CN101276418A - Microorganism recognition system and method based on microscopic image - Google Patents
Microorganism recognition system and method based on microscopic image Download PDFInfo
- Publication number
- CN101276418A CN101276418A CNA2008100937606A CN200810093760A CN101276418A CN 101276418 A CN101276418 A CN 101276418A CN A2008100937606 A CNA2008100937606 A CN A2008100937606A CN 200810093760 A CN200810093760 A CN 200810093760A CN 101276418 A CN101276418 A CN 101276418A
- Authority
- CN
- China
- Prior art keywords
- image
- microorganism
- micro
- microscope
- grain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Apparatus Associated With Microorganisms And Enzymes (AREA)
- Image Analysis (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention provides a system and a method for identifying microorganism on the basis of microscopic image, the system and the method utilizes computer image processing technology to pre-process the microscopic images of the obtained grain-stored microorganism, automatically extracts mathematical statistics characteristics of the images, such as texture and geometric shapes, according to target areas of the microscopic images of the grain-stored microorganism, and then uses BP neural network to classify and identify, thus accurately identifying the microorganism in the grain. The achievement of the method can shorten the inspection period for the grain-stored microorganism and precisely forecast condition of the grain-stored microorganism, therefore enabling the staff can punctually take the prevention measures.
Description
Technical field
The present invention relates to detection of a kind of microorganism micro-image and recognition methods and device, particularly relate to a kind of microorganism recognition system and method based on micro-image.
Background technology
The grain storage microorganism is to post the general designation that is attached to the microorganism on grain and the grain and food, has comprised the main monoid of some in the microorganism: eubacteria in the bacterium class and actinomyces, the mould in the Mycophyta, saccharomycete and disease fungus etc.They are often posted and are attached to the surperficial and inner of grain and goods thereof.Cereal microorganism can be decomposed the organic substance in the grain under the suitable condition of environment, make it to go bad, mould corruption, and what have can also produce the toxin with strong toxicity and carcinogenicity.Data shows that the grain loss that China causes every year thus reaches 2.5 hundred million yuan.Therefore accurately discern the microorganism in the grain and take effective measures to prevent and treat and seem particularly important.
Summary of the invention
Purpose of the present invention just is to provide a kind of microorganism recognition system and method based on micro-image, described system and method utilizes computer image processing technology, the grain storage microorganism micro-image that obtains is carried out after the pre-service extracting mathematical statistics features such as the texture of image and geometric configuration automatically according to the target area of grain storage microorganism micro-image, carry out Classification and Identification with the BP neural network then, can accurately discern the microorganism in the grain.
For realizing the object of the invention, the invention provides a kind of microorganism recognition methods based on micro-image, described method comprises following steps: step 1: image acquisition; Step 2: the pre-service of original image; Described pre-service comprises denoising, enhancing; Step 3: the target area of determining identification; Promptly pretreated image is carried out rim detection based on iteration threshold and mathematical morphology, background and two parts of target are cut apart respectively with image; Step 4: extract characteristics of image; Described characteristics of image comprises mathematical statistics features such as the texture of image and geometric configuration; Step 5: carry out Classification and Identification with the BP neural network.
Simultaneously, the invention provides a kind of microorganism recognition system based on micro-image, described system comprises microorganism micro-image checkout equipment and microorganism micro-image identification equipment, described microorganism micro-image checkout equipment comprises ccd video camera, image pick-up card, optical microscope and even illumination chamber, micro-biological samples is by described optical microscope imaging, and described ccd video camera is connected with described image pick-up card as the image collecting device in the described microorganism micro-image checkout equipment and the light signal of image is converted into electric signal; Described image pick-up card is connected with described microorganism micro-image identification equipment; It is indoor that described ccd video camera is arranged on even illumination.
In the preferred embodiments of the present invention, described optical microscope is bright territory microscope, phase microscope, polarizing microscope or interferes the contrast differences micrometric(al) microscope.
In another preferred embodiment of the present invention, described microorganism micro-image identification equipment is the computer that has microprocessor, possesses computing function.
Description of drawings
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are at length set forth.
Fig. 1 is the hardware configuration synoptic diagram of a kind of microorganism recognition system based on micro-image of the present invention.
Fig. 2 is the structured flowchart of image pick-up card selected in a kind of microorganism recognition system based on micro-image of the present invention.
Fig. 3 is the process flow diagram of a kind of microorganism recognition methods based on micro-image of the present invention.
Embodiment
With reference to figure 1, the invention provides a kind of microorganism recognition system based on micro-image, described system comprises microorganism micro-image checkout equipment 100 and microorganism micro-image identification equipment 200, and described microorganism micro-image checkout equipment 100 comprises ccd video camera 101, image pick-up card 102, optical microscope 103 and even illumination chamber 104.Micro-biological samples is by described optical microscope 103 imagings, and described ccd video camera 101 is connected with described image pick-up card 102 as the image collecting device in the described microorganism micro-image checkout equipment and the light signal of image is converted into electric signal; Described image pick-up card 102 is connected with described microorganism micro-image identification equipment 200; Described ccd video camera 101 is arranged in the even illumination chamber 102 with described optical microscope 103.
Because each imaging will influence information content of image, also can produce this imaging system exclusive, some information that can not duplicate with additive method, thereby be that the selection of optical microscope is very important to imaging system.Can be divided in the optical microscope: bright territory microscope, phase microscope, polarizing microscope and interference contrast differences micrometric(al) microscope. various microscopes are suitable for different situations, for example bright territory microscope is suitable for observing not well-illuminated or highly colored microscopic matter, and phase microscope is suitable for observing material alive and need not be earlier through chemical staining.Selected bright territory microscope in the present embodiment for use.
Ccd video camera is converted into electric signal with light signal, through the A/D conversion of image card, a zone in the microscopic field of view is converted into a width of cloth digital picture again, and ccd video camera is the sensor of total system.Thereby its performance quality is bigger to the influence of this device.The selection of ccd video camera need be considered 1. resolution, and low excessively sampled point will influence the measuring accuracy of device; 2. the linearity of ccd video camera; Be about to the linearity that light signal is converted into electric signal.The video camera of linear difference can bring systematic error.In the present embodiment, select SONYSSC-DC14P type colour TV camera for use, the target surface 1/3 of this model C CD video camera ", resolution is 470 lines, adopts AV24V as power supply.
Image pick-up card, the present embodiment have then been selected CA-CPE-3000 image card.
CA-CPE-3000 is based on colour (black and white) image collection card of microcomputer pci bus structure.It has adopted advanced digital decoding mode, composite coloured (or black and white) vision signal or S-Video signal (being the Y-C separation signal) digitizing with the PAL-system of standard input, TSC-system, SECAM-system, after decoding, be converted to the numerical information of the RGB-24bits form that is suitable for image processing, be sent to PC Installed System Memory (or video display buffer) in real time through pci bus then.The structured flowchart of this card such as Fig. 2.
The CA-CPE-3000 image collection card adopts the bus control technology based on capture card, and image transfer speed can realize that up to 60MB/S the video camera image transmits in real time to the reliable of calculator memory, and the image of continuous adjacent chastity is accurately shown up.Owing to adopted high precision Gen Lock technology and linear clamped technology, the visual lattice position precision height of collection, A/1.Digital video signal error after the conversion is little, is suitable for various high precision industry and science image processing field.Because CA-CPE-3000 directly is sent to the internal memory of main frame with image, can store adjacent how auspicious image continuously, image processing algorithm is carried out at host memory, helps improving processing speed, gives full play to more and more higher CPU potentiality, is convenient to user program.
In the present embodiment, to even illuminating chamber require as follows: the illumination in the ccd video camera vision area is wanted evenly, in order to avoid the image local that is absorbed is dark partially, the part is bright partially; Reflective phenomenon can not be arranged.In the present embodiment, described microorganism micro-image identification equipment 200 is the computers that have microprocessor, possess computing function.
As shown in Figure 3, the invention provides a kind of microorganism recognition methods based on micro-image, described method comprises following steps: step 301: image acquisition; Step 302: the pre-service of original image; Described pre-service comprises denoising, enhancing; Step 303: the target area of determining identification; Promptly pretreated image is carried out rim detection, background and two parts of target are cut apart respectively with image; Step 304: extract characteristics of image; Described characteristics of image comprises mathematical statistics features such as the texture of image and geometric configuration; Step 305: carry out Classification and Identification with the BP neural network.Method is a hardware foundation with aforementioned a kind of microorganism recognition system based on micro-image as shown in Figure 3.By under the even indoor no-reflection of illumination, even illumination condition, the micro-image sample of ccd video camera picked-up after the image pick-up card collection quantizes, is sent into computing machine by pci bus, and the microorganism image is carried out Treatment Analysis.
After obtaining original image, system enters step 302, further image is carried out denoising, and enhancement process is to help that more image is carried out Feature Extraction.In this step, at first coloured image is converted into gray level image, because microorganism difference on color is little, gray level image more helps image is carried out Feature Extraction simultaneously.Microorganism photo behind the gray processing is carried out pre-service with level and smooth and sharpening technique to it, so that strengthen microorganism image itself and the contrast of background and the sharpness of entire image.
Enter step 303 then, determine the target area of identification; Promptly pretreated image is carried out rim detection, background and two parts of target are cut apart respectively with image.In this step, employing not only can suppress The noise effectively based on the edge detection method of iteration threshold and mathematical morphology, can objectively, correctly choose the threshold value of rim detection simultaneously, change the order of rim detection, realize the clear detection of microorganism image border.In this step, at first try to achieve the optimal threshold of image segmentation, and image is divided into background and two parts of target by iterative algorithm.The passing threshold dividing processing had both strengthened the contrast of image and target, had strengthened the microorganism image border, can extract the microorganism zone exactly again.And then utilize the profile extraction algorithm, and cutting out the inner picture element of microorganism, last remainder image is exactly the edge of microorganism, thereby has realized the rim detection of microorganism.By each picture element self gray-scale value must be analyzed and calculate, judge whether this point is marginal point like this, avoided in the mathematical computations process of rim detection, the influence of noise further being enlarged, destroy edge image.
Determining to enter step 304 behind the target area to be identified, extract characteristics of image; Described characteristics of image comprises mathematical statistics features such as the texture of image and geometric configuration; Described characteristics of image comprises mathematical statistics features such as the texture of image and geometric configuration; Wherein image texture features comprises contrast, second moment, pixel correlativity, unfavourable balance square, the entropy to gray scale; The geometric characteristic of image comprises girth, area, major axis, minor axis, rectangle degree, circularity.Image texture features is a kind of important region description method.So-called texture is a kind of characteristics of image that reflects the space distribution attribute of pixel grey scale, is usually expressed as local irregularities but macroscopic view feature clocklike.It is one of important evidence of identifying object.Simultaneously, through the observation of a large amount of pictures and microbiologist's suggestion, find for main shape and morphological feature such as spherical, shaft-like, the wire etc. by microorganism itself of microorganism identification.Therefore intend extracting the sample index of these 6 features of girth, area, major axis, minor axis, rectangle degree and circularity of microorganism as the grain storage microorganism classification.Further comprise the step that reduces the proper vector dimension after extracting feature.
After extraction finishes characteristics of image, promptly enter step 305, adopt the BP neural network to carry out Classification and Identification.In Computer Image Processing, extracting of morphological is occupied very consequence, and textural characteristics reflection is the space distribution attribute of pixel, and its texture of the image of the different phase of growth of microorganism distributes and has certain difference.The clustering network of at first sample characteristics that extracts being imported unsupervised learning in the Classification and Identification of BP network is carried out cluster analysis, to containing the BP sorter network segmentation that multiple microbiology class else adopts supervised learning again.
Features such as the texture of the present invention by automatically extracting static grain storage microorganism image, geometric configuration, and the feature application BP neural network of extracting trained identification.The computing machine automatic mode identification that can be the grain storage microorganism provides the stable characteristics parameter value, has effectively improved discrimination, for new way has been opened up in Rapid identification and the sort research of grain storage microorganism.
The present invention a kind of microorganism recognition system and method based on micro-image are feasible through evidence. this method has not only been expanded the application of image recognition, and lays a good foundation for the online detection that realizes the grain storage microorganism, has improved efficiency.The realization of this method can also be shortened the sense cycle of grain storage microorganism, and the situation of the grain storage microorganism that forecasts with unerring accuracy makes the staff can take prophylactico-therapeutic measures in time.Can bring considerable economic and social benefit.
Should be noted that at last: above embodiment is only in order to illustrate that technical scheme of the present invention is not intended to limit, although the present invention is had been described in detail with reference to the foregoing description, those of ordinary skill in the field are to be understood that: still can make amendment or be equal to replacement the specific embodiment of the present invention, and do not break away from any modification of spirit and scope of the invention or be equal to replacement, it all should be encompassed in the middle of the claim scope of the present invention.
Claims (7)
1, a kind of microorganism recognition methods based on micro-image is characterized in that described method comprises following steps:
Step 1: image acquisition;
Step 2: the pre-service of original image; Described pre-service comprises denoising, enhancing;
Step 3: the target area of determining identification; Promptly pretreated image is carried out rim detection based on iteration threshold and mathematical morphology, background and two parts of target are cut apart respectively with image;
Step 4: extract characteristics of image; Described characteristics of image comprises mathematical statistics features such as the texture of image and geometric configuration;
Step 5: carry out Classification and Identification with the BP neural network.
2, the microorganism recognition methods based on micro-image according to claim 1 is characterized in that in step 3, at first tries to achieve the optimal threshold of image segmentation by iterative algorithm, and image is divided into background and two parts of target; And then utilize the profile extraction algorithm, and cutting out the inner picture element of microorganism, last remainder image is exactly the edge of microorganism, thereby has realized the rim detection of microorganism.
3, the microorganism recognition methods based on micro-image according to claim 1 is characterized in that further comprising the step that reduces the proper vector dimension after described step 4 is extracted feature.
4, the microorganism recognition methods based on micro-image according to claim 1 is characterized in that in the feature that described step 4 extracts, and wherein image texture features comprises contrast, second moment, pixel correlativity, unfavourable balance square, the entropy to gray scale; The geometric characteristic of image comprises girth, area, major axis, minor axis, rectangle degree, circularity.
5, a kind of microorganism recognition system based on micro-image, described system comprises microorganism micro-image checkout equipment and microorganism micro-image identification equipment, it is characterized in that, described microorganism micro-image checkout equipment comprises ccd video camera, image pick-up card, optical microscope and even illumination chamber, micro-biological samples is by described optical microscope imaging, and described ccd video camera is connected with described image pick-up card as the image collecting device in the described microorganism micro-image checkout equipment and the light signal of image is converted into electric signal; Described image pick-up card is connected with described microorganism micro-image identification equipment; It is indoor that described ccd video camera is arranged on even illumination.
As the microorganism recognition system as described in the claim 5, it is characterized in that 6, described optical microscope is bright territory microscope, phase microscope, polarizing microscope or interferes the contrast differences micrometric(al) microscope based on micro-image.
7, as the microorganism recognition system as described in the claim 5, it is characterized in that described microorganism micro-image identification equipment is the computer that has microprocessor, possesses computing function based on micro-image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810093760A CN100593172C (en) | 2008-04-18 | 2008-04-18 | Microorganism recognition system and method based on microscopic image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810093760A CN100593172C (en) | 2008-04-18 | 2008-04-18 | Microorganism recognition system and method based on microscopic image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101276418A true CN101276418A (en) | 2008-10-01 |
| CN100593172C CN100593172C (en) | 2010-03-03 |
Family
ID=39995847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810093760A Expired - Fee Related CN100593172C (en) | 2008-04-18 | 2008-04-18 | Microorganism recognition system and method based on microscopic image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100593172C (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011140679A1 (en) * | 2010-05-13 | 2011-11-17 | 中国科学院自动化研究所 | Method for classifying shape images based on the topological theory of perceptual organization |
| CN102971747A (en) * | 2010-05-14 | 2013-03-13 | 生物梅里埃有限公司 | Identification and/or characterization of a microbial agent using taxonomic hierarchical classification |
| CN103808722A (en) * | 2014-03-06 | 2014-05-21 | 山东理工大学 | Mildew detection device and detection method for grains with different depths in same time period in granary |
| WO2017206615A1 (en) * | 2016-05-30 | 2017-12-07 | 武汉沃亿生物有限公司 | Method of automatically modifying imaging range in biological sample microscopic imaging |
| CN108520206A (en) * | 2018-03-22 | 2018-09-11 | 南京大学 | A kind of fungi microscopic image identification method based on full convolutional neural networks |
| CN109643448A (en) * | 2017-03-03 | 2019-04-16 | 华为技术有限公司 | Fine granularity object identification in robot system |
| CN112308936A (en) * | 2019-07-30 | 2021-02-02 | 中国石油天然气股份有限公司 | Method for determining influence of microbial action on microbial carbonate reservoir development |
-
2008
- 2008-04-18 CN CN200810093760A patent/CN100593172C/en not_active Expired - Fee Related
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011140679A1 (en) * | 2010-05-13 | 2011-11-17 | 中国科学院自动化研究所 | Method for classifying shape images based on the topological theory of perceptual organization |
| US8732172B2 (en) | 2010-05-13 | 2014-05-20 | Institute Of Automation, Chinese Academy Of Sciences | Shape classification method based on the topological perceptual organization theory |
| CN102971747A (en) * | 2010-05-14 | 2013-03-13 | 生物梅里埃有限公司 | Identification and/or characterization of a microbial agent using taxonomic hierarchical classification |
| CN103808722A (en) * | 2014-03-06 | 2014-05-21 | 山东理工大学 | Mildew detection device and detection method for grains with different depths in same time period in granary |
| CN103808722B (en) * | 2014-03-06 | 2016-03-30 | 山东理工大学 | To go mouldy pick-up unit and detection method with period different depth grain in silo |
| WO2017206615A1 (en) * | 2016-05-30 | 2017-12-07 | 武汉沃亿生物有限公司 | Method of automatically modifying imaging range in biological sample microscopic imaging |
| US10365207B2 (en) | 2016-05-30 | 2019-07-30 | Wuhan Oe-Bio Co., Ltd. | Method of automatically modifying imaging range in biological sample microscopic imaging |
| CN109643448A (en) * | 2017-03-03 | 2019-04-16 | 华为技术有限公司 | Fine granularity object identification in robot system |
| CN108520206A (en) * | 2018-03-22 | 2018-09-11 | 南京大学 | A kind of fungi microscopic image identification method based on full convolutional neural networks |
| CN112308936A (en) * | 2019-07-30 | 2021-02-02 | 中国石油天然气股份有限公司 | Method for determining influence of microbial action on microbial carbonate reservoir development |
| CN112308936B (en) * | 2019-07-30 | 2024-05-28 | 中国石油天然气股份有限公司 | Method for determining the effect of microbial action on microbial carbonate reservoir development |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100593172C (en) | 2010-03-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11221107B2 (en) | Method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing | |
| CN100593172C (en) | Microorganism recognition system and method based on microscopic image | |
| CN103518224B (en) | Method for analysing microbial growth | |
| WO2022099598A1 (en) | Video dynamic target detection method based on relative statistical features of image pixels | |
| CN103034838B (en) | A kind of special vehicle instrument type identification based on characteristics of image and scaling method | |
| CN103020639A (en) | Method for automatically identifying and counting white blood cells | |
| CN110334760B (en) | Optical component damage detection method and system based on RESUnet | |
| CN112862744B (en) | Intelligent detection method for internal defects of capacitor based on ultrasonic image | |
| Di Ruberto et al. | A leucocytes count system from blood smear images: Segmentation and counting of white blood cells based on learning by sampling | |
| CN110335233B (en) | Highway guardrail plate defect detection system and method based on image processing technology | |
| Ates et al. | An image-processing based automated bacteria colony counter | |
| Gao et al. | A novel VBM framework of fiber recognition based on image segmentation and DCNN | |
| CN111768402A (en) | MU-SVM-based method for evaluating freshness of iced pomfret | |
| CN111832569B (en) | Wall painting pigment layer falling disease labeling method based on hyperspectral classification and segmentation | |
| Ling et al. | A model for automatic recognition of vertical texts in natural scene images | |
| CN117132594A (en) | Intelligent detection method for underground water microplastic based on hyperspectral image | |
| Hu et al. | Detection of chemical fabric defects on the basis of morphological processing | |
| Zhang et al. | Fabric defect detection based on visual saliency map and SVM | |
| CN113628252A (en) | Method for detecting gas cloud cluster leakage based on thermal imaging video | |
| CN117542301A (en) | Display screen detection method and system | |
| Gui et al. | A fast caption detection method for low quality video images | |
| Hittawe et al. | Machine vision for timber grading singularities detection and applications | |
| Deng et al. | A new measuring method of wool fiber diameter based on image processing | |
| Fang et al. | A hybrid approach for efficient detection of plastic mulching films in cotton | |
| Bhardwaj et al. | An imaging approach for the automatic thresholding of photo defects |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100303 Termination date: 20120418 |