CN108985308A - The system and method for electric energy meter presentation quality is quickly analyzed based on data mining algorithm - Google Patents
The system and method for electric energy meter presentation quality is quickly analyzed based on data mining algorithm Download PDFInfo
- Publication number
- CN108985308A CN108985308A CN201710394788.2A CN201710394788A CN108985308A CN 108985308 A CN108985308 A CN 108985308A CN 201710394788 A CN201710394788 A CN 201710394788A CN 108985308 A CN108985308 A CN 108985308A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy meter
- image
- classifier
- data
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The present invention discloses a kind of system and method that electric energy meter presentation quality is quickly analyzed based on data mining algorithm, wherein the system comprises electric energy meter calibration pipeline system, the image capturing system being arranged in inside the electric energy meter calibration pipeline system, the storage server being connect with described image acquisition system, the upper layer data management system being connect with the storage server, it is also integrated with classifier system inside the storage server, calculates analysis system, alarm unit and the display unit connecting with the alarm unit.The present invention carries out analytic operation to the image that image acquisition units acquire using Adaboosting algorithm, this method, which is referred to, can not only make to detect speed quickening in the detection of Internet of Things electric energy meter, detection accuracy is more accurate, additionally it is possible to tension management system be made to carry out more fully monitoring and management to executing agency of lower layer.
Description
Technical field
The present invention relates to electrical energy measurement fields, and quickly divide more particularly to based on Adaboosting data mining algorithm
Analyse the system and method for electric energy meter presentation quality.
Background technique
With the development of powder technology, various industries can all be related to electricity consumption, and electric energy meter is as the metering measured in electrical energy system
One of utensil, the normal operation of relationship between quality to various industries, therefore its quality testing meaning is just very great.Electric energy meter
Quality not only includes the calibrating of its performance parameter, starting, shunt running, resistance test, error-detecting etc., further includes appearance inspection
Fixed, appearance detection includes presentation quality consistency detection, i.e., according to the quality condition consistency of bid sample table and live table
Detection, including quality of hardware, software quality and appearance mark.Appearance mark be mainly reflected in apparent size, nameplate mark and
Liquid crystal display shows that the detection of appearance identity coherence is the important component of electric energy meter quality conformance detection.And appearance detects
Another form be just to look at table and see the bad phenomenons such as slight crack, scratch in vitro, in the case where electric energy meter quantity is few, can adopt
With human eye detection, but more for batch, and when the bad phenomenon of the various appearances such as scratch for thering is human eye not observe, just
A kind of system and method are needed rapidly to analyze the presentation quality of electric energy meter.
Summary of the invention
In view of the above technical problems, the present invention provides one kind quickly analyzes electric energy meter appearance matter based on data mining algorithm
The system and method for amount, the appearance inspection suitable for batch electric energy meter on batch electric energy meter manufacturer, electric energy meter calibration assembly line
It surveys, and early warning can be made to abnormal conditions in time, to guarantee the safe and reliable operation of electrical energy measurement.
The invention adopts the following technical scheme:
A kind of system for quickly analyzing electric energy meter presentation quality based on data mining algorithm, including electric energy meter calibration flowing water linear system
The image capturing system that unite, is arranged in inside the electric energy meter calibration pipeline system is connect with described image acquisition system
Storage server, the upper layer data management system connecting with the storage server are also integrated with inside the storage server
Classifier system calculates analysis system, alarm unit and the display unit connecting with the alarm unit, in which:
Described image acquisition system is used to acquire the appearance images of the batch electric energy meter in electric energy meter calibration pipeline system；
The storage server is used to manage and handle the electric energy meter appearance images data of described image acquisition system acquisition；
The upper layer data management system is used to carry out data and information communication, realization and bottom with the batch storage server
The management and control of electric energy meter calibration data in electric energy meter calibration pipeline system；
The image data that the categorizing system is used to acquire described image acquisition system is classified；
The calculating analysis system is for being calculated and being analyzed to the sorted detection data of the categorizing system；
The display unit calculates the data of output for the calculating analysis system；
The alarm unit is used for the abnormal data warning note to output.
In further technical solution, described image acquisition system includes to be arranged in the electric energy meter calibration flowing water linear system
The light-source system united on framework senses the ccd image sensor of electric energy meter appearance images, the light source by the light-source system
System is LCD matrix series of light sources.
In further technical solution, the calculating analysis system includes Adaboosting algorithm model.
In further technical solution, the classifier system is by least two strong classifiers after cascade.
In further technical solution, the connection of the electric energy meter calibration pipeline system and described image acquisition system
Mode, the connection type of described image acquisition system and the storage server and the storage server and the upper number of plies
Communication modes according to management system are one of WLAN, WIFI, infrared ray, bluetooth, CAN communication bus.
A method of electric energy meter presentation quality is quickly analyzed based on Adaboosting algorithm, comprising the following steps:
(S1) detection and batch electric energy meter to be detected in electric energy meter calibration pipeline system are acquired by image capturing system
Image；
(S2) image that described image acquisition system acquires is saved in the storage server, starts classifier system, it is right
The characteristics of image saved is classified, wherein the method for the classification are as follows:
(S21) sample is selected from the characteristics of image of preservation, the sample of selection is trained, training sample set；
(S22) trained sample set is pre-processed；
(S23) selection matrix feature constitutes Weak Classifier in characteristics of image after the pre-treatment；
(S24) several Weak Classifiers are constituted into strong classifier；
(S25) several Weak Classifiers are constituted into strong classifier；
(S26) strong classifier is cascaded and constitutes Multilayer Classifier；
(S27) Multilayer Classifier is cascaded, constitutes multilayer cascade classifier；
(S3) start the calculating analysis system, image characteristic analysis, calculating to classifier system classification；The wherein calculating
The method that analysis system is calculated and analyzed are as follows:
(S31) multilayer cascade classifier is loaded, initial work is completed；
(S32) validity feature of image is extracted based on Adaboosting algorithm；
(S33) it transfers and is stored in electric energy meter image in server；
(S34) original image is zoomed in and out, to carry out integral calculation to image, and extracts image Harr feature；
(S35) it is exhaustively searched under different scale with sliding window；
(S36) point in image is found out using multilayer cascade classifier, finds out the line feature different from normal electric energy meter appearance
Or net-like character or other feature；
(S37) calculated result is exported.
(S4) start data and display calculating analysis system that the display unit shows the categorizing system classification
Count the data of point counting analysis.
In further method: the effective spy for extracting image based on Adaboosting algorithm in the step (S32)
Sign detects target signature to use integral nomography further to eliminate the noise of image.
Positive beneficial effect:
The present invention carries out Image Acquisition using electric energy meter appearance of the industrial CCD imaging sensor to bottom, acquires fast speed,
There is faster speed in a large amount of detection work；
Communication modes between data of the present invention are WLAN, WIFI, infrared ray, bluetooth, one in CAN communication bus
Kind, it can be needed according to user and site layout project selects different communication modes；
The present invention carries out analytic operation to the image that image acquisition units acquire using Adaboosting algorithm, by this method
Referring in the detection of Internet of Things electric energy meter, which can not only make to detect speed, accelerates, and detection accuracy is more accurate, additionally it is possible to make upper layer
Management system carries out more fully monitoring and management to executing agency of lower layer.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of system of the invention；
Fig. 2 is the flow diagram of method of the invention；
Fig. 3 is the method flow diagram of classifier system classification in the present invention；
Fig. 4 is the method schematic diagram of Adaboosting algorithm in the present invention；
Fig. 5 is a kind of Harr feature schematic diagram of embodiment of the invention；
Fig. 6 is the schematic diagram that a kind of Harr feature of embodiment of the invention extends；
Fig. 7 is the digital schematic diagram of the Harr feature of another specific embodiment of the invention；
Fig. 8 is the digital schematic diagram of another kind of the Harr feature of another specific embodiment of the invention；
Fig. 9 is another digital schematic diagram of the Harr feature of another specific embodiment of the invention.
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 every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, a kind of system for quickly analyzing electric energy meter presentation quality based on Adaboosting algorithm, feature
It is: including electric energy meter calibration pipeline system, the Image Acquisition system being arranged in inside the electric energy meter calibration pipeline system
System, the storage server being connect with described image acquisition system, the upper layer data management system being connect with the storage server,
It is also integrated with classifier system inside the storage server, calculates analysis system, alarm unit and connects with the alarm unit
The display unit connect, in which:
Described image acquisition system is used to acquire the appearance images of the batch electric energy meter in electric energy meter calibration pipeline system；
The storage server is used to manage and handle the electric energy meter appearance images data of described image acquisition system acquisition；
The upper layer data management system is used to carry out data and information communication, realization and bottom with the batch storage server
The management and control of electric energy meter calibration data in electric energy meter calibration pipeline system；
The image data that the categorizing system is used to acquire described image acquisition system is classified；
The calculating analysis system is for being calculated and being analyzed to the sorted detection data of the categorizing system；
The display unit calculates the data of output for the calculating analysis system, and in a particular embodiment, display unit is
LCD liquid crystal display device.
The alarm unit is used for the abnormal data warning note to output.In a particular embodiment, it can also manually adjust
Whole is silent mode, and alarm unit is embedded in inside storage server, loudspeaker is provided on alarm unit and is raised with described
The single-chip microcontroller of sound device connection connects with by the single-chip microcontroller and by monolithic processor controlled digital switch.
In a further embodiment, described image acquisition system includes to be arranged in the electric energy meter calibration pipeline system
Light-source system on framework senses the ccd image sensor of electric energy meter appearance images, the light source system by the light-source system
System is LCD matrix series of light sources.Ccd image sensor sensitivity, resolution ratio, in terms of have it is apparent excellent
Gesture, ccd image sensor can directly convert optical signals into analog current signal, and current signal turns by amplification and modulus
It changes, realizes acquisition, storage, transmission, processing and the reproduction of image.The present invention is online using ccd image sensor sensing electric energy meter
Information, speed is fast, and accuracy is high.
In further technical solution, the calculating analysis system includes Adaboosting algorithm model.
In further technical solution, the classifier system is by least two strong classifiers after cascade.
In further technical solution, the connection of the electric energy meter calibration pipeline system and described image acquisition system
Mode, the connection type of described image acquisition system and the storage server and the storage server and the upper number of plies
Communication modes according to management system are one of WLAN, WIFI, infrared ray, bluetooth, CAN communication bus.
As shown in figs 2-4, a method of electric energy meter presentation quality is quickly analyzed based on Adaboosting algorithm,
It is characterized in that: the following steps are included:
(S1) detection and batch electric energy meter to be detected in electric energy meter calibration pipeline system are acquired by image capturing system
Image；
(S2) image that described image acquisition system acquires is saved in the storage server, starts classifier system, it is right
The characteristics of image saved is classified, wherein the method for the classification are as follows:
(S21) sample is selected from the characteristics of image of preservation, the sample of selection is trained, training sample set；
(S22) trained sample set is pre-processed；
(S23) selection matrix feature constitutes Weak Classifier in characteristics of image after the pre-treatment；
(S24) several Weak Classifiers are constituted into strong classifier；
(S25) several Weak Classifiers are constituted into strong classifier；
(S26) strong classifier is cascaded and constitutes Multilayer Classifier；
(S27) Multilayer Classifier is cascaded, constitutes multilayer cascade classifier；
(S3) start the calculating analysis system, image characteristic analysis, calculating to classifier system classification；The wherein calculating
The method that analysis system is calculated and analyzed are as follows:
(S31) multilayer cascade classifier is loaded, initial work is completed；
(S32) validity feature of image is extracted based on Adaboosting algorithm；
(S33) it transfers and is stored in electric energy meter image in server；
(S34) original image is zoomed in and out, to carry out integral calculation to image, and extracts image Harr feature；
(S35) it is exhaustively searched under different scale with sliding window；
(S36) point in image is found out using multilayer cascade classifier, finds out the line feature different from normal electric energy meter appearance
Or net-like character or other feature；
(S37) calculated result is exported.
(S4) start data and display calculating analysis system that the display unit shows the categorizing system classification
Count the data of point counting analysis.
In further method: the effective spy for extracting image based on Adaboosting algorithm in the step (S32)
Sign detects target signature to use integral nomography further to eliminate the noise of image.
In the above-mentioned methods:
For step S1: image acquisition units can be set on the frame of electric energy meter calibration assembly line, by WLAN,
One of WIFI, infrared ray, bluetooth, CAN communication bus communication modes are connect with storage server, the position of image acquisition units
Setting can need to be arranged in place according to user.
For step S2: the pretreatment to image is the characteristic image for image to be processed being made 24*24dpi, will be surveyed
Sample originally normalizes to the image size of its integral multiple, both can quickly detection image feature, can also be at actually detected place
Window sliding is carried out in reason, completes the detection of substantially image.When choosing sample, detected image is melted into a data set
It closes, data acquisition system is trained to Weak Classifier, when being classified, as makes the quantity of sample more as much as possible as possible, thus
Weak Classifier can be trained to strong classifier by multiple samples, so that strong classifier pond is formed, then in classifier pond
One classifier of reselection, can be added in cascaded series, carry out being cascaded into multilayer strong classifier, pass through the multiple instruction of loop iteration
Practice, is finally trained to object classifiers, i.e. multilayer strong classifier.Algorithm itself is to change data distribution to realize, it is according to every
Whether the classification of each sample among secondary training set correct and the accuracy rate of general classification of last time, to determine each sample
This weight.It gives the new data for modifying weight to sub-classification device to be trained, the classifier for then obtaining each training
Fusion is got up, as last Decision Classfication device.Each strong classifier is cascaded into Multilayer Classifier again, the purpose done so is not
It only can be improved the speed of service, for particularly necessary in large-scale batch detection.
For step S3: trained multilayer cascade classifier being loaded, prepares subsequent work, then uses
Adaboosting algorithm extracts the validity feature of image, when carrying out feature extraction, eliminates making an uproar for image using integral nomography
Sound so that noise can be eliminated, and can be improved picture quality, and can detecte target signature.When carrying out feature extraction,
Establish modified Haar-like rectangular characteristic collection, which can be in detection line feature, center ring characteristics, diagonal
Line feature and edge feature have compatibility.
In this step, as shown in Fig. 5-Fig. 6, it is assumed that define 4 kinds of different rectangular characteristics, the A and B in figure are referred to as two
Rectangular characteristic, then C and D is known respectively as three rectangular characteristics and four rectangular characteristics, the grey rectangle of characteristic value being calculated as in figure
In the sum of pixel value subtract the value of the sum of pixel value in white rectangle, features described above figure is inadequate in a particular embodiment
With, therefore again in specific embodiment, usual expansible use.Fig. 5 is expansible practical embodiment diagram, in the figure, into
Multiple rectangular extensions are gone.
When carrying out integral calculation, as shown in Figure 7 and Figure 8, the definition of integral image: i(x, y are set) indicate original image coordinate
The gray value of point (x, y), the value of integral image coordinate points (x, y) are denoted as ii(x, y), then integral image are as follows:
Formula 1
I.e. from the sum of all pixels point of the upper left corner point-to-point (x, y) of image (rectangular area of grey in figure) gray value, ii
The specific calculating of (x, y) can be obtained by following iterative formula to calculate:
Formula 2
Formula 3
Wherein s (x, y) is that the accumulation of image line and boundary value s (x, -1) and ii(-1, y) are defined as 0.It was calculating in this way
Many troubles are just saved in journey, are directly started counting from 0, are calculated.Therefore, by above-mentioned formula, the calculating of rectangular characteristic just becomes
It at simple addition and subtraction, can exhaustively be searched under different scale with sliding window, be carried out according to the image of search
Different operations is found out the point in image using above-mentioned trained multilayer cascade classifier, is found out different from normal electric energy meter
The line feature or net-like character or other feature of appearance, can meet the needs of users.
Integral algorithm is further described in conjunction with a specific embodiment below.
As shown in figs. 7 to 9, can be exactly for value of the integral image in position 1 with the method that integrogram calculates rectangular characteristic
The sum of rectangle A all pixels point gray value, similarly, the value of position 2 correspond to rectangle A+B, 3 corresponding rectangle A+C, 4 corresponding A+B+C+
D, then seeking the sum of pixel value in rectangle D is 4+1-(2+3), it is Haar_*2 rectangular characteristic in Fig. 9, it can by its definition
Know, characteristic value is (1+5-2-4)-(2+6-3-5), it is only necessary to know that the value of 6 points on integral image, by simply adding and subtracting
Method can be found out, therefore other kinds of rectangular characteristic can be calculated similarly, in a particular embodiment, three rectangles
Feature then needs 8 points on integral image.Therefore the image for being just visually extracted acquisition image using integral nomography is special
Sign, and operation is carried out according to the feature of image.
For step S4: the calculated data in above-mentioned steps being shown by display unit, according to the specific of user
It needs, can show the data of categorizing system classification, can also show that the calculating analysis system calculates the data of analysis, display
Data for customer analysis and use.
Although specific embodiments of the present invention have been described above, it will be appreciated by those of skill in the art that these
Specific embodiment is merely illustrative of, those skilled in the art in the case where not departing from the principle and substance of the present invention,
Various omissions, substitutions and changes can be carried out to the details of the above method and system.For example, merge above method step, thus
Substantially identical function is executed according to substantially identical method to realize that substantially identical result then belongs to the scope of the present invention.Cause
This, the scope of the present invention is only limited by the claims that follow.
Claims (7)
1. a kind of system for quickly analyzing electric energy meter presentation quality based on data mining algorithm, it is characterised in that: including electric energy meter
Calibrating pipeline system, the image capturing system being arranged in inside the electric energy meter calibration pipeline system are adopted with described image
The storage server of collecting system connection, the upper layer data management system being connect with the storage server, the storage server
Inside is also integrated with classifier system, calculates analysis system, alarm unit and the display unit connecting with the alarm unit,
In:
Described image acquisition system is used to acquire the appearance images of the batch electric energy meter in electric energy meter calibration pipeline system；
The storage server is used to manage and handle the electric energy meter appearance images data of described image acquisition system acquisition；
The upper layer data management system is used to carry out data and information communication, realization and bottom with the batch storage server
The management and control of electric energy meter calibration data in electric energy meter calibration pipeline system；
The image data that the categorizing system is used to acquire described image acquisition system is classified；
The calculating analysis system is for being calculated and being analyzed to the sorted detection data of the categorizing system；
The display unit calculates the data of output for the calculating analysis system,
The alarm unit is used for the abnormal data warning note to output.
2. the system according to claim 1 for quickly analyzing electric energy meter presentation quality based on data mining algorithm, feature
Be: described image acquisition system includes the light-source system being arranged on the electric energy meter calibration pipeline system framework, is passed through
The ccd image sensor of the light-source system sensing electric energy meter appearance images, the light-source system are LCD matrix series of light sources.
3. the system according to claim 1 for quickly analyzing electric energy meter presentation quality based on data mining algorithm, feature
Be: the calculating analysis system includes Adaboosting algorithm model.
4. the system according to claim 1 for quickly analyzing electric energy meter presentation quality based on data mining algorithm, feature
Be: the classifier system is by least two strong classifiers after cascade.
5. the system according to claim 1 for quickly analyzing electric energy meter presentation quality based on data mining algorithm, feature
Be: the connection type of the electric energy meter calibration pipeline system and described image acquisition system, described image acquisition system with
The communication modes of the connection type of the storage server and the storage server and the upper layer data management system are
One of WLAN, WIFI, infrared ray, bluetooth, CAN communication bus.
6. a kind of method for quickly analyzing electric energy meter presentation quality based on data mining algorithm, it is characterised in that: including following step
It is rapid:
(S1) detection and batch electric energy meter to be detected in electric energy meter calibration pipeline system are acquired by image capturing system
Image；
(S2) image that described image acquisition system acquires is saved in the storage server, starts classifier system, it is right
The characteristics of image saved is classified, wherein the method for the classification are as follows:
(S21) sample is selected from the characteristics of image of preservation, the sample of selection is trained, training sample set；
(S22) trained sample set is pre-processed；
(S23) selection matrix feature constitutes Weak Classifier in characteristics of image after the pre-treatment；
(S24) several Weak Classifiers are constituted into strong classifier；
(S25) several Weak Classifiers are constituted into strong classifier；
(S26) strong classifier is cascaded and constitutes Multilayer Classifier；
(S27) Multilayer Classifier is cascaded, constitutes multilayer cascade classifier；
(S3) start the calculating analysis system, image characteristic analysis, calculating to classifier system classification；The wherein calculating
The method that analysis system is calculated and analyzed are as follows:
(S31) multilayer cascade classifier is loaded, initial work is completed；
(S32) validity feature of image is extracted based on Adaboosting algorithm；
(S33) it transfers and is stored in electric energy meter image in server；
(S34) original image is zoomed in and out, to carry out integral calculation to image, and extracts image Harr feature；
(S35) it is exhaustively searched under different scale with sliding window；
(S36) point in image is found out using multilayer cascade classifier, finds out the line feature different from normal electric energy meter appearance
Or net-like character or other feature；
(S37) calculated result is exported；
(S4) start data and the display calculating analysis system meter that the display unit shows the categorizing system classification
The data of point counting analysis.
7. a kind of method that electric energy meter presentation quality is quickly analyzed based on data mining algorithm according to claim 6,
It is characterized in that: the validity feature of image being extracted as using integral graphic calculation based on Adaboosting algorithm in the step (S32)
Method detects target signature further to eliminate the noise of image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710394788.2A CN108985308A (en) | 2017-05-30 | 2017-05-30 | The system and method for electric energy meter presentation quality is quickly analyzed based on data mining algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710394788.2A CN108985308A (en) | 2017-05-30 | 2017-05-30 | The system and method for electric energy meter presentation quality is quickly analyzed based on data mining algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108985308A true CN108985308A (en) | 2018-12-11 |
Family
ID=64500911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710394788.2A Pending CN108985308A (en) | 2017-05-30 | 2017-05-30 | The system and method for electric energy meter presentation quality is quickly analyzed based on data mining algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108985308A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111929633A (en) * | 2020-05-31 | 2020-11-13 | 宁夏隆基宁光仪表股份有限公司 | Electric energy meter detection system and method based on fusion ant colony algorithm |
| CN113052516A (en) * | 2021-05-31 | 2021-06-29 | 深圳高灯计算机科技有限公司 | Wind control method, system and equipment based on stream type calculation |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678755A (en) * | 2015-12-31 | 2016-06-15 | 青岛歌尔声学科技有限公司 | Product state detection method and system based on Adaboost algorithm |
-
2017
- 2017-05-30 CN CN201710394788.2A patent/CN108985308A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678755A (en) * | 2015-12-31 | 2016-06-15 | 青岛歌尔声学科技有限公司 | Product state detection method and system based on Adaboost algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 胡雄心等: "基于Adaboosting算法的表面裂纹图象检测", 《机械设计与制造》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111929633A (en) * | 2020-05-31 | 2020-11-13 | 宁夏隆基宁光仪表股份有限公司 | Electric energy meter detection system and method based on fusion ant colony algorithm |
| CN113052516A (en) * | 2021-05-31 | 2021-06-29 | 深圳高灯计算机科技有限公司 | Wind control method, system and equipment based on stream type calculation |
| CN113052516B (en) * | 2021-05-31 | 2022-01-04 | 深圳高灯计算机科技有限公司 | Wind control method, system and equipment based on stream type calculation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103528617B (en) | A kind of cockpit instrument identifies and detection method and device automatically | |
| CN101426150B (en) | Video image quality evaluation method and system | |
| CN104809463B (en) | A kind of high-precision fire disaster flame detection method for converting dictionary learning based on intensive scale invariant feature | |
| CN111310692B (en) | Detection object management method, system, machine readable medium and equipment | |
| CN109977191B (en) | Problem map detection method, device, electronic equipment and medium | |
| CN102589705B (en) | Single-blackbody temperature-controlled MRTD (Minimum Resolvable Temperature Difference) field online automatic detection device and method for thermal imager | |
| CN111202504A (en) | Abnormal object management method, system, machine readable medium and equipment | |
| TW201250608A (en) | Image comparison system and method | |
| US11908183B2 (en) | Image analysis and processing pipeline with real-time feedback and autocapture capabilities, and visualization and configuration system | |
| CN109948637A (en) | Object test equipment, method for checking object and computer-readable medium | |
| CN105589801A (en) | Mobile phone cluster test method and system | |
| CN112014413A (en) | Mobile phone glass cover plate window area defect detection method based on machine vision | |
| Han et al. | Improved visual background extractor using an adaptive distance threshold | |
| CN111656393A (en) | Histological image analysis | |
| Ma et al. | Dynamic gesture contour feature extraction method using residual network transfer learning | |
| CN108960413A (en) | A kind of depth convolutional neural networks method applied to screw surface defects detection | |
| CN108985308A (en) | The system and method for electric energy meter presentation quality is quickly analyzed based on data mining algorithm | |
| Shao et al. | Research on automatic identification system of tobacco diseases | |
| Guosheng et al. | An intelligent defect detection system for warp-knitted fabric | |
| CN112699824B (en) | Method and device for detecting constant of electric energy meter and storage medium | |
| Zhang et al. | Automatic counting of retinal ganglion cells in the entire mouse retina based on improved YOLOv5 | |
| CN108563997A (en) | It is a kind of establish Face datection model, recognition of face method and apparatus | |
| Pujari et al. | Detection and classification of fungal disease with radon transform and support vector machine affected on cereals | |
| Nan et al. | Pedestrian detection based on HOG features and SVM realizes vehicle-human-environment interaction | |
| Deng et al. | Automatic estimation of rice grain number based on a convolutional neural network |
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: 20181211 |