CN112990179A - Single-pointer type dial reading automatic identification method based on picture processing - Google Patents
Single-pointer type dial reading automatic identification method based on picture processing Download PDFInfo
- Publication number
- CN112990179A CN112990179A CN202110421534.1A CN202110421534A CN112990179A CN 112990179 A CN112990179 A CN 112990179A CN 202110421534 A CN202110421534 A CN 202110421534A CN 112990179 A CN112990179 A CN 112990179A
- Authority
- CN
- China
- Prior art keywords
- image
- dial
- dial plate
- reading
- recognized
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a single pointer type dial reading automatic identification method based on picture processing, which comprises the following steps: s1, preprocessing an image to be identified; s2, constructing and training a dial plate detection and positioning model, and cutting out a dial plate image area in the image to be recognized; s3, obtaining the coordinates of key points of the table image area in the image to be identified; s4, setting a standard dial plate, and correcting a dial plate image area in the image to be recognized to obtain a dial plate corrected image; s5, preliminarily identifying the dial plate correction image corresponding to the image to be identified, and determining the whole scale of the dial plate pointer reading; and S6, carrying out fine identification on the pointer reading of the dial plate correction image according to the primary identification result to obtain the pointer reading of the dial plate. The invention determines the whole scale through the classification algorithm on the premise of image enhancement, dial plate detection and positioning and dial plate correction, and carries out fine identification on the basis, thereby effectively improving the accuracy of dial plate reading automatic identification.
Description
Technical Field
The invention relates to pointer dial reading, in particular to a single-pointer type dial reading automatic identification method based on picture processing.
Background
Pointer instruments (especially single pointer instruments) are widely applied in daily work, but currently, the pointer instruments are mainly read by human eyes of operators, and when the pointer instruments are applied to the industrial field, the efficiency is low, reading errors are often caused by fatigue of the human eyes, and the measuring results are seriously influenced.
In recent years, machine reading instead of reading is gradually becoming a research hotspot, and currently, machine reading is mainly realized by adopting an image processing algorithm, but the current image processing algorithm has the problem of low precision when pointer reading identification is carried out.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a single-pointer type dial reading automatic identification method based on picture processing.
The purpose of the invention is realized by the following technical scheme: a single pointer type dial reading automatic identification method based on picture processing comprises the following steps:
s1, preprocessing an image to be identified;
s2, establishing and training a dial plate detection and positioning model, carrying out dial plate detection and positioning on the preprocessed image to be recognized, and cutting out a dial plate image area in the image to be recognized;
s3, carrying out key point detection on a dial plate image area in the image to be recognized to obtain key point coordinates of the dial plate image area in the image to be recognized;
s4, setting a standard dial plate, and correcting a dial plate image area in the image to be recognized to obtain a dial plate corrected image;
s5, preliminarily identifying the dial plate correction image corresponding to the image to be identified, and determining the whole scale of the dial plate pointer reading;
and S6, carrying out fine identification on the pointer reading of the dial plate correction image according to the primary identification result to obtain the pointer reading of the dial plate.
The invention has the beneficial effects that: the invention firstly carries out image enhancement, dial plate detection and positioning and dial plate correction on the image to be recognized, is beneficial to improving the accuracy of the image to be recognized, firstly proposes to adopt a classification method to determine the whole scale of the image on the basis, obtains the pointer reading of the dial plate through further fine recognition after obtaining the whole scale, and effectively improves the precision of automatic dial plate reading recognition.
Drawings
FIG. 1 is a flow chart of the method of the present invention
FIG. 2 is a schematic diagram of a partially cropped image of the fine recognition process in an embodiment.
Detailed Description
The technical solutions of the present invention are further described in detail below with reference to the accompanying drawings, but the scope of the present invention is not limited to the following.
As shown in fig. 1, a single pointer type dial reading automatic identification method based on picture processing includes the following steps:
s1, preprocessing an image to be identified;
s2, establishing and training a dial plate detection and positioning model, carrying out dial plate detection and positioning on the preprocessed image to be recognized, and cutting out a dial plate image area in the image to be recognized;
s3, carrying out key point detection on a dial plate image area in the image to be recognized to obtain key point coordinates of the dial plate image area in the image to be recognized;
s4, setting a standard dial plate, and correcting a dial plate image area in the image to be recognized to obtain a dial plate corrected image;
s5, preliminarily identifying the dial plate correction image corresponding to the image to be identified, and determining the whole scale of the dial plate pointer reading;
and S6, carrying out fine identification on the pointer reading of the dial plate correction image according to the primary identification result to obtain the pointer reading of the dial plate.
In an embodiment of the present application, the preprocessing process described in step S1 includes:
the image enhancement operation is carried out through contrast stretching, the contrast of an excessively dark or bright image is adjusted, the image details are richer, and the difference between the dial plate and the background is increased.
In an embodiment of the present application, the step S2 includes:
s201, obtaining a plurality of images with dials, and performing image enhancement operation through contrast stretching to obtain a plurality of sample images;
s202, for any sample image, selecting a dial plate position by using a rectangular frame, marking position coordinates of four vertexes of the rectangular frame where the dial plate position is located as dial plate position coordinates, and taking the sample image and the corresponding dial plate position coordinates as a training sample;
s203, repeating the step S202 for each sample image to finally obtain a plurality of training samples, and adding the training samples into the same set to form a sample set;
s204, constructing a dial plate detection and positioning model by using a target detection algorithm, inputting a sample image of each sample in a sample set as a model, outputting dial plate position coordinates corresponding to the sample image, and training the dial plate detection and positioning model to obtain a mature dial plate detection and positioning model;
s205, inputting the preprocessed image to be recognized into a mature dial plate detection and positioning model, and outputting a plurality of candidate dial plate position coordinates and the confidence coefficient of each candidate dial plate position coordinate by the dial plate detection and positioning model, wherein the confidence coefficient is positioned in an interval [0, 1] and is used for representing the probability of the dial plate existing at the position coordinate of the subsequent dial plate position and belongs to the self-contained parameter in the target detection algorithm;
s206, selecting the candidate dial position coordinate with the maximum confidence coefficient, comparing the candidate dial position coordinate with a preset threshold value, and judging whether the confidence coefficient is greater than the preset threshold value:
if yes, the dial is considered to be detected, and a dial image area in the image to be recognized is cut out according to the candidate dial position coordinate with the maximum confidence coefficient;
if not, the dial is not recognized, and the process returns to step S1 to perform preprocessing of the next image to be recognized.
In the embodiment of the present application, the object detection algorithm includes an ACF object detection algorithm or a yolov3 network algorithm.
In an embodiment of the present application, the step S3 includes:
s301, obtaining an image with a dial, performing contrast stretching to perform image enhancement operation, inputting the mature dial detection and positioning model in the step S205, and obtaining a dial image area in the image according to the steps S205-S206;
s302, repeatedly executing the step S301 for multiple times to obtain multiple dial area images, and marking the key point coordinates of each dial area image;
s303, constructing a regression network by using a deep learning method, taking each dial area image as input, taking the key point coordinates corresponding to the dial area image as output, training the regression network, and taking the regression network which is trained well as a key point detection model;
s304, inputting the dial image area in the image to be recognized into the key point detection model to obtain the key point coordinates of the dial image area in the image to be recognized.
In the embodiment of the present application, the key point in step S302 is defined as a start position, a middle point position, an end position or a dial center position of the dial image area scale.
In an embodiment of the present application, the step S4 includes:
s401, setting a standard dial template, finding corresponding key points on the standard dial according to the definition of the key points, and marking the coordinates of the key points on the standard dial;
s402, taking a dial image area in an image to be identified as an original dial image, correspondingly registering key point coordinates of the original dial image and key point coordinates on a standard dial, and calculating a perspective transformation matrix from the original dial image to the standard dial through a perspective transformation formula;
in the embodiment of the present application, the Perspective Transformation (Perspective Transformation) is to project a picture to a new Viewing Plane (Viewing Plane), also called projection Mapping (projection); the perspective transformation matrix can be obtained through a plurality of known corresponding point coordinates, and in the same way, after the perspective matrix is obtained, coordinate mapping can also be carried out according to the perspective matrix;
and S403, mapping each pixel point coordinate in the original dial image through a perspective transformation matrix to obtain each mapped pixel point coordinate, so as to obtain a dial correction image.
In an embodiment of the present application, the step S5 includes:
s501, dividing the dial into a plurality of areas according to the whole scale, wherein each area corresponds to one whole scale, and each area is defined as a category;
s502, taking a plurality of images with dials, processing according to the steps S1-S4 to obtain a plurality of dial correction images, and defining the category of each dial correction image according to the area of the pointer in the dial;
s503, constructing a classification model by using a deep learning algorithm, taking each dial plate correction image as the input of the classification model, taking the category of the dial plate correction image as the output of the classification model, and training the classification model to obtain a mature classification model;
s504, inputting the dial plate correction image corresponding to the image to be recognized into a mature classification model to obtain class information, and determining the pointer whole scale of the dial plate correction image corresponding to the image to be recognized according to the class information.
In an embodiment of the present application, the step S6 includes:
s601, according to the pointer whole scale obtained by the primary recognition result, finding the area where the scale is located in the dial plate correction image, expanding the area range, and cutting to obtain a local cutting image;
s602, binarizing the local cutting image, wherein the background is black, and the pointer and the scale are white;
s603, as shown in FIG. 2, finding two adjacent scale positions of the initial identification, which are respectively represented as P1 and P2, and finding a position P0 where the pointer intersects with the scale lines;
s604, for the standard dial template, the reading between two adjacent scales is known and is set as k, and the distances from a scale point P0 to P1 and P2 are obtained and are represented as L1 and L2;
estimating the offset reading of the pointer as (L1/(L1 + L2)) × k;
and S605, adding the initial identification result and the offset reading to obtain a final reading result.
While the foregoing description shows and describes a preferred embodiment of the invention, it is to be understood, as noted above, that the invention is not limited to the form disclosed herein, but is not intended to be exhaustive or to exclude other embodiments and may be used in various other combinations, modifications, and environments and may be modified within the scope of the inventive concept described herein by the above teachings or the skill or knowledge of the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A single pointer type dial reading automatic identification method based on picture processing is characterized in that: the method comprises the following steps:
s1, preprocessing an image to be identified;
s2, establishing and training a dial plate detection and positioning model, carrying out dial plate detection and positioning on the preprocessed image to be recognized, and cutting out a dial plate image area in the image to be recognized;
s3, carrying out key point detection on a dial plate image area in the image to be recognized to obtain key point coordinates of the dial plate image area in the image to be recognized;
s4, setting a standard dial plate, and correcting a dial plate image area in the image to be recognized to obtain a dial plate corrected image;
s5, preliminarily identifying the dial plate correction image corresponding to the image to be identified, and determining the whole scale of the dial plate pointer reading;
and S6, carrying out fine identification on the pointer reading of the dial plate correction image according to the primary identification result to obtain the pointer reading of the dial plate.
2. The automatic identification method of the single pointer type dial reading based on the picture processing as claimed in claim 1, characterized in that: the preprocessing process described in step S1 includes:
the image enhancement operation is carried out through contrast stretching, the contrast of an excessively dark or bright image is adjusted, the image details are richer, and the difference between the dial plate and the background is increased.
3. The automatic identification method of the single pointer type dial reading based on the picture processing as claimed in claim 1, characterized in that: the step S2 includes:
s201, obtaining a plurality of images with dials, and performing image enhancement operation through contrast stretching to obtain a plurality of sample images;
s202, for any sample image, selecting a dial plate position by using a rectangular frame, marking position coordinates of four vertexes of the rectangular frame where the dial plate position is located as dial plate position coordinates, and taking the sample image and the corresponding dial plate position coordinates as a training sample;
s203, repeating the step S202 for each sample image to finally obtain a plurality of training samples, and adding the training samples into the same set to form a sample set;
s204, constructing a dial plate detection and positioning model by using a target detection algorithm, inputting a sample image of each sample in a sample set as a model, outputting dial plate position coordinates corresponding to the sample image, and training the dial plate detection and positioning model to obtain a mature dial plate detection and positioning model;
s205, inputting the preprocessed image to be recognized into a mature dial plate detection and positioning model, and outputting a plurality of candidate dial plate position coordinates and the confidence coefficient of each candidate dial plate position coordinate by the dial plate detection and positioning model, wherein the confidence coefficient is positioned in an interval [0, 1] and is used for representing the probability of the dial plate existing at the position coordinate of the subsequent dial plate position and belongs to the self-contained parameter in the target detection algorithm;
s206, selecting the candidate dial position coordinate with the maximum confidence coefficient, comparing the candidate dial position coordinate with a preset threshold value, and judging whether the confidence coefficient is greater than the preset threshold value:
if yes, the dial is considered to be detected, and a dial image area in the image to be recognized is cut out according to the candidate dial position coordinate with the maximum confidence coefficient;
if not, the dial is not recognized, and the process returns to step S1 to perform preprocessing of the next image to be recognized.
4. The automatic identification method of the single pointer type dial reading based on the picture processing as claimed in claim 3, characterized in that: the target detection algorithm comprises an ACF target detection algorithm or a yolov3 network algorithm.
5. The automatic identification method of the single pointer type dial reading based on the picture processing as claimed in claim 3, characterized in that: the step S3 includes:
s301, obtaining an image with a dial, performing contrast stretching to perform image enhancement operation, inputting the mature dial detection and positioning model in the step S205, and obtaining a dial image area in the image according to the steps S205-S206;
s302, repeatedly executing the step S301 for multiple times to obtain multiple dial area images, and marking the key point coordinates of each dial area image;
s303, constructing a regression network by using a deep learning method, taking each dial area image as input, taking the key point coordinates corresponding to the dial area image as output, training the regression network, and taking the regression network which is trained well as a key point detection model;
s304, inputting the dial image area in the image to be recognized into the key point detection model to obtain the key point coordinates of the dial image area in the image to be recognized.
6. The automatic identification method of the single pointer type dial reading based on the picture processing as claimed in claim 3, characterized in that: the key point in the step S302 is defined as the starting position of the dial image area scale, the scale midpoint position or the dial center position.
7. The automatic identification method of the single pointer type dial reading based on the picture processing as claimed in claim 6, characterized in that: the step S4 includes:
s401, setting a standard dial template, finding corresponding key points on the standard dial according to the definition of the key points, and marking the coordinates of the key points on the standard dial;
s402, taking a dial image area in an image to be identified as an original dial image, correspondingly registering key point coordinates of the original dial image and key point coordinates on a standard dial, and calculating a perspective transformation matrix from the original dial image to the standard dial through a perspective transformation formula;
and S403, mapping each pixel point coordinate in the original dial image through a perspective transformation matrix to obtain each mapped pixel point coordinate, so as to obtain a dial correction image.
8. The automatic identification method of the single pointer type dial reading based on the picture processing as claimed in claim 7, characterized in that: the step S5 includes:
s501, dividing the dial into a plurality of areas according to the whole scale, wherein each area corresponds to one whole scale, and each area is defined as a category;
s502, taking a plurality of images with dials, processing according to the steps S1-S4 to obtain a plurality of dial correction images, and defining the category of each dial correction image according to the area of the pointer in the dial;
s503, constructing a classification model by using a deep learning algorithm, taking each dial plate correction image as the input of the classification model, taking the category of the dial plate correction image as the output of the classification model, and training the classification model to obtain a mature classification model;
s504, inputting the dial plate correction image corresponding to the image to be recognized into a mature classification model to obtain class information, and determining the pointer whole scale of the dial plate correction image corresponding to the image to be recognized according to the class information.
9. The automatic identification method of the single pointer type dial reading based on the picture processing as claimed in claim 8, characterized in that: the step S6 includes:
s601, according to the pointer whole scale obtained by the primary recognition result, finding the area where the scale is located in the dial plate correction image, expanding the area range, and cutting to obtain a local cutting image;
s602, binarizing the local cutting image, wherein the background is black, and the pointer and the scale are white;
s603, finding two adjacent scale positions of the initial identification, wherein the two adjacent scale positions are respectively represented as P1 and P2, and finding a position P0 where the pointer intersects with the scale lines;
s604, for the standard dial template, the reading between two adjacent scales is known and is set as k, and the distances from a scale point P0 to P1 and P2 are obtained and are represented as L1 and L2;
estimating the offset reading of the pointer as (L1/(L1 + L2)) × k;
and S605, adding the initial identification result and the offset reading to obtain a final reading result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110421534.1A CN112990179A (en) | 2021-04-20 | 2021-04-20 | Single-pointer type dial reading automatic identification method based on picture processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110421534.1A CN112990179A (en) | 2021-04-20 | 2021-04-20 | Single-pointer type dial reading automatic identification method based on picture processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112990179A true CN112990179A (en) | 2021-06-18 |
Family
ID=76341231
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110421534.1A Pending CN112990179A (en) | 2021-04-20 | 2021-04-20 | Single-pointer type dial reading automatic identification method based on picture processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112990179A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113537153A (en) * | 2021-08-20 | 2021-10-22 | 杭州灵伴科技有限公司 | Meter image identification method and device, electronic equipment and computer readable medium |
CN113902894A (en) * | 2021-10-26 | 2022-01-07 | 中国人民解放军火箭军工程大学 | Strip type level meter automatic reading identification method based on image processing |
CN114494684A (en) * | 2022-04-01 | 2022-05-13 | 深圳市海清视讯科技有限公司 | Reading identification method, device, equipment and storage medium for pointer type dial plate |
CN115496807A (en) * | 2022-11-18 | 2022-12-20 | 南方电网数字电网研究院有限公司 | Meter pointer positioning method and device, computer equipment and storage medium |
CN116012828A (en) * | 2022-12-02 | 2023-04-25 | 长扬科技(北京)股份有限公司 | Pointer instrument identification method and device, electronic equipment and storage medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105809179A (en) * | 2014-12-31 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Pointer type instrument reading recognition method and device |
US20190095739A1 (en) * | 2017-09-27 | 2019-03-28 | Harbin Institute Of Technology | Adaptive Auto Meter Detection Method based on Character Segmentation and Cascade Classifier |
CN109583324A (en) * | 2018-11-12 | 2019-04-05 | 武汉大学 | A kind of pointer meters reading automatic identifying method based on the more box detectors of single-point |
CN109871754A (en) * | 2019-01-08 | 2019-06-11 | 深圳禾思众成科技有限公司 | A kind of instrument read method, equipment and computer readable storage medium |
CN109948469A (en) * | 2019-03-01 | 2019-06-28 | 吉林大学 | The automatic detection recognition method of crusing robot instrument based on deep learning |
CN111652244A (en) * | 2020-04-27 | 2020-09-11 | 合肥中科类脑智能技术有限公司 | Pointer type meter identification method based on unsupervised feature extraction and matching |
CN111738229A (en) * | 2020-08-05 | 2020-10-02 | 江西小马机器人有限公司 | Automatic reading method for scale of pointer dial |
CN111814919A (en) * | 2020-08-31 | 2020-10-23 | 江西小马机器人有限公司 | Instrument positioning and identifying system based on deep learning |
CN111950330A (en) * | 2019-05-16 | 2020-11-17 | 杭州测质成科技有限公司 | Pointer instrument indicating number detection method based on target detection |
CN112507815A (en) * | 2020-11-24 | 2021-03-16 | 北京超维世纪科技有限公司 | Artificial intelligence image recognition algorithm and system for pointer instrument panel scale |
-
2021
- 2021-04-20 CN CN202110421534.1A patent/CN112990179A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105809179A (en) * | 2014-12-31 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Pointer type instrument reading recognition method and device |
US20190095739A1 (en) * | 2017-09-27 | 2019-03-28 | Harbin Institute Of Technology | Adaptive Auto Meter Detection Method based on Character Segmentation and Cascade Classifier |
CN109583324A (en) * | 2018-11-12 | 2019-04-05 | 武汉大学 | A kind of pointer meters reading automatic identifying method based on the more box detectors of single-point |
CN109871754A (en) * | 2019-01-08 | 2019-06-11 | 深圳禾思众成科技有限公司 | A kind of instrument read method, equipment and computer readable storage medium |
CN109948469A (en) * | 2019-03-01 | 2019-06-28 | 吉林大学 | The automatic detection recognition method of crusing robot instrument based on deep learning |
CN111950330A (en) * | 2019-05-16 | 2020-11-17 | 杭州测质成科技有限公司 | Pointer instrument indicating number detection method based on target detection |
CN111652244A (en) * | 2020-04-27 | 2020-09-11 | 合肥中科类脑智能技术有限公司 | Pointer type meter identification method based on unsupervised feature extraction and matching |
CN111738229A (en) * | 2020-08-05 | 2020-10-02 | 江西小马机器人有限公司 | Automatic reading method for scale of pointer dial |
CN111814919A (en) * | 2020-08-31 | 2020-10-23 | 江西小马机器人有限公司 | Instrument positioning and identifying system based on deep learning |
CN112507815A (en) * | 2020-11-24 | 2021-03-16 | 北京超维世纪科技有限公司 | Artificial intelligence image recognition algorithm and system for pointer instrument panel scale |
Non-Patent Citations (2)
Title |
---|
WEIDONG CAI 等: "A pointer meter Recognition method based on virtual sample generation technology", 《MEASUREMENT》 * |
龙劲峄: "基于深度学习的目标检测在智能制造中的运用研究", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113537153A (en) * | 2021-08-20 | 2021-10-22 | 杭州灵伴科技有限公司 | Meter image identification method and device, electronic equipment and computer readable medium |
CN113902894A (en) * | 2021-10-26 | 2022-01-07 | 中国人民解放军火箭军工程大学 | Strip type level meter automatic reading identification method based on image processing |
CN113902894B (en) * | 2021-10-26 | 2024-05-31 | 中国人民解放军火箭军工程大学 | Automatic reading identification method for strip level based on image processing |
CN114494684A (en) * | 2022-04-01 | 2022-05-13 | 深圳市海清视讯科技有限公司 | Reading identification method, device, equipment and storage medium for pointer type dial plate |
CN115496807A (en) * | 2022-11-18 | 2022-12-20 | 南方电网数字电网研究院有限公司 | Meter pointer positioning method and device, computer equipment and storage medium |
CN115496807B (en) * | 2022-11-18 | 2023-01-20 | 南方电网数字电网研究院有限公司 | Meter pointer positioning method and device, computer equipment and storage medium |
CN116012828A (en) * | 2022-12-02 | 2023-04-25 | 长扬科技(北京)股份有限公司 | Pointer instrument identification method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112990179A (en) | Single-pointer type dial reading automatic identification method based on picture processing | |
US11551341B2 (en) | Method and device for automatically drawing structural cracks and precisely measuring widths thereof | |
CN103759758B (en) | A kind of method for detecting position of the automobile meter pointer based on mechanical angle and scale identification | |
CN107256379B (en) | Information acquisition method based on image recognition, mobile terminal and storage medium | |
CN111950330A (en) | Pointer instrument indicating number detection method based on target detection | |
CN108537218B (en) | Answer sheet identification processing method and device | |
CN112348019B (en) | Answer sheet correction method and device, electronic equipment and storage medium | |
CN106033535B (en) | Electronic paper marking method | |
CN113870267B (en) | Defect detection method, defect detection device, computer equipment and readable storage medium | |
CN109886257B (en) | Method for correcting invoice image segmentation result by adopting deep learning in OCR system | |
CN113592839B (en) | Distribution network line typical defect diagnosis method and system based on improved fast RCNN | |
CN113902894B (en) | Automatic reading identification method for strip level based on image processing | |
CN116862910A (en) | Visual detection method based on automatic cutting production | |
CN110674811A (en) | Image recognition method and device | |
CN113076941A (en) | Single pointer dial reading identification method based on video frame fusion | |
CN114565911B (en) | Instrument reading method and device, computer equipment and storage medium | |
CN115761468A (en) | Water level detection system and method based on image segmentation and target detection technology | |
CN112507838B (en) | Pointer meter identification method and device and electric power inspection robot | |
CN114694128A (en) | Pointer instrument detection method and system based on abstract metric learning | |
CN114529803A (en) | Pointer instrument identification enhancement detection method | |
CN109740618B (en) | Test paper score automatic statistical method and device based on FHOG characteristics | |
CN115731458A (en) | Processing method and device for remote sensing image and electronic equipment | |
CN114092542A (en) | Bolt measuring method and system based on two-dimensional vision | |
CN113378820A (en) | Method and system for identifying digital pathological section target area | |
CN111931716B (en) | Pointer type dial plate identification method and system based on multi-dimensional characteristic analysis |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |