CN100498819C - Automatic recognising method for digital telemetering image of flow meter and digital telemetering recording system - Google Patents
Automatic recognising method for digital telemetering image of flow meter and digital telemetering recording system Download PDFInfo
- Publication number
- CN100498819C CN100498819C CNB2006101558699A CN200610155869A CN100498819C CN 100498819 C CN100498819 C CN 100498819C CN B2006101558699 A CNB2006101558699 A CN B2006101558699A CN 200610155869 A CN200610155869 A CN 200610155869A CN 100498819 C CN100498819 C CN 100498819C
- Authority
- CN
- China
- Prior art keywords
- image
- meter
- voyage
- digital
- feature
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Processing (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
A method for identifying digital telemetering image of flow rate charging meter includes preprocessing image, positioning characters, detailing image, picking up characteristics and identifying characters. The digital telemetering-copying system of flow rate charging meter is also disclosed.
Description
Technical field
The invention belongs to number automatic identification technology field, the digital telemetering kilowatt meter reading-out system that relates in particular to a kind of charge on traffic table digital telemetering automatic distinguishing method for image and match with said method.
Background technology
Since reform and opening-up, China's urban population sharply increases.Along with the rapid expansion of Construction Scale of Residential Building, the installation of water meter and gas meter also increases considerably.Bring the following problem thus:
(1) domestic floor in recent years generally is higher than before the reform and opening-up, and meter reading personnel's labour intensity obviously strengthens;
(2) resident family obviously is less than before the reform and opening-up time of being in, when causing checking meter in the family unmanned situation often take place, some resident families will come and go repeatedly can finish the work of checking meter;
(3) pretend to be the person's of checking meter private to rush private residence and make cases and take place often, cause the distrust of resident family, refuse it and enter for the meter reading personnel;
(4) for the protection individual privacy, the stranger that is unwilling of some resident families enters;
(5) check meter result and the inconsistent situation of resident family's reading also takes place often, owing to have no basis and can look into, thereby often cause unnecessary controversial issue.
One of best method that addresses the above problem is exactly the teletransmission charging way of realization table meter, and the table meter continuous data that is about to each user is delivered to a concentrated billing terminal by the teletransmission mode, thereby does not need the person of checking meter to enter user's dwelling house statistics.
Along with people's living standard improves constantly, common people have higher requirement to living environment; Under the inspiration of government policy, home intelligence has obtained development at a high speed.Simultaneously, along with development of science and technology, the sub-district dwelling house also will bring resident family with convenient, timesaving estate management except satisfying the most basic inhabitation requirement of people.Realize the intelligent meter data recording system of dwelling house, become the essential condition of novel intelligent sub-district.
By above-mentioned analysis as can be known developing intellectual resource table meter metering reading remote meter-reading system have very clear and definite, broad, the urgent market demand.Therefore, on the basis of analyzing similar products at home and abroad, reliable, the lower-cost table meter of development work remote meter-reading system is the new problem of being badly in need of solution that the fast development of novel intelligent sub-district proposes the scientific research personnel.By to this important function for of research, can make Running-water Company, Gas Company and property department fundamentally cancel numerous and diverse work of manually checking meter to the doorstep, reach accurately and easily charge, can save the dispute that manually can reduce again between water supply department and the client.It not only can improve the work efficiency of administrative authority, also adapts to the new demand that modern day user is paid the fees to water usefulness gas.
The reading technique of present most enterprises still is the pulsimeter numerical expression, but the kilowatt meter reading-out system of this active mode all can occur producing error because of outage, broken string make table meter and teletransmission data in actual applications.
The present domestic multiple passive remote meter-reading system of having developed, except that the camera shooting type remote meter-reading system, other passive remote meter-reading systems are basically all with sensor or read components and parts to be installed in the table meter inner.These remote meter-reading systems can be worked in dry-type meter or gas meter, but can't be in the medium-term and long-term work of wet-type meter.Simultaneously, the data capture unit of these a few class remote meter-reading systems all has certain complicacy.
Because above-mentioned existing problems, thus at present at home the immediate development trend of remote meter-reading system be to be direction substantially with " passive ", " direct-reading ".The camera shooting type remote meter-reading system belongs to a kind of real passive direct-reading working method, has begun to obtain researchist's concern.No matter do, wet environment, it can steady operation, so the camera shooting type remote meter-reading system will become the developing direction of remote meter-reading system from now on.
Summary of the invention
The present invention is intended to overcome the deficiencies in the prior art part and a kind of high efficiency is provided, the counting cost by gas meter cost is low, can realize the automatic collection of table meter view data in the certain limit, and related data is sent to management control center in real time, on this management control center server, focus on and the charge on traffic table digital telemetering automatic distinguishing method for image of identification automatically.In addition, the present invention also provides the digital telemetering kilowatt meter reading-out system that a kind of and above-mentioned image-recognizing method matches.
The object of the present invention is achieved like this: charge on traffic table digital telemetering automatic distinguishing method for image, can implement according to following steps:
1) image pre-service;
2) character locating;
3) image thinning;
4) feature extraction;
5) character recognition;
Described step 1) comprises that the original reading image to collecting carries out noise reduction, dividing processing; Adopt the noise in the template filter method removal image, adopt the adaptive threshold method that image is carried out binary conversion treatment simultaneously; Described step 2) adopt the multiple projections method to locate the position of each numeral in table meter image; Described step 3) is to adopt thinning algorithm to obtain the wide number body of single pixel; Described step 4) takes the Extraction of Geometrical Features method that corresponding feature is extracted; Described geometric properties comprises threading feature, voyage feature and some feature; Described step 5) adopts many Feature Fusion method, carries out character recognition in conjunction with the relevant different geometric properties that extracted.
A kind ofly implement the digital telemetering kilowatt meter reading-out system that above-mentioned charge on traffic table digital telemetering automatic distinguishing method for image is adopted, it comprises: image acquisition and preprocessing part, digital signal processing part, data memory module, display part and tcp data segment; Described image acquisition and preprocessing part acquisition tables meter character wheel number image also carry out pre-service to it; Described digital signal processing partly receives the data from image acquisition and preprocessing part, carry out calculation process after, again correlated results is stored in the data memory module; Described display part his-and-hers watches gauge mark sign indicating number image recognition information is shown; Described image acquisition and preprocessing part comprise: array image sensor, video decode part, FPGA (Field Programmable Gate Array) control section; The exchanges data of realization of described FPGA (Field Programmable Gate Array) control section and array image sensor, video decode part and data memory module; Described video decode part will convert Digital Image Data to from the picture signal of array image sensor, isolate corresponding synchronizing signal simultaneously; Described digital signal processing part is stored in data image signal in the data memory module under the coordination of synchronizing signal; The result that will check meter is sent in the terminal device described tcp data segment.
The present invention includes the relevant design of hardware and software of embedded system, at the technology such as Digital Image Processing algorithm research, data transmission and storage of table meter dial plate.The present invention combines embedded system with Digital Image Processing and mode identification technology, can satisfy social needs the social life that is convenient for people to.
Water meter, gas meter remote meter-reading system based on image recognition also are sent to the table meter image data acquiring in the certain limit administrative center of these building in real time by adopting mechanics of communication, Digital Signal Processing, control technology etc. by communication network.On the server of this administrative center, focus on and discern automatically the metering reading of each table meter, thereby realized the teletransmission automatic data logging that table is counted, improved the work efficiency of checking meter, reduced the cost of counting cost by gas meter.
Adopting machine vision technique to replace human eye vision and read table meter continuous data, is that existing table meter continuous data teletransmission method is incomparable, also is main characteristic of the present invention, mainly shows the following aspects:
(1) have table meter remote transmitting system sensor now and be installed in table meter inside, the user cannot see, even detected result and table meter dial plate dish data consistent also cause user's suspection easily, is difficult to check when going wrong.And the data that native system the obtains reading that in fact to be exactly the user see on table meter dial plate, and can store in the mode of image by the metering reading when checking meter, be convenient to inquire about afterwards.
(2) native system does not need real-time power supply, and power supply just just is provided when needs are checked meter temporarily.In fact the data of being obtained are exactly the reading that the user sees on table meter dial plate, therefore, do not exist because the mistake of checking meter that factors such as systematic error, cumulative errors cause.
(3) this kilowatt meter reading-out system utilizes DSP to make up the embedded system operation, has realized that the off-line processing of continuous data and scene obtain.
(4) aspect the identification of table meter reading, because the rolling of table meter wheel disc causes the number body usually to be divided into two parts up and down, as shown in Figure 1.When occurring up and down two countings on reading position in the table meter, promptly two numerals are incomplete situation up and down, and this kilowatt meter reading-out system can identify correct result exactly.
Water meter, gas meter remote meter-reading system based on image recognition are not worked at ordinary times, not electricity consumption, no power consumption; Working environment there is not specific (special) requirements (water temperature, working pressure etc.).
Description of drawings
The invention will be further described below in conjunction with the drawings and specific embodiments.But protection scope of the present invention will not only be confined to the statement of following content.
Fig. 1 the present invention is based on digit recognition process flow diagram in the table meter image of many Feature Fusion;
Fig. 2 carries out result schematic diagram after noise reduction and binaryzation are cut apart for the present invention to the image that is collected;
Fig. 3 carries out result schematic diagram after reading on each reading position positions for the present invention to pretreated image;
Fig. 4 is an image thinning synoptic diagram of the present invention;
Fig. 5 is the voyage synoptic diagram of the present invention's numeral body;
Fig. 6 is the threading feature synoptic diagram of character of the present invention;
Fig. 7 puts the feature synoptic diagram for the present invention;
The hardware architecture block diagram that Fig. 8 discerns automatically for table meter reading of the present invention;
The hardware circuit principle figure that Fig. 9 discerns automatically for table meter reading of the present invention.
Embodiment
Charge on traffic table digital telemetering automatic distinguishing method for image, can implement according to following steps:
1) image pre-service;
2) character locating;
3) image thinning;
4) feature extraction;
5) character recognition.
Wherein, step 1) comprises that the original reading image to collecting carries out noise reduction, dividing processing, can specifically adopt the noise in the template filter method removal image, adopts the adaptive threshold method that image is carried out binary conversion treatment simultaneously; Step 2) can adopt the multiple projections method to locate the position of each numeral in table meter image; Step 3) system adopts thinning algorithm to obtain the wide number body of single pixel; Step 4) takes the Extraction of Geometrical Features method that corresponding feature is extracted; Described geometric properties comprises threading feature, voyage feature and some feature; Described step 5) adopts many Feature Fusion method, carries out character recognition in conjunction with the relevant different geometric properties that extracted.
With the digital telemetering kilowatt meter reading-out system that above-mentioned charge on traffic table digital telemetering automatic distinguishing method for image matches, it comprises: image acquisition and preprocessing part, digital signal processing part, data memory module, display part; Described image acquisition and preprocessing part acquisition tables meter character wheel number image also carry out pre-service to it; Described digital signal processing partly receives the data from image acquisition and preprocessing part, carry out calculation process after, again correlated results is stored in the data memory module; Described display part his-and-hers watches gauge mark sign indicating number image recognition information is shown.Wherein, image acquisition and preprocessing part comprise: array image sensor, video decode part, FPGA (Field Programmable Gate Array) control section; The exchanges data of realization of described FPGA (Field Programmable Gate Array) control section and array image sensor, video decode part and data memory module; Described video decode part will convert Digital Image Data to from the picture signal of array image sensor, isolate corresponding synchronizing signal simultaneously; Described digital signal processing part is stored in data image signal in the data memory module under the coordination of synchronizing signal.
The present invention is important technical with the Computer Vision Detection, and the knowledge of integrated use Flame Image Process and pattern-recognition has realized the automatic identification technology of table meter continuous datas such as water meter, gas meter.In conjunction with the DSP circuit, the location of the collection by his-and-hers watches gauge mark sign indicating number image, Flame Image Process, number body, number identification scheduling algorithm have been finished a kind of water meter based on image recognition, gas meter remote meter-reading system aspect two of software and hardwares.
The present invention includes recognition methods and hardware and realize two aspects.
One. recognition methods
The present invention is by following step in recognition methods:
Step 1: image pre-service
The image pre-service comprises: image noise reduction, adaptive threshold method are carried out binaryzation to image and are cut apart.
Step 2: character locating
Adopt the method for multiple projections to determine the accurate position of each numeral in image.
Step 3: image thinning
Adopt thinning algorithm to obtain the wide number body of single pixel.
Step 4: feature extraction
Comprise geometric properties such as threading feature, voyage feature, some feature.
Step 5: character recognition
The feature of utilizing above-mentioned steps to obtain adopts the Feature Fusion technology, according to the method for progressively segmentation each number is discerned.
Two. the hardware circuit based on DSP is realized
Hardware circuit design based on DSP among the present invention mainly is made up of five parts such as image acquisition and pre-process circuit, Digital Image Processing circuit, data storage circuitry, data transmission and recognition result display circuits.
Image acquisition and pre-process circuit utilize opto-electronic conversion to come acquisition tables meter character wheel number image, and carry out necessary pre-service, comprise that anti-aliasing filter, amplification and A/D conversion etc. obtain showing to count the Digital Image Data of character wheel number, and offer digital signal processor (DSP).The Digital Image Processing circuit carries out further computing and processing with the Digital Image Data that collects, as binaryzation etc., obtain and show the corresponding data of gauge mark sign indicating number, and be kept in the data storage circuitry, by display circuit the result is intuitively shown at last and foundation is exported the preservation meter reading data with communicating by letter of miscellaneous equipment.
Utilize foregoing circuit the present invention realized based on the DSP circuit water meter, gas meter remote meter-reading system.
The present invention propose at the digit recognition method flow process of table meter as shown in Figure 1, concrete implementation step is as follows:
Step 1: image pre-service
The first, image noise reduction
The method of employing template filtering is removed the noise in the image.
The second, image segmentation
The present invention adopts the adaptive threshold method that image is carried out binary conversion treatment, thereby the reading on each reading position is separated with table meter image.
The dial plate of his-and-hers watches meter carries out image acquisition, and the original reading image that collects is carried out noise reduction, dividing processing, and resulting image as shown in Figure 2.
Step 2: character locating
The present invention adopts the method for multiple projections accurately to locate the position of each numeral on each reading position (comprising the imperfect numeral that is occurred) in table meter image.
The first, carry out the overall positions of the reading in the vertical direction on each reading position in the horizontal projection navigation watch meter image.
The second, carry out that on each reading position bits per inch word position in the horizontal direction in the vertical projection navigation watch meter image.
The 3rd, carry out horizontal projection and locate the individual digit on each reading position or the position of two imperfect digital in the vertical directions.
Shown in Figure 3 is the positioning result of the reading on all reading positions in the his-and-hers watches meter image.
Step 3: image thinning
The numeral that extracts is carried out thinning processing, obtain the wide digital picture of single pixel.Image after the refinement as shown in Figure 4.
Step 4: feature extraction
Character recognition of the present invention is based on the recognition methods of geometric properties, comprising threading feature, voyage feature and end points feature etc.
Feature extraction
(1) voyage feature extraction
Last voyage is meant and begins to arrive vertically downward the pixel distance that the number body is passed by from the coboundary of number.Its computing method are: the position of number body in image, location, and top, bottom, left, right are respectively the position of number body in image.With voyage on the array numbertop record number body, array size is right-left+1.In the posting of number body, i represents the ordinate of orthogonal axes of number body, and j represents the transverse axis coordinate of number body, 0＜=i＜bottom-top+1,0＜=j＜right-left+1.J number unit is numbertop[j], when the transverse axis coordinate was j, i increased gradually since 0, up to touching the number body for finishing.Numbertop[j] value of i when having write down end.Have array numbertop[j] in the last voyage that is number.
Following voyage is that the lower boundary from the number body begins to arrive vertically upward the pixel distance that the number body is passed by.
Left side voyage is that the left margin from the number body begins level and arrives the pixel distance that the number body is passed by to the right.
Right voyage is that the right margin from the number body begins level and arrives the pixel distance that the number body is passed by left.
The voyage area refer to each element in the voyage array and, be divided into upper and lower, left and right voyage area equally.Above voyage area is an example, is exactly the number of passes group numbertop[j of Shanghai Airways, Ltd.] in each numerical value and.Fig. 5 is 0 to 9 all digital voyage synoptic diagram.Wherein, a5 is the image after the binaryzation, and b5 is the image after locating, and c5 is left voyage, and d5 is right voyage, and e5 is last voyage, and f5 is following voyage.
(2) threading feature extraction
The threading feature is to utilize threading method that resulting a kind of geometric properties handled in character.
Threading method is to utilize one group of parallel straight line body of checking numbers to pass through the number of calculated line and number body intersection point, thereby class number.Shown in Figure 6 is to utilize an alphabetical S to represent the threading feature, and wherein a is the original character image after cutting apart, and b is horizontal threading process, and c is vertical threading process.
Among Fig. 6, when passing through English character " S " with three parallel lines levels, from top to bottom, the intersection point number of article one straight line and number is 2, and it is 1 that second is 1, the three.When vertically passing through English character " S " with three parallel lines, from left to right, the intersection point number of article one straight line and number is 2, and it is 2 that second is 3, the three.Wherein, a6 is a letter image, and b6 is horizontal threading, and c6 is vertical threading.
(3) some feature extraction
Because uneven illumination is even, the reasons such as dial plate reflection of table meter exist, the numeral on the table meter image that obtains has distortion in various degree, distortion such as adhesion, broken string perhaps occur.At this moment the geometric properties such as threading, voyage that only utilize character can't solve the image fault distortion and influence the problem of recognition result.
Image behind the edge thinning is handled according to a feature, and the unique point on its edge can be divided into following a few class: four crunodes, triradius, line point and distal point, Fig. 7 are the synoptic diagram of these a few category feature points.Utilized this 3 class points feature of four crunodes, triradius and distal point in this recognition methods.Wherein, a7 is four crunodes, and b7 is a triradius, and c7 is the line point, and d7 is a distal point.
(4) other Extraction of Geometrical Features
Step 5: digit recognition
The present invention proposes a kind of many Feature Fusion method, the feature such as threading, voyage, unique point that promptly merges digital body is carried out the identification of digital body.In identifying, adopt from top to bottom Xi Fen recognition methods step by step.
Hardware based on DSP is realized
This device hardware components is mainly formed system hardware general structure such as Fig. 8, shown in Figure 9 by five parts such as image acquisition and pre-process circuit, Digital Image Processing circuit, data storage circuitry, data transmission circuit and recognition result display circuits.
Image acquisition and pre-process circuit utilize opto-electronic conversion to come acquisition tables meter character wheel number image, and carry out necessary pre-service, comprise that anti-aliasing filter, amplification and A/D conversion etc. obtain showing to count the Digital Image Data of character wheel number, and offer digital signal processor (DSP).The Digital Image Processing circuit carries out further computing and processing with the Digital Image Data that collects, as binaryzation etc., obtain and show the corresponding data of gauge mark sign indicating number, and be kept in the data storage circuitry, by display circuit the result is intuitively shown at last and foundation is transmitted the preservation meter reading data with communicating by letter of miscellaneous equipment.
The principle of work of Circuits System: by the analog picture signal of simulation camera collection through treatment conversion such as the amplification of image pre-process circuit and A/D conversions for satisfying the data image signal of system requirements, isolate the synchronizing signal of correspondence simultaneously; Then, digital signal processor (DSP) is saved in data image signal under the coordination of synchronizing signal in the image data storage space of system, for follow-up secondary pre-service of number image and identification are ready to data source; Just this image is cut apart and secondary pre-service such as binaryzation later on when having stored a complete table gauge mark sign indicating number image, carried out the identification of number then and handle; Recognition result is shown intuitively (Fig. 9) by the LED display circuit after having discerned a width of cloth number image.
Claims (2)
1, charge on traffic table digital telemetering automatic distinguishing method for image is characterized in that, can implement according to following steps:
1) image pre-service;
2) character locating;
3) image thinning;
4) feature extraction;
5) character recognition;
Described step 1) comprises that the original reading image to collecting carries out noise reduction, dividing processing; Adopt the noise in the template filter method removal image, adopt the adaptive threshold method that image is carried out binary conversion treatment simultaneously;
Described step 2) adopt the multiple projections method to locate the position of each numeral in table meter image; It comprises: the overall positions of A) carrying out the reading in the vertical direction on each reading position in the horizontal projection navigation watch meter image; B) carry out that on each reading position bits per inch word position in the horizontal direction in the vertical projection navigation watch meter image; C) carry out horizontal projection and locate the individual digit on each reading position or the position of two imperfect digital in the vertical directions;
Described step 3) is to adopt thinning algorithm to obtain the wide number body of single pixel;
Described step 4) takes the Extraction of Geometrical Features method that corresponding feature is extracted; Described geometric properties comprises threading feature, voyage feature and some feature;
(1) voyage feature extraction
Begin to arrive vertically downward the last voyage of the pixel distance that the number body passed by from the coboundary of number; Begin to arrive vertically upward the following voyage of the pixel distance that the number body passed by from the lower boundary of number body; Begin the left voyage that level arrives the pixel distance that the number body passed by to the right from the left margin of number body; Begin the right voyage that level arrives the pixel distance that the number body passed by left from the right margin of number body; The voyage area of each element sum in the voyage array;
(2) threading feature extraction
Utilize one group of parallel straight line body of checking numbers to pass through the number of calculated line and number body intersection point, thereby class number;
(3) some feature extraction
Image behind the edge thinning is handled according to a feature, and the unique point on its edge can be divided into following a few class: four crunodes, triradius, line point and distal point;
Described step 5) adopts many Feature Fusion method, carries out character recognition in conjunction with the relevant different geometric properties that extracted.
2, a kind of enforcement digital telemetering kilowatt meter reading-out system of being adopted of charge on traffic table digital telemetering automatic distinguishing method for image according to claim 1, it is characterized in that, comprising: image acquisition and preprocessing part, digital signal processing part, data memory module, display part and tcp data segment; Described image acquisition and preprocessing part acquisition tables meter character wheel number image also carry out pre-service to it; Described digital signal processing partly receives the data from image acquisition and preprocessing part, carry out calculation process after, again correlated results is stored in the data memory module; Described display part his-and-hers watches gauge mark sign indicating number image recognition information is shown; Described image acquisition and preprocessing part comprise: array image sensor, video decode part, FPGA (Field Programmable Gate Array) control section; The exchanges data of realization of described FPGA (Field Programmable Gate Array) control section and array image sensor, video decode part and data memory module; Described video decode part will convert Digital Image Data to from the picture signal of array image sensor, isolate corresponding synchronizing signal simultaneously; Described digital signal processing part is stored in data image signal in the data memory module under the coordination of synchronizing signal; The result that will check meter is sent in the terminal device described tcp data segment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2006101558699A CN100498819C (en) | 2006-12-31 | 2006-12-31 | Automatic recognising method for digital telemetering image of flow meter and digital telemetering recording system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2006101558699A CN100498819C (en) | 2006-12-31 | 2006-12-31 | Automatic recognising method for digital telemetering image of flow meter and digital telemetering recording system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101000652A CN101000652A (en) | 2007-07-18 |
| CN100498819C true CN100498819C (en) | 2009-06-10 |
Family
ID=38692618
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2006101558699A Expired - Fee Related CN100498819C (en) | 2006-12-31 | 2006-12-31 | Automatic recognising method for digital telemetering image of flow meter and digital telemetering recording system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100498819C (en) |
Families Citing this family (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556732A (en) * | 2009-05-26 | 2009-10-14 | 无锡虹业腾文电子科技有限公司 | Wireless gas meter reading system |
| CN102236788B (en) * | 2010-04-20 | 2015-09-02 | 荣科科技股份有限公司 | Power meter automatic distinguishing method for image |
| CN103136532A (en) * | 2011-11-22 | 2013-06-05 | 深圳信息职业技术学院 | Dial digital image reading device and method |
| CN103209211B (en) * | 2013-03-06 | 2015-12-02 | 江苏运赢物联网产业发展有限公司 | A kind of method of gauge table Recognition of Reading, the self-service kilowatt meter reading-out system of gauge table and meter register method thereof |
| CN103226706B (en) * | 2013-05-17 | 2016-08-03 | 广东今盛投资有限公司 | A kind of based on the water, electricity and gas meter reading automatic identifying method rolling coupling |
| US10133948B2 (en) * | 2014-07-10 | 2018-11-20 | Sanofi-Aventis Deutschland Gmbh | Device and method for performing optical character recognition |
| CN104680614A (en) * | 2015-03-16 | 2015-06-03 | 四川航天***工程研究所 | Pipeline inspection and flash measurement system based on Beidou |
| CN105120244B (en) * | 2015-04-01 | 2016-07-13 | 国网山东省电力公司嘉祥县供电公司 | Based on the method that electric energy meter is carried out automatic data logging by cmos image collection |
| CN105740849A (en) * | 2015-04-01 | 2016-07-06 | 周杰 | Method for performing automatic data logging on electric energy meter based on image collection |
| CN105657230A (en) * | 2015-04-01 | 2016-06-08 | 周杰 | Method for automatically reading electric energy meter through automatic meter reading platform |
| CN104899587A (en) * | 2015-06-19 | 2015-09-09 | 四川大学 | Machine learning-based digital meter identification method |
| CN105279945A (en) * | 2015-12-04 | 2016-01-27 | 四川有获科技有限公司 | Automatic meter reading system for communities |
| CN105574531A (en) * | 2015-12-11 | 2016-05-11 | 中国电力科学研究院 | Intersection point feature extraction based digital identification method |
| CN106228159A (en) * | 2016-07-29 | 2016-12-14 | 深圳友讯达科技股份有限公司 | A kind of gauge table meter copying device based on image recognition and method thereof |
| CN107356201B (en) * | 2017-07-07 | 2019-11-08 | 杭州山科智能科技股份有限公司 | A kind of camera shooting water meter character wheel coordinate acquiring method and device |
| CN107808159B (en) * | 2017-11-20 | 2019-01-29 | 杭州先锋电子技术股份有限公司 | A kind of digital automatic identification meter register method for measuring instrument machinery dial plate |
| CN110084083B (en) * | 2018-01-26 | 2024-04-19 | 新天科技股份有限公司 | Character detection method based on stroke characteristics |
| CN108416356B (en) * | 2018-05-28 | 2023-08-25 | 成都创智联云科技有限公司 | Character wheel image verification device and control method thereof |
| CN109285333A (en) * | 2018-09-05 | 2019-01-29 | 江苏爱尔数字科技有限公司 | A kind of multidimensional data independence wireless acquisition terminal based on Internet of Things |
| CN109145006A (en) * | 2018-09-21 | 2019-01-04 | 深圳蜜獾智抄科技有限公司 | A kind of collection copies data analysis management system |
| CN110782647A (en) * | 2019-11-06 | 2020-02-11 | 重庆神缘智能科技有限公司 | Intelligent meter reading system based on image recognition |
| CN112149655A (en) * | 2020-09-28 | 2020-12-29 | 怀化建南机器厂有限公司 | Water meter reading identification method, device, equipment and storage medium |
| CN113449639A (en) * | 2021-06-29 | 2021-09-28 | 深圳市海亿达科技股份有限公司 | Non-contact data acquisition method for instrument by gateway of Internet of things |
| CN113743405A (en) * | 2021-09-07 | 2021-12-03 | 南方电网数字电网研究院有限公司 | Intelligent meter reading method and device for electric energy meter |
-
2006
- 2006-12-31 CN CNB2006101558699A patent/CN100498819C/en not_active Expired - Fee Related
Non-Patent Citations (4)
| Title |
|---|
| 人民币纸币序列号识别方法. 王瑞玲，第9-20页，中国优秀博/硕士论文全文数据库. 2006 |
| 人民币纸币序列号识别方法. 王瑞玲，第9-20页，中国优秀博/硕士论文全文数据库. 2006 * |
| 基于DSP的纸币号码识别***. 郑传琴，苑玮琦，于洪霞.成都信息工程学院学报，第20卷第5期. 2005 |
| 基于DSP的纸币号码识别***. 郑传琴，苑玮琦，于洪霞.成都信息工程学院学报，第20卷第5期. 2005 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101000652A (en) | 2007-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100498819C (en) | Automatic recognising method for digital telemetering image of flow meter and digital telemetering recording system | |
| CN106373365A (en) | Camera shooting type remote water meter reading system achieving fast recognition and reading recognition method thereof | |
| CN106447856A (en) | Intelligent and safe tool cabinet system and management method thereof | |
| CN103067426A (en) | System and method of remote intelligent meter reading and instrument front-end collecting device | |
| CN111914667B (en) | Smoking detection method and device | |
| CN112330623B (en) | Method and device for detecting alignment degree of pole pieces of battery cell pole group | |
| CN103136532A (en) | Dial digital image reading device and method | |
| CN108734072B (en) | Multi-source object association method and device | |
| CN107479511A (en) | Textile manufacturing managing device and system | |
| CN107247914A (en) | A kind of visual identifying system of direct-reading water meter and its recognition methods | |
| CN109885605A (en) | A kind of city sign Index model data preprocess method | |
| CN210244400U (en) | Automatic reading device of passive self-generating instrument | |
| CN103513624A (en) | Intelligent monitoring method and system based on remote controller | |
| CN110287967B (en) | Image-based digit and mechanical watch digit identification method | |
| CN201035737Y (en) | Digital remote transmission meter reading system of flow accounting meter | |
| CN116311082A (en) | Wearing detection method and system based on matching of key parts and images | |
| CN203350905U (en) | Lending and returning management system for ground wires | |
| CN109543584A (en) | A kind of identification of intelligent behavior and analysis system | |
| CN205680139U (en) | The fingerprint attendance system of employee in a kind of enterprise management system | |
| CN103544740A (en) | Portable disease surveillance recorder | |
| CN201345117Y (en) | Offline patrol management device | |
| CN201477655U (en) | Same screen comparison type true and false checker for tickets | |
| CN201107075Y (en) | Water meter image collecting equipment | |
| CN1395223A (en) | Fingerprint patrol system | |
| CN103116970B (en) | A kind of meter data gathers automatically, teletransmission and processing system and method |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090610 Termination date: 20141231 |
|
| EXPY | Termination of patent right or utility model |