CN116246265A - Property management method and device based on image processing - Google Patents
Property management method and device based on image processing Download PDFInfo
- Publication number
- CN116246265A CN116246265A CN202310530663.3A CN202310530663A CN116246265A CN 116246265 A CN116246265 A CN 116246265A CN 202310530663 A CN202310530663 A CN 202310530663A CN 116246265 A CN116246265 A CN 116246265A
- Authority
- CN
- China
- Prior art keywords
- image
- dial
- reading
- character
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 title claims abstract description 50
- 238000007726 management method Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 61
- 238000003860 storage Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 14
- 238000005520 cutting process Methods 0.000 claims description 9
- 238000005286 illumination Methods 0.000 abstract description 28
- 238000005516 engineering process Methods 0.000 abstract description 24
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 24
- 230000000694 effects Effects 0.000 abstract description 11
- 230000002411 adverse Effects 0.000 abstract description 8
- 239000000284 extract Substances 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 13
- 238000001514 detection method Methods 0.000 description 11
- 230000011218 segmentation Effects 0.000 description 7
- 230000005611 electricity Effects 0.000 description 6
- 238000012937 correction Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000013145 classification model Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000001174 ascending effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
- G06Q50/163—Real estate management
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Character Input (AREA)
Abstract
The invention discloses a property management method and device based on image processing, which relate to the technical field of image processing and can accurately and automatically read readings of various domestic meters such as water meters, gas meters and electric meters. After acquiring dial images of a life table, the method cuts the dial images into table plate images with balanced brightness, extracts reading areas in the table plate images, then splits the reading areas of the table plate into table plate reading areas, and finally carries out character recognition on the table plate reading areas to obtain the table plate reading. The method can solve the adverse effect of illumination or reflection on the character reading technology based on image recognition to a certain extent, and the illumination of each dial image is approximately uniform as long as the dial image is cut to a certain size.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a property management method and device based on image processing.
Background
With the high-speed development of the internet, the technology of utilizing the internet of things, big data and cloud computing show strong driving force in constructing smart cities. In recent years, the internet of things technology has been widely applied to industries such as smart home, remote meter reading, smart security, and the like, and the 'everything interconnection' is gradually realized. The water, electricity and gas are indispensable parts in daily life, and meter reading is a necessary means for water, electricity and gas consumption statistics of water supply, electricity and gas supply companies for residents. At present, the water meter used by users is mainly a traditional water meter, and the users need to manually go to the door to read the meter, which is time-consuming and labor-consuming.
With the continuous development of the technology of the automatic Internet of things, the reading of the domestic meter is identified through the image identification technology, so that the meter reading problem of the traditional water meter can be effectively solved, and the method has the characteristics of wide coverage, low cost, low power consumption, high reliability and the like. However, the conventional image recognition reading technology ignores the influence of illumination and the like, and false detection is easy to occur when character recognition is performed.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person of ordinary skill in the art.
Disclosure of Invention
The invention aims to provide a property management method and device based on image processing, which can solve the adverse effect of illumination or reflection on a character reading technology based on image recognition to a certain extent.
In a first aspect, the present invention provides a property management method based on image processing, including:
s1, acquiring dial images of a life table;
s2, cutting the dial plate image into a plurality of dial plate images, wherein the absolute value of the brightness value difference value of any two pixels in each dial plate image is smaller than a brightness balance threshold;
s3, dividing the reading areas in the table plate images;
s4, the reading areas in the table plate images are spliced into table plate reading areas;
and S5, identifying the characters in the dial reading area one by one according to the reading sequence to obtain the dial reading.
The steps S1 to S5 are a default order, but any order of the steps S1 to S5 may be exchanged according to actual situations.
It can be appreciated that the invention discloses a property management method based on image processing, which can accurately and automatically read the readings of various domestic meters such as a water meter, a gas meter, an electric meter and the like. After acquiring dial images of a life table, the method cuts the dial images into table plate images with balanced brightness, extracts reading areas in the table plate images, then splits the reading areas of the table plate into table plate reading areas, and finally carries out character recognition on the table plate reading areas to obtain the table plate reading. The method can solve the adverse effect of illumination or reflection on the character reading technology based on image recognition to a certain extent, and the illumination of each dial image is approximately uniform as long as the dial image is cut to a certain size.
In an alternative embodiment of the present invention, step S2 includes: and performing half-cut on the dial plate image to obtain dial plate images until the absolute value of the brightness value difference value of any two pixels in each dial plate image is smaller than the brightness balance threshold value.
It will be appreciated that the dial images are cut in half continuously, and once a certain number of times is reached, the dial images are cut to a certain small size, and the illumination of each dial image is approximately uniform.
In an alternative embodiment of the present invention, after step S1, before step S2, the method further comprises: and after carrying out Gaussian equalization processing on the dial image, updating the dial image.
It can be understood that the brightness of the dial image is more uniform after Gaussian equalization treatment, which is more beneficial to overcoming the adverse effect of illumination or reflection on the character reading technology based on image recognition.
In an alternative embodiment of the present invention, step S3 includes:
s31, converting each dial sub-image into a corresponding gray-scale image, and taking the corresponding gray-scale image as a dial gray-scale sub-image;
s32, gradually reducing the gray threshold value in the gray adjustment range, extracting character pixels smaller than the gray threshold value in the dial gray sub-image after each time of adjusting the gray threshold value, and adding the character pixels into the reading area until the number of the character pixels in the reading area is larger than the pixel number threshold value.
Here, steps S31 to S32 are a default order, but any of the step orders in steps S31 to S32 may be exchanged according to actual situations.
In an alternative embodiment of the present invention, step S5 includes:
s51, cutting each character in the dial reading area to obtain each character area;
s52, identifying the characters of each character area in the dial reading area one by one according to the reading sequence, and obtaining the dial reading.
Wherein, after step S51, before step S52, the method further comprises:
s521, acquiring a first character area of the dial reading area according to a default sequence, and extracting a character area original image corresponding to the position of the first character area in the dial image;
s522, identifying the pixel color of the original image of the character area;
s523, confirming that the reverse order of the default order is the reading order when the pixel color of the character area original image is the target color;
and S524, confirming that the default sequence is the reading sequence when the pixel color of the original image of the character area is a non-target color.
Here, steps S521 to S524 are a default order, but any of the step orders in steps S521 to S524 may be exchanged according to actual situations.
In practice, a life meter such as a water meter is not necessarily a forward device, and thus the acquired dial image may be inverted. The existing reading technology based on image processing does not judge the orientation of the characters, and defaults that the characters of the water meter reading are placed in the forward direction, and the applicability of an algorithm when the characters are inverted is not considered.
It will be appreciated that since most of the decimal characters of the life form are different from other characters in color, the decimal character is generally red, and therefore, it can be determined whether the initial character is a decimal character by identifying whether the pixel color of the original image of the character area corresponding to the position of the initial character area in the dial image is a target color. If the first character is a decimal character, reversing the default order; if the first character is a non-decimal character then the default order may be confirmed as the reading order.
In an embodiment of the present invention, the identifying the pixel color of the original image of the character area includes: calculating average red components, average green components and average blue components of all pixels in the original image of the character area;
and when the pixel color of the character area original image is the target color, confirming that the reverse order of the default order is the reading order, including: calculating a target color component duty cycle from the average red component, the average green component, and the average blue component; confirming that the reverse order of the default order is the reading order under the condition that the target color component duty ratio reaches a target threshold value;
and when the pixel color of the original image of the character area is a non-target color, confirming that the default sequence is the reading sequence comprises the following steps: calculating a target color component duty cycle from the average red component, the average green component, and the average blue component; and confirming the default sequence as the reading sequence under the condition that the target color component duty ratio is smaller than a target threshold value.
In a second aspect, the present invention provides an image processing based property management apparatus comprising means for performing the method of any of the first aspects.
In a third aspect, the present invention provides a property management apparatus based on image processing, comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is for storing a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method according to any of the first aspects.
In a fourth aspect, the present invention provides a computer readable storage medium storing a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of any of the first aspects.
Compared with the prior art, the invention discloses a property management method and device based on image processing, which can accurately and automatically read the readings of various domestic meters such as water meters, gas meters, electric meters and the like. After acquiring dial images of a life table, the method cuts the dial images into table plate images with balanced brightness, extracts reading areas in the table plate images, then splits the reading areas of the table plate into table plate reading areas, and finally carries out character recognition on the table plate reading areas to obtain the table plate reading. The method can solve the adverse effect of illumination or reflection on the character reading technology based on image recognition to a certain extent, and the illumination of each dial image is approximately uniform as long as the dial image is cut to a certain size.
In addition, the property management method based on image processing can judge whether the first character is a decimal character by identifying whether the pixel color of an original image of a character area corresponding to the position of the first character area in a dial image is a target color. If the first character is a decimal character, reversing the default order into a reading order; if the first character is a non-decimal character then the default order may be confirmed as the reading order.
Drawings
FIG. 1 is a schematic flow chart of a property management method based on image processing;
fig. 2 is a schematic diagram of a dial image of a life table obtained by photographing with a camera;
FIG. 3 is a schematic diagram of a cutting of a dial image into a plurality of dial images;
FIG. 4 is a schematic diagram of a reading identification step of a dial reading area;
fig. 5 is a schematic structural diagram of a property management device based on image processing.
Detailed Description
The following detailed description of embodiments of the invention is, therefore, to be taken in conjunction with the accompanying drawings, and it is to be understood that the scope of the invention is not limited to the specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the term "comprise" or variations thereof such as "comprises" or "comprising", etc. will be understood to include the stated element or component without excluding other elements or components.
With the high-speed development of the internet, the technology of utilizing the internet of things, big data and cloud computing show strong driving force in constructing smart cities. In recent years, the internet of things technology has been widely applied to industries such as smart home, remote meter reading, smart security, and the like, and the 'everything interconnection' is gradually realized. The water, electricity and gas are indispensable parts in daily life, and meter reading is a necessary means for water, electricity and gas consumption statistics of water supply, electricity and gas supply companies for residents. At present, the water meter used by users is mainly a traditional water meter, and the users need to manually go to the door to read the meter, which is time-consuming and labor-consuming.
With the continuous development of the technology of the automatic Internet of things, the reading of the domestic meter is identified through the image identification technology, so that the meter reading problem of the traditional water meter can be effectively solved, and the method has the characteristics of wide coverage, low cost, low power consumption, high reliability and the like.
Life table reading identification based on image processing is mainly divided into two parts: character detection and character classification recognition. Character detection techniques locate character positions and segment individual characters for subsequent individual character recognition. For this technology, the main methods at present are: 1. a shape fitting method; 2. segmentation of the connected domain; 3. and detecting the model.
The method based on shape fitting is mainly divided into two types, one is to fit a character area according to a standard life table, the method firstly utilizes rectangles and circles to construct a life table template area according to a standard dial plate, then carries out circular and rectangular matching on an actual detection image, and carries out character segmentation according to the matched areas. The second is to fit a rectangular frame of the reading area where the life meter is located, and the rectangular frame is usually determined by using parallel straight lines detected by Hough transformation. The method can quickly position the rectangular region frame in the image, but has poor generalization capability, and the life table image required to be shot is not inclined in the vertical direction, otherwise, the shooting angle can cause the inclination of a straight line, and the matching effect is poor. Under the influence of strong illumination and dark illumination, the single character frame lines are fuzzy and are easily influenced by background lines, and more detection omission and false detection conditions exist.
The detection method based on connected domain segmentation generally includes preprocessing a life table image, converting the life table image into a corresponding binary image, processing the binary image by morphological operation, calculating a connected region of the binary image, and segmenting characters according to the connected region. Compared with the shape fitting method, the method has better universality, but the problem of mutual adhesion of the binarized images caused by illumination and frame influence cannot be solved well.
The detection method based on the multistage network model can be directly positioned to the character area through the model, and the method is mainly realized by carrying out feature analysis on the image through the model to obtain output similar to training data used in early model training. Positioning characters with models is relatively robust to illumination, but there are still two problems: the network algorithm with higher reliability consumes longer time than the traditional image processing; the detection result has great correlation with the training data and the labeling information thereof, and if the difference is large during use, the detection effect of the model still can be poor.
The character classification technology is to classify and identify the detected single character, and the main methods at present are as follows: 1. a template matching-based method; 2. a method based on a multi-level classification model.
The method based on template matching firstly needs to establish a standard binary character template library, converts characters into binary images, and sequentially carries out logic operation on the binary images of the characters and the standard templates to obtain the recognition character output with the largest similarity coefficient. The performance of this method is highly dependent on the font style and the quality of the binarized image. In addition, the digital life table is often a half word which is being converted, and the accuracy of classifying the half word characters by using a template matching method is low.
Classifying the characters by using a method based on a multi-stage classification model, wherein the number of the characters is 0-9 in terms of a life table, and 10 characters in total are subjected to feature extraction to construct a softmax classifier for classification. Compared with character recognition based on template matching, the method has better robustness to the font style, and if the influence of noise, blurring, illumination, frames and the like in the simulated real environment is added during training, the robustness to external interference can be improved, and the classification accuracy is relatively high.
In the current technical scheme, the recognition of the reading characters of the life table is greatly influenced by illumination and frames, and meanwhile, the method is limited to the forward life table character recognition, and the inverted life table images cannot be processed at the same time, so that the practicability is poor.
In order to solve the above problems, in a first aspect, as shown in fig. 1, the present invention provides a property management method based on image processing, which includes:
s1, acquiring dial images of a life table.
The dial image may be captured by a camera provided on the life watch. Fig. 2 is a schematic diagram of a dial image of a life watch obtained by photographing with a camera.
S2, cutting the dial image into a plurality of table plate images, wherein the absolute value of the brightness value difference value of any two pixels in each table plate image is smaller than the brightness balance threshold value.
In an alternative embodiment of the present invention, step S2 includes: and performing half-cut on the dial image to obtain table plate images until the absolute value of the brightness value difference value of any two pixels in each table plate image is smaller than the brightness balance threshold value.
It will be appreciated that the dial images are cut in half continuously, and once a certain number of times is reached, the dial images are cut to a certain small size, and the illumination of each dial image is approximately uniform.
For example, as shown in FIG. 3, the panel images are successively cut in half, as shown by the dashed lines, wherein the difference in luminance value between any two pixels in each panel image is less than a certain level, i.e., the brightness of the panel image is equalized.
S3, dividing the reading areas in the table plate images.
In an alternative embodiment of the present invention, step S3 includes:
s31, converting each dial sub-image into a corresponding gray-scale image serving as a dial gray-scale sub-image;
s32, gradually reducing the gray threshold value in the gray adjustment range, and extracting character pixels smaller than the gray threshold value in the dial gray sub-image to be added into the reading area after the gray threshold value is adjusted each time until the number of the character pixels in the reading area is larger than the pixel number threshold value.
Here, steps S31 to S32 are a default order, but any of the step orders in steps S31 to S32 may be exchanged according to actual situations.
The gray scale adjustment range is generally 255-0, and the gray scale threshold value can be gradually reduced by 1 for each set gray scale threshold value by gradually reducing the gray scale threshold value.
It can be understood that the existing life table is generally a white background and black word, so that the pixel gray of the reading character is smaller than the pixel gray of the blank area, after the gray threshold value is adjusted each time, the pixels smaller than the gray threshold value in the dial gray sub-image are the character pixels, and the character pixels are added into the reading area until the number of the character pixels in the reading area reaches a certain degree, and the segmentation of the reading area is completed.
S4, the reading areas in the table plate images are spliced into table plate reading areas.
And S5, identifying characters in the dial reading area one by one according to the reading sequence to obtain dial reading.
The steps S1 to S5 are a default order, but any order of the steps S1 to S5 may be exchanged according to actual situations.
It can be appreciated that the invention discloses a property management method based on image processing, which can accurately and automatically read the readings of various domestic meters such as a water meter, a gas meter, an electric meter and the like. After acquiring dial images of a life table, the method cuts the dial images into table plate images with balanced brightness, extracts reading areas in the table plate images, then splits the reading areas of the table plate into table plate reading areas, and finally carries out character recognition on the table plate reading areas to obtain the table plate reading. The method can solve the adverse effect of illumination or reflection on the character reading technology based on image recognition to a certain extent, and the illumination of each dial image is approximately uniform as long as the dial image is cut to a certain size.
Since the character is black and the background is white, the gray inversion is firstly carried out on the gray level diagram of the life table image, so that the gray level value of the background is smaller than that of the character, and the life table image is further processed. And then, detecting a text region by using a maximum stable extremum region (Maximally Stable Extremal Regions, MSER), and obtaining a corresponding MSER target binary image. The MSER carries out binarization processing on an image which is processed into gray scale, the threshold value of the processing is increased from 0 to 255, the increment of the threshold value is similar to the ascending of a horizontal plane on a piece of land, the land area with the uneven height is continuously submerged along with the ascending of the horizontal plane, the water diversion ridge algorithm is adopted, and the difference of the height is the difference of gray scale values in the image. On an image containing text, some areas (such as text) are not covered for a period of time when the horizontal plane (threshold) continues to increase because the color (gray value) is consistent, and are not submerged until the threshold increases to the gray value of the text itself, which are called maximum stable extremum areas.
In an alternative embodiment of the present invention, after step S1, before step S2, the method further comprises: after Gaussian equalization processing is performed on the dial image, the dial image is updated.
It can be understood that the brightness of the dial image is more uniform after Gaussian equalization treatment, which is more beneficial to overcoming the adverse effect of illumination or reflection on the character reading technology based on image recognition.
In an alternative embodiment of the present invention, step S5 includes:
s51, cutting each character in the reading area of the table disc to obtain each character area.
S52, identifying the characters of each character area in the dial reading area one by one according to the reading sequence, and obtaining the dial reading.
Wherein, step S51 includes:
s511, converting the dial reading area into a corresponding binary image.
S512, processing the binary image corresponding to the dial reading area by utilizing morphological operation.
S513, calculating a communication area of the binary image corresponding to the dial reading area, and dividing each character area according to the communication area.
The character region detection method based on connected domain segmentation has better universality than the common shape fitting method.
The difference of the part is that the illumination is Gaussian balanced before binarization, so that the problems of illumination brightness and shadow are improved, and the effect of binarization by using MSER is poor because the gray level difference between the character and the background after preprocessing is reduced. Therefore, in the second stage, the enhanced gray level image is binarized by using a block maximum inter-class variance method, and the image is divided into a plurality of blocks and respectively subjected to threshold segmentation, so that the uneven influence caused by illumination or reflection can be solved to a certain extent. The blocks are chosen to be small enough so that the illumination of each block is approximately uniform, so that when thresholding is automatic, high thresholding will be used in the high gray scale regions and low thresholding will be used in the low gray scale regions. The method is characterized in that the method comprises the steps of calculating the inclination angle to obtain an affine matrix, and carrying out inclination correction on a binary image and a life table image, wherein the method is used for further solving the problem that the single character is segmented by adhesion caused by external influence, and the single character is segmented by using a connected domain and projection adjustment mode. Firstly, obtaining an external rectangular frame of a single character connected domain, counting peak-valley points of a binary image, and adjusting if the width of the rectangular frame obtained by the connected domain is unreasonable compared with the valley points. Finally, judging whether to divide the characters with the corresponding number or not again, if the characters are not equal to the number of the characters of the life table to be detected, in order to ensure that the life table can obtain the identification result under more conditions, dividing the third part does not carry out inclination correction. The reason is that the binarized target affects the angle calculation of the tilt correction, and when the background noise has serious dark fringes, a large deviation occurs in the tilt angle calculation, so that the image tilt correction fails. Based on the part, the inclination correction operation is not carried out, and the single character segmentation is carried out in a mode of directly carrying out connected domain plus projection adjustment after illumination equalization and binarization processing.
Wherein, after step S51, before step S52, the method further comprises:
s521, the first character area of the dial reading area is acquired according to the default sequence, and the original character area image corresponding to the position of the first character area in the dial image is extracted.
S522, identifying the pixel color of the original image of the character area.
S523, in the case where the pixel color of the character area original image is the target color, it is confirmed that the reverse order of the default order is the reading order, as shown in fig. 4.
If the pixel color of the original image of the character area is the non-target color, the default order is confirmed to be the reading order, as shown in fig. 4.
Wherein, step S522 includes: and calculating an average red component, an average green component and an average blue component of each pixel in the original image of the character area. Step S523 includes: calculating a target color component duty cycle from the average red component, the average green component, and the average blue component; and confirming that the reverse order of the default order is the reading order under the condition that the target color component duty ratio reaches a target threshold value. Step S524 includes: calculating a target color component duty cycle from the average red component, the average green component, and the average blue component; and confirming the default sequence as the reading sequence under the condition that the target color component duty ratio is smaller than a target threshold value.
Here, steps S521 to S524 are a default order, but any of the step orders in steps S521 to S524 may be exchanged according to actual situations.
In practice, a life meter such as a water meter is not necessarily a forward device, and thus the dial image acquired may be inverted, as shown in the lower diagram of fig. 4. The existing reading technology based on image processing does not judge the orientation of the characters, and defaults that the characters of the water meter reading are placed in the forward direction, and the applicability of an algorithm when the characters are inverted is not considered.
It will be appreciated that since most of the decimal characters of the life form are different from other characters in color, the decimal character is generally red, and therefore, it can be determined whether the initial character is a decimal character by identifying whether the pixel color of the original image of the character area corresponding to the position of the initial character area in the dial image is a target color. If the first character is a decimal character, reversing the default order; if the first character is a non-decimal character then the default order may be confirmed as the reading order.
In step S52, the image processing technology related to character recognition is to classify and identify the detected single character, and for this technology, the main methods currently exist: 1. a template matching-based method; 2. a method based on a multi-level classification model.
The method based on template matching firstly needs to establish a standard binary character template library, converts characters into binary images, and sequentially carries out logic operation on the binary images of the characters and the standard templates to obtain the recognition character output with the largest similarity coefficient. The performance of this method is highly dependent on the font style and the quality of the binarized image. In addition, the digital water meter is often a half word which is being converted, and the accuracy of classifying the half word characters by using a template matching method is low.
Classifying the characters by using a method based on a multi-stage classification model, wherein the characters are 0-9 for the water meter, and 10 characters in total, and the characters are subjected to feature extraction to construct a softmax classifier for classification. Compared with character recognition based on template matching, the method has better robustness to the font style, and if the influence of noise, blurring, illumination, frames and the like in the simulated real environment is added during training, the robustness to external interference can be improved, and the classification accuracy is relatively high.
In a second aspect, the invention discloses a property management device based on image processing, which comprises a module for executing the method in any one of the first aspects. The specific implementation is similar to that described in the first aspect, and will not be repeated here.
In a third aspect, as shown in fig. 5, the present invention provides a property management apparatus based on image processing. As shown in fig. 5, the image processing-based property management device includes one or more processors 501; one or more input devices 502, one or more output devices 503, and a memory 504. The processor 501, the input device 502, the output device 503, and the memory 504 are connected via a bus 505. The memory 504 is used for storing a computer program comprising program instructions, and the processor 501 is used for executing the program instructions stored in the memory 504. Wherein the processor 501 is configured to invoke the program instructions to perform the operations of any of the methods of the first aspect:
it should be appreciated that in embodiments of the present invention, the processor 501 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 502 may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of a fingerprint), a microphone, etc., and the output device 503 may include a display (LCD, etc.), a speaker, etc.
The memory 504 may include read only memory and random access memory and provide instructions and data to the processor 501. A portion of memory 504 may also include non-volatile random access memory. For example, the memory 504 may also store information of device type.
In a specific implementation, the processor 501, the input device 502, and the output device 503 described in the embodiments of the present invention may perform an implementation described in any of the methods of the first aspect, or may perform an implementation of the terminal device described in the embodiments of the present invention, which is not described herein again.
In a fourth aspect, the present invention provides a computer readable storage medium storing a computer program comprising program instructions which when executed by a processor implement the steps of any of the methods of the first aspect.
Compared with the prior art, the invention discloses a property management method and device based on image processing, which can accurately and automatically read the readings of various domestic meters such as water meters, gas meters, electric meters and the like. After acquiring dial images of a life table, the method cuts the dial images into table plate images with balanced brightness, extracts reading areas in the table plate images, then splits the reading areas of the table plate into table plate reading areas, and finally carries out character recognition on the table plate reading areas to obtain the table plate reading. The method can solve the adverse effect of illumination or reflection on the character reading technology based on image recognition to a certain extent, and the illumination of each dial image is approximately uniform as long as the dial image is cut to a certain size.
In addition, the property management method based on image processing can judge whether the first character is a decimal character by identifying whether the pixel color of an original image of a character area corresponding to the position of the first character area in a dial image is a target color. If the first character is a decimal character, reversing the default order into a reading order; if the first character is a non-decimal character then the default order may be confirmed as the reading order.
The computer readable storage medium may be an internal storage unit of the terminal device of any of the foregoing embodiments, for example, a hard disk or a memory of the terminal device. The computer readable storage medium may be an external storage device of the terminal device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, which are provided in the terminal device. Further, the computer-readable storage medium may further include both an internal storage unit and an external storage device of the terminal device. The computer-readable storage medium is used for storing the computer program and other programs and data required by the terminal device. The above-described computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing descriptions of specific exemplary embodiments of the present invention are presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application to thereby enable one skilled in the art to make and utilize the invention in various exemplary embodiments and with various modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (10)
1. The property management method based on image processing is characterized by comprising the following steps:
acquiring a dial image of a life table;
cutting the dial plate image into a plurality of dial plate images, wherein the absolute value of the brightness value difference value of any two pixels in each dial plate image is smaller than a brightness balance threshold;
dividing the reading area in each table plate image;
splitting the reading areas in each of the table dish images into table dish reading areas; and
and identifying the characters in the dial reading area one by one according to the reading sequence to obtain the dial reading.
2. The image processing-based property management method of claim 1, wherein,
the step of cutting the dial plate image into a plurality of dial plate images, wherein the absolute value of the brightness value difference value of any two pixels in each dial plate image is smaller than a brightness balance threshold value, and the step of: and performing half-cut on the dial plate image to obtain dial plate images until the absolute value of the brightness value difference value of any two pixels in each dial plate image is smaller than the brightness balance threshold value.
3. The image processing-based property management method of claim 1, wherein,
the dividing the reading area in each table plate image comprises the following steps:
converting each dial sub-image into a corresponding gray level image, and taking the corresponding gray level image as a dial gray level sub-image;
gradually reducing the gray threshold value in the gray adjustment range, extracting character pixels smaller than the gray threshold value in the dial gray sub-image after the gray threshold value is adjusted each time, and adding the character pixels into the reading area until the number of the character pixels in the reading area is larger than the pixel number threshold value.
4. The image processing-based property management method of claim 1, wherein,
after the acquiring of the dial image of the life table, before the cutting of the dial image into a plurality of table dish images, the absolute value of the difference value of the brightness values of any two pixels in each table dish image is smaller than the brightness balance threshold value, the method further comprises:
and after carrying out Gaussian equalization processing on the dial image, updating the dial image.
5. The image processing-based property management method of claim 1, wherein,
the step of identifying the characters in the dial reading area one by one according to the reading sequence to obtain dial reading comprises the following steps:
cutting each character in the dial reading area to obtain each character area;
and identifying the characters of each character area in the dial reading area one by one according to the reading sequence to obtain the dial reading.
6. The image processing-based property management method of claim 5, wherein,
after each character in the dial reading area is cut to obtain each character area, the characters in each character area in the dial reading area are identified one by one according to the reading sequence, and before the dial reading is obtained, the method further comprises the steps of:
acquiring a first character area of the dial reading area according to a default sequence, and extracting a character area original image corresponding to the position of the first character area in the dial image;
identifying the pixel color of the original image of the character area;
under the condition that the pixel color of the original image of the character area is the target color, confirming that the reverse order of the default order is the reading order; and
and confirming the default sequence as the reading sequence under the condition that the pixel color of the original image of the character area is a non-target color.
7. The image processing-based property management method of claim 6, wherein,
the identifying the pixel color of the character area original image comprises the following steps: calculating average red components, average green components and average blue components of all pixels in the original image of the character area;
and when the pixel color of the character area original image is the target color, confirming that the reverse order of the default order is the reading order, including: calculating a target color component duty cycle from the average red component, the average green component, and the average blue component; confirming that the reverse order of the default order is the reading order under the condition that the target color component duty ratio reaches a target threshold value;
and when the pixel color of the original image of the character area is a non-target color, confirming that the default sequence is the reading sequence comprises the following steps: calculating a target color component duty cycle from the average red component, the average green component, and the average blue component; and confirming the default sequence as the reading sequence under the condition that the target color component duty ratio is smaller than a target threshold value.
8. A property management apparatus based on image processing, characterized by comprising means for performing the method of any of claims 1 to 7.
9. A property management apparatus based on image processing, characterized by comprising a processor, an input device, an output device and a memory, the processor, the input device, the output device and the memory being interconnected, wherein the memory is for storing a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1 to 7.
10. A computer readable storage medium, characterized in that the computer storage medium stores a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310530663.3A CN116246265B (en) | 2023-05-12 | 2023-05-12 | Property management method and device based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310530663.3A CN116246265B (en) | 2023-05-12 | 2023-05-12 | Property management method and device based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116246265A true CN116246265A (en) | 2023-06-09 |
| CN116246265B CN116246265B (en) | 2023-08-08 |
Family
ID=86631700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310530663.3A Active CN116246265B (en) | 2023-05-12 | 2023-05-12 | Property management method and device based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116246265B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000194851A (en) * | 1998-12-24 | 2000-07-14 | Nippon Telegr & Teleph Corp <Ntt> | Character area extraction method and device and storage medium recording the method |
| CN103164702A (en) * | 2011-12-13 | 2013-06-19 | 李卫伟 | Extracting method and device of marker central point and image processing system |
| CN106960208A (en) * | 2017-03-28 | 2017-07-18 | 哈尔滨工业大学 | A kind of instrument liquid crystal digital automatic segmentation and the method and system of identification |
| CN108304785A (en) * | 2018-01-16 | 2018-07-20 | 桂林电子科技大学 | Road traffic sign detection based on self-built neural network and recognition methods |
| CN109360396A (en) * | 2018-09-27 | 2019-02-19 | 长江大学 | Remote meter reading method and system based on image recognition technology and NB-IoT technology |
| CN110263785A (en) * | 2019-06-19 | 2019-09-20 | 深圳前海达闼云端智能科技有限公司 | A kind of automatic meter reading method, device and computer readable storage medium |
| JP2021072484A (en) * | 2019-10-29 | 2021-05-06 | 京セラドキュメントソリューションズ株式会社 | Image processing apparatus, image processing method, and image processing program |
| CN113554022A (en) * | 2021-06-07 | 2021-10-26 | 华北电力科学研究院有限责任公司 | Automatic acquisition method and device for detection test data of power instrument |
| US20220174182A1 (en) * | 2020-12-02 | 2022-06-02 | Sharp Kabushiki Kaisha | Image processing device, control method, and non-transitory recording medium |
| CN115278104A (en) * | 2022-07-04 | 2022-11-01 | 浙江大华技术股份有限公司 | Image brightness adjusting method and device, electronic equipment and storage medium |
-
2023
- 2023-05-12 CN CN202310530663.3A patent/CN116246265B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000194851A (en) * | 1998-12-24 | 2000-07-14 | Nippon Telegr & Teleph Corp <Ntt> | Character area extraction method and device and storage medium recording the method |
| CN103164702A (en) * | 2011-12-13 | 2013-06-19 | 李卫伟 | Extracting method and device of marker central point and image processing system |
| CN106960208A (en) * | 2017-03-28 | 2017-07-18 | 哈尔滨工业大学 | A kind of instrument liquid crystal digital automatic segmentation and the method and system of identification |
| CN108304785A (en) * | 2018-01-16 | 2018-07-20 | 桂林电子科技大学 | Road traffic sign detection based on self-built neural network and recognition methods |
| CN109360396A (en) * | 2018-09-27 | 2019-02-19 | 长江大学 | Remote meter reading method and system based on image recognition technology and NB-IoT technology |
| CN110263785A (en) * | 2019-06-19 | 2019-09-20 | 深圳前海达闼云端智能科技有限公司 | A kind of automatic meter reading method, device and computer readable storage medium |
| JP2021072484A (en) * | 2019-10-29 | 2021-05-06 | 京セラドキュメントソリューションズ株式会社 | Image processing apparatus, image processing method, and image processing program |
| US20220174182A1 (en) * | 2020-12-02 | 2022-06-02 | Sharp Kabushiki Kaisha | Image processing device, control method, and non-transitory recording medium |
| CN113554022A (en) * | 2021-06-07 | 2021-10-26 | 华北电力科学研究院有限责任公司 | Automatic acquisition method and device for detection test data of power instrument |
| CN115278104A (en) * | 2022-07-04 | 2022-11-01 | 浙江大华技术股份有限公司 | Image brightness adjusting method and device, electronic equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| LINNA ZHOU 等: "Combined Algorithm of Steganography with Matrix Pattern and Pixel Value Difference", 《2019 IEEE 2ND INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION ENGINEERING TECHNOLOGY (CCET)》, pages 6 - 10 * |
| 张宏屏: "基于数字图像处理的水表读数识别系统应用研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 2, pages 138 - 1407 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116246265B (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10635946B2 (en) | Eyeglass positioning method, apparatus and storage medium | |
| Kaneko et al. | Robust image registration by increment sign correlation | |
| CN108399405B (en) | Business license identification method and device | |
| CN108268867B (en) | License plate positioning method and device | |
| CN111444781B (en) | Water meter reading identification method, device and storage medium | |
| Anthimopoulos et al. | Detection of artificial and scene text in images and video frames | |
| CN109116129B (en) | Terminal detection method, detection device, system and storage medium | |
| CN111783757A (en) | OCR technology-based identification card recognition method in complex scene | |
| CN110502977B (en) | Building change classification detection method, system, device and storage medium | |
| CN111539330B (en) | Transformer substation digital display instrument identification method based on double-SVM multi-classifier | |
| CN110969164A (en) | Low-illumination imaging license plate recognition method and device based on deep learning end-to-end | |
| CN114332513A (en) | New energy automobile abnormal parking amplification data detection method for smart city | |
| CN116433701B (en) | Workpiece hole profile extraction method, device, equipment and storage medium | |
| CN111784675A (en) | Method and device for processing article texture information, storage medium and electronic equipment | |
| CN113361467A (en) | License plate recognition method based on field adaptation | |
| CN115880260A (en) | Method, device and equipment for detecting base station construction and computer readable storage medium | |
| CN110728279A (en) | Water meter digital identification method based on embedded platform machine vision | |
| CN112686122B (en) | Human body and shadow detection method and device, electronic equipment and storage medium | |
| WO2022121021A1 (en) | Identity card number detection method and apparatus, and readable storage medium and terminal | |
| CN111199240A (en) | Training method of bank card identification model, and bank card identification method and device | |
| CN116246265B (en) | Property management method and device based on image processing | |
| Shuo et al. | Digital recognition of electric meter with deep learning | |
| CN111178359A (en) | License plate number recognition method, device and equipment and computer storage medium | |
| CN114529906A (en) | Method and system for detecting abnormity of digital instrument of power transmission equipment based on character recognition | |
| Abdusalomov et al. | Robust shadow removal technique for improving image enhancement based on segmentation method |
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 |