taking module and acquisition module；
The taking module, shot for selecting skin area to be measured, and to skin area to be measured；
The acquisition module, for obtaining the White-light image of the skin area to be measured.
In the present embodiment, with reference to figure 6, Fig. 7 and Fig. 8, with ashing module, extraction module, mark module, elimination mould
Block, module, computing module and noise reduction module are rebuild, by being obtained to the White-light image of skin, generation mark hair after ashing
The mark image in region is sent out, and then eliminates mark image, then the reconstruction to White-light image is carried out by mask, so as to complete pair
The noise reduction process of the White-light image of skin to be detected.The present invention is greatly reduced and examined by the noise reduction to skin picture to be measured
Interference of the hair to skin picture during disconnected, the precision to skin symptom detection is substantially increased, is eliminated to skin to be tested
Skin is highly susceptible to the influence that hair blocks during being identified, and then examines identification to cause serious do to skin symptom
The problem of disturbing.
It should be appreciated that although the present specification is described in terms of embodiments, not each embodiment only includes one
Individual independent technical scheme, this narrating mode of specification is only that those skilled in the art will should say for clarity
For bright book as an entirety, the technical scheme in each embodiment may also be suitably combined to form those skilled in the art can
With the other embodiment of understanding.
Applicant states that the present invention can only for of the invention by a series of describe in detail of those listed above
Row embodiment illustrates, but the invention is not limited in above-mentioned detailed process equipment and technological process.And i.e. not
Mean that the present invention should rely on above-mentioned detailed process equipment and technological process and could implement.Person of ordinary skill in the field should
This is clear, any improvement in the present invention, and the equivalence replacement and auxiliary element to each raw material of product of the present invention are added, are specific square
Selection of formula etc., within the scope of all falling within protection scope of the present invention and disclosing.
Claims (10)
1. a kind of noise-reduction method for being used to detect skin symptom, it is characterised in that comprise the following steps：
After the White-light image of skin to be detected is obtained, gray processing processing is carried out to the White-light image, obtains gray-scale map；
The hair area in the gray-scale map is extracted, as the first mask images；
The hair area of former White-light image is marked according to first mask images, generation mark image；
The hair area in the mark image is eliminated, generates the second mask images；
According to the second mask images, the region that hair blocks in the White-light image is rebuild.
2. the noise-reduction method of detection skin symptom as claimed in claim 1, it is characterised in that described to obtain skin to be detected
White-light image after, to the White-light image carry out gray processing processing, after obtaining gray-scale map, in addition to：
Calculus of differences will be carried out with former gray-scale map after gray-scale map progress closed operation operation, obtain difference image；
The difference image is subjected to noise reduction process.
3. the noise-reduction method of detection skin symptom as claimed in claim 2, it is characterised in that described to enter the difference image
Row noise reduction process, including：
The difference image is subjected to binary conversion treatment；
After the binary conversion treatment to the difference image, Threshold segmentation is fixed.
4. the noise-reduction method of detection skin symptom as claimed in claim 1, it is characterised in that described to eliminate the mark image
In the hair area, generate the second mask images, including：
Medium filtering is carried out so as to eliminate hair area to the mark image, generates the second mask images.
5. the noise-reduction method of the detection skin symptom as any one of claim 1-4, it is characterised in that described to obtain
After the White-light image of skin to be detected, gray processing processing is carried out to the White-light image, before obtaining gray-scale map, in addition to：
Skin area to be measured is selected, and skin area to be measured is shot；
Obtain the White-light image of the skin area to be measured.
A kind of 6. denoising device for being used to detect skin symptom, it is characterised in that including：It is ashed module, extraction module, mark mould
Block, cancellation module and reconstruction module；
The ashing module, for after the White-light image of skin to be detected is obtained, being carried out to the White-light image at gray processing
Reason, obtains gray-scale map；
The extraction module, for extracting the hair area in the gray-scale map, as the first mask images；
The mark module, for the hair area of former White-light image to be marked according to first mask images, generation
Mark image；
The cancellation module, for eliminating the hair area in the mark image, generate the second mask images；
The reconstruction module, for according to the second mask images, rebuilding the region that hair blocks in the White-light image.
7. the denoising device of detection skin symptom as claimed in claim 6, it is characterised in that also include：Computing module and drop
Make an uproar module；
The computing module, for calculus of differences will to be carried out with former gray-scale map after gray-scale map progress closed operation operation, obtain
Difference image；
The noise reduction module, for the difference image to be carried out into noise reduction process.
8. the denoising device of detection skin symptom as claimed in claim 7, it is characterised in that the noise reduction module, including：Two
Value unit and cutting unit
The binarization unit, for the difference image to be carried out into binary conversion treatment；
The cutting unit, for after the binary conversion treatment to the difference image, Threshold segmentation to be fixed.
9. the denoising device of detection skin symptom as claimed in claim 8, it is characterised in that the cancellation module, including：Filter
Ripple unit；
Filter unit, for carrying out medium filtering to the mark image so as to eliminate hair area, generate the second mask images.
10. the denoising device of detection skin symptom as claimed in claim 9, it is characterised in that also include：Taking module and obtain
Modulus block；
The taking module, shot for selecting skin area to be measured, and to skin area to be measured；
The acquisition module, for obtaining the White-light image of the skin area to be measured.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710264107.0A CN107423736A (en) | 2017-04-20 | 2017-04-20 | A kind of noise-reduction method and device for detecting skin symptom |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710264107.0A CN107423736A (en) | 2017-04-20 | 2017-04-20 | A kind of noise-reduction method and device for detecting skin symptom |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107423736A true CN107423736A (en) | 2017-12-01 |
Family
ID=60423214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710264107.0A Pending CN107423736A (en) | 2017-04-20 | 2017-04-20 | A kind of noise-reduction method and device for detecting skin symptom |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107423736A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111209924A (en) * | 2018-11-19 | 2020-05-29 | 零氪科技（北京）有限公司 | System for automatically extracting medical advice and application |
| CN111402347A (en) * | 2020-03-20 | 2020-07-10 | 吴刚 | New crown pneumonia epidemic situation prevention and control system based on Internet of things |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101686819A (en) * | 2007-01-05 | 2010-03-31 | 迈斯金公司 | System, device and method for dermal imaging |
| CN103337071A (en) * | 2013-06-19 | 2013-10-02 | 北京理工大学 | Device and method for structure-reconstruction-based subcutaneous vein three-dimensional visualization |
| US20160154993A1 (en) * | 2014-12-01 | 2016-06-02 | Modiface Inc. | Automatic segmentation of hair in images |
| US20170039704A1 (en) * | 2015-06-17 | 2017-02-09 | Stoecker & Associates, LLC | Detection of Borders of Benign and Malignant Lesions Including Melanoma and Basal Cell Carcinoma Using a Geodesic Active Contour (GAC) Technique |
-
2017
- 2017-04-20 CN CN201710264107.0A patent/CN107423736A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101686819A (en) * | 2007-01-05 | 2010-03-31 | 迈斯金公司 | System, device and method for dermal imaging |
| CN103337071A (en) * | 2013-06-19 | 2013-10-02 | 北京理工大学 | Device and method for structure-reconstruction-based subcutaneous vein three-dimensional visualization |
| US20160154993A1 (en) * | 2014-12-01 | 2016-06-02 | Modiface Inc. | Automatic segmentation of hair in images |
| US20170039704A1 (en) * | 2015-06-17 | 2017-02-09 | Stoecker & Associates, LLC | Detection of Borders of Benign and Malignant Lesions Including Melanoma and Basal Cell Carcinoma Using a Geodesic Active Contour (GAC) Technique |
Non-Patent Citations (2)
| Title |
|---|
| QAISAR ABBAS等: "A Feature-Preserving Hair Removal Algorithm for Dermoscopy Images", 《SKIN RESEARCH AND TECHNOLOGY》 * |
| 明镝: "皮肤镜图像分割算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111209924A (en) * | 2018-11-19 | 2020-05-29 | 零氪科技（北京）有限公司 | System for automatically extracting medical advice and application |
| CN111209924B (en) * | 2018-11-19 | 2023-04-18 | 零氪科技（北京）有限公司 | System for automatically extracting medical advice and application |
| CN111402347A (en) * | 2020-03-20 | 2020-07-10 | 吴刚 | New crown pneumonia epidemic situation prevention and control system based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Garcia-Arroyo et al. | Segmentation of skin lesions in dermoscopy images using fuzzy classification of pixels and histogram thresholding | |
| Amin et al. | A method for the detection and classification of diabetic retinopathy using structural predictors of bright lesions | |
| Hilmi et al. | Prediction of changes in visual acuity and contrast sensitivity function by tissue redness after pterygium surgery | |
| Zhao et al. | Image processing based recognition of images with a limited number of pixels using simulated prosthetic vision | |
| Veiga et al. | Automatic microaneurysm detection using laws texture masks and support vector machines | |
| Achakanalli et al. | Statistical analysis of skin cancer image–A case study | |
| Nayak et al. | Automatic identification of diabetic maculopathy stages using fundus images | |
| CN107424167A (en) | A kind of method and apparatus of pore fixation and recognition | |
| Singh et al. | Recent advancement in the early detection of melanoma using computerized tools: An image analysis perspective | |
| CN107423736A (en) | A kind of noise-reduction method and device for detecting skin symptom | |
| Kia et al. | Computer-aided diagnosis (CAD) of the skin disease based on an intelligent classification of sonogram using neural network | |
| Burroni et al. | Impact of digital dermoscopy analysis on the decision to follow up or to excise a pigmented skin lesion: a multicentre study | |
| Anil et al. | Transforming dental caries diagnosis through artificial intelligence-based techniques | |
| Thulkar et al. | An integrated system for detection exudates and severity quantification for diabetic macular edema | |
| Zhao et al. | Evaluation of regional bulbar redness using an image-based objective method | |
| Karbalaie et al. | Image enhancement effect on inter and intra-observer reliability of nailfold capillary assessment | |
| Kunwar | Malaria detection using image processing and machine learning | |
| Zia et al. | A healthcare model to predict skin cancer using deep extreme machine learning | |
| Neela | Implementation of support vector machine for identification of skin cancer | |
| Sameen et al. | Skin cancer disease detection using image processing techniques | |
| Pauline et al. | Detection of skin cancer by image processing techniques | |
| Silva et al. | Image Processing for mHealth-Based Approach to Detect the Local Tissue Inflammation in Cutaneous Leishmaniasis: A Proof of Concept Study | |
| Li et al. | A Deep-Learning-Enabled Monitoring System for Ocular Redness Assessment | |
| Chang et al. | Robust dermatological wound image segmentation in clinical photos | |
| Diaz et al. | Testing abnormality in the spatial arrangement of cells in the corneal endothelium using spatial point processes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| 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: 20171201 |