CN101477630A - System and method for intelligent water treatment micro-organism machine vision identification - Google Patents
System and method for intelligent water treatment micro-organism machine vision identification Download PDFInfo
- Publication number
- CN101477630A CN101477630A CNA2009100941061A CN200910094106A CN101477630A CN 101477630 A CN101477630 A CN 101477630A CN A2009100941061 A CNA2009100941061 A CN A2009100941061A CN 200910094106 A CN200910094106 A CN 200910094106A CN 101477630 A CN101477630 A CN 101477630A
- Authority
- CN
- China
- Prior art keywords
- microorganism
- image
- micro
- water treatment
- organism
- 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
Images
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides an intelligent water-treatment microorganism machine vision identification system and a method. By using artificial intelligent technology, the system and the method can real-timely shoot microscopic images of microorganism in water and carry out the steps of automatic image pre-treatment, image segmentation, microorganism characteristic parameter extraction and selection, and microorganism classification and identification. The system and the method have the advantages that optimal segmentation threshold value can be searched automatically in HIS color space by using self-adaptive image segmentation algorithm; and the classifier is designed in a voting manner to obviate the low classification accuracy by using single classifier so as to effectively improve the entire classification accuracy and accurately identify microorganisms in drinking water and urban domestic sewage. The implementation of the method can further shorten the microorganism detection period in the water treatment process and accurately predict the condition of the water-treatment microorganisms to allow the operators to take measures in time. Accordingly, the method and the system can powerfully ensure the safety of drinking water and the normal operation of urban domestic sewage treatment facility so as to achieve considerable economic and social benefits.
Description
Technical field
The present invention relates to a kind of intelligent water treatment micro-organism machine vision identification system and method, belong to computing machine biomedical engineering applied technical field.
Background technology
In the drinking water treatment field, the Chinese government one repeatedly issues and has revised the hygienic standard of potable water to very being concerned about and paying attention to water hygiene and safety guarantee work.Drinking Water is directly to supply with the water that the resident drinks as human body and lives and use by centralized water supply unit, and the water quality of this water must be guaranteed resident's safe for drinking.Show that according to the World Health Organization (WHO) (WorldHealth Organization) investigation the death of child reason more than the human diseases more than 80% and 50% is relevant with the drinkable water poor water quality.The quality of water directly affects the healthy of people.Desirable potable water should not contain known pathogenic microorganisms, should not contain water body fecal pollution indicator bacteria yet.Kind, the population quantity of grasping microorganism in the water in real time is to weigh tap water whether to reach one of important indicator of drinking water sanitary standard, is directly connected to the success or failure of drinking water safety safeguard work.So, regularly survey sample and whether contain pathogenic microorganisms in the water and water body fecal pollution indicator bacteria is very important for the drinking water safety safeguard work.
At sewage treatment area, along with the quickening of China's urbanization speed, city domestic sewage in the sewage total amount shared ratio up to more than 70%.The sewage that people's daily life produces mainly contains some non-toxic organic things, and wherein plant nutrient such as nitrogen, phosphorus is higher.These polluters enter natural water cognition in a large number and cause body eutrophication, water transparency reduces, natural water function and water quality deterioration, the destruction that finally causes ecologic structure, this will produce long-range, inestimable influence to our institute's survival environment.So, strengthen municipal sewage treatment, have great social significance and economic implications for the sustainable development that ensures the city.And since microorganism of a great variety, the kalabolism ability is strong, reproduction speed is fast.So with the microbiological treatment city domestic sewage is that the present effect in the whole world is best, the minimum method of disposal cost.Extensively adopted by countries in the world wastewater treatment industry.In the microorganism sewage disposal process,, can and use the micro-image of microorganism in the sewage disposal system to come microorganism is carried out Classification and Identification and survival state forecast by Real Time Observation for the operation conditions of accurately grasping sewage disposal system and the controlling factor of in time adjusting disposal system.So the observation to the microorganism micro-image in the operation of sewage disposal system process just seems particularly important.Pollute serious day by day today at water, can kind, the population quantity that grasp microorganism in the water have in real time become estimates micro-organism treatment process key of success in the city domestic sewage processing procedure, has been subjected to increasing professional wastewater treatment operational management personnel's great attention.
Utilize traditional optical microscope, the observation personnel can only lean on and visually analyze and check, and not only labour intensity is big, efficient is low, and is difficult to object being observed is carried out objective record and accurate in locating quantitative test.Along with the development of technology such as machine vision, computing machine and Flame Image Process, make we use the analysis of digital microscopy images treatment technology replace traditional manual method to microorganism observe, analyze, the hope of work such as identification and state forecast becomes possibility.Because the analysis of digital microscopy images treatment technology can be got rid of the influence of various subjective factors, obtain quantitative measurement data fast and accurately, disclose the rule of microbial life activity and survival state more objectively, compare with traditional manual analysis mode, both improved work efficiency, strengthened the objectivity of analyzing again, therefore since the nineties in 20th century, it becomes the development focus of international computer biomedical engineering applied technical field gradually.
Summary of the invention
Purpose of the present invention just is to provide a kind of intelligent water treatment micro-organism machine vision identification system and method, and described system and method utilizes artificial intelligence technology, and microorganism micro-image in the water of real time shooting is carried out the image pre-service automatically; Image segmentation; Microorganism characteristic parameter extraction and selection; Microorganism classification and identification.Its advantage is: can seek optimum segmentation threshold automatically at the HSI color space by adaptive image segmentation algorithm; The ballot mode is adopted in the design of sorter, has avoided dividing the time-like precision lower problem by single sorter, effectively raises whole nicety of grading, can accurately discern the microorganism in potable water and the city domestic sewage at short notice.In handling, tap water can be the water quality scientific basis that provides up to standard whether, the shortcoming that overcomes that original artificial optics microscopy labour intensity is big, the time spent is long, can't compare one by one various pathogenic microorganismss; In the city domestic sewage microbiological treatment, can and adjust control disposal system controlling factor in good time important decision-making foundation is provided for correct commander's production technology, overcome original technology by blindness and the subjectivity of site operation personnel with sense organ and experience commander production, the normal operation of energy sound assurance city domestic sewage treatment facility.
For realizing the object of the invention, the invention provides a kind of intelligent water treatment micro-organism machine vision discrimination method, described method comprises following steps:
Step 1: microorganism micro-image picked-up
Shoot with video-corder carrying out the instantaneous of micro-image, in order to the use of successive image processing procedure through the micro-image picked-up hardware system among the pretreated water sample use the present invention to be checked of water sample.
Step 2: image pre-service
Micro-image by RGB (red Red, green Green, blue Blue) color mode is converted to HSI (tone Hue, color saturation Saturation, brightness Intensity) color mode and grayscale mode (Grayscale Mode) image, and use image de-noising method to carry out image denoising and enhancing, the irrelevant information in the removal of images based on the small echo adaptive threshold to the image of changing, recover useful real information, strengthen for information about detectability and reduced data to greatest extent.
Step 3: image segmentation
At the S territory of HSI color space computed image standard deviation d, with d is that partitioning algorithm is selected foundation, when d is big, adopt maximum variance between clusters to determine segmentation threshold, when d hour, adopt and revise averaging method and determine segmentation threshold, carry out post processing of image with mathematics form method at last and finish image segmentation, thereby realized the self-adaptation dynamic threshold of image is cut apart, effectively improved in the successive image processing procedure correct understanding for image.
Step 4: characteristic parameter extraction and selection
In structure and modal singularity,, altogether the microorganism image has been carried out 21 Feature Extraction at microorganism, specifically has been divided into for accuracy and the reliability that improves image characteristics extraction and selection:
(1), morphological feature: the area, girth, girth area ratio, major axis, minor axis, excentricity, circularity, rectangle degree, the central moment that comprise microorganism.
(2), textural characteristics: comprise contrast, second moment, entropy, maximum probability, pixel correlativity, unfavourable balance square to gray scale.
(3), optical density feature: comprise comprehensive optical density, optical density variance, average gray, gray scale density.
(4), chromaticity: comprise rgb color space colourity distribution character, HSI color space colourity distribution character.
Step 5: microorganism classification ballot
Selected Bayesian network (Bayes Network), decision tree (Decision Tree), support vector machine (SupportVector Machine), the most contiguous algorithm of K (K-Nearest Neighbor Algorithm), BP neural network (BackPropagation Neural Network) altogether, totally five kinds of sorter models are used for the type of microorganism is distinguished.
In the design of sorter, adopt the ballot mode, avoided microorganism being carried out the lower problem of branch time-like precision by single sorter.Concrete classification step is divided into:
(1), respectively microorganism is classified, and, when the classification results that has three sorters at least is consistent, just use this consistent result as final classification results to the classification results computing of voting with five sorters;
(2), when five sorters have nothing in common with each other to the classification results of microorganism, unknown micro-biological samples of the system that then this microorganism is judged as and prompting require artificial aid identification;
(3), when classification results has only two sorter classification results of a group or two groups consistent, the ballot computing weight of five kinds of sorters being set gradually from left to right for the difference of microorganism classification effect significance level according to various disaggregated models is 11,12,15,19,21, because the weight of all combined situation all has nothing in common with each other, one group of result of weight maximum is as final classification results after the computing of then can selecting to vote.
Step 6: microorganism identification and statistics
According to the kind of water treatment micro-organism recognition result to microorganism in the water sample to be checked, population quantity, parameters such as dominant population are analyzed and statistical work, use as the real-time dynamic data in its dynamic data base in order to the water treatment micro-organism situation prediction expert system of transferring among the present invention.
Simultaneously, the invention provides a kind of intelligent water treatment micro-organism machine vision identification system, described system comprises water treatment micro-organism micro-image picked-up hardware system, microorganism image recognition software system, water treatment micro-organism situation prediction expert system.
(1), micro-image picked-up hardware system
Mainly comprise Photobiology microscope, the double mode video camera of CCD sound attitude, image pick-up card, picture monitor, automatic carrier, illuminator.The water sample to be checked that contains micro-biological samples through the water sample pre-service after by described Photobiology microscope imaging, through the double mode video camera of described CCD sound attitude optical signalling is converted to digital signal, at last by the micro image collection input microorganism micro-image recognition system host computer of described image pick-up card with microorganism.
(2), microorganism image recognition software system
Adopted a kind of intelligent water treatment micro-organism machine vision discrimination method provided by the present invention, and utilization has the commercial computer of the little process chip of high-performance as its analysis, calculating, processing unit.Realized microorganism in potable water and the city domestic sewage changed identification accurately, fast and automatically.Compare with traditional manual analysis mode, both improved work efficiency, strengthened the objectivity of analyzing again.
(3), water treatment micro-organism situation prediction expert system
Set up a kind of expert system (Expert System) that is specifically designed to the forecast of water treatment field microorganism survival condition, described water treatment micro-organism situation prediction expert system mainly comprises expert knowledge library, dynamic data base, knowledge acquisition mechanism, explanation facility, inference machine.Transfer to described inference machine after translating by described explanation facility after entering described dynamic data base by the identification of the microorganism of microorganism image recognition software system gained and statistics, inference machine is according to the knowledge and the experience of the expert's level level in the described expert knowledge library, utilize the method that the human expert deals with problems and strategy comes microorganism identification and statistics is analyzed, comparison, reasoning and judgement, simulating human expert's decision process solves the challenge that needed the human expert to handle originally.And then control the process and the equipment action at water treatment scene according to the conclusion of differentiating.
Description of drawings
Fig. 1 is the overall flow structural representation of intelligent water treatment micro-organism machine vision identification system of the present invention and method.
Fig. 2 is the structured flowchart of the micro-image picked-up hardware system of intelligent water treatment micro-organism machine vision identification system of the present invention and method.
Fig. 3 is the process flow diagram of the microorganism image recognition software system of intelligent water treatment micro-organism machine vision identification system of the present invention and method.
Fig. 4 is the process flow diagram of the water treatment micro-organism situation prediction expert system of intelligent water treatment micro-organism machine vision identification system of the present invention and method.
Embodiment
Below in conjunction with accompanying drawing, optimization of the present invention is implemented example be described in detail.
As shown in Figure 2, the invention provides a kind of micro-image picked-up hardware system, described system is made of following 15 main function components: the double mode video camera H1 of CCD sound attitude, electric tuning light filter H2, Photobiology microscope H3 goes up chip system H6, illuminator H7 automatically, objective table H8, the three-dimensional controllor for step-by-step motor H9 of objective table, zoom system, pancreatic system H10, identification result output unit H11, external data storage and recovery system H12, micro-image recognition system host computer H13, host display H14, picture monitor H15, electric tuning light filter control system H16, image pick-up card H17.During real-time working, the water sample H4 to be checked that at first will contain micro-biological samples makes wave plate to be checked after through water sample pre-service H5; Automatically go up chip system H6 by micro-image recognition system host computer H13 control then, make slide upload to objective table H8, H6 detects slide and uploads to and send for behind the objective table host computer H13 slice to finish signal, afterwards by the three-dimensional controllor for step-by-step motor H9 of main frame H13 control objective table, make objective table H8 carry out trickle moving, make slide be in the desired tram of Photobiology microscope H3, and carry out automatic focus by zoom system, pancreatic system H10.Can also make Photobiology microscope H3 under low power and high power, automatically switch by control zoom system, pancreatic system H10 by main frame H13 in this process.Next by Photobiology microscope H3 imaging, through the double mode video camera H1 of CCD sound attitude optical signalling is converted to digital signal, by the micro image collection input microorganism micro-image recognition system host computer H13 of image pick-up card H17, finish the picked-up operation of whole water treatment micro-organism micro-image at last with microorganism.
Photobiology microscope H3 implements to have selected Olympus (OLYMPUS) IX65 type inversion type phase microscope in the example in optimization of the present invention.
Optical microscope has multiple sorting technique: can be divided into binocular and monocular microscope by the number that uses eyepiece; Whether there is stereoscopic sensation can be divided into stereoscopic vision and non-stereoscopic vision microscope by image; Can be divided into biological and metaloscope etc. by observing to picture; Can be divided into bright territory, polarisation, differ with elementary errors and interfere comparison micrscope etc. by optical principle; Can be divided into normal optical, fluorescence, ultraviolet light, infrared light and laser microscope etc. by light source type.The different qualities of research object comes optical microscope is selected according to the observation.
Required research and identification is the water treatment micro-organism micro-image among the present invention, because the microorganism in the water belongs to undyed biological living sample, the refractive index of microorganism each several part fine structure and thickness different, when light wave passes through, too big variation can't take place in wavelength (color) and amplitude (brightness), only phase place changes (difference of vibration), and this difference of vibration human eye can't be observed, and causes being difficult to observe the microorganism sample when light field is observed.And phase microscope (having another name called phasecontrast microscope) is by changing this phase differential, and utilize diffraction of light and interference, the phase difference variable that human eye can not be able to be differentiated is distinguishable difference of vibration, thereby makes the observer can observe active somatic cell and undyed microorganism sample clearly.Even it is high-visible that water white material also can become.This big convenience the observation of living microorganism.
The purpose that inverted microscope produces is in order to adapt to microexaminations such as tissue culture in the fields such as biology, medical science, cell cultured in vitro, planktonic organism, environmental protection, Food Inspection.Because the restriction of above-mentioned sample characteristics, tested object might be placed in the double dish (or culture flask), so just requires the operating distance of microscopical object lens and condenser very long, can directly carry out microexamination and research to the tested object in the double dish.Therefore, inverted microscope all reverses the position of object lens, condenser and light source and has reached the designing requirement that increases operating distance between object lens and condenser.
For these reasons, implement to have selected the inversion type phase microscope in the example in optimization of the present invention.
The double mode video camera H1 of CCD sound attitude implements to have selected the dynamic and static double mode ccd video camera of SONYFCB-AX480C type in the example in optimization of the present invention.
Ccd video camera can be converted into electric signal with light signal, thereby certain the piece zone in the microscopic field of view can be converted into a width of cloth digital picture.Ccd video camera is the sensor of total system.Thereby its performance quality is bigger to the influence of native system.Because CCD pixel, horizontal resolution, three parameters of CCD target surface size directly have influence on the size of field angle and the sharpness of image, so should consider above-mentioned three parameters emphatically when ccd video camera is selected.Implement to have selected the dynamic and static double mode ccd video camera of the FCB-AX480C of Sony (SONY) type in the example in optimization of the present invention.The valid pixel of this ccd video camera is 3,000,000, and resolution is 480 lines, and target surface is 1/4 ＂, and display speed reached for 25 frame/seconds, and the USB2.0 data transmission is supported TWAIN, and the VFW interface adopts 220VAC as power supply.
Image pick-up card H17 implements to have selected the high-quality professional image pick-up card of MDO8000 in the example in optimization of the present invention.
The MDO8000 image pick-up card, support maximum four road composite videos inputs, support the S-Video input, can stablize the video standard signal (PAL, NTSC, SECOM) of reception from various video source, its highest resolution can reach 1024x768 (PAL, SECAM) or 640x480 (NTSC).MDO8000 capture card image quality is clear, compatible good, be to monitor in each field such as biomedicine, military affairs, public security and the ideal selection of image processing system.This image pick-up card is coloured silk, pseudo-color, black and white mode images acquired very, optional majority kind acquisition mode; Its video image is passed to calculator memory in real time by computer PCI bus; Images acquired can show on the VGA card in real time; Have multiple additional image processing function, be convenient to the image later stage compilation, for example carry out image level, vertical direction is dwindled arbitrarily and window, image pushes up end inversion etc. in real time.Can gather the image of single frames, arbitrary interval and successive frame in real time; Brightness, contrast, colourity, saturation degree, picture size ratio all can be by software adjustment; Sampling resolution: black and white mode 8Bit, color mode is supported multiple picture formats such as RGB15, RGB16, RGB24, RGB32, YUV; Acquisition rate: 25 frame/seconds when PAL-system, SECAM-system, 30 frame/seconds during TSC-system; Support Plug ﹠amp; The Play connected mode, plug and play;
Micro-image recognition system host computer H13 implements to have selected in the example SONYVAIO VGN-SR28 of Sony type notebook computer to improve the handling property and the portable performance of system in optimization of the present invention.
As shown in Figure 3, the invention provides a kind of microorganism image recognition software system, described system comprises following steps: step 1: microorganism micro-image picked-up S1; Step 2: image pre-service S2; Step 3: image segmentation S3; Step 4: extracting parameter extracts and selects S4; Step 5: microorganism classification ballot S5; Step 6: microorganism identification and statistics S6.By microorganism micro-image picked-up S1, after obtaining original image, system enters image pre-service S2, and original image is carried out image denoising and enhancing, irrelevant information in the removal of images and enhancing detectability for information about.Enter image segmentation S3 then, seek the optimized image segmentation threshold, thereby realize the self-adaptation dynamic threshold of image is cut apart at the HIS color space.After having determined target area to be identified, enter characteristic parameter extraction and select S4, extract 21 characteristic parameters of microorganism micro-image respectively, to improve the accuracy and the reliability of image characteristics extraction and selection.After having extracted characteristics of image, promptly enter microorganism classification ballot S5, this step has adopted five kinds of sorter models to be used for differentiation to the microorganism type altogether, and in the design of sorter, also adopted the ballot mode, avoided to greatest extent microorganism being carried out the lower problem of branch time-like precision by single sorter.After classification is finished, system finally enters microorganism identification and statistics S6, according to the kind of water treatment micro-organism recognition result to microorganism in the water sample to be checked, population quantity, parameters such as dominant population are analyzed and statistical work, use as the real-time dynamic data in its dynamic data base in order to the water treatment micro-organism situation prediction expert system of transferring among the present invention.
As shown in Figure 4, the invention provides a kind of expert system (Expert System) that is specifically designed to the forecast of water treatment field microorganism survival condition, described water treatment micro-organism situation prediction expert system mainly comprises: microorganism identification and statistics E1, explanation facility E2, inference machine E3, dynamic data base E4, expert knowledge library E5, knowledge acquisition mechanism E6, knowledge engineer E7, water treatment field expert E8, the microbial status forecast is E9 as a result, instructs actual process operation E10.Described water treatment micro-organism situation prediction expert system is when operation, at first will put into dynamic data base E4 by the microorganism identification and the statistics E1 of microorganism image recognition software system gained, afterwards by transferring to inference machine E3 after the explanation facility E2 translation, inference machine E3 is according to the knowledge and the experience of the expert's level level in the expert knowledge library E5, utilize the method that the human expert deals with problems and strategy comes microorganism identification and statistics is analyzed, comparison, reasoning and judgement, simulating human expert's decision process solves the challenge that needed the human expert to handle originally.And then the microbial status that obtains according to differentiation forecast as a result E9 control the process and the equipment action at water treatment scene.Described water treatment micro-organism situation prediction expert system can also constantly understand and sum up, transform the expert knowledge and the experience of water treatment field as required to water treatment field expert E8 by knowledge engineer E7 when operation simultaneously, finally up-to-date water treatment field expert knowledge and experience are charged to expert knowledge library E5 by knowledge acquisition mechanism E6, realized continual renovation to described water treatment micro-organism situation prediction expert system, professional and authoritative to guarantee it.
Intelligent water treatment micro-organism machine vision identification system of the present invention and method are feasible through evidence.This method has not only been expanded the application of computer picture recognition, and be to realize the online detection of contained pathogenic microorganisms in the potable water and water body fecal pollution indicator bacteria is laid a good foundation, for carrying out smoothly of drinking water safety safeguard work provides a kind of emerging support technology.The realization of this method can also be shortened the sense cycle of microorganism in the city domestic sewage microbiological treatment process, the situation of water treatment micro-organism forecasts with unerring accuracy, make the staff can take prophylactico-therapeutic measures in time, improved efficiency, sound assurance the normal operation of drinking water safety and city domestic sewage treatment facility, can bring considerable economic and social benefit.
What instructions of the present invention should be set forth at last is: above optimization enforcement example only is used for illustrating a kind of feasible technical scheme of the present invention and is not to be the restriction that the present invention is carried out.Although implementing example with reference to above-mentioned optimization has been described in detail the present invention, under the technician of water treatment field should reach following common recognition: still can make amendment or be equal to replacement the specific embodiment of the present invention, and so long as do not break away from any modification of inherent technical characterictic of the present invention and technological innovation design or be equal to replacement, it all should be encompassed among the claim scope of the present invention.
Claims (9)
1, a kind of intelligent water treatment micro-organism machine vision discrimination method is characterized in that this method may further comprise the steps:
Step 1: microorganism micro-image picked-up;
Step 2: image pre-service;
Step 3: image segmentation;
Step 4: characteristic parameter extraction and selection;
Step 5: microorganism classification ballot;
Step 6: microorganism identification and statistics.
2, intelligent water treatment micro-organism machine vision discrimination method according to claim 1, it is characterized in that in step 2, micro-image by RGB (red Red, green Green, blue Blue) color mode is converted to HSI (tone Hue, color saturation Saturation, brightness Intensity) color mode and grayscale mode (Grayscale Mode) image, and use image de-noising method to carry out image denoising and enhancing based on the small echo adaptive threshold to the image of changing, irrelevant information in the removal of images, recover useful real information, strengthen for information about detectability and reduced data to greatest extent.
3, intelligent water treatment micro-organism machine vision discrimination method according to claim 1, it is characterized in that in step 3, at the S territory of HSI color space computed image standard deviation d, with d is that partitioning algorithm is selected foundation, when d is big, adopt maximum variance between clusters to determine segmentation threshold, when d hour, adopt the correction averaging method to determine segmentation threshold, carry out post processing of image with mathematics form method at last and finish image segmentation, thereby realized the self-adaptation dynamic threshold of image is cut apart, effectively improved in the successive image processing procedure correct understanding for image.
4, intelligent water treatment micro-organism machine vision discrimination method according to claim 1, it is characterized in that in step 4, at microorganism in structure and modal singularity, for accuracy and the reliability that improves image characteristics extraction and selection, altogether the microorganism image has been carried out 21 Feature Extraction, specifically has been divided into:
(1), morphological feature: the area, girth, girth area ratio, major axis, minor axis, excentricity, circularity, rectangle degree, the central moment that comprise microorganism.
(2), textural characteristics: comprise contrast, second moment, entropy, maximum probability, pixel correlativity, unfavourable balance square to gray scale.
(3), optical density feature: comprise comprehensive optical density, optical density variance, average gray, gray scale density.
(4), chromaticity: comprise rgb color space colourity distribution character, HSI color space colourity distribution character.
5, intelligent water treatment micro-organism machine vision discrimination method according to claim 1, it is characterized in that in step 5, selected Bayesian network (Bayes Network), decision tree (Decision Tree), support vector machine (SupportVector Machine), the most contiguous algorithm of K (K-Nearest Neighbor Algorithm), BP neural network (BackPropagation Neural Network) altogether, totally five kinds of sorter models are used for the type of microorganism is distinguished.
6, intelligent water treatment micro-organism machine vision discrimination method according to claim 1 is characterized in that in step 5, adopts the ballot mode in the design of sorter, has avoided by single sorter microorganism being carried out the lower problem of branch time-like precision.Respectively microorganism is classified with five sorters, and, when the classification results that has three sorters at least is consistent, just use this consistent result as final classification results to the classification results computing of voting; When five sorters had nothing in common with each other to the classification results of microorganism, unknown micro-biological samples of the system that then this microorganism is judged as and prompting required artificial aid identification; When classification results has only two sorter classification results of a group or two groups consistent, the ballot computing weight of five kinds of sorters being set gradually from left to right for the difference of microorganism classification effect significance level according to various disaggregated models is 11,12,15,19,21, because the weight of all combined situation all has nothing in common with each other, one group of result of weight maximum is as final classification results after the computing of then can selecting to vote.
7, a kind of intelligent water treatment micro-organism machine vision identification system, described system comprises water treatment micro-organism micro-image picked-up hardware system, microorganism image recognition software system, water treatment micro-organism situation prediction expert system, it is characterized in that described microorganism micro-image picked-up hardware system mainly comprises Photobiology microscope, the double mode video camera of CCD sound attitude, image pick-up card, picture monitor, automatic carrier, illuminator.The water sample to be checked that contains micro-biological samples through the water sample pre-service after by described Photobiology microscope imaging, through the double mode video camera of described CCD sound attitude optical signalling is converted to digital signal, at last by the micro image collection input microorganism micro-image recognition system host computer of described image pick-up card with microorganism.
8, as the water treatment micro-organism situation prediction expert system as described in the claim 7, it is characterized in that, set up a kind of expert system (Expert System) that is specifically designed to the forecast of water treatment field microorganism survival condition, described water treatment micro-organism situation prediction expert system mainly comprises expert knowledge library, dynamic data base, knowledge acquisition mechanism, explanation facility, inference machine.Transfer to described inference machine after translating by described explanation facility after entering described dynamic data base by the identification of the microorganism of microorganism image recognition software system gained and statistics, inference machine is according to the knowledge and the experience of the expert's level level in the described expert knowledge library, utilize the method that the human expert deals with problems and strategy comes microorganism identification and statistics is analyzed, comparison, reasoning and judgement, simulating human expert's decision process solves the challenge that needed the human expert to handle originally.And then control the process and the equipment action at water treatment scene according to the conclusion of differentiating.
9, as the microorganism image recognition software system as described in the claim 7, it is characterized in that, described microorganism image recognition software system has adopted a kind of according to claim 1 intelligent water treatment micro-organism machine vision discrimination method, and utilization has the commercial computer of the little process chip of high-performance as its analysis, calculating, processing unit.Realized microorganism in potable water and the city domestic sewage changed identification accurately, fast and automatically.Compare with traditional manual analysis mode, both improved work efficiency, strengthened the objectivity of analyzing again.The realization of this method can also be shortened the sense cycle of water treatment procedure microorganism, and the situation of the water treatment micro-organism that forecasts with unerring accuracy makes the staff can take prophylactico-therapeutic measures in time.Sound assurance the normal operation of drinking water safety and city domestic sewage treatment facility, can bring considerable economic and social benefit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2009100941061A CN101477630A (en) | 2009-02-17 | 2009-02-17 | System and method for intelligent water treatment micro-organism machine vision identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2009100941061A CN101477630A (en) | 2009-02-17 | 2009-02-17 | System and method for intelligent water treatment micro-organism machine vision identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101477630A true CN101477630A (en) | 2009-07-08 |
Family
ID=40838339
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2009100941061A Pending CN101477630A (en) | 2009-02-17 | 2009-02-17 | System and method for intelligent water treatment micro-organism machine vision identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101477630A (en) |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101805029A (en) * | 2010-03-26 | 2010-08-18 | 北京白象新技术有限公司 | Pure water equipment with traceability |
| CN101866427A (en) * | 2010-07-06 | 2010-10-20 | 西安电子科技大学 | Method for detecting and classifying fabric defects |
| CN102063062A (en) * | 2011-02-18 | 2011-05-18 | 哈尔滨工业大学 | Sludge bulking control expert system for diagnosis based on filamentous bacteria population structure |
| CN103473563A (en) * | 2013-09-23 | 2013-12-25 | 程涛 | Fingernail image processing method and system, and fingernail feature analysis method and system |
| CN104040561A (en) * | 2011-12-02 | 2014-09-10 | 生物梅里埃有限公司 | Method for identifying microorganisms via mass spectrometry and score normalisation |
| CN104749334A (en) * | 2015-02-16 | 2015-07-01 | 燕山大学 | Mode-recognition-based design method for biological abnormal water quality evaluation system |
| CN104794502A (en) * | 2015-05-15 | 2015-07-22 | 哈尔滨工业大学 | Image processing and mode recognition technology-based rice blast spore microscopic image recognition method |
| CN104881646A (en) * | 2015-05-26 | 2015-09-02 | 重庆金山科技（集团）有限公司 | WCE video segmentation extraction distinguishing characteristic information method |
| CN105938524A (en) * | 2016-04-26 | 2016-09-14 | 清华大学 | Microorganism association network prediction method and apparatus |
| CN106097386A (en) * | 2016-05-27 | 2016-11-09 | 长沙明鹏科技有限公司 | A kind of appliance computer image processing method |
| CN106530082A (en) * | 2016-10-25 | 2017-03-22 | 清华大学 | Stock predication method and stock predication system based on multi-machine learning |
| CN106769893A (en) * | 2016-11-22 | 2017-05-31 | 西安建筑科技大学 | A kind of characterizing method of the sludge microbe COMMUNITY CHARACTERISTICS based on color space |
| CN106846312A (en) * | 2017-01-22 | 2017-06-13 | 西安建筑科技大学 | A kind of method of the monitoring sludge system hydraulics change based on color space |
| CN106841199A (en) * | 2017-01-22 | 2017-06-13 | 西安建筑科技大学 | It is a kind of to judge the method whether anaerobic ammonia oxidation process sludge system is subject to impact |
| CN107227257A (en) * | 2017-06-05 | 2017-10-03 | 承启医学（深圳）科技有限公司 | Microorganism optical density detection means and detection method |
| CN108469770A (en) * | 2017-12-22 | 2018-08-31 | 中山市和智电子科技有限公司 | A kind of sewage disposal debugging system |
| CN109165615A (en) * | 2018-08-31 | 2019-01-08 | 中国人民解放军军事科学院军事医学研究院 | A kind of parameter training algorithm under multi-categorizer single channel mode towards EEG signals |
| CN109470701A (en) * | 2018-12-18 | 2019-03-15 | 江苏镭博智能科技有限公司 | A kind of method of the online biological monitoring of water process |
| CN109564617A (en) * | 2016-06-13 | 2019-04-02 | 纳诺利弗股份有限公司 | The method of characterization and imaging micro-object |
| CN110009632A (en) * | 2019-04-17 | 2019-07-12 | 国网重庆市电力公司电力科学研究院 | A kind of appraisal procedure, device and the equipment of metal erosion state |
| CN110119710A (en) * | 2019-05-13 | 2019-08-13 | 广州锟元方青医疗科技有限公司 | Cell sorting method, device, computer equipment and storage medium |
| CN110210579A (en) * | 2019-06-19 | 2019-09-06 | 同济大学 | The method and device of on-line real time monitoring air-conditioner set microbial contamination |
| CN110334691A (en) * | 2019-07-16 | 2019-10-15 | 武汉成名仪器有限公司 | Microorganism water quality monitoring method, system and storage medium |
| CN110717533A (en) * | 2019-09-27 | 2020-01-21 | 广东聚源管业实业有限公司 | Water body purification method based on image recognition pipeline device |
| JP2020032394A (en) * | 2018-08-31 | 2020-03-05 | 株式会社明電舎 | Sewage treatment operation status evaluation device and sewage treatment operation status evaluation method |
| JPWO2018207885A1 (en) * | 2017-05-10 | 2020-03-12 | 日本電気株式会社 | Analysis device, stratum age estimation device, analysis method, stratum age estimation method, and program |
| CN110879955A (en) * | 2018-09-06 | 2020-03-13 | 埃森哲环球解决方案有限公司 | Digital quality control using computer vision with deep learning |
| CN111983794A (en) * | 2019-05-21 | 2020-11-24 | 卡尔蔡司显微镜有限责任公司 | Automatic focusing optical microscope |
| CN112651305A (en) * | 2020-12-10 | 2021-04-13 | 哈尔滨师范大学 | Method for identifying microorganism species |
| CN113049593A (en) * | 2021-04-02 | 2021-06-29 | 南通迈程汽车技术有限公司 | Method for realizing online biological monitoring by using intelligent imaging and recognition technology |
| TWI741777B (en) * | 2020-09-02 | 2021-10-01 | 鴻海精密工業股份有限公司 | Image data classification method, computer device and readable storage medium |
| CN113639823A (en) * | 2021-08-18 | 2021-11-12 | 清华大学 | High-precision liquid level detection system and method based on ripple image recognition |
| CN116092078A (en) * | 2023-04-11 | 2023-05-09 | 深圳市信远环保水务有限公司 | Intelligent control system for sewage treatment |
| US11682111B2 (en) | 2020-03-18 | 2023-06-20 | International Business Machines Corporation | Semi-supervised classification of microorganism |
| CN116758580A (en) * | 2023-05-05 | 2023-09-15 | 中国地质大学（北京） | Benthonic organism recognition method, benthonic organism recognition device, electronic equipment and storage medium |
| CN117745622A (en) * | 2024-02-21 | 2024-03-22 | 深圳市盘古环保科技有限公司 | Garbage leachate membrane concentrate catalytic oxidation device |
| CN118005195A (en) * | 2024-03-27 | 2024-05-10 | 广东省源天工程有限公司 | Riverway ecological environment restoration system and method |
-
2009
- 2009-02-17 CN CNA2009100941061A patent/CN101477630A/en active Pending
Cited By (55)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101805029A (en) * | 2010-03-26 | 2010-08-18 | 北京白象新技术有限公司 | Pure water equipment with traceability |
| CN101805029B (en) * | 2010-03-26 | 2011-12-28 | 北京白象新技术有限公司 | Pure water equipment with traceability |
| CN101866427A (en) * | 2010-07-06 | 2010-10-20 | 西安电子科技大学 | Method for detecting and classifying fabric defects |
| CN102063062A (en) * | 2011-02-18 | 2011-05-18 | 哈尔滨工业大学 | Sludge bulking control expert system for diagnosis based on filamentous bacteria population structure |
| CN104040561A (en) * | 2011-12-02 | 2014-09-10 | 生物梅里埃有限公司 | Method for identifying microorganisms via mass spectrometry and score normalisation |
| CN104040561B (en) * | 2011-12-02 | 2018-06-05 | 生物梅里埃有限公司 | Pass through the method for the regular identification microorganism of mass spectrometry and fraction |
| US10546735B2 (en) | 2011-12-02 | 2020-01-28 | Biomerieux, Inc. | Method for identifying microorganisms via mass spectrometry and score normalization |
| CN103473563A (en) * | 2013-09-23 | 2013-12-25 | 程涛 | Fingernail image processing method and system, and fingernail feature analysis method and system |
| CN104749334A (en) * | 2015-02-16 | 2015-07-01 | 燕山大学 | Mode-recognition-based design method for biological abnormal water quality evaluation system |
| CN104794502A (en) * | 2015-05-15 | 2015-07-22 | 哈尔滨工业大学 | Image processing and mode recognition technology-based rice blast spore microscopic image recognition method |
| CN104881646A (en) * | 2015-05-26 | 2015-09-02 | 重庆金山科技（集团）有限公司 | WCE video segmentation extraction distinguishing characteristic information method |
| CN104881646B (en) * | 2015-05-26 | 2018-08-03 | 重庆金山科技（集团）有限公司 | The method that WCE video segmentations extract notable feature information |
| CN105938524A (en) * | 2016-04-26 | 2016-09-14 | 清华大学 | Microorganism association network prediction method and apparatus |
| CN106097386A (en) * | 2016-05-27 | 2016-11-09 | 长沙明鹏科技有限公司 | A kind of appliance computer image processing method |
| CN109564617A (en) * | 2016-06-13 | 2019-04-02 | 纳诺利弗股份有限公司 | The method of characterization and imaging micro-object |
| US11798300B2 (en) | 2016-06-13 | 2023-10-24 | Nanolive Sa | Method of characterizing and imaging microscopic objects |
| CN109564617B (en) * | 2016-06-13 | 2023-09-26 | 纳诺利弗股份有限公司 | Method for characterizing and imaging microscopic objects |
| CN106530082A (en) * | 2016-10-25 | 2017-03-22 | 清华大学 | Stock predication method and stock predication system based on multi-machine learning |
| CN106769893A (en) * | 2016-11-22 | 2017-05-31 | 西安建筑科技大学 | A kind of characterizing method of the sludge microbe COMMUNITY CHARACTERISTICS based on color space |
| CN106769893B (en) * | 2016-11-22 | 2019-04-05 | 西安建筑科技大学 | A kind of characterizing method of the sludge microbe COMMUNITY CHARACTERISTICS based on color space |
| CN106841199B (en) * | 2017-01-22 | 2019-04-16 | 西安建筑科技大学 | A method of determining whether anaerobic ammonia oxidation process sludge system is impacted |
| CN106846312A (en) * | 2017-01-22 | 2017-06-13 | 西安建筑科技大学 | A kind of method of the monitoring sludge system hydraulics change based on color space |
| CN106846312B (en) * | 2017-01-22 | 2019-09-03 | 西安建筑科技大学 | A method of the monitoring sludge system hydraulics variation based on color space |
| CN106841199A (en) * | 2017-01-22 | 2017-06-13 | 西安建筑科技大学 | It is a kind of to judge the method whether anaerobic ammonia oxidation process sludge system is subject to impact |
| JPWO2018207885A1 (en) * | 2017-05-10 | 2020-03-12 | 日本電気株式会社 | Analysis device, stratum age estimation device, analysis method, stratum age estimation method, and program |
| US11448634B2 (en) | 2017-05-10 | 2022-09-20 | Nec Corporation | Analysis apparatus, stratum age estimation apparatus, analysis method, stratum age estimation method, and program |
| CN107227257B (en) * | 2017-06-05 | 2020-07-14 | 承启医学（深圳）科技有限公司 | Microbial optical density detection device and detection method |
| CN107227257A (en) * | 2017-06-05 | 2017-10-03 | 承启医学（深圳）科技有限公司 | Microorganism optical density detection means and detection method |
| CN108469770A (en) * | 2017-12-22 | 2018-08-31 | 中山市和智电子科技有限公司 | A kind of sewage disposal debugging system |
| JP2020032394A (en) * | 2018-08-31 | 2020-03-05 | 株式会社明電舎 | Sewage treatment operation status evaluation device and sewage treatment operation status evaluation method |
| CN109165615A (en) * | 2018-08-31 | 2019-01-08 | 中国人民解放军军事科学院军事医学研究院 | A kind of parameter training algorithm under multi-categorizer single channel mode towards EEG signals |
| JP7172302B2 (en) | 2018-08-31 | 2022-11-16 | 株式会社明電舎 | Sewage treatment operation status evaluation device and sewage treatment operation status evaluation method |
| CN110879955B (en) * | 2018-09-06 | 2024-05-14 | 埃森哲环球解决方案有限公司 | Digital quality control using computer vision with deep learning |
| CN110879955A (en) * | 2018-09-06 | 2020-03-13 | 埃森哲环球解决方案有限公司 | Digital quality control using computer vision with deep learning |
| CN109470701A (en) * | 2018-12-18 | 2019-03-15 | 江苏镭博智能科技有限公司 | A kind of method of the online biological monitoring of water process |
| CN110009632A (en) * | 2019-04-17 | 2019-07-12 | 国网重庆市电力公司电力科学研究院 | A kind of appraisal procedure, device and the equipment of metal erosion state |
| CN110119710A (en) * | 2019-05-13 | 2019-08-13 | 广州锟元方青医疗科技有限公司 | Cell sorting method, device, computer equipment and storage medium |
| CN111983794B (en) * | 2019-05-21 | 2022-07-26 | 卡尔蔡司显微镜有限责任公司 | Automatic focusing optical microscope |
| CN111983794A (en) * | 2019-05-21 | 2020-11-24 | 卡尔蔡司显微镜有限责任公司 | Automatic focusing optical microscope |
| CN110210579A (en) * | 2019-06-19 | 2019-09-06 | 同济大学 | The method and device of on-line real time monitoring air-conditioner set microbial contamination |
| CN110334691A (en) * | 2019-07-16 | 2019-10-15 | 武汉成名仪器有限公司 | Microorganism water quality monitoring method, system and storage medium |
| CN110717533A (en) * | 2019-09-27 | 2020-01-21 | 广东聚源管业实业有限公司 | Water body purification method based on image recognition pipeline device |
| US11682111B2 (en) | 2020-03-18 | 2023-06-20 | International Business Machines Corporation | Semi-supervised classification of microorganism |
| TWI741777B (en) * | 2020-09-02 | 2021-10-01 | 鴻海精密工業股份有限公司 | Image data classification method, computer device and readable storage medium |
| CN112651305A (en) * | 2020-12-10 | 2021-04-13 | 哈尔滨师范大学 | Method for identifying microorganism species |
| CN112651305B (en) * | 2020-12-10 | 2022-08-30 | 哈尔滨师范大学 | Method for identifying microorganism species |
| CN113049593A (en) * | 2021-04-02 | 2021-06-29 | 南通迈程汽车技术有限公司 | Method for realizing online biological monitoring by using intelligent imaging and recognition technology |
| CN113639823B (en) * | 2021-08-18 | 2022-04-19 | 清华大学 | High-precision liquid level detection system and method based on ripple image recognition |
| CN113639823A (en) * | 2021-08-18 | 2021-11-12 | 清华大学 | High-precision liquid level detection system and method based on ripple image recognition |
| CN116092078A (en) * | 2023-04-11 | 2023-05-09 | 深圳市信远环保水务有限公司 | Intelligent control system for sewage treatment |
| CN116092078B (en) * | 2023-04-11 | 2023-06-09 | 深圳市信远环保水务有限公司 | Intelligent control system for sewage treatment |
| CN116758580A (en) * | 2023-05-05 | 2023-09-15 | 中国地质大学（北京） | Benthonic organism recognition method, benthonic organism recognition device, electronic equipment and storage medium |
| CN117745622B (en) * | 2024-02-21 | 2024-05-07 | 深圳市盘古环保科技有限公司 | Garbage leachate membrane concentrate catalytic oxidation device |
| CN117745622A (en) * | 2024-02-21 | 2024-03-22 | 深圳市盘古环保科技有限公司 | Garbage leachate membrane concentrate catalytic oxidation device |
| CN118005195A (en) * | 2024-03-27 | 2024-05-10 | 广东省源天工程有限公司 | Riverway ecological environment restoration system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101477630A (en) | System and method for intelligent water treatment micro-organism machine vision identification | |
| CN103080331B (en) | Method for detecting microorganisms, device for detecting microorganisms and program | |
| CN109583342A (en) | Human face in-vivo detection method based on transfer learning | |
| CN102334422B (en) | Machine vision based real-time diagnosis method and system of vegetable leaf diseases | |
| WO2018101004A1 (en) | Cell image evaluation system and program for controlling cell image evaluation | |
| CN107771212A (en) | Bacterium colony contrast is collected | |
| CN101221118A (en) | System and method for intelligent recognizing and counting sputum smear micro-image tubercle bacillus | |
| CN103902962B (en) | One kind is blocked or the adaptive face identification method of light source and device | |
| CN102304472A (en) | Device and method for detecting sputum smear tubercle bacillus quickly | |
| CN102982511B (en) | A kind of image intelligent optimized treatment method | |
| CN101900737A (en) | Automatic identification system for urinary sediment visible components based on support vector machine | |
| CN109271900A (en) | A kind of rubbish recognition methods based on computer vision | |
| CN109259528A (en) | A kind of home furnishings intelligent mirror based on recognition of face and skin quality detection | |
| CN109598681A (en) | The reference-free quality evaluation method of image after a kind of symmetrical Tangka repairs | |
| Han et al. | Research on multiple jellyfish classification and detection based on deep learning | |
| Sumriddetchkajorn et al. | Fault-tolerant optical-penetration-based silkworm gender identification | |
| Majidpour et al. | NSGA-II-DL: Metaheuristic optimal feature selection with Deep Learning Framework for HER2 classification in Breast Cancer | |
| Xie et al. | An improved floc image segmentation algorithm based on Otsu and particle swarm optimisation | |
| Zhou et al. | A study of automatic recognition and counting system of urine-sediment visual components | |
| CN103246878A (en) | Facial-recognition-based trial makeup system and trial makeup method thereof | |
| CN115629072A (en) | Bone marrow smear image analysis and diagnosis method and pathological section scanner device | |
| Kaur et al. | A novel methodology for automatic bacterial colony counter | |
| Fan et al. | Automated chondrocyte viability analysis of articular cartilage based on deep learning segmentation and classification of two-photon microscopic images | |
| CN114518362A (en) | Sperm quality analysis device, system, method and readable storage medium | |
| Cui et al. | Automatic Identification Technology of Optical Fiber based on Genetic Neural Network Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20090708 |