CN114419624A - Image character checking method and system based on image visual algorithm - Google Patents
Image character checking method and system based on image visual algorithm Download PDFInfo
- Publication number
- CN114419624A CN114419624A CN202210308524.1A CN202210308524A CN114419624A CN 114419624 A CN114419624 A CN 114419624A CN 202210308524 A CN202210308524 A CN 202210308524A CN 114419624 A CN114419624 A CN 114419624A
- Authority
- CN
- China
- Prior art keywords
- image
- edge
- window
- denoised
- algorithm
- 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
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides an image character checking method based on an image visual algorithm, which comprises the following steps of firstly, obtaining an image in display equipment; removing noise in the image by adopting an edge detection and adjacent region density algorithm to obtain a denoised edge image; acquiring the horizontal projection of the denoised edge image, taking a peak value for the projection, and performing vertical projection on the image in the area near the peak value to obtain a continuous area, namely a character area; recognizing characters of the character area through the optical characters; checking characters in an image of display equipment according to a train arrival schedule; and if the verification fails, acquiring the equipment model, the equipment position, the image and the verification time of the display equipment, and reporting to the ground center through a wireless network. The method provided by the invention can identify whether the picture characters in the display equipment are consistent with the corresponding sites in time, has high accuracy, improves the user experience, and realizes unmanned equipment monitoring.
Description
Technical Field
The invention belongs to the field of train equipment display, and particularly relates to an image character checking method and system based on an image visual algorithm.
Background
Along with the improvement of living standard, install on the train including passageway LED display screen, LCD dynamic map, media screen etc. and show the relevant content of corresponding website, on the one hand as the propaganda, let the passenger know local culture custom etc. on the other hand, also richened the time of taking a bus.
Due to the problems of equipment or communication, when the picture characters of the display equipment are not consistent with the corresponding sites, the picture characters cannot be found and processed in time, and the user experience is influenced.
Disclosure of Invention
The invention mainly aims to overcome the defects in the prior art, provides an image character checking method based on an image visual algorithm, can identify whether the image characters in the display equipment are consistent with the corresponding sites or not in time, has high accuracy, improves the user experience, and realizes unmanned equipment monitoring.
The technical scheme of the invention is as follows:
an image character checking method based on an image visual algorithm comprises the following steps:
acquiring an image in a display device;
removing noise in the image by adopting an edge detection and adjacent region density algorithm to obtain a denoised edge image;
acquiring the horizontal projection of the denoised edge image, taking a peak value for the projection, and performing vertical projection on the image in the area near the peak value to obtain a continuous area, namely a character area;
recognizing characters of the character area through the optical characters;
checking characters in an image of display equipment according to a train arrival schedule;
and if the verification fails, acquiring the equipment model, the equipment position, the image and the verification time of the display equipment, and reporting to the ground center through a wireless network.
Specifically, the removing noise in the image by using the edge detection and adjacent region density algorithm to obtain the denoised edge image includes:
smoothing the image by adopting a Gaussian filter function;
calculating the gradient amplitude and direction of the denoised image;
carrying out non-maximum inhibition on the gradient amplitude;
removing false edge points by adopting a method of setting a high threshold and a low threshold and connecting edges to obtain an edge image;
specifically, the removing noise in the image by using the edge detection and adjacent region density algorithm to obtain the denoised edge image further includes:
setting a denoising window in the obtained edge image, enabling the upper left corner point of the denoising window to be a window starting point, and enabling the denoising window to move in the image along the X-axis direction and the Y-axis direction in a set step length manner to obtain a window;
sequentially calculating the density of edge points contained in all windows in the whole image, wherein the density is the number of the edge points in the windows;
when the density of the edge points contained in the window is greater than a set threshold value, and the density of the edge points contained in K windows of the adjacent window of the window is the same as the set threshold value, K is a set numerical value, the window is reserved, otherwise, the window is deleted;
and traversing all windows to obtain the denoised edge image.
Specifically, the method also comprises the following steps of:
and matching and mapping the equipment model and the equipment position.
Another embodiment of the present invention provides an image text verification system based on an image visual algorithm, including:
an image acquisition unit: acquiring an image in a display device;
an edge detection and denoising unit: removing noise in the image by adopting an edge detection and adjacent region density algorithm to obtain a denoised edge image;
a character region acquisition unit: acquiring the horizontal projection of the denoised edge image, taking a peak value for the projection, and performing vertical projection on the image in the area near the peak value to obtain a continuous area, namely a character area;
a character recognition unit: recognizing characters of the character area through the optical characters;
a character checking unit: checking characters in an image of display equipment according to a train arrival schedule;
a result transmitting unit: and if the verification fails, acquiring the equipment model, the equipment position and the verification time of the display equipment, and reporting to the ground center through a wireless network.
Specifically, in the edge detection and denoising unit, an edge detection and adjacent region density algorithm is used to remove noise in the image, and a denoised edge image is obtained, including:
smoothing the image by adopting a Gaussian filter function;
calculating the gradient amplitude and direction of the denoised image;
carrying out non-maximum inhibition on the gradient amplitude;
removing false edge points by adopting a method of setting a high threshold and a low threshold and connecting edges to obtain an edge image;
specifically, in the edge detection and denoising unit, an edge detection and adjacent region density algorithm is used to remove noise in the image to obtain a denoised edge image, and the method further includes:
setting a denoising window in the obtained edge image, enabling the upper left corner point of the denoising window to be a window starting point, and enabling the denoising window to move in the image along the X-axis direction and the Y-axis direction in a set step length manner to obtain a window;
sequentially calculating the density of edge points contained in all windows in the whole image, wherein the density is the number of the edge points in the windows;
when the density of the edge points contained in the window is greater than a set threshold value, and the density of the edge points contained in K windows of the adjacent window of the window is the same as the set threshold value, K is a set numerical value, the window is reserved, otherwise, the window is deleted;
and traversing all windows to obtain the denoised edge image.
Specifically, the method further comprises a mapping unit:
and matching and mapping the equipment model and the equipment position.
Yet another embodiment of the present invention provides an electronic device, including: the image and text verification method based on the image vision algorithm comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the image and text verification method based on the image vision algorithm when executing the computer program.
The invention further provides a computer readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the image text verification method based on the image vision algorithm.
As can be seen from the above description of the present invention, compared with the prior art, the present invention has the following advantages:
(1) the invention provides an image character checking method based on an image visual algorithm, which comprises the following steps of firstly, obtaining an image in display equipment; removing noise in the image by adopting an edge detection and adjacent region density algorithm to obtain a denoised edge image; acquiring the horizontal projection of the denoised edge image, taking a peak value for the projection, and performing vertical projection on the image in the area near the peak value to obtain a continuous area, namely a character area; recognizing characters of the character area through the optical characters; checking characters in an image of display equipment according to a train arrival schedule; and if the verification fails, acquiring the equipment model, the equipment position, the image and the verification time of the display equipment, and reporting to the ground center through a wireless network. The method provided by the invention can identify whether the picture characters in the display equipment are consistent with the corresponding sites in time, has high accuracy, improves the user experience, and realizes unmanned equipment monitoring.
(2) The image character checking method based on the image visual algorithm combines the edge detection and the density algorithm of the adjacent area as a key process for removing noise in the caption detection process, thereby realizing the accurate positioning of the caption area.
(3) The image character checking method based on the image vision algorithm is simple in algorithm operation, can be realized in an embedded mode, avoids the situation that an industrial personal computer system is unstable, and is more advantageous in cost than the industrial personal computer.
Drawings
Fig. 1 is a flowchart of an image text verification method based on an image vision algorithm according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a neighborhood of a denoising window 4 according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a projection result of a denoised edge image according to an embodiment of the present invention, where fig. 3(a) is a diagram of a projection result in a horizontal direction, and fig. 3(b) is a diagram of a projection result in a vertical direction for an area near a horizontal peak;
fig. 4 is a structural diagram of an image text verification system based on an image vision algorithm according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
The invention provides an image character checking method based on an image visual algorithm, which can timely identify whether the image characters in display equipment are consistent with the corresponding sites or not, has high accuracy, improves user experience, and realizes unmanned equipment monitoring.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element. The above description is merely exemplary of the present application and is presented to enable those skilled in the art to understand and practice the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
As shown in fig. 1, an image text verification method based on an image visual algorithm provided by an embodiment of the present invention includes the following steps:
s101: acquiring an image in a display device;
the train is usually provided with a channel LED display screen, an LCD dynamic map, a media screen and the like, and relevant contents of corresponding stations are displayed, so that on one hand, the trains are used as propaganda to enable passengers to know local cultural customs and the like, and on the other hand, the riding time is also enriched; and acquiring images in the display equipment through the arranged cameras.
S102: removing noise in the image by adopting an edge detection and adjacent region density algorithm to obtain a denoised edge image;
specifically, the removing noise in the image by using the edge detection and adjacent region density algorithm to obtain the denoised edge image includes:
smoothing the image by adopting a Gaussian filter function;
calculating the gradient amplitude and direction of the denoised image;
carrying out non-maximum inhibition on the gradient amplitude;
removing false edge points by adopting a method of setting a high threshold and a low threshold and connecting edges to obtain an edge image; t is1Is a low threshold value, T2For high threshold, set T in the example2 ＝3T1。
Performing edge detection operation on the whole image to obtain an edge image, wherein a large number of background areas can be removed, and only a character image part is reserved, so that edge information of a subtitle area is obtained, and edge information of the background area is also reserved; however, there is a problem in that when the background is complicated, the amount of the edge information of the background area is excessive, thereby seriously affecting the detection of the subtitle area.
The method adopts the density algorithm of adjacent areas to remove noise, and tries to reduce the interference of a complex background on the detection of the caption area; the image after edge detection can obtain a large number of edge feature points in a small range of a subtitle area; and screening the subtitle area by taking the density of the edge points in the area as a characteristic.
Firstly, setting a denoising window of m × m, taking an upper left corner point of the denoising window as a window starting point, moving the denoising window in an image along X-axis and Y-axis directions by a step length l equal to m/2 to obtain a window position P (X)a,Yb) The following were used:
and sequentially calculating the density of the edge points contained in all the windows in the whole image, wherein the density is the number of the edge points in the windows. For clear display, the number of characters in the video is higher than 20 pixels, so that m is 20;
when the denoising window moves to the starting point PA(x, y) detecting the area A and the window in the 4 neighborhoods of the area A, namely, the starting point is PA（x，y），P1（x，y-l），P2（x，y+l），P3(x-l, y) and P4(x + l, y) density of 5 region edge points. The neighborhood schematic diagram of the denoising window 4 is shown in FIG. 2;
and calculating the density of the edge points in the area A and the 4 neighborhoods thereof. Note that the region value is S, the density is P, and let the threshold value g =2m, then:
i.e. when the areal density > g, the area is noted as 1, otherwise it is noted as 0. In consideration of the character region arrangement characteristics in the caption, the following method is proposed:
namely, when the area A is marked as 1 and 3 neighborhoods in 4 neighborhoods are also marked as 1, the area A is regarded as a character area and reserved; otherwise, the area A is considered as a non-character area and is removed.
And traversing all windows to obtain the denoised edge image.
S103: acquiring the horizontal projection of the denoised edge image, taking a peak value for the projection, and performing vertical projection on the image in the area near the peak value to obtain a continuous area, namely a character area;
the projection result of the denoised edge image is shown in fig. 3, wherein fig. 3(a) is the result of calculating the horizontal projection, and the projection result of the vertical projection of the area near the horizontal peak is shown in fig. 3 (b).
S104: recognizing characters of the character area through the optical characters;
optical character recognition is a well established technique and is not described in detail here.
S105: checking characters in an image of display equipment according to a train arrival schedule;
and determining the station position according to the arrival schedule of the train, and determining whether characters in the image of the display equipment are matched or not according to the station position.
S106: and if the verification fails, acquiring the equipment model, the equipment position, the image and the verification time of the display equipment, and reporting to the ground center through a wireless network.
The method also comprises the following steps of:
and matching and mapping the equipment model and the equipment position.
The method provided by the invention realizes unmanned monitoring of the equipment, and the ground center can know which equipment is in fault display at any time, record fault information, time and equipment information and display pictures, and is convenient to maintain and change in time. The local board card is provided with a solid state disk or an SD card as a storage device, and all fault information can be recorded in the local board card. The ground center can transfer the information recorded on the vehicle through the network, and the analysis board card on the vehicle can also send fault information to the ground in real time.
Referring to fig. 4, an image text verification system based on an image vision algorithm is provided for another embodiment of the present invention, including:
the image acquisition unit 401: acquiring an image in a display device;
the train is usually provided with a channel LED display screen, an LCD dynamic map, a media screen and the like, and relevant contents of corresponding stations are displayed, so that on one hand, the trains are used as propaganda to enable passengers to know local cultural customs and the like, and on the other hand, the riding time is also enriched; and acquiring images in the display equipment through the arranged cameras.
Edge detection and denoising unit 402: removing noise in the image by adopting an edge detection and adjacent region density algorithm to obtain a denoised edge image;
specifically, the removing noise in the image by using the edge detection and adjacent region density algorithm to obtain the denoised edge image includes:
smoothing the image by adopting a Gaussian filter function;
calculating the gradient amplitude and direction of the denoised image;
carrying out non-maximum inhibition on the gradient amplitude;
removing false edge points by adopting a method of setting a high threshold and a low threshold and connecting edges to obtain an edge image; t is1Is a low threshold value, T2For high threshold, set T in the example2 ＝3T1。
Performing edge detection operation on the whole image to obtain an edge image, wherein a large number of background areas can be removed, and only a character image part is reserved, so that edge information of a subtitle area is obtained, and edge information of the background area is also reserved; however, there is a problem in that when the background is complicated, the amount of the edge information of the background area is excessive, thereby seriously affecting the detection of the subtitle area.
The method adopts the density algorithm of adjacent areas to remove noise, and tries to reduce the interference of a complex background on the detection of the caption area; the image after edge detection can obtain a large number of edge feature points in a small range of a subtitle area; and screening the subtitle area by taking the density of the edge points in the area as a characteristic.
Firstly, setting a denoising window of m × m, taking an upper left corner point of the denoising window as a window starting point, moving the denoising window in an image along X-axis and Y-axis directions by a step length l equal to m/2 to obtain a window position P (X)a,Yb) The following were used:
and sequentially calculating the density of the edge points contained in all the windows in the whole image, wherein the density is the number of the edge points in the windows. For clear display, the number of characters in the video is higher than 20 pixels, so that m is 20;
when the denoising window moves to the starting point PA(x, y) detecting the area A and the window in the 4 neighborhoods of the area A, namely, the starting point is PA（x，y），P1（x，y-l），P2（x，y+l），P3(x-l, y) and P4(x + l, y) density of 5 region edge points. The neighborhood schematic diagram of the denoising window 4 is shown in FIG. 2;
and calculating the density of the edge points in the area A and the 4 neighborhoods thereof. Note that the region value is S, the density is P, and let the threshold value g =2m, then:
i.e. when the areal density > g, the area is noted as 1, otherwise it is noted as 0. In consideration of the character region arrangement characteristics in the caption, the following method is proposed:
namely, when the area A is marked as 1 and 3 neighborhoods in 4 neighborhoods are also marked as 1, the area A is regarded as a character area and reserved; otherwise, the area A is considered as a non-character area and is removed.
And traversing all windows to obtain the denoised edge image.
Character region acquisition section 403: acquiring the horizontal projection of the denoised edge image, taking a peak value for the projection, and performing vertical projection on the image in the area near the peak value to obtain a continuous area, namely a character area;
the projection result of the denoised edge image is shown in fig. 3, wherein fig. 3(a) is the result of calculating the horizontal projection, and the projection result of the vertical projection of the area near the horizontal peak is shown in fig. 3 (b).
Character recognition unit 404: recognizing characters of the character area through the optical characters;
optical character recognition is a well established technique and is not described in detail here.
Text verification unit 405: checking characters in an image of display equipment according to a train arrival schedule;
and determining the station position according to the arrival schedule of the train, and determining whether characters in the image of the display equipment are matched or not according to the station position.
The result transmitting unit 406: and if the verification fails, acquiring the equipment model, the equipment position and the verification time of the display equipment, and reporting to the ground center through a wireless network.
Specifically, the method further comprises a mapping unit:
and matching and mapping the equipment model and the equipment position.
As shown in fig. 5, an electronic device 500 according to an embodiment of the present invention includes a memory 510, a processor 520, and a computer program 511 stored in the memory 520 and executable on the processor 520, where the processor 520 executes the computer program 511 to implement an image text verification method based on an image vision algorithm according to an embodiment of the present invention.
In a specific implementation, when the processor 520 executes the computer program 511, any of the embodiments corresponding to fig. 1 may be implemented.
Since the electronic device described in this embodiment is a device used for implementing a data processing apparatus in the embodiment of the present invention, based on the method described in this embodiment of the present invention, a person skilled in the art can understand the specific implementation manner of the electronic device in this embodiment and various variations thereof, so that how to implement the method in this embodiment of the present invention by the electronic device is not described in detail herein, and as long as the person skilled in the art implements the device used for implementing the method in this embodiment of the present invention, the device used for implementing the method in this embodiment of the present invention belongs to the protection scope of the present invention.
Referring to fig. 6, fig. 6 is a schematic diagram illustrating an embodiment of a computer-readable storage medium according to the present invention.
As shown in fig. 6, the present embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored, and when executed by a processor, the computer program 611 implements an image text verification method based on an image vision algorithm according to the present embodiment;
in a specific implementation, the computer program 611 may implement any of the embodiments corresponding to fig. 1 when executed by a processor.
It should be noted that, in the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to relevant descriptions of other embodiments for parts that are not described in detail in a certain embodiment.
As will be appreciated by one skilled in the art, 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 invention provides an image character checking method based on an image visual algorithm, which comprises the following steps of firstly, obtaining an image in display equipment; removing noise in the image by adopting an edge detection and adjacent region density algorithm to obtain a denoised edge image; acquiring the horizontal projection of the denoised edge image, taking a peak value for the projection, and performing vertical projection on the image in the area near the peak value to obtain a continuous area, namely a character area; recognizing characters of the character area through the optical characters; checking characters in an image of display equipment according to a train arrival schedule; and if the verification fails, acquiring the equipment model, the equipment position, the image and the verification time of the display equipment, and reporting to the ground center through a wireless network. The method provided by the invention can identify whether the picture characters in the display equipment are consistent with the corresponding sites in time, has high accuracy, improves the user experience, and realizes unmanned equipment monitoring.
The image character checking method based on the image visual algorithm combines the edge detection and the density algorithm of the adjacent area as a key process for removing noise in the caption detection process, thereby realizing the accurate positioning of the caption area.
The image character checking method based on the image vision algorithm is simple in algorithm operation, can be realized in an embedded mode, avoids the situation that an industrial personal computer system is unstable, and is more advantageous in cost than the industrial personal computer.
The above description is only an embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept should fall within the scope of the invention.
Claims (10)
1. An image character checking method based on an image visual algorithm is characterized by comprising the following steps:
acquiring an image in a display device;
removing noise in the image by adopting an edge detection and adjacent region density algorithm to obtain a denoised edge image;
acquiring the horizontal projection of the denoised edge image, taking a peak value for the projection, and performing vertical projection on the image in the area near the peak value to obtain a continuous area, namely a character area;
recognizing characters of the character area through the optical characters;
checking characters in an image of display equipment according to a train arrival schedule;
and if the verification fails, acquiring the equipment model, the equipment position, the image and the verification time of the display equipment, and reporting to the ground center through a wireless network.
2. The image text verification method based on the image visual algorithm as claimed in claim 1, wherein the removing noise in the image by using the edge detection and adjacent region density algorithm to obtain the denoised edge image comprises:
smoothing the image by adopting a Gaussian filter function;
calculating the gradient amplitude and direction of the denoised image;
carrying out non-maximum inhibition on the gradient amplitude;
and removing false edge points and connecting edges by adopting a method of setting high and low thresholds to obtain an edge image.
3. The image text verification method based on the image visual algorithm as claimed in claim 2, wherein the removing noise in the image by using the edge detection and neighboring area density algorithm to obtain the denoised edge image further comprises:
setting a denoising window in the obtained edge image, enabling the upper left corner point of the denoising window to be a window starting point, and enabling the denoising window to move in the image along the X-axis direction and the Y-axis direction in a set step length manner to obtain a window;
sequentially calculating the density of edge points contained in all windows in the whole image, wherein the density is the number of the edge points in the windows;
when the density of the edge points contained in the window is greater than a set threshold value, and the density of the edge points contained in K windows of the adjacent window of the window is the same as the set threshold value, K is a set numerical value, the window is reserved, otherwise, the window is deleted;
and traversing all windows to obtain the denoised edge image.
4. The image text verification method based on the image vision algorithm as claimed in claim 1, characterized in that the steps are preceded by:
and matching and mapping the equipment model and the equipment position.
5. An image text verification system based on an image vision algorithm, comprising:
an image acquisition unit: acquiring an image in a display device;
an edge detection and denoising unit: removing noise in the image by adopting an edge detection and adjacent region density algorithm to obtain a denoised edge image;
a character region acquisition unit: acquiring the horizontal projection of the denoised edge image, taking a peak value for the projection, and performing vertical projection on the image in the area near the peak value to obtain a continuous area, namely a character area;
a character recognition unit: recognizing characters of the character area through the optical characters;
a character checking unit: checking characters in an image of display equipment according to a train arrival schedule;
a result transmitting unit: and if the verification fails, acquiring the equipment model, the equipment position and the verification time of the display equipment, and reporting to the ground center through a wireless network.
6. The image text verification system based on image visual algorithm of claim 5, wherein in the edge detection and denoising unit, an edge detection and adjacent region density algorithm is adopted to remove noise in the image, and a denoised edge image is obtained, including:
smoothing the image by adopting a Gaussian filter function;
calculating the gradient amplitude and direction of the denoised image;
carrying out non-maximum inhibition on the gradient amplitude;
and removing false edge points and connecting edges by adopting a method of setting high and low thresholds to obtain an edge image.
7. The image text verification system based on image visual algorithm of claim 6, wherein in the edge detection and denoising unit, an edge detection and adjacent region density algorithm is adopted to remove noise in the image to obtain a denoised edge image, further comprising:
setting a denoising window in the obtained edge image, enabling the upper left corner point of the denoising window to be a window starting point, and enabling the denoising window to move in the image along the X-axis direction and the Y-axis direction in a set step length manner to obtain a window;
sequentially calculating the density of edge points contained in all windows in the whole image, wherein the density is the number of the edge points in the windows;
when the density of the edge points contained in the window is greater than a set threshold value, and the density of the edge points contained in K windows of the adjacent window of the window is the same as the set threshold value, K is a set numerical value, the window is reserved, otherwise, the window is deleted;
and traversing all windows to obtain the denoised edge image.
8. The image text verification system based on image vision algorithm as claimed in claim 5, further comprising a mapping unit:
and matching and mapping the equipment model and the equipment position.
9. An electronic device, comprising: memory, processor and computer program stored on the memory and executable on the processor, wherein the processor implements the method steps of any of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210308524.1A CN114419624A (en) | 2022-03-28 | 2022-03-28 | Image character checking method and system based on image visual algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210308524.1A CN114419624A (en) | 2022-03-28 | 2022-03-28 | Image character checking method and system based on image visual algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114419624A true CN114419624A (en) | 2022-04-29 |
Family
ID=81263927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210308524.1A Pending CN114419624A (en) | 2022-03-28 | 2022-03-28 | Image character checking method and system based on image visual algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114419624A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102226907A (en) * | 2011-05-24 | 2011-10-26 | 武汉嘉业恒科技有限公司 | License plate positioning method and apparatus based on multiple characteristics |
| CN109409378A (en) * | 2018-10-17 | 2019-03-01 | 北京信息科技大学 | A kind of digitalized processing method of Nahsi Dongba Confucian classics |
| CN110633705A (en) * | 2019-08-22 | 2019-12-31 | 长沙千视通智能科技有限公司 | Low-illumination imaging license plate recognition method and device |
| CN110689003A (en) * | 2019-08-22 | 2020-01-14 | 长沙千视通智能科技有限公司 | Low-illumination imaging license plate recognition method and system, computer equipment and storage medium |
| CN111506378A (en) * | 2020-04-17 | 2020-08-07 | 腾讯科技（深圳）有限公司 | Method, device and equipment for previewing text display effect and storage medium |
| CN112232339A (en) * | 2020-10-15 | 2021-01-15 | 中国民航大学 | Flight display equipment fault detection method and monitoring device based on convolutional neural network |
| CN112383743A (en) * | 2020-10-12 | 2021-02-19 | 佛山市新东方电子技术工程有限公司 | Method, storage medium and system for adjusting character labels of monitoring pictures |
| CN114170612A (en) * | 2021-12-15 | 2022-03-11 | 江门市浩远科技有限公司 | Recovery production method based on defect judgment of LED unit board |
-
2022
- 2022-03-28 CN CN202210308524.1A patent/CN114419624A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102226907A (en) * | 2011-05-24 | 2011-10-26 | 武汉嘉业恒科技有限公司 | License plate positioning method and apparatus based on multiple characteristics |
| CN109409378A (en) * | 2018-10-17 | 2019-03-01 | 北京信息科技大学 | A kind of digitalized processing method of Nahsi Dongba Confucian classics |
| CN110633705A (en) * | 2019-08-22 | 2019-12-31 | 长沙千视通智能科技有限公司 | Low-illumination imaging license plate recognition method and device |
| CN110689003A (en) * | 2019-08-22 | 2020-01-14 | 长沙千视通智能科技有限公司 | Low-illumination imaging license plate recognition method and system, computer equipment and storage medium |
| CN111506378A (en) * | 2020-04-17 | 2020-08-07 | 腾讯科技（深圳）有限公司 | Method, device and equipment for previewing text display effect and storage medium |
| CN112383743A (en) * | 2020-10-12 | 2021-02-19 | 佛山市新东方电子技术工程有限公司 | Method, storage medium and system for adjusting character labels of monitoring pictures |
| CN112232339A (en) * | 2020-10-15 | 2021-01-15 | 中国民航大学 | Flight display equipment fault detection method and monitoring device based on convolutional neural network |
| CN114170612A (en) * | 2021-12-15 | 2022-03-11 | 江门市浩远科技有限公司 | Recovery production method based on defect judgment of LED unit board |
Non-Patent Citations (2)
| Title |
|---|
| 董小舒 等: "高效视频字幕检测方法", 《指挥信息***与技术》 * |
| 董小舒 等: "高效视频字幕检测方法", 《指挥信息***与技术》, 30 June 2017 (2017-06-30), pages 1 - 2 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10896349B2 (en) | Text detection method and apparatus, and storage medium | |
| US7302098B2 (en) | Character segmentation method and apparatus | |
| CN111382704B (en) | Vehicle line pressing violation judging method and device based on deep learning and storage medium | |
| US9311533B2 (en) | Device and method for detecting the presence of a logo in a picture | |
| TW201218129A (en) | A vehicle registration-plate detecting method and system thereof | |
| CN105405142A (en) | Edge defect detection method and system for glass panel | |
| CN109583299B (en) | Electronic device, certificate identification method, and storage medium | |
| CN103034856B (en) | The method of character area and device in positioning image | |
| CN109740424A (en) | Traffic violations recognition methods and Related product | |
| KR101621370B1 (en) | Method and Apparatus for detecting lane of road | |
| CN110929635B (en) | False face video detection method and system based on face cross-over ratio under trust mechanism | |
| CN108830133A (en) | Recognition methods, electronic device and the readable storage medium storing program for executing of contract image picture | |
| CN111325769A (en) | Target object detection method and device | |
| WO2015066984A1 (en) | Complex background-oriented optical character recognition method and device | |
| CN112418214A (en) | Vehicle identification code identification method and device, electronic equipment and storage medium | |
| US8442348B2 (en) | Image noise reduction for digital images using Gaussian blurring | |
| CN115240197A (en) | Image quality evaluation method, image quality evaluation device, electronic apparatus, scanning pen, and storage medium | |
| CN110807457A (en) | OSD character recognition method, device and storage device | |
| CN111340045A (en) | License plate number recognition method and device and storage medium | |
| CN108268866B (en) | Vehicle detection method and system | |
| CN112396060A (en) | Identity card identification method based on identity card segmentation model and related equipment thereof | |
| CN114419624A (en) | Image character checking method and system based on image visual algorithm | |
| CN108985197B (en) | Automatic detection method for taxi driver smoking behavior based on multi-algorithm fusion | |
| CN113762027B (en) | Abnormal behavior identification method, device, equipment and storage medium | |
| CN115223173A (en) | Object identification method and device, electronic equipment and storage medium |
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 |
Application publication date: 20220429 |
|
| RJ01 | Rejection of invention patent application after publication |