CN109977944B - Digital water meter reading identification method - Google Patents
Digital water meter reading identification method Download PDFInfo
- Publication number
- CN109977944B CN109977944B CN201910129726.8A CN201910129726A CN109977944B CN 109977944 B CN109977944 B CN 109977944B CN 201910129726 A CN201910129726 A CN 201910129726A CN 109977944 B CN109977944 B CN 109977944B
- Authority
- CN
- China
- Prior art keywords
- water meter
- digital
- image
- bounding box
- identifying
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
Abstract
The invention provides a digital water meter reading identification method, which comprises the steps of respectively carrying out binarization processing and edge detection processing on a water meter image to be processed to obtain a water meter binarization image and a water meter edge image; expanding the water meter edge map to expand the connected domain, drawing a corresponding directional bounding box according to the expanded connected domain, screening all the directional bounding boxes according to a preset distance relation and a digital bounding box interval value to obtain a digital bounding box, and calculating according to the digital bounding box to obtain an image rotation angle; cutting a water meter binarization graph according to the maximum value of the horizontal and vertical coordinates of the digital bounding box, carrying out rotation correction on the cut water meter binarization graph according to the image rotation angle to obtain a rotation correction water meter graph, scanning the rotation correction water meter graph to obtain a plurality of digital pictures, and identifying the digital pictures by adopting a template matching method and a deep learning method. The method for identifying the digital water meter reading saves a great amount of time and improves the accuracy of identification.
Description
Technical Field
The invention relates to the field of water meter image processing, in particular to a method for identifying digital water meter readings.
Background
Most of the current household water meters need to be manually opened to read water consumption, and the installation environment of some water meters is very bad, so that the water meters are difficult to read, have high labor intensity and low efficiency. The existing meter reading method has two modes for realizing digital identification: firstly, a camera module is installed to shoot a water meter picture and then the water meter picture is uploaded to a cloud for identification, the uploading time is long, and the picture compression seriously affects the identification effect; secondly, a remote meter reading terminal is adopted to shoot, identify and remotely transmit the readings of the water meter, and an image processing program adopted by the terminal is generally developed in a windows system and then transplanted to a linux system, so that cross compiling is difficult. The image processing module of the practical character wheel type water meter in the market mostly adopts Hough straight line to detect and identify the rotation angle to position the character wheel of the water meter, occupies large memory, has long calculation time and can only correct the rotation angle with smaller amplitude. Therefore, the current digital water meter reading identification method can only correct the rotation angle with smaller amplitude, and the identification accuracy is lower.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a method for identifying the reading of a digital water meter, which can solve the problems that the existing method for identifying the reading of the digital water meter can only correct the rotation angle with smaller amplitude and has lower identification accuracy.
The invention provides the following technical scheme for realizing the purpose:
a method of identifying a digital water meter reading, comprising the steps of:
s1, acquiring a water meter image to be processed and preset control parameters, wherein the control parameters comprise morphological operation convolution kernel values and digital bounding box interval values;
s3, performing binarization processing and edge detection processing on the water meter image to be processed respectively to obtain a water meter binarization image and a water meter edge image;
s4, performing expansion and connected domain expansion treatment on the water meter edge map according to the morphological operation convolution kernel value to obtain a morphological operation map containing a plurality of expanded connected domains;
s5, drawing a corresponding directional bounding box according to the enlarged connected domains, wherein each enlarged connected domain corresponds to one directional bounding box, and each enlarged connected domain is positioned in the corresponding directional bounding box;
s6, screening all the directed bounding boxes according to a preset distance relation and the digital bounding box interval value to obtain a digital bounding box, wherein the preset distance relation is a distance range of the position of the digital connected domain in the water meter from the center point of the water meter;
s7, calculating an image rotation angle according to the included angle between the long side of the digital bounding box and the horizontal direction;
s8, cutting the water meter binarization map according to the maximum value of the abscissa of the digital bounding box to obtain a cut water meter binarization map, carrying out rotation correction on the cut water meter binarization map according to the image rotation angle to obtain a rotation correction water meter map, and filling the background of the rotation correction water meter map into white;
and S9, scanning the rotation correction water chart by adopting a vertical scanning method to obtain a plurality of digital pictures, and identifying the digital pictures by adopting a template matching method and a deep learning method to obtain a final reading result.
Further, the method further comprises S2 before the step S3, and the water meter image to be processed is subjected to image preprocessing.
Further, the image preprocessing specifically includes: and carrying out image denoising treatment on the water meter image to be treated by adopting a median filtering method, and carrying out image enhancement treatment on the water meter image to be treated by adopting a histogram equalization method.
Further, the step S6 specifically includes: and performing first screening treatment on all the directed bounding boxes according to a preset distance relation to obtain a plurality of first directed bounding boxes, and performing second screening treatment on all the first directed bounding boxes according to the digital bounding box interval value to obtain the digital bounding boxes.
Further, the identifying the digital picture by using the template matching method and the deep learning method specifically includes: performing sliding comparison on each digital picture and each preset template picture in a preset template picture library to obtain similarity, and taking the number in the preset template picture at the moment as a first reading when the similarity is not smaller than a preset threshold value; when the similarity is smaller than a preset threshold, inputting the digital picture into a preset digital model library for identification to obtain a second reading, and summarizing the first reading and the second reading to obtain a final reading result.
Further, the digital picture is composed of a plurality of pixel points, and the preset template picture is composed of a plurality of template pixel points; the step of carrying out sliding comparison on each digital picture and each preset template picture in a preset template picture library specifically comprises the following steps: and carrying out sliding comparison on each digital picture and each preset template picture in a preset template picture library to obtain the number of non-coincident pixel points, and calculating the similarity according to the number of non-coincident pixel points and the total number of pixel points of the digital pictures.
Further, the preset threshold is 0.9.
Further, the number of the preset template pictures is 11.
Further, the morphologically operational convolution kernel is a multiple of dilation.
Further, the scanning the rotation correction water meter map by using the vertical scanning method specifically comprises the following steps: and respectively carrying out transverse scanning and longitudinal scanning on the rotation correction water meter image, and dividing each digital obtained by scanning to obtain a plurality of digital images.
Compared with the prior art, the invention has the beneficial effects that: the invention relates to a method for identifying digital water meter reading, which comprises the steps of obtaining a water meter image to be processed and preset control parameters, wherein the control parameters comprise morphological operation convolution kernel values and digital bounding box interval values; respectively carrying out binarization processing and edge detection processing on the water meter image to be processed to obtain a water meter binarization image and a water meter edge image; expanding the connected domain expansion processing is carried out on the water meter edge map according to the morphological operation convolution kernel value, so that a plurality of expanded connected domains are obtained; drawing a corresponding directed bounding box according to the enlarged communicating domains, wherein each enlarged communicating domain corresponds to one directed bounding box, and each enlarged communicating domain is positioned in the corresponding directed bounding box; screening all the bounding boxes according to a preset distance relation and a digital bounding box interval value to obtain a digital bounding box, wherein the preset distance relation is a distance range of the position of a digital connected domain in the water meter from the center point of the water meter; calculating an image rotation angle according to the included angle between the long side of the digital bounding box and the horizontal direction; cutting a water meter binarization graph according to the maximum value of the horizontal and vertical coordinates of the digital bounding box to obtain a cut water meter binarization graph, carrying out rotation correction on the cut water meter binarization graph according to the image rotation angle to obtain a rotation correction water meter graph, and filling the background of the rotation correction water meter graph into white; and scanning and correcting the water chart by adopting a vertical scanning method to obtain a plurality of digital pictures, and identifying the digital pictures by adopting a template matching method and a deep learning method to obtain a final reading result. The method for identifying the digital water meter reading can identify the numerical values corresponding to the complete number and the transition number, saves a great amount of time, improves the accuracy of identification, and is suitable for digital water meter images with different rotation angles.
The foregoing description is only an overview of the present invention, and is intended to provide a better understanding of the present invention, as it is embodied in the following description, with reference to the preferred embodiments of the present invention and the accompanying drawings. Specific embodiments of the present invention are given in detail by the following examples and the accompanying drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a flow chart of a method for identifying readings of a digital water meter according to the present invention;
FIG. 2 is a schematic diagram of a water meter image to be processed of a method for identifying digital water meter readings according to the present invention;
FIG. 3 is a schematic diagram of a water meter binarization map of a method of identifying digital water meter readings according to the present invention;
FIG. 4 is a schematic diagram of a water meter edge map of a method of identifying digital water meter readings according to the present invention;
FIG. 5 is a schematic diagram of a morphological operation chart of a method for identifying a digital water meter reading according to the present invention;
FIG. 6 is a schematic diagram of a directed bounding box diagram of a method of identifying digital water meter readings in accordance with the present invention;
FIG. 7 is a schematic diagram of a rotation correction chart of a method for identifying digital meter readings according to the present invention;
fig. 8 is a schematic diagram of a digital picture of a method for identifying a digital water meter reading according to the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and detailed description, wherein it is to be understood that, on the premise of no conflict, the following embodiments or technical features may be arbitrarily combined to form new embodiments.
As shown in fig. 1, the method for identifying the reading of the digital water meter of the invention comprises the following steps:
s1, acquiring a water meter image to be processed and preset control parameters, wherein the control parameters comprise morphological operation convolution kernel values and digital bounding box interval values; in this embodiment, as shown in fig. 2, the image of the water meter to be processed is a 256-level gray scale water meter map for real-time shooting and identification, and the water meter in the image has a rotation condition; the morphological operation convolution kernel value is the size value of the morphological operation convolution kernel, and is actually the expansion multiple; the value of the digital bounding box section is the size of the digital bounding box section, and is a preset value.
S2, carrying out image preprocessing on the water meter image to be processed. The method comprises the following steps: carrying out image denoising treatment on the water meter image to be treated by adopting a median filtering method, and carrying out image enhancement treatment on the water meter image to be treated by adopting a histogram equalization method; the stain dust existing in the water meter dial in the water meter image to be processed can be valued through image denoising, and the influence of external light rays can be reduced through image enhancement processing, so that the gray scale of the water meter image to be processed is uniformly distributed.
S3, respectively carrying out binarization processing and edge detection processing on the water meter image to be processed to obtain a water meter binarization image and a water meter edge image. Because the gray level distribution of the dial reading area in the water meter image to be processed to be extracted is different from that of the background, the water meter image to be processed is firstly subjected to binarization processing, the image to be processed is processed by adopting a maximum inter-class variance method, the result is stored into a binary image, and the water meter binarization image is obtained, and the water meter binarization image is shown in fig. 3, and the image storage space can be saved and the interested area is highlighted by the binarization processing. The edge detection process specifically includes: the method comprises the steps of processing a water meter image to be processed by adopting a canny edge detection operator, saving a result as an edge map, obtaining a water meter edge map, wherein the background is black, the edge is white, and particularly as shown in fig. 4, the water meter edge map is an image containing a plurality of connected domains, and the connected domains are white areas in the map.
S4, performing expansion and connected domain expansion treatment on the water meter edge map according to the morphological operation convolution kernel value to obtain a morphological operation map containing a plurality of expanded connected domains. In this embodiment, in step S1, a morphological operation convolution kernel, that is, expansion multiple, is given, and the connected domain in the water meter edge graph as shown in fig. 4 is expanded according to the morphological operation convolution kernel, so as to obtain a morphological operation graph as shown in fig. 5, where the expanded connected domain is the white area in fig. 5; morphological operation is performed on the water meter edge map, so that the digital region is ensured to be an independent connected region.
And S5, drawing corresponding directed bounding boxes according to the enlarged communicating domains, wherein each enlarged communicating domain corresponds to one directed bounding box, and each enlarged communicating domain is positioned in the corresponding directed bounding box. The method comprises the following steps: drawing lines along the edge of each expanded communication domain to obtain a directed bounding box corresponding to the expanded communication domain; as shown in fig. 6, the device comprises a plurality of directional bounding boxes.
And S6, screening all the directed bounding boxes according to a preset distance relation and a digital bounding box interval value to obtain a digital bounding box, wherein the preset distance relation is a distance range of the position of the digital connected domain in the water meter from the center point of the water meter. And performing first screening treatment on all the directed bounding boxes according to a preset distance relation to obtain a plurality of first directed bounding boxes, and performing second screening treatment on all the first directed bounding boxes according to the numerical bounding box interval value to obtain the numerical bounding boxes. In this embodiment, the distance range takes 80-150 pixels according to the size of the resolution of the selected camera.
And S7, calculating an image rotation angle according to the included angle between the long side of the digital bounding box and the horizontal direction.
S8, cutting the water meter binarization graph according to the maximum value of the abscissa of the digital bounding box to obtain a cut water meter binarization graph, carrying out rotation correction on the cut water meter binarization graph according to the rotation angle of the image to obtain a rotation correction water meter graph, and filling the background of the rotation correction water meter graph into white. The method comprises the following steps: cutting a water meter binarization graph according to the maximum and minimum values of the horizontal and vertical coordinates of the digital bounding box, namely, comparing the horizontal and vertical coordinates of the 4 vertexes of the digital bounding box to find out 4 coordinate points which are the maximum value and the minimum value, namely (Xmin, ymin), (Xmax, ymin), (Xmin, ymax), (Xmax, ymax) and four coordinate points, cutting the rectangle surrounded by the four coordinate points on the water meter binarization graph in the step S3 to obtain a cut water meter binarization graph, carrying out rotation correction on the cut water meter binarization graph according to the image rotation angle calculated in the step S7, filling the background into white, and obtaining a rotation correction water meter graph, wherein the rotation correction water meter graph is shown in the figure 7.
And S9, scanning and correcting the water chart by adopting a vertical scanning method to obtain a plurality of digital pictures, and identifying the digital pictures by adopting a template matching method and a deep learning method to obtain a final reading result. The method comprises the following steps:
1. respectively performing transverse scanning and longitudinal scanning on the rotation correction water chart, and dividing each digital obtained by scanning to obtain a plurality of digital pictures, wherein the digital pictures are composed of a plurality of pixel points; the lateral scan and the longitudinal scan in this embodiment are: (1) And (3) carrying out transverse scanning on the H ROWs from the first ROW to the last ROW of the rotation correction water chart, counting black pixel points of each ROW, and storing the black pixel points into an array ROW [1], ROW [2],. ROW [ H ]. The starting line and the ending line of the array with gray values greater than 0 for n consecutive lines are found, where n ranges between 30 and 80 depending on the selected camera resolution size. (2) And carrying out longitudinal scanning from the first column to the last column of the rotation correction water chart, wherein the starting point of the longitudinal scanning is the starting line obtained in the last step, the end point is the ending line, and counting black pixel points of each column, and storing the black pixel points into an array COL 1, COL 2 and COL W. Finding a starting column and a stopping column with gray values larger than 0 in m continuous columns, wherein the number of the starting column and the stopping column is the same as the number of digits, and m ranges from 10 to 40 according to the resolution of the selected camera; finally, the numbers conforming to the numbers (1) and (2) are divided to obtain a plurality of digital pictures, wherein the digital pictures are shown in fig. 8, and each number is an array.
2. Each digital picture is subjected to sliding comparison with each preset template picture in a preset template picture library, each preset template picture in the embodiment also comprises a plurality of template pixel points, each digital picture is subjected to sliding comparison with each preset template picture in the preset template picture library, the total number of the preset template pictures is 11, namely 0, 1, 2, 3, 4, 5, 6, 7, 8, 9 and 0 are ordered from top to bottom, so that the digital pictures are also compared with the preset template pictures from top to bottom, the number of non-overlapping pixel points is obtained, and the similarity is calculated according to the number of non-overlapping pixel points and the total number of pixel points of the digital pictures; similarity = 1-number of misaligned pixels/number of total pixels of the digital picture; when the similarity is not smaller than a preset threshold value, taking the number in the preset template picture at the moment as a first reading; when the similarity is smaller than a preset threshold, inputting the digital picture into a preset digital model library for identification to obtain a second reading, and summarizing the first reading and the second reading to obtain a final reading result; in this embodiment, the preset threshold is 0.9, that is, when the similarity is smaller than 0.9, the digital picture is input into a preset digital model library for identification, so as to obtain a second reading; and summarizing the first reading and the second reading to obtain a final reading result, and outputting the final reading result, wherein the final result is text information with a plurality of numbers.
The invention relates to a method for identifying digital water meter reading, which comprises the steps of obtaining a water meter image to be processed and preset control parameters, wherein the control parameters comprise morphological operation convolution kernel values and digital bounding box interval values; respectively carrying out binarization processing and edge detection processing on the water meter image to be processed to obtain a water meter binarization image and a water meter edge image; expanding the connected domain expansion processing is carried out on the water meter edge map according to the morphological operation convolution kernel value, so that a plurality of expanded connected domains are obtained; drawing a corresponding directed bounding box according to the enlarged communicating domains, wherein each enlarged communicating domain corresponds to one directed bounding box, and each enlarged communicating domain is positioned in the corresponding directed bounding box; screening all the bounding boxes according to a preset distance relation and a digital bounding box interval value to obtain a digital bounding box, wherein the preset distance relation is a distance range of the position of a digital connected domain in the water meter from the center point of the water meter; calculating an image rotation angle according to the included angle between the long side of the digital bounding box and the horizontal direction; cutting a water meter binarization graph according to the maximum value of the horizontal and vertical coordinates of the digital bounding box to obtain a cut water meter binarization graph, carrying out rotation correction on the cut water meter binarization graph according to the image rotation angle to obtain a rotation correction water meter graph, and filling the background of the rotation correction water meter graph into white; and scanning and correcting the water chart by adopting a vertical scanning method to obtain a plurality of digital pictures, and identifying the digital pictures by adopting a template matching method and a deep learning method to obtain a final reading result. The method for identifying the digital water meter reading can identify the numerical values corresponding to the complete number and the transition number, saves a great amount of time, improves the accuracy of identification, and is suitable for digital water meter images with different rotation angles.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way; those skilled in the art can smoothly practice the invention as shown in the drawings and described above; however, those skilled in the art will appreciate that many modifications, adaptations, and variations of the present invention are possible in light of the above teachings without departing from the scope of the invention; meanwhile, any equivalent changes, modifications and evolution of the above embodiments according to the essential technology of the present invention still fall within the scope of the present invention.
Claims (9)
1. A method for identifying a digital water meter reading, comprising the steps of:
s1, acquiring a water meter image to be processed and preset control parameters, wherein the control parameters comprise morphological operation convolution kernel values and digital bounding box interval values;
s3, performing binarization processing and edge detection processing on the water meter image to be processed respectively to obtain a water meter binarization image and a water meter edge image;
s4, performing expansion and connected domain expansion treatment on the water meter edge map according to the morphological operation convolution kernel value to obtain a morphological operation map containing a plurality of expanded connected domains;
s5, drawing a corresponding directional bounding box according to the enlarged connected domains, wherein each enlarged connected domain corresponds to one directional bounding box, and each enlarged connected domain is positioned in the corresponding directional bounding box;
s6, screening all the directed bounding boxes according to a preset distance relation and the digital bounding box interval value to obtain a digital bounding box, wherein the preset distance relation is a distance range of the position of the digital connected domain in the water meter from the center point of the water meter;
s7, calculating an image rotation angle according to the included angle between the long side of the digital bounding box and the horizontal direction;
s8, cutting the water meter binarization map according to the maximum value of the abscissa of the digital bounding box to obtain a cut water meter binarization map, carrying out rotation correction on the cut water meter binarization map according to the image rotation angle to obtain a rotation correction water meter map, and filling the background of the rotation correction water meter map into white;
s9, scanning the rotation correction water chart by adopting a vertical scanning method to obtain a plurality of digital pictures, and identifying the digital pictures by adopting a template matching method and a deep learning method, wherein the method specifically comprises the following steps of: performing sliding comparison on each digital picture and each preset template picture in a preset template picture library to obtain similarity, and taking the number in the preset template picture at the moment as a first reading when the similarity is not smaller than a preset threshold value; when the similarity is smaller than a preset threshold, inputting the digital picture into a preset digital model library for identification to obtain a second reading, and summarizing the first reading and the second reading to obtain a final reading result.
2. A method of identifying a digital water meter reading as in claim 1, wherein: and S2 is further included before the step S3, and the image of the water meter to be processed is subjected to image preprocessing.
3. A method of identifying a digital water meter reading as in claim 2, wherein: the image preprocessing specifically comprises the following steps: and carrying out image denoising treatment on the water meter image to be treated by adopting a median filtering method, and carrying out image enhancement treatment on the water meter image to be treated by adopting a histogram equalization method.
4. A method of identifying a digital water meter reading as in claim 1, wherein: the step S6 specifically comprises the following steps: and performing first screening treatment on all the directed bounding boxes according to a preset distance relation to obtain a plurality of first directed bounding boxes, and performing second screening treatment on all the first directed bounding boxes according to the digital bounding box interval value to obtain the digital bounding boxes.
5. A method of identifying a digital water meter reading as in claim 1, wherein: the digital picture consists of a plurality of pixel points, and the preset template picture consists of a plurality of template pixel points; the step of carrying out sliding comparison on each digital picture and each preset template picture in a preset template picture library specifically comprises the following steps: and carrying out sliding comparison on each digital picture and each preset template picture in a preset template picture library to obtain the number of non-coincident pixel points, and calculating the similarity according to the number of non-coincident pixel points and the total number of pixel points of the digital pictures.
6. A method of identifying a digital water meter reading as in claim 1, wherein: the preset threshold is 0.9.
7. A method of identifying a digital water meter reading as in claim 1, wherein: the number of the preset template pictures is 11.
8. A method of identifying a digital water meter reading as in claim 1, wherein: the morphological operation convolution kernel is a multiple of dilation.
9. A method of identifying a digital water meter reading as in claim 1, wherein: the method for scanning the rotation correction water meter map by adopting the vertical scanning method comprises the following steps: and respectively carrying out transverse scanning and longitudinal scanning on the rotation correction water meter image, and dividing each digital obtained by scanning to obtain a plurality of digital images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910129726.8A CN109977944B (en) | 2019-02-21 | 2019-02-21 | Digital water meter reading identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910129726.8A CN109977944B (en) | 2019-02-21 | 2019-02-21 | Digital water meter reading identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109977944A CN109977944A (en) | 2019-07-05 |
| CN109977944B true CN109977944B (en) | 2023-08-01 |
Family
ID=67077136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910129726.8A Active CN109977944B (en) | 2019-02-21 | 2019-02-21 | Digital water meter reading identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109977944B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110837834B (en) * | 2019-09-30 | 2023-04-18 | 杭州朗阳科技有限公司 | Digital instrument reading method and system |
| CN112489071A (en) * | 2020-11-03 | 2021-03-12 | 辽宁长江智能科技股份有限公司 | Pointer water meter identification method and system |
| CN112434693A (en) * | 2020-11-03 | 2021-03-02 | 辽宁长江智能科技股份有限公司 | Digital water meter identification method and system |
| CN113537220B (en) * | 2021-09-17 | 2021-12-14 | 济南瑞泉电子有限公司 | Camera direct-reading water meter identification method based on end ray method |
| CN114998887B (en) * | 2022-08-08 | 2022-10-11 | 山东精惠计量检测有限公司 | Intelligent identification method for electric energy meter |
| CN116645682B (en) * | 2023-07-24 | 2023-10-20 | 济南瑞泉电子有限公司 | Water meter dial number identification method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682665A (en) * | 2016-12-27 | 2017-05-17 | 陕西科技大学 | Digital recognition method for seven-segment digital indicator |
| CN106934796A (en) * | 2017-02-15 | 2017-07-07 | 山东大学 | High-speed belt conveyor rock slag video analytic system and method that rock tunnel(ling) machine is carried |
| CN106951900A (en) * | 2017-04-13 | 2017-07-14 | 杭州申昊科技股份有限公司 | A kind of automatic identifying method of arrester meter reading |
| WO2019000653A1 (en) * | 2017-06-30 | 2019-01-03 | 清华大学深圳研究生院 | Image target identification method and apparatus |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7548649B2 (en) * | 2005-01-25 | 2009-06-16 | Siemens Medical Solutions Usa, Inc. | Multidimensional segmentation based on adaptive bounding box and ellipsoid models |
-
2019
- 2019-02-21 CN CN201910129726.8A patent/CN109977944B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682665A (en) * | 2016-12-27 | 2017-05-17 | 陕西科技大学 | Digital recognition method for seven-segment digital indicator |
| CN106934796A (en) * | 2017-02-15 | 2017-07-07 | 山东大学 | High-speed belt conveyor rock slag video analytic system and method that rock tunnel(ling) machine is carried |
| CN106951900A (en) * | 2017-04-13 | 2017-07-14 | 杭州申昊科技股份有限公司 | A kind of automatic identifying method of arrester meter reading |
| WO2019000653A1 (en) * | 2017-06-30 | 2019-01-03 | 清华大学深圳研究生院 | Image target identification method and apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 车牌识别中的图像提取及分割算法;张禹;马驷良;韩笑;张忠波;;吉林大学学报(理学版)(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109977944A (en) | 2019-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109977944B (en) | Digital water meter reading identification method | |
| CN111626190B (en) | Water level monitoring method for scale recognition based on clustering partition | |
| CN106960208B (en) | Method and system for automatically segmenting and identifying instrument liquid crystal number | |
| CN110781885A (en) | Text detection method, device, medium and electronic equipment based on image processing | |
| CN111598889B (en) | Identification method and device for inclination fault of equalizing ring and computer equipment | |
| CN111739020B (en) | Automatic labeling method, device, equipment and medium for periodic texture background defect label | |
| CN116704516B (en) | Visual inspection method for water-soluble fertilizer package | |
| CN109766750A (en) | A kind of table line position finding and detection method of financial statement | |
| CN112734729B (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
| CN111354047A (en) | Camera module positioning method and system based on computer vision | |
| CN112767359A (en) | Steel plate corner detection method and system under complex background | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN111724354A (en) | Image processing-based method for measuring spike length and small spike number of multiple wheat | |
| CN109784328B (en) | Method for positioning bar code, terminal and computer readable storage medium | |
| WO2022121021A1 (en) | Identity card number detection method and apparatus, and readable storage medium and terminal | |
| CN111553927B (en) | Checkerboard corner detection method, detection system, computer device and storage medium | |
| CN111738936A (en) | Image processing-based multi-plant rice spike length measuring method | |
| CN115082504B (en) | Light spot identification method for solar photovoltaic panel | |
| CN115797327A (en) | Defect detection method and device, terminal device and storage medium | |
| CN112668578B (en) | Pointer type instrument reading method, pointer type instrument reading device, computer equipment and storage medium | |
| CN113284115B (en) | Steel coil tower shape identification method, system, medium and terminal | |
| Sun et al. | Research on image segmentation and extraction algorithm for bicolor water level gauge | |
| CN108563674B (en) | Sea area geographic element measurement method, system and device based on RS and GIS | |
| CN111626299A (en) | Outline-based digital character recognition method | |
| CN111178111A (en) | Two-dimensional code detection method, electronic device, storage medium and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |