CN116704529A - Work ticket auditing system based on image recognition technology - Google Patents
Work ticket auditing system based on image recognition technology Download PDFInfo
- Publication number
- CN116704529A CN116704529A CN202310693708.9A CN202310693708A CN116704529A CN 116704529 A CN116704529 A CN 116704529A CN 202310693708 A CN202310693708 A CN 202310693708A CN 116704529 A CN116704529 A CN 116704529A
- Authority
- CN
- China
- Prior art keywords
- image
- work ticket
- ticket
- constraint condition
- work
- 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
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 63
- 238000000034 method Methods 0.000 claims abstract description 23
- 230000001815 facial effect Effects 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 13
- 238000010276 construction Methods 0.000 abstract description 10
- 230000009467 reduction Effects 0.000 description 27
- 230000008569 process Effects 0.000 description 16
- 230000000694 effects Effects 0.000 description 6
- 238000003708 edge detection Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/1444—Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Image Processing (AREA)
Abstract
The application belongs to the field of auditing, and discloses a work ticket auditing system based on an image recognition technology, which comprises a first camera module, a second camera module, a calculation module and a terminal module; the first camera module is used for acquiring an image of the work ticket; the second camera module is used for acquiring facial images of the staff; the computing module is used for identifying the image of the work ticket and the facial image of the worker to obtain an identification result, and checking whether the worker has passing permission or not based on the identification result to obtain a checking result; the terminal module is used for outputting the auditing result. The method comprises the steps of firstly carrying out straight line detection on the image of the work ticket to obtain a detection result, then judging whether the first constraint condition is met according to the detection result, re-acquiring the image of the work ticket if the first constraint condition is not met, and continuously judging whether the second constraint condition is met if the first constraint condition is met, so that preliminary judgment on the image of the work ticket is completed, and the influence on the efficiency of judging whether workers are allowed to enter a construction site is avoided.
Description
Technical Field
The application relates to the field of auditing, in particular to a work ticket auditing system based on an image recognition technology.
Background
The work ticket is a written order that allows work on the electrical equipment and system software, and is also a written basis for implementing technical measures to ensure safety. After the staff gets the working ticket, before entering the construction site, the staff needs to be identified and checked to avoid the non-staff from entering the construction site. In the prior art, the content in the working ticket is generally acquired by identifying the working ticket, the face image of the working personnel is acquired, then the face recognition is carried out, the name of the working personnel in the face image is acquired, and whether the working personnel is allowed to enter a construction site or not is judged based on the content in the working ticket and the name of the working personnel. Wherein, the content in the work ticket comprises construction site, construction time and the like.
In the prior art, in the process of carrying out image recognition on a work ticket, an obtained image is generally directly sent to a recognition device for recognition, but if the work ticket is folded or blocked in the process of obtaining the image of the work ticket, a complete image recognition is required to be carried out before a recognition result is obtained, and the recognition result is that the content of the work ticket cannot be obtained correctly and the shooting is required to be carried out again. After the situation, the whole process of identifying the image of the work ticket is invalid. This affects the efficiency of determining whether to allow a worker to enter a job site.
Disclosure of Invention
The application aims to disclose a work ticket auditing system based on an image recognition technology, which solves the problem that the efficiency of judging whether to allow workers to enter a construction site is affected because the recognition process is invalid when the complete recognition process is carried out on the image of the work ticket under the condition that the work ticket is folded or blocked.
In order to achieve the above purpose, the application adopts the following technical scheme:
a work ticket auditing system based on an image recognition technology comprises a first camera module, a second camera module, a calculation module and a terminal module;
the first camera module is used for acquiring an image of the work ticket;
the second camera module is used for acquiring facial images of the staff;
the computing module is used for identifying the image of the work ticket and the facial image of the worker to obtain an identification result, and checking whether the worker has passing permission or not based on the identification result to obtain a checking result;
the terminal module is used for outputting the auditing result,
wherein, the image of the work ticket is obtained, including;
shooting a work ticket to obtain an image of the work ticket;
secondly, performing linear detection on the image of the work ticket to obtain a detection result;
thirdly, judging whether the image of the work ticket accords with the first constraint condition according to the detection result, if so, entering a fifth step, and if not, entering a fourth step;
fourth, sending preset prompt information to the person responsible for shooting, and entering the first step;
and fifthly, judging whether the image of the work ticket meets the set second constraint condition according to the detection result, if so, transmitting the image of the work ticket to a calculation module, and if not, entering a fourth step.
Optionally, the first camera module comprises a shooting unit, a judging unit and a prompting unit;
the shooting unit is used for shooting the work ticket to obtain an image of the work ticket;
the judging unit is used for carrying out straight line detection on the image of the work ticket to obtain a first detection result, judging whether the image of the work ticket accords with a first constraint condition according to the detection result, and judging whether the image of the work ticket accords with a set second constraint condition according to the detection result when the image of the work ticket accords with the first constraint condition;
the prompting unit is used for sending preset prompting information to a person in charge of shooting when the image of the work ticket does not accord with the first constraint condition or does not accord with the second constraint condition;
the shooting unit is also used for shooting the work ticket again to obtain the image of the work ticket when the image of the work ticket does not accord with the first constraint condition or does not accord with the second constraint condition.
Optionally, the performing the straight line detection on the image of the work ticket to obtain a detection result includes:
performing inclination correction on the image of the work ticket to obtain an inclination correction image;
and performing linear detection on the inclination correction image by using a linear detection algorithm to obtain a detection result.
Optionally, the detection result includes a straight line segment included in the image of the work ticket.
Optionally, the determining, according to the detection result, whether the image of the work ticket meets the first constraint condition includes:
and calculating whether the number of the straight line segments is larger than a set number threshold, if so, indicating that the image of the work ticket meets the first constraint condition, and if not, indicating that the image of the work ticket does not meet the first constraint condition.
Optionally, the determining, according to the detection result, whether the image of the work ticket meets the set second constraint condition includes:
acquiring a first linear line segment strlinxfix and a last linear line segment strlinxlst in the horizontal direction in an image of a work ticket;
acquiring a first linear line segment strlinyfir and a last linear line segment strlinyl st in the vertical direction in an image of a work ticket;
calculating a first distance dis between strlinxfir and strlinxlst;
calculating a second distance dissed between strlinyfir and strlinylst;
calculating a distance ratio disrate:
if the distance ratio disrate does not belong to the interval [ midi st, madist ], the image of the work ticket does not accord with the set second constraint condition, and if the distance ratio disrate belongs to the interval [ midi st, madist ], the image of the work ticket accords with the set second constraint condition, the midi st and the madist respectively represent the lower limit value and the upper limit value of the distance ratio disrate.
Optionally, the identifying the image of the work ticket and the face image of the worker to obtain an identification result includes:
the method comprises the steps of adopting an OCR recognition algorithm to recognize an image of a work ticket, and obtaining information contained in the image of the work ticket, wherein the information contained in the image of the work ticket comprises a responsible person name, working time and working place;
identifying the face image to obtain the image characteristics of the face image;
the information contained in the image of the work ticket and the image characteristics of the face image are used as the recognition results.
Optionally, the checking whether the staff has the passing authority based on the identification result to obtain the checking result includes:
acquiring names of people corresponding to the facial images according to the image characteristics;
judging whether the name of a responsible person in the image of the work ticket is consistent with the name of a person corresponding to the face image, if not, judging whether the working time and the working place meet the requirements or not if the auditing result is that the worker does not have the passing authority;
if the working time and the working place meet the requirements, the auditing result is that the staff has the passing authority.
In the process of checking the working ticket, the application carries out straight line detection on the image of the working ticket to obtain a detection result, then judges whether the image of the working ticket accords with a first constraint condition according to the detection result, and re-acquires the image of the working ticket if the image of the working ticket does not accord with the first constraint condition, and continuously judges whether the image of the working ticket accords with a second constraint condition if the image of the working ticket accords with the second constraint condition, thereby completing preliminary judgment on the image of the working ticket in the acquisition stage, avoiding that the image of the working ticket which does not accord with the constraint condition enters a calculation module to calculate, and affecting the efficiency of judging whether workers enter a construction site.
Drawings
The application will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the application, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings.
FIG. 1 is a diagram of an embodiment of a ticket auditing system based on image recognition technology according to the present application.
FIG. 2 is a diagram of an embodiment of the present application for capturing an image of a work ticket.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
The application provides a work ticket auditing system based on an image recognition technology, which is shown in an embodiment in fig. 1, and comprises a first camera module, a second camera module, a calculation module and a terminal module;
the first camera module is used for acquiring an image of the work ticket;
the second camera module is used for acquiring facial images of the staff;
the computing module is used for identifying the image of the work ticket and the facial image of the worker to obtain an identification result, and checking whether the worker has passing permission or not based on the identification result to obtain a checking result;
the terminal module is used for outputting the auditing result,
wherein, as shown in fig. 2, the image of the work ticket is acquired, including;
shooting a work ticket to obtain an image of the work ticket;
secondly, performing linear detection on the image of the work ticket to obtain a detection result;
thirdly, judging whether the image of the work ticket accords with the first constraint condition according to the detection result, if so, entering a fifth step, and if not, entering a fourth step;
fourth, sending preset prompt information to the person responsible for shooting, and entering the first step;
and fifthly, judging whether the image of the work ticket meets the set second constraint condition according to the detection result, if so, transmitting the image of the work ticket to a calculation module, and if not, entering a fourth step.
In the process of checking the working ticket, the application carries out straight line detection on the image of the working ticket to obtain a detection result, then judges whether the image of the working ticket accords with a first constraint condition according to the detection result, and re-acquires the image of the working ticket if the image of the working ticket does not accord with the first constraint condition, and continuously judges whether the image of the working ticket accords with a second constraint condition if the image of the working ticket accords with the second constraint condition, thereby completing preliminary judgment on the image of the working ticket in the acquisition stage, avoiding that the image of the working ticket which does not accord with the constraint condition enters a calculation module to calculate, and affecting the efficiency of judging whether workers enter a construction site.
Optionally, the first camera module comprises a shooting unit, a judging unit and a prompting unit;
the shooting unit is used for shooting the work ticket to obtain an image of the work ticket;
the judging unit is used for carrying out straight line detection on the image of the work ticket to obtain a first detection result, judging whether the image of the work ticket accords with a first constraint condition according to the detection result, and judging whether the image of the work ticket accords with a set second constraint condition according to the detection result when the image of the work ticket accords with the first constraint condition;
the prompting unit is used for sending preset prompting information to a person in charge of shooting when the image of the work ticket does not accord with the first constraint condition or does not accord with the second constraint condition;
the shooting unit is also used for shooting the work ticket again to obtain the image of the work ticket when the image of the work ticket does not accord with the first constraint condition or does not accord with the second constraint condition.
Specifically, after the prompt unit sends out preset prompt information to the person responsible for shooting, the shooting unit can adaptively set waiting time, and the image of the work ticket is acquired again after the waiting time is over.
The photographing unit may also be manually controlled by a person in charge of photographing to perform photographing.
Specifically, the prompt message is used for prompting the personnel responsible for shooting, and the work ticket is folded or has the shielding condition. For example, the prompt message may be "please confirm whether the work ticket is folded or blocked".
Alternatively, the prompt message may prompt the person responsible for shooting in the form of voice or prompt the person responsible for shooting in the form of text.
Optionally, the performing the straight line detection on the image of the work ticket to obtain a detection result includes:
performing inclination correction on the image of the work ticket to obtain an inclination correction image;
and performing linear detection on the inclination correction image by using a linear detection algorithm to obtain a detection result.
In the process of photographing the work ticket, photographing may occur on a plane where the work ticket is not vertically located, and therefore, before the straight line detection is performed, it is necessary to perform tilt correction on the image of the work ticket to obtain a correct judgment result.
The straight line detection algorithm can adopt a Hough_line straight line detection algorithm, an LSD straight line detection algorithm, an FLD straight line detection algorithm and the like.
Optionally, the detection result includes a straight line segment included in the image of the work ticket.
Optionally, the determining, according to the detection result, whether the image of the work ticket meets the first constraint condition includes:
and calculating whether the number of the straight line segments is larger than a set number threshold, if so, indicating that the image of the work ticket meets the first constraint condition, and if not, indicating that the image of the work ticket does not meet the first constraint condition.
In the application, the image judgment process of the working ticket is carried out step by step, and the number of the straight line segments is mainly limited in the first constraint condition, and the working ticket contains the straight line segments such as filling lines, table lines and the like, so that the preliminary judgment can be carried out through the judgment of the number of the straight line segments. In addition, in the application, the number of straight line segments contained in the image of the ticket after the content is filled is not required to be consistent with that of the ticket without the content, and a redundant space is reserved to avoid that the first constraint condition is too severe, so that some images of the ticket which are originally satisfactory are discarded by mistake. Because the job ticket is photographed obliquely, even if the inclination correction is performed, there may still be a small number of line segments that are not correctly corrected to straight line segments.
Optionally, the determining, according to the detection result, whether the image of the work ticket meets the set second constraint condition includes:
acquiring a first linear line segment strlinxfix and a last linear line segment strlinxlst in the horizontal direction in an image of a work ticket;
acquiring a first linear line segment strlinyfir and a last linear line segment strlinyl st in the vertical direction in an image of a work ticket;
calculating a first distance dis between strlinxfir and strlinxlst;
calculating a second distance dissed between strlinyfir and strlinylst;
calculating a distance ratio disrate:
if the distance ratio disrate does not belong to the interval [ midi st, madist ], the image of the work ticket does not accord with the set second constraint condition, and if the distance ratio disrate belongs to the interval [ midi st, madist ], the image of the work ticket accords with the set second constraint condition, the midi st and the madist respectively represent the lower limit value and the upper limit value of the distance ratio disrate.
In the application, the second constraint condition is mainly that a first distance and a second distance are calculated by respectively acquiring specific two line segments in a horizontal mode and a vertical direction in a work ticket, then a distance ratio is calculated, and then whether the set constraint condition is met or not is judged according to the distance ratio. Because even if the distances to the work ticket are different, if the work ticket is not blocked, folded, etc., the distance ratio should be floated within the allowable range of error, so that it can be accurately judged whether the work ticket is blocked or folded.
The first constraint is very simple but at the same time very effective, and if there is a fold or occlusion, a significant change in the number of straight line segments occurs. The image of the work ticket is judged by setting simple judging conditions, so that the judging efficiency can be improved, the judging process of the first constraint condition is extremely simple, the quick judging process can be realized, the work ticket can be directly obtained again after the first constraint condition is not met, and if the second constraint condition is directly carried out, the overall judging efficiency can be influenced because the calculating complexity of the second constraint condition is higher than that of the judging process of the first constraint condition.
Optionally, the identifying the image of the work ticket and the face image of the worker to obtain an identification result includes:
the method comprises the steps of adopting an OCR recognition algorithm to recognize an image of a work ticket, and obtaining information contained in the image of the work ticket, wherein the information contained in the image of the work ticket comprises a responsible person name, working time and working place;
identifying the face image to obtain the image characteristics of the face image;
the information contained in the image of the work ticket and the image characteristics of the face image are used as the recognition results.
Optionally, the checking whether the staff has the passing authority based on the identification result to obtain the checking result includes:
acquiring names of people corresponding to the facial images according to the image characteristics;
judging whether the name of a responsible person in the image of the work ticket is consistent with the name of a person corresponding to the face image, if not, judging whether the working time and the working place meet the requirements or not if the auditing result is that the worker does not have the passing authority;
if the working time and the working place meet the requirements, the auditing result is that the staff has the passing authority.
Specifically, the working time recorded in the working ticket and the shooting time when the working ticket is shot can be compared to judge whether the working time meets the requirement. The normal working time includes a start time and an end time, and if the start time is after the shooting time and the time difference between the start time and the shooting time is smaller than the set time difference threshold, or if the shooting time is between the start time and the end time, the working time meets the requirement.
And the judgment of the working place is to judge whether the distance between the shooting place of the image of the working ticket and the working place recorded on the working ticket is smaller than a set distance threshold value, if so, the working place meets the requirement.
Optionally, the computing module stores data such as names, facial image features and the like of all the staff in advance. In the process of acquiring the names of the persons corresponding to the face images according to the image features, the names of the corresponding persons can be obtained by only matching the face image features stored in the image feature calculation module one by one.
Optionally, the identifying the facial image to obtain the image feature of the facial image includes:
carrying out graying treatment on the face image to obtain a treated image;
calculating the processed image by using an edge detection algorithm to obtain a set edgcol of edge pixel points in the processed image;
acquiring a boundary image according to the set edgcol;
forming a non-boundary image by pixel points which do not belong to the boundary image in the processed image;
denoising the boundary image by using a wavelet denoising algorithm to obtain a first denoising image;
denoising the non-boundary image by using a Gaussian filter algorithm to obtain a second denoising image;
combining the first noise reduction image and the second noise reduction image to obtain an image to be extracted;
and acquiring image features contained in the image to be extracted by using a feature extraction algorithm.
Specifically, noise reduction processing is required before the image features are acquired to reduce the influence of noise on the acquired image features. In the prior art, the same noise reduction method is often used directly for carrying out noise reduction on all pixel points, but the noise reduction method does not consider the balance between the noise reduction efficiency and the noise reduction effect. If a noise reduction algorithm with a short processing time is adopted, the noise reduction effect may be difficult to reach the expected value, especially the noise reduction on the edge is difficult to treat the edge as noise by mistake, so that edge details are reduced, and the accuracy of the obtained image features is affected. If a noise reduction algorithm with longer processing time is adopted, although a better noise reduction effect can be achieved, the processing time is longer, so that the auditing result of the work ticket is not beneficial to be output in time, and the efficiency of judging whether to allow workers to enter a construction site is affected.
Therefore, the boundary image and the non-boundary image are acquired, and then different noise reduction modes are adopted to carry out noise reduction treatment on the boundary image, the boundary image adopts a wavelet noise reduction algorithm which is better in edge reservation but is time-consuming, and for the non-boundary image, the boundary image adopts a Gaussian filter algorithm which is less in time consumption and is common in noise reduction effect, so that good balance is achieved in the aspects of noise reduction effect and noise reduction efficiency.
Optionally, the obtaining the boundary image according to the set edgcol includes:
storing the pixel points in the set edgcol into the set edgimgcol of the pixel points of the boundary image;
for the pixel points edgpix in the set edgcol, the edgpix is expanded by adopting an adaptive rule:
s1, using edgpix as a dynamic pixel point;
s2, calculating an expansion coefficient of the dynamic pixel point;
s3, judging the magnitude relation between the expansion coefficient and the set expansion coefficient threshold value:
if the expansion coefficient is smaller than the set expansion coefficient threshold value, ending the expansion processing of the dynamic pixel points, and storing the dynamic pixel points into a set edgimgcol; if the expansion coefficient is larger than or equal to the set expansion coefficient threshold value, acquiring a set non of pixel points which do not belong to the set edgimgcol in the neighborhood of the designated size of the dynamic pixel point;
s4, respectively calculating the expansion coefficient of each pixel point in the set nonic, taking the pixel point corresponding to the maximum expansion coefficient as a new dynamic pixel point, and entering S3.
Different from the existing mode of carrying out noise reduction processing on only detected single noise pixel points or edge pixel points, the method adopts the mode of carrying out expansion processing on the pixel points in the set edgcol to obtain a boundary image, and then carrying out noise reduction processing on the boundary image. Because the edge detection is performed before the noise reduction, if only a single noise pixel or an edge pixel obtained by calculation is processed, an incorrect noise reduction result is easy to obtain, one pixel in a larger range around the noise pixel or the edge pixel is lack as a noise reduction reference, an incorrect noise reduction result is easy to obtain, and the other noise pixel is easy to be identified as an edge pixel in the process of performing the edge detection, so that a larger range expansion is required for the range of the edge pixel, and more reference pixels are convenient to provide for noise reduction of the noise pixel.
And for the pixel points which are not obtained by the edge detection algorithm near the edge of the image, the application adopts a mode of expanding by using an expansion coefficient to further detect and obtain the pixel points, and can improve the accuracy of detection results. The noise pixel points around the edge are generally noise pixel points which are difficult to process correctly, and because the noise pixel points are relatively close to the edge, if the noise reduction effect is not good enough, the false edge can be identified, and the accuracy of the obtained image characteristics is affected.
Optionally, the calculation function of the expansion coefficient is:
in the above calculation function, exfac dyn Expansion coefficient representing pixel dyn, lambda representing scale parameter, lambda e (0, 1), nlrgnei dyn In the neighborhood of the designated size representing the pixel dyn, the number of pixels having a gray value smaller than the pixel dyn is nall dyn Representing the total number of pixel points in the neighborhood of the specified size of pixel point dyn, dynpixset representing the set of pixel points in the neighborhood of the specified size of pixel point dyn, pixgrad i The gradient value in the horizontal direction of the pixel point i in dynpixset is shown, and stdgrad is a set gradient value variance contrast value.
Specifically, the neighborhood of the specified size may be a square region centered on dyn and having a side length of K.
In the expansion process, the application utilizes the expansion coefficient to judge whether to continue expansion, and the larger the expansion coefficient is, the larger the probability of continuing expansion is, so that the probability of obtaining noise pixel points around the edge is improved. The expansion coefficient is mainly comprehensively considered from the two aspects of the size relation between the pixel point and the pixel point in the neighborhood of the designated size and the gradient value, and the larger the pixel value difference between the pixel point and the pixel point in the neighborhood of the designated size is, the larger the variance of the gradient value is, the larger the probability that the pixel point belongs to the noise pixel point is, so that the more noise pixel points are obtained by expansion.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (8)
1. The work ticket auditing system based on the image recognition technology is characterized by comprising a first camera module, a second camera module, a calculation module and a terminal module;
the first camera module is used for acquiring an image of the work ticket;
the second camera module is used for acquiring facial images of the staff;
the computing module is used for identifying the image of the work ticket and the facial image of the worker to obtain an identification result, and checking whether the worker has passing permission or not based on the identification result to obtain a checking result;
the terminal module is used for outputting the auditing result,
wherein, the image of the work ticket is obtained, including;
shooting a work ticket to obtain an image of the work ticket;
secondly, performing linear detection on the image of the work ticket to obtain a detection result;
thirdly, judging whether the image of the work ticket accords with the first constraint condition according to the detection result, if so, entering a fifth step, and if not, entering a fourth step;
fourth, sending preset prompt information to the person responsible for shooting, and entering the first step;
and fifthly, judging whether the image of the work ticket meets the set second constraint condition according to the detection result, if so, transmitting the image of the work ticket to a calculation module, and if not, entering a fourth step.
2. The work ticket auditing system based on the image recognition technology according to claim 1, wherein the first camera module comprises a shooting unit, a judging unit and a prompting unit;
the shooting unit is used for shooting the work ticket to obtain an image of the work ticket;
the judging unit is used for carrying out straight line detection on the image of the work ticket to obtain a first detection result, judging whether the image of the work ticket accords with a first constraint condition according to the detection result, and judging whether the image of the work ticket accords with a set second constraint condition according to the detection result when the image of the work ticket accords with the first constraint condition;
the prompting unit is used for sending preset prompting information to a person in charge of shooting when the image of the work ticket does not accord with the first constraint condition or does not accord with the second constraint condition;
the shooting unit is also used for shooting the work ticket again to obtain the image of the work ticket when the image of the work ticket does not accord with the first constraint condition or does not accord with the second constraint condition.
3. The ticket auditing system based on the image recognition technology according to claim 1, wherein the performing the straight line detection on the image of the ticket to obtain the detection result includes:
performing inclination correction on the image of the work ticket to obtain an inclination correction image;
and performing linear detection on the inclination correction image by using a linear detection algorithm to obtain a detection result.
4. A ticket auditing system based on image recognition technology according to claim 3, in which the detection result comprises a straight line segment contained in the image of the ticket.
5. The ticket auditing system based on image recognition technology of claim 4, wherein the determining whether the image of the ticket meets the first constraint according to the detection result comprises:
and calculating whether the number of the straight line segments is larger than a set number threshold, if so, indicating that the image of the work ticket meets the first constraint condition, and if not, indicating that the image of the work ticket does not meet the first constraint condition.
6. The ticket auditing system based on image recognition technology according to claim 5, wherein the determining whether the image of the ticket meets the set second constraint condition according to the detection result comprises:
acquiring a first linear line segment strlinxfix and a last linear line segment strlinxlst in the horizontal direction in an image of a work ticket;
acquiring a first linear line segment strlinyfir and a last linear line segment strlinyl st in the vertical direction in an image of a work ticket;
calculating a first distance dis between strlinxfir and strlinxlst;
calculating a second distance dissed between strlinyfir and strlinylst;
calculating a distance ratio disrate:
if the distance ratio disrate does not belong to the interval [ midi st, madist ], the image of the work ticket does not accord with the set second constraint condition, and if the distance ratio disrate belongs to the interval [ midi st, madist ], the image of the work ticket accords with the set second constraint condition, the midi st and the madist respectively represent the lower limit value and the upper limit value of the distance ratio disrate.
7. The ticket auditing system based on the image recognition technology according to claim 1, wherein the recognizing the image of the ticket and the face image of the staff to obtain the recognition result includes:
the method comprises the steps of adopting an OCR recognition algorithm to recognize an image of a work ticket, and obtaining information contained in the image of the work ticket, wherein the information contained in the image of the work ticket comprises a responsible person name, working time and working place;
identifying the face image to obtain the image characteristics of the face image;
the information contained in the image of the work ticket and the image characteristics of the face image are used as the recognition results.
8. The ticket auditing system based on image recognition technology of claim 7, wherein the auditing staff member based on the recognition result has a right of way, and obtaining the auditing result comprises:
acquiring names of people corresponding to the facial images according to the image characteristics;
judging whether the name of a responsible person in the image of the work ticket is consistent with the name of a person corresponding to the face image, if not, judging whether the working time and the working place meet the requirements or not if the auditing result is that the worker does not have the passing authority;
if the working time and the working place meet the requirements, the auditing result is that the staff has the passing authority.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310693708.9A CN116704529A (en) | 2023-06-12 | 2023-06-12 | Work ticket auditing system based on image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310693708.9A CN116704529A (en) | 2023-06-12 | 2023-06-12 | Work ticket auditing system based on image recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116704529A true CN116704529A (en) | 2023-09-05 |
Family
ID=87833561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310693708.9A Pending CN116704529A (en) | 2023-06-12 | 2023-06-12 | Work ticket auditing system based on image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116704529A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065435A (en) * | 2021-03-24 | 2021-07-02 | 海南电网有限责任公司澄迈供电局 | Safety tool ex-warehouse device based on video identification |
| CN113705733A (en) * | 2021-09-29 | 2021-11-26 | 平安医疗健康管理股份有限公司 | Medical bill image processing method and device, electronic device and storage medium |
| CN114399819A (en) * | 2022-01-10 | 2022-04-26 | 国网河南省电力公司检修公司 | Biological identification authentication equipment for auditing work ticket of power system |
| CN114627456A (en) * | 2020-12-10 | 2022-06-14 | 航天信息股份有限公司 | Bill text information detection method, device and system |
| CN114693946A (en) * | 2020-12-29 | 2022-07-01 | 顺丰科技有限公司 | Image anomaly detection method and device, computer equipment and storage medium |
| CN114724154A (en) * | 2022-04-18 | 2022-07-08 | 中国科学技术大学 | Table recognition method and device, storage medium and electronic equipment |
| CN115439103A (en) * | 2022-10-19 | 2022-12-06 | 国网安徽省电力有限公司马鞍山供电公司 | Work ticket verification management method based on signature standard verification |
| CN115641694A (en) * | 2022-10-19 | 2023-01-24 | 广东电网有限责任公司东莞供电局 | Front-middle-rear-end collaborative security management method based on intelligent image processing |
| CN115984870A (en) * | 2023-01-04 | 2023-04-18 | 国网山东省电力公司潍坊供电公司 | Method, system and terminal for checking work ticket |
| CN116030466A (en) * | 2023-03-23 | 2023-04-28 | 深圳思谋信息科技有限公司 | Image text information identification and processing method and device and computer equipment |
-
2023
- 2023-06-12 CN CN202310693708.9A patent/CN116704529A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114627456A (en) * | 2020-12-10 | 2022-06-14 | 航天信息股份有限公司 | Bill text information detection method, device and system |
| CN114693946A (en) * | 2020-12-29 | 2022-07-01 | 顺丰科技有限公司 | Image anomaly detection method and device, computer equipment and storage medium |
| CN113065435A (en) * | 2021-03-24 | 2021-07-02 | 海南电网有限责任公司澄迈供电局 | Safety tool ex-warehouse device based on video identification |
| CN113705733A (en) * | 2021-09-29 | 2021-11-26 | 平安医疗健康管理股份有限公司 | Medical bill image processing method and device, electronic device and storage medium |
| CN114399819A (en) * | 2022-01-10 | 2022-04-26 | 国网河南省电力公司检修公司 | Biological identification authentication equipment for auditing work ticket of power system |
| CN114724154A (en) * | 2022-04-18 | 2022-07-08 | 中国科学技术大学 | Table recognition method and device, storage medium and electronic equipment |
| CN115439103A (en) * | 2022-10-19 | 2022-12-06 | 国网安徽省电力有限公司马鞍山供电公司 | Work ticket verification management method based on signature standard verification |
| CN115641694A (en) * | 2022-10-19 | 2023-01-24 | 广东电网有限责任公司东莞供电局 | Front-middle-rear-end collaborative security management method based on intelligent image processing |
| CN115984870A (en) * | 2023-01-04 | 2023-04-18 | 国网山东省电力公司潍坊供电公司 | Method, system and terminal for checking work ticket |
| CN116030466A (en) * | 2023-03-23 | 2023-04-28 | 深圳思谋信息科技有限公司 | Image text information identification and processing method and device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100885366B1 (en) | Authentication apparatus, authentication method, authentication program, and computer readable recording media | |
| CN111191532B (en) | Face recognition method and device based on construction area and computer equipment | |
| JP5045128B2 (en) | Face recognition device | |
| CN109002786B (en) | Face detection method, face detection equipment and computer-readable storage medium | |
| EP1857963B1 (en) | Registration device, collation device, extraction method, and program | |
| CN111612104B (en) | Vehicle loss assessment image acquisition method, device, medium and electronic equipment | |
| CN113705426B (en) | Face verification method, device, server and readable storage medium | |
| CN111126257B (en) | Behavior detection method and device | |
| CN111898610B (en) | Card unfilled corner detection method, device, computer equipment and storage medium | |
| CN111523383A (en) | Non-perception face recognition system and method based on pedestrian ReID | |
| CN117853484B (en) | Intelligent bridge damage monitoring method and system based on vision | |
| CN114943841A (en) | Method and device for assisting operation safety control based on image recognition | |
| CN116704529A (en) | Work ticket auditing system based on image recognition technology | |
| JP5179329B2 (en) | Face recognition system | |
| CN111192214B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN109785343B (en) | Definition-based face matting picture optimization method and device | |
| CN111985400A (en) | Face living body identification method, device, equipment and storage medium | |
| JP5285401B2 (en) | Face recognition system | |
| JP2011113311A (en) | Image correction method | |
| CN114898475A (en) | Underground personnel identity identification method and device, electronic equipment and readable storage medium | |
| CN212846888U (en) | Metal element recognition device | |
| US20230103555A1 (en) | Information processing apparatus, information processing method, and program | |
| CN113014914A (en) | Neural network-based single face-changing short video identification method and system | |
| CN112906495A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN115527295B (en) | Automatic ticket checker control method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |