CN109087287A - Method based on image analysis evaluation space cabin material surface bacterial plaque elimination effect - Google Patents
Method based on image analysis evaluation space cabin material surface bacterial plaque elimination effect Download PDFInfo
- Publication number
- CN109087287A CN109087287A CN201810794165.9A CN201810794165A CN109087287A CN 109087287 A CN109087287 A CN 109087287A CN 201810794165 A CN201810794165 A CN 201810794165A CN 109087287 A CN109087287 A CN 109087287A
- Authority
- CN
- China
- Prior art keywords
- bacterial plaque
- image
- material surface
- marked
- analysis evaluation
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a kind of methods based on image analysis evaluation space cabin material surface bacterial plaque elimination effect, it respectively shoots the material surface carried out before and after bacterial plaque is removed comprising steps of removing the camera in equipment using bacterial plaque first, obtains the bacterial plaque image for removing front and back;The highlight area in bacterial plaque image is accurately obtained using clustering method and is marked;High-intensity region processing is carried out to the bacterial plaque image for having marked highlight area;Feature extraction is carried out to the bacterial plaque image after removal bloom, feature vector is normalized and is trained as the data the set pair analysis model of neural network, bacterial plaque and is marked for identification.To the bacterial plaque region reference area of bacterial plaque image tagged.Clearance rate is that bacterial plaque removes the ratio between label bacterial plaque region area in the image of front and back.The present invention can effectively obtain bacterial plaque and remove bacterial plaque area in the image of front and back, so as to more accurately obtain bacterial plaque elimination efficiency.
Description
Technical field
The present invention relates to a kind of methods based on image analysis evaluation space cabin material surface bacterial plaque removing degree.This method
The image for removing front and back for analysis space cabin material surface bacterial plaque obtains degerming rate.
Technical background
Space cabin material surface is easily adhered to by microorganism, and forms bacterial plaque.If removing these bacterial plaques not in time, micro- life
Object will corrosion material, and then will affect the bulk life time of equipment, and seriously threaten to the formation of the life and health of occupant.Therefore right
Microorganism, which is purged, in airtight space cabin is of great significance.Bacterium colony is formed after microorganism attachment, bacterium colony concentration is high,
It is difficult to directly count, under the environment of space station, since space and goods and materials are all limited, cannot be carried out as on ground prolonged
Microculture is evaluated come the effect removed to microorganism, and microculture needs a large amount of experiment consumptive material, and
A large amount of rubbish can be generated.
Therefore after being purged in the cabin of space to bacterial plaque, how quickly, in real time to the material surface after removing
It is particularly critical to evaluate to bacterial plaque removing degree that microorganism richness carries out quantization signifying.
Summary of the invention
In view of the above-mentioned problems, the invention proposes a kind of space cabin material surface bacterial plaque removing degree based on image analysis
The method of evaluation.
The present invention is shot to obtain image by the material surface for removing front and back to bacterial plaque, is then analyzed image
The surface microorganism richness for removing front and back to bacterial plaque carries out quantization signifying.
The object of the invention is achieved through the following technical solutions:
Based on the method for image analysis evaluation space cabin material surface bacterial plaque removing degree, the method includes the steps of:
A. Image Acquisition: the camera in equipment is removed respectively to the material table for carrying out bacterial plaque and removing front and back using bacterial plaque first
Face is shot.
B. image high-intensity region: in addition to this due to space station environmental restrictions, when taking pictures to metal material, image is very
It is easy to produce highlight area, covers original shape, the color, Texture eigenvalue of bacterial plaque, the detection and identification to bacterial plaque can all produce
Raw very big interference.So carrying out reflective processing to image first.The pixel in image is gathered using K-means first
Class realization accurately selects highlight area: selecting K point as initial cluster center, calculates each pixel to cluster centre
DistanceIt is divided by distance, calculates each cluster centre again,
It is terminated when measure function (mean square deviation of pixel in same class) reaches convergence.It more can accurately be obtained by operating above
Obtain highlight area.It will treated that image is converted into that SF image (retains collection of objects information in original image, but eliminates mirror
Face reflection), formula Vsf,i(p)=Vi(p)-Vmin(p), SF image is modified to obtain MSF image, formula isWherein Vi(p) be i-th of the channel pixel P color value, and: Vmin(p)=min (V1
(p)+V2(p)+V3(p)),Wherein N is the number of image slices vegetarian refreshments.By comparing Vi(p) and Vmsf,i(p) it
Between difference, image pixel can be divided into diffusing reflection point and highlight:
Wherein i=1,2,3.
C. bacterial plaque identifies: the image after high-intensity region being carried out feature extraction and obtains Color characteristics parameters, red component is equal
It is worth (R), green component mean value (G), blue component mean value (B), luminance component mean value (I), chrominance component mean value (H) and saturation degree
Component mean value (S) is used as color characteristic, because bacterial plaque color is shallower G/B, G/R and R/B are brought into color characteristic.So
The statistic histogram of the LBP characteristic spectrum of image is obtained afterwards as feature vector.Work is normalized in features above vector
It is trained for the data the set pair analysis model of neural network, bacterial plaque and is marked for identification.
D. bacterial plaque areal calculation: to the bacterial plaque region reference area of image tagged.
E. calculate clearance rate: clearance rate is that bacterial plaque removes the ratio between front and back label bacterial plaque region area.
Detailed description of the invention
The program switch logic flow chart of Fig. 1 the present embodiment.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts all other
Embodiment shall fall within the protection scope of the present invention.
Example 1
1 uses fungi to be cultivated as the strain that corrosion material uses on rubber material surface, carries out after growing bacterial plaque
It takes pictures processing.Then bacterial plaque is purged, processing of taking pictures is carried out after removing.
2, which carry out cluster to the pixel in image using K-means first, realizes selection selection K accurate to highlight area progress
Put the distance that each pixel is calculated as initial cluster center to cluster centre
It is divided by distance, calculates each cluster centre again, when measure function (mean square deviation of pixel in same class) reaches
It is terminated to convergence.Highlight area more can be accurately obtained by operating above.By treated, image is converted into SF figure
As (retain collection of objects information in original image, but eliminate mirror-reflection), formula Vsf,i(p)=Vi(p)-Vmin(p),
SF image is modified to obtain MSF image, formula isWherein Vi(p) be as
The color value in i-th of the channel plain P, and: Vmin(p)=min (V1(p)+V2(p)+V3(p)),Wherein
N is the number of image slices vegetarian refreshments.Compare Vi(p) and Vmsf,i(p) image pixel is divided into diffusing reflection point and height by the difference between
Luminous point, so that the highlight area in image be removed.
Image after high-intensity region is carried out feature extraction by 3 obtains Color characteristics parameters, red component mean value (R), green
Component mean value (G), blue component mean value (B), luminance component mean value (I), chrominance component mean value (H) and saturation degree component mean value
(S) it is used as color characteristic, because bacterial plaque color is shallower G/B, G/R and R/B are brought into color characteristic.Then schemed
The statistic histogram of the LBP characteristic spectrum of picture is as feature vector.Features above vector is normalized as nerve net
The data the set pair analysis model of network is trained, and is identified bacterial plaque and is marked.
The bacterial plaque region reference area of 4 pairs of image taggeds.
5, which calculate bacterial plaque, removes the ratio between front and back label bacterial plaque region area as bacterial plaque clearance rate.
Claims (6)
1. a kind of method based on image analysis evaluation space cabin material surface bacterial plaque removing degree, which is characterized in that including step
It is rapid:
High light processing is carried out to the bacterial plaque image of acquisition, the accurate highlight area obtained in bacterial plaque image, to having marked bloom
The bacterial plaque image in region is handled into high-intensity region;
The statistics histogram that feature extraction obtains Color characteristics parameters and LBP characteristic spectrum is carried out to the bacterial plaque image after high-intensity region
Figure is used as feature vector, and features above vector is normalized and is instructed as the data the set pair analysis model of neural network
Practice, identify bacterial plaque and is marked;
Bacterial plaque areal calculation: to the bacterial plaque region reference area of image tagged;
Calculate clearance rate: clearance rate is that bacterial plaque removes the ratio between front and back image tagged bacterial plaque region area.
2. the method according to claim 1 based on image analysis evaluation space cabin material surface bacterial plaque elimination effect,
It is characterized in that, obtains the highlight area in bacterial plaque image using K-means clustering algorithm.
3. the method according to claim 1 based on image analysis evaluation space cabin material surface bacterial plaque elimination effect,
Be characterized in that, calculate each pixel to cluster centre distance:
It is divided by distance and is classified to bacterial plaque image pixel, obtain highlight area and be marked.
4. the method according to claim 1 based on image analysis evaluation space cabin material surface bacterial plaque elimination effect,
It is characterized in that, high-intensity region operation is carried out to the bacterial plaque image for having marked highlight area, comprising:
It has marked the bacterial plaque image of highlight area to be converted into SF image (to retain collection of objects information in original image, but remove
Mirror-reflection), formula are as follows:
Vsf,i(p)=Vi(p)-Vmin(p)
SF image is modified to obtain MSF image, formula are as follows:
Wherein Vi(p) be i-th of the channel pixel P color value, and:
Vmin(p)=min (V1(p)+V2(p)+V3(p))
Wherein N is the number of image slices vegetarian refreshments.By comparing Vi(p) and Vmsf,i(p) difference between can draw image pixel
It is divided into diffusing reflection point and highlight:
。
5. the method according to claim 1 based on image analysis evaluation space cabin material surface bacterial plaque elimination effect,
It is characterized in that, carries out feature extraction operation to by high-intensity region treated image, comprising:
Red component mean value (R), green component mean value (G), blue component mean value (B), luminance component mean value (I), chrominance component
Mean value (H) and saturation degree component mean value (S) are used as color characteristic.
6. the method according to claim 5 based on image analysis evaluation space cabin material surface bacterial plaque elimination effect,
It is characterized in that, the color characteristic extracted is combined, G/B, G/R and R/B are brought into color characteristic.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810794165.9A CN109087287A (en) | 2018-07-19 | 2018-07-19 | Method based on image analysis evaluation space cabin material surface bacterial plaque elimination effect |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810794165.9A CN109087287A (en) | 2018-07-19 | 2018-07-19 | Method based on image analysis evaluation space cabin material surface bacterial plaque elimination effect |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109087287A true CN109087287A (en) | 2018-12-25 |
Family
ID=64837840
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810794165.9A Pending CN109087287A (en) | 2018-07-19 | 2018-07-19 | Method based on image analysis evaluation space cabin material surface bacterial plaque elimination effect |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109087287A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978780A (en) * | 2019-03-12 | 2019-07-05 | 深圳市象形字科技股份有限公司 | A kind of uroscopy instrument test paper image color correction method |
CN109991216A (en) * | 2019-03-12 | 2019-07-09 | 深圳市象形字科技股份有限公司 | A kind of uroscopy instrument test strips color identification method |
CN112121293A (en) * | 2020-10-09 | 2020-12-25 | 东莞职业技术学院 | Foot disinfection device, method and storage medium thereof |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050244794A1 (en) * | 2004-04-30 | 2005-11-03 | Kemp James H | Computer-implemented system and method for automated and highly accurate plaque analysis, reporting, and visualization |
CN104907284A (en) * | 2015-06-01 | 2015-09-16 | 北京航空航天大学 | Equipment and method for directionally removing bacterial plaque from surface of material in cabin |
CN105184748A (en) * | 2015-09-17 | 2015-12-23 | 电子科技大学 | Image bit depth enhancing method |
-
2018
- 2018-07-19 CN CN201810794165.9A patent/CN109087287A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050244794A1 (en) * | 2004-04-30 | 2005-11-03 | Kemp James H | Computer-implemented system and method for automated and highly accurate plaque analysis, reporting, and visualization |
CN104907284A (en) * | 2015-06-01 | 2015-09-16 | 北京航空航天大学 | Equipment and method for directionally removing bacterial plaque from surface of material in cabin |
CN105184748A (en) * | 2015-09-17 | 2015-12-23 | 电子科技大学 | Image bit depth enhancing method |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109978780A (en) * | 2019-03-12 | 2019-07-05 | 深圳市象形字科技股份有限公司 | A kind of uroscopy instrument test paper image color correction method |
CN109991216A (en) * | 2019-03-12 | 2019-07-09 | 深圳市象形字科技股份有限公司 | A kind of uroscopy instrument test strips color identification method |
CN112121293A (en) * | 2020-10-09 | 2020-12-25 | 东莞职业技术学院 | Foot disinfection device, method and storage medium thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bulanon et al. | Development of a real-time machine vision system for the apple harvesting robot | |
CN104572971B (en) | The method and apparatus of image retrieval | |
CN109087287A (en) | Method based on image analysis evaluation space cabin material surface bacterial plaque elimination effect | |
WO2017088365A1 (en) | Skin-colour detection method and apparatus | |
CN109191428B (en) | Masking texture feature-based full-reference image quality evaluation method | |
CN103914708B (en) | Food kind detection method based on machine vision and system | |
CN104573719B (en) | The mountain fire detection method analyzed based on image intelligent | |
CN106384117B (en) | A kind of vehicle color identification method and device | |
CN106803257B (en) | Method for segmenting disease spots in crop disease leaf image | |
CN103942816B (en) | A kind of wood single-plate knot quantity based on image procossing and the recognition methods of size | |
CN106709453A (en) | Sports video key posture extraction method based on deep learning | |
CN102915446A (en) | Plant disease and pest detection method based on SVM (support vector machine) learning | |
CN104050480A (en) | Cigarette smoke detection method based on computer vision | |
CN106097366A (en) | A kind of image processing method based on the Codebook foreground detection improved | |
CN112990103A (en) | String mining secondary positioning method based on machine vision | |
CN107154058A (en) | A kind of method for guiding user to reduce magic square | |
CN110210577A (en) | A kind of deep learning and recognition methods for intensive flock of birds | |
CN109874584A (en) | A kind of fruit tree growing way monitoring system based on deep learning convolutional neural networks | |
CN103929629B (en) | A kind of image processing method based on image primary color | |
CN108090426A (en) | A kind of group rearing pig personal identification method based on machine vision | |
Bulanon et al. | A machine vision system for the apple harvesting robot | |
CN113610185B (en) | Wood color sorting method based on dominant hue identification | |
CN113283538A (en) | Insect classification and counting method based on convolutional neural network | |
CN117274994A (en) | Image recognition technology-based hypsizigus marmoreus cap phenotype analysis method | |
US20130251252A1 (en) | Method and a device for extracting color features |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181225 |