CN111898605A - Set top box information detection method and system based on image OCR recognition - Google Patents
Set top box information detection method and system based on image OCR recognition Download PDFInfo
- Publication number
- CN111898605A CN111898605A CN202010885393.4A CN202010885393A CN111898605A CN 111898605 A CN111898605 A CN 111898605A CN 202010885393 A CN202010885393 A CN 202010885393A CN 111898605 A CN111898605 A CN 111898605A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- top box
- information
- gray
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 81
- 238000005260 corrosion Methods 0.000 claims abstract description 14
- 230000007797 corrosion Effects 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 13
- 238000004380 ashing Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Character Input (AREA)
- Character Discrimination (AREA)
Abstract
The invention relates to the technical field of image recognition, aims to solve the problem that the prior art can not quickly and accurately find that information in a set top box is wrong, provides a set top box information detection method and system based on image OCR recognition, and adopts the technical scheme as follows: acquiring an image of a set top box, wherein the image comprises to-be-detected information of the set top box; determining the position coordinates of a to-be-detected area corresponding to the to-be-detected information, and cutting the obtained image according to the position coordinates to obtain an image to be detected; and carrying out image processing on the image to be detected to separate a character image and a background image in the image to be detected, wherein the image processing at least comprises the following steps: gray level processing, binarization processing and expansion corrosion processing; and judging whether the information of the set top box is wrong or not according to the character information in the image to be detected after OCR recognition processing. The invention realizes the quick and accurate detection of the information of the set-top box and is suitable for the set-top box.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a set top box information detection method and system based on image OCR recognition.
Background
With the improvement of living standard, the set-top box becomes a necessary device for each family, so the quality of the set-top box is very important. However, if the information written by the set-top box is wrong, the set-top box cannot operate normally, and the watching experience of the user is greatly influenced.
In the prior art, information detection of video boxes such as a set top box and the like still stays in traditional manual test judgment, namely, the information on a video image is compared in a manual mode to check correctness and falseness, but the manual detection mode has many individual subjective viewpoints, and the problem that the information in the set top box is wrong cannot be found quickly and accurately.
Disclosure of Invention
The invention aims to solve the problem that the prior art cannot quickly and accurately find that information in a set top box is wrong, and provides a set top box information detection method and system based on image OCR recognition.
The technical scheme adopted by the invention for solving the technical problems is as follows: the set top box information detection method based on image OCR recognition comprises the following steps:
step 1, acquiring an image of a set top box, wherein the image comprises to-be-detected information of the set top box;
step 2, determining the position coordinates of the to-be-detected region corresponding to the to-be-detected information, and cutting the acquired image according to the position coordinates to obtain an image to be detected;
step 3, carrying out image processing on the image to be detected to separate a character image and a background image in the image to be detected, wherein the image processing at least comprises the following steps: gray level processing, binarization processing and expansion corrosion processing;
and 4, judging whether the information of the set top box is wrong or not according to the character information in the image to be detected after OCR recognition processing.
Further, in step 3, the gray processing includes:
performing ashing treatment on an image to be detected to obtain a gray image only containing one gray value, wherein the ashing formula is as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)；
where f (x, y) represents a gray scale value of a pixel in a gray scale image, R represents a red component value, G represents a green component value, and B represents a blue component value.
Further, in step 3, the binarization processing includes:
determining a gray threshold value, and performing binarization processing on a gray image according to the gray threshold value to obtain a binary image, wherein the method for determining the gray threshold value comprises the following steps:
setting an initial gray threshold, calculating a Kirsh operator of each pixel of the gray image, and dynamically adjusting the initial gray threshold according to the initial gray threshold and the size of the Kirsh operator to obtain the gray threshold.
Further, in step 3, the expansion corrosion treatment includes:
traversing each pixel of the binary image, aligning the currently traversed pixel with the central point of the structural element, obtaining the maximum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the maximum value;
traversing each pixel of the binary image, aligning the center point of the structural element with the pixel currently being traversed, acquiring the minimum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the minimum value.
Further, in step 4, the character information in the image to be detected after the OCR recognition processing specifically includes:
and inputting the processed image to be detected into a Tesseract-OCR engine, and performing character recognition on the image to be detected by the Tesseract-OCR engine to obtain character information of the image to be detected.
Further, in step 4, the step of judging whether the information of the set top box is incorrect according to the text information specifically includes:
and comparing whether the text information is consistent with the preset text information, if so, indicating that the information of the set top box is correct, otherwise, indicating that the information of the set top box is wrong.
The invention also provides a set top box information detection system based on image OCR recognition, which comprises: the device comprises an acquisition unit, a cutting unit, an image processing unit and a Tesseract-OCR engine;
the acquisition unit is used for acquiring an image of the set top box, wherein the image comprises to-be-detected information of the set top box;
the cutting unit is used for determining the position coordinates of the to-be-detected region corresponding to the to-be-detected information and cutting the acquired image according to the position coordinates to obtain the to-be-detected image;
the image processing unit is used for carrying out image processing on the image to be detected so as to separate a character image and a background image in the image to be detected, and the image processing at least comprises the following steps: gray level processing, binarization processing and expansion corrosion processing;
the Tesseract-OCR engine is used for identifying character information in the processed image to be detected and judging whether the information of the set top box is wrong or not according to the character information.
Further, the gradation processing includes:
performing ashing treatment on an image to be detected to obtain a gray image only containing one gray value, wherein the ashing formula is as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)；
where f (x, y) represents a gray scale value of a pixel in a gray scale image, R represents a red component value, G represents a green component value, and B represents a blue component value.
Further, the binarization processing includes:
determining a gray threshold value, and performing binarization processing on a gray image according to the gray threshold value to obtain a binary image, wherein the method for determining the gray threshold value comprises the following steps:
setting an initial gray threshold, calculating a Kirsh operator of each pixel of the gray image, and dynamically adjusting the initial gray threshold according to the initial gray threshold and the size of the Kirsh operator to obtain the gray threshold.
Further, the swelling corrosion treatment includes:
traversing each pixel of the binary image, aligning the currently traversed pixel with the central point of the structural element, obtaining the maximum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the maximum value;
traversing each pixel of the binary image, aligning the center point of the structural element with the pixel currently being traversed, acquiring the minimum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the minimum value.
The invention has the beneficial effects that: according to the set top box information detection method and system based on image OCR recognition, the acquired image is cut to form the image to be detected with a smaller area, the calculated amount of image recognition is reduced, gray processing, binarization processing and expansion corrosion processing are sequentially performed on the image to be detected, and the accuracy of character recognition in the image is improved.
Drawings
FIG. 1 is a schematic flow chart of a set top box information detection method based on image OCR recognition according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a set top box information detection system based on image OCR recognition according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The invention aims to solve the problem that the prior art can not quickly and accurately find that the information in the set top box is wrong, and provides a set top box information detection method and system based on image OCR recognition, wherein the technical concept is as follows: acquiring an image of a set top box, wherein the image comprises to-be-detected information of the set top box; determining the position coordinates of a to-be-detected area corresponding to the to-be-detected information, and cutting the obtained image according to the position coordinates to obtain an image to be detected; and carrying out image processing on the image to be detected to separate a character image and a background image in the image to be detected, wherein the image processing at least comprises the following steps: gray level processing, binarization processing and expansion corrosion processing; and judging whether the information of the set top box is wrong or not according to the character information in the image to be detected after OCR recognition processing.
Firstly, an image containing set top box information is obtained from a set top box, then, a cutting area is determined according to the position coordinates of a to-be-detected area corresponding to the to-be-detected information in the image, a smaller to-be-detected image is obtained, then, the obtained smaller to-be-detected image is sequentially subjected to corresponding processing, so that a character image and a background image in the to-be-detected image are separated, and then the accuracy of character recognition is improved, wherein the image processing comprises the following steps: gray level processing, binarization processing and expansion corrosion processing; specifically, the gray level processing is carried out on an image to be detected to obtain a gray level image, the binarization processing is carried out on the gray level image to obtain a binary image, the expansion and corrosion processing is carried out on the binary image to obtain a processed image to be detected, finally, character information in the processed image to be detected is recognized based on OCR, and the detection of the information of the set top box is realized based on the recognized character information.
Examples
The set top box information detection method based on image OCR recognition, as shown in FIG. 1, includes the following steps:
s1, acquiring an image of the set top box, wherein the image comprises information to be detected of the set top box;
specifically, the image of the set-top box can be obtained through the HDMI device, and the information to be detected of the set-top box can be a set-top box production serial number, a set-top box encryption serial number, a locking mode serial number, a set-top box encryption card serial number, and the like.
Step S2, determining the position coordinates of the to-be-detected region corresponding to the to-be-detected information, and cutting the acquired image according to the position coordinates to obtain an image to be detected;
specifically, the position coordinates of the cutting area can be determined according to the position of the information to be detected in the image, and then the acquired image is cut according to the position coordinates of the cutting area to obtain the image to be detected, wherein the image to be detected contains the information to be detected of the set top box.
Step S3, image processing is carried out on the image to be detected, so that the character image and the background image in the image to be detected are separated, and the image processing at least comprises the following steps: gray level processing, binarization processing and expansion corrosion processing;
it is understood that the gradation processing, the binarization processing, and the dilation etching processing are sequentially performed, wherein the gradation processing includes:
performing ashing treatment on an image to be detected to obtain a gray image only containing one gray value, wherein the ashing formula is as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)；
where f (x, y) represents a gray scale value of a pixel in a gray scale image, R represents a red component value, G represents a green component value, and B represents a blue component value.
The binarization processing includes: determining a gray threshold, and carrying out binarization processing on the gray image according to the gray threshold to obtain a binary image, wherein the binary image is an image represented by only black and white colors, and 0 is used for representing black (0) and 1 is used for representing white (255) in terms of numbers. Pixels in an image belonging to the same object have great similarity in gray value, and on the contrary, different objects usually show great difference in gray value. Therefore, in the embodiment, through the automatic thresholding technology, the segmentation gray value capable of sufficiently reflecting the difference between the foreground and the background is selected, so that the characters to be recognized are roughly separated.
The method for determining the gray level threshold value according to the automatic thresholding technology comprises the following steps: setting an initial gray threshold, calculating a Kirsh operator of each pixel of the gray image, and dynamically adjusting the initial gray threshold according to the initial gray threshold and the size of the Kirsh operator to obtain the gray threshold.
The expansion treatment comprises the following steps: traversing each pixel of the binary image, aligning the currently traversed pixel with the central point of the structural element, obtaining the maximum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the maximum value; since the maximum value of the binary image is 1, the binary image is replaced by 1, namely, the binary image becomes a white foreground object. If all the current structural elements are the background under the coverage, the original image is not changed because all the structural elements are 0; if all foreground pixels are, the original image is not changed, because all foreground pixels are 1; only when a structuring element is located at the edge of a foreground object will two different pixel values, 0 and 1, appear in the area it covers, at which time the change of the current pixel to 1 changes. The overall brightness of the expanded image will increase, the size of the lighter objects in the image will increase, and the size of the darker objects will decrease or even disappear.
The corrosion treatment comprises the following steps: traversing each pixel of the binary image, aligning the center point of the structural element with the pixel currently being traversed, acquiring the minimum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the minimum value; since the binary image minimum value is 0, it is replaced by 0, i.e. becomes a black background. If all the current structural elements are the background under the coverage, the original image is not changed because all the structural elements are 0; if all foreground pixels are, the original image is not changed, because all the foreground pixels are 1, only when the structural element is located at the edge of the foreground object, two different pixel values of 0 and 1 can appear in the area covered by the structural element, and at this time, the current pixel is changed into 0. The corroded image becomes dark in whole, the area of a brighter area in the image becomes smaller or even disappears, and the area of a darker area in the image is increased.
The embodiment has the effects of filling a fine black area in a white object and connecting adjacent objects by performing expansion-first and corrosion-later treatment on the binary image, and can also smooth the boundary without obviously changing the area of the binary image, so that the information to be recognized in the binary image is more obvious, and the accuracy of character recognition is further improved.
And step S4, judging whether the information of the set top box is wrong or not according to the character information based on the character information in the image to be detected after OCR recognition processing.
After the image to be detected is processed, an image which is easier to recognize characters can be obtained.
The static character classifier used by the Tesseract-OCR engine comprises a special design idea, namely the separation of classifier training and a classification recognition process. Most classifiers have the same processing mode for training samples and recognition characters, so that the recognition success rate can be ensured only when the characters to be recognized are close to the training samples. The Tesseract-OCR engine uses a breakthrough solution, and when a sample set is trained, the system selects an approximate polygon segment of a character as a characteristic; in the recognition process, the system selects short line segments with fixed length belonging to character boundaries as characteristics, and a many-to-one mode is used to correspond to the standard characteristics of the system.
The specific steps of character recognition are as follows:
the method comprises the steps of sorting categories which are possibly matched with features to be detected, obtaining a group of vectors which are possibly matched with the categories of each feature to be identified of unknown characters through table lookup, adding the matched vectors by a system, and selecting several categories with the highest scores as a list of the most possible unknown character matching;
the final class is determined by calculating the similarity, each standard character is represented by a logical box, and the 'distance' between the feature to be recognized and the standard character can be calculated. And finally, the category with the shortest distance obtained by integration is the category with the highest similarity to the unknown character.
The classification design of the Tesseract-OCR engine can identify damaged characters and has strong robustness, so that the damaged characters do not need to be introduced when a training sample of the classifier is selected, and the identification speed and accuracy are high.
And after the character information is identified, comparing whether the character information is consistent with the preset character information or not, if so, indicating that the information of the set top box is correct, otherwise, indicating that the information of the set top box is wrong.
Based on the above technical solution, an embodiment of the present invention further provides a set top box information detection system based on image OCR recognition, as shown in fig. 2, including: the device comprises an acquisition unit, a cutting unit, an image processing unit and a Tesseract-OCR engine;
the acquisition unit is used for acquiring an image of the set top box, wherein the image comprises to-be-detected information of the set top box;
the cutting unit is used for determining the position coordinates of the to-be-detected region corresponding to the to-be-detected information and cutting the acquired image according to the position coordinates to obtain the to-be-detected image;
the image processing unit is used for carrying out image processing on the image to be detected so as to separate a character image and a background image in the image to be detected, and the image processing at least comprises the following steps: gray level processing, binarization processing and expansion corrosion processing;
the Tesseract-OCR engine is used for identifying character information in the processed image to be detected and judging whether the information of the set top box is wrong or not according to the character information.
It can be understood that, because the set top box information detection system based on image OCR recognition according to the embodiment of the present invention is a system for implementing the set top box information detection method based on image OCR recognition according to the embodiment, for the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is simpler, and for the relevant points, refer to the partial description of the method.
Claims (10)
1. The set top box information detection method based on image OCR recognition is characterized by comprising the following steps of:
step 1, acquiring an image of a set top box, wherein the image comprises to-be-detected information of the set top box;
step 2, determining the position coordinates of the to-be-detected region corresponding to the to-be-detected information, and cutting the acquired image according to the position coordinates to obtain an image to be detected;
step 3, carrying out image processing on the image to be detected to separate a character image and a background image in the image to be detected, wherein the image processing at least comprises the following steps: gray level processing, binarization processing and expansion corrosion processing;
and 4, judging whether the information of the set top box is wrong or not according to the character information in the image to be detected after OCR recognition processing.
2. The set-top box information detection method based on image OCR recognition as recited in claim 1, wherein in step 3, the grayscale processing includes:
performing ashing treatment on an image to be detected to obtain a gray image only containing one gray value, wherein the ashing formula is as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)；
where f (x, y) represents a gray scale value of a pixel in a gray scale image, R represents a red component value, G represents a green component value, and B represents a blue component value.
3. A set top box information detection method based on image OCR recognition as recited in claim 2, wherein in step 3, the binarization processing includes:
determining a gray threshold value, and performing binarization processing on a gray image according to the gray threshold value to obtain a binary image, wherein the method for determining the gray threshold value comprises the following steps:
setting an initial gray threshold, calculating a Kirsh operator of each pixel of the gray image, and dynamically adjusting the initial gray threshold according to the initial gray threshold and the size of the Kirsh operator to obtain the gray threshold.
4. The set-top box information detection method based on image OCR recognition as claimed in claim 3, wherein in step 3, the dilation-erosion process comprises:
traversing each pixel of the binary image, aligning the currently traversed pixel with the central point of the structural element, obtaining the maximum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the maximum value;
traversing each pixel of the binary image, aligning the center point of the structural element with the pixel currently being traversed, acquiring the minimum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the minimum value.
5. The set-top box information detection method based on image OCR recognition as recited in claim 1, wherein in step 4, the text information in the image to be detected after being processed based on OCR recognition specifically includes:
and inputting the processed image to be detected into a Tesseract-OCR engine, and performing character recognition on the image to be detected by the Tesseract-OCR engine to obtain character information of the image to be detected.
6. The set-top box information detection method based on image OCR recognition as recited in claim 1, wherein in step 4, said determining whether the information of the set-top box is incorrect according to the text information specifically includes:
and comparing whether the text information is consistent with the preset text information, if so, indicating that the information of the set top box is correct, otherwise, indicating that the information of the set top box is wrong.
7. Set top box information detection system based on image OCR discernment, its characterized in that includes: the device comprises an acquisition unit, a cutting unit, an image processing unit and a Tesseract-OCR engine;
the acquisition unit is used for acquiring an image of the set top box, wherein the image comprises to-be-detected information of the set top box;
the cutting unit is used for determining the position coordinates of the to-be-detected region corresponding to the to-be-detected information and cutting the acquired image according to the position coordinates to obtain the to-be-detected image;
the image processing unit is used for carrying out image processing on the image to be detected so as to separate a character image and a background image in the image to be detected, and the image processing at least comprises the following steps: gray level processing, binarization processing and expansion corrosion processing;
the Tesseract-OCR engine is used for identifying character information in the processed image to be detected and judging whether the information of the set top box is wrong or not according to the character information.
8. The set-top box information detection system based on image OCR recognition as recited in claim 7, wherein the grayscale processing includes:
performing ashing treatment on an image to be detected to obtain a gray image only containing one gray value, wherein the ashing formula is as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)；
where f (x, y) represents a gray scale value of a pixel in a gray scale image, R represents a red component value, G represents a green component value, and B represents a blue component value.
9. The set-top box information detection system based on image OCR recognition according to claim 8, wherein said binarization process includes:
determining a gray threshold value, and performing binarization processing on a gray image according to the gray threshold value to obtain a binary image, wherein the method for determining the gray threshold value comprises the following steps:
setting an initial gray threshold, calculating a Kirsh operator of each pixel of the gray image, and dynamically adjusting the initial gray threshold according to the initial gray threshold and the size of the Kirsh operator to obtain the gray threshold.
10. The set-top box information detection system based on image OCR recognition as recited in claim 9, wherein the dilation-erosion process comprises:
traversing each pixel of the binary image, aligning the currently traversed pixel with the central point of the structural element, obtaining the maximum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the maximum value;
traversing each pixel of the binary image, aligning the center point of the structural element with the pixel currently being traversed, acquiring the minimum value of all pixels in the corresponding area of the binary image covered by the current structural element, and replacing the current pixel value with the minimum value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010885393.4A CN111898605A (en) | 2020-08-28 | 2020-08-28 | Set top box information detection method and system based on image OCR recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010885393.4A CN111898605A (en) | 2020-08-28 | 2020-08-28 | Set top box information detection method and system based on image OCR recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111898605A true CN111898605A (en) | 2020-11-06 |
Family
ID=73224677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010885393.4A Pending CN111898605A (en) | 2020-08-28 | 2020-08-28 | Set top box information detection method and system based on image OCR recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111898605A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113905269A (en) * | 2021-10-08 | 2022-01-07 | 南京启数智能***有限公司 | Method and device for realizing video monitoring OSD subtitle and clock detection by using OCR technology |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971524A (en) * | 2014-05-21 | 2014-08-06 | 电子科技大学 | Traffic flow detection method based on machine vision |
| CN104616019A (en) * | 2015-03-04 | 2015-05-13 | 国网山东省电力公司泰安供电公司 | Identification method for electronic equipment signboard image |
| CN104866849A (en) * | 2015-04-30 | 2015-08-26 | 天津大学 | Food nutrition label identification method based on mobile terminal |
| CN104992152A (en) * | 2015-06-30 | 2015-10-21 | 深圳訾岽科技有限公司 | Character recognition method and system based on template character library |
| CN105046254A (en) * | 2015-07-17 | 2015-11-11 | 腾讯科技（深圳）有限公司 | Character recognition method and apparatus |
| CN107169491A (en) * | 2017-05-19 | 2017-09-15 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of ring gear die number detection method |
| CN109492643A (en) * | 2018-10-11 | 2019-03-19 | 平安科技（深圳）有限公司 | Certificate recognition methods, device, computer equipment and storage medium based on OCR |
| CN110097046A (en) * | 2019-03-11 | 2019-08-06 | 上海肇观电子科技有限公司 | A kind of character detecting method and device, equipment and computer readable storage medium |
| CN110766017A (en) * | 2019-10-22 | 2020-02-07 | 国网新疆电力有限公司信息通信公司 | Mobile terminal character recognition method and system based on deep learning |
| CN111461100A (en) * | 2020-03-31 | 2020-07-28 | 重庆农村商业银行股份有限公司 | Bill identification method and device, electronic equipment and storage medium |
-
2020
- 2020-08-28 CN CN202010885393.4A patent/CN111898605A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971524A (en) * | 2014-05-21 | 2014-08-06 | 电子科技大学 | Traffic flow detection method based on machine vision |
| CN104616019A (en) * | 2015-03-04 | 2015-05-13 | 国网山东省电力公司泰安供电公司 | Identification method for electronic equipment signboard image |
| CN104866849A (en) * | 2015-04-30 | 2015-08-26 | 天津大学 | Food nutrition label identification method based on mobile terminal |
| CN104992152A (en) * | 2015-06-30 | 2015-10-21 | 深圳訾岽科技有限公司 | Character recognition method and system based on template character library |
| CN105046254A (en) * | 2015-07-17 | 2015-11-11 | 腾讯科技（深圳）有限公司 | Character recognition method and apparatus |
| CN107169491A (en) * | 2017-05-19 | 2017-09-15 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of ring gear die number detection method |
| CN109492643A (en) * | 2018-10-11 | 2019-03-19 | 平安科技（深圳）有限公司 | Certificate recognition methods, device, computer equipment and storage medium based on OCR |
| CN110097046A (en) * | 2019-03-11 | 2019-08-06 | 上海肇观电子科技有限公司 | A kind of character detecting method and device, equipment and computer readable storage medium |
| CN110766017A (en) * | 2019-10-22 | 2020-02-07 | 国网新疆电力有限公司信息通信公司 | Mobile terminal character recognition method and system based on deep learning |
| CN111461100A (en) * | 2020-03-31 | 2020-07-28 | 重庆农村商业银行股份有限公司 | Bill identification method and device, electronic equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113905269A (en) * | 2021-10-08 | 2022-01-07 | 南京启数智能***有限公司 | Method and device for realizing video monitoring OSD subtitle and clock detection by using OCR technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240161265A1 (en) | Information processing device, information processing method, and storage medium | |
| CN110119741B (en) | Card image information identification method with background | |
| KR100523898B1 (en) | Identification, separation and compression of multiple forms with mutants | |
| CN114937055A (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| US8175380B2 (en) | Apparatus and method for improving text recognition capability | |
| CN106951899A (en) | Method for detecting abnormality based on image recognition | |
| CN107610114A (en) | Optical satellite remote sensing image cloud snow mist detection method based on SVMs | |
| CN107292307B (en) | Automatic identification method and system for inverted Chinese character verification code | |
| CN108985305B (en) | Laser etching industrial detonator coded image positioning and correcting method | |
| JP5337563B2 (en) | Form recognition method and apparatus | |
| US20150010233A1 (en) | Method Of Improving Contrast For Text Extraction And Recognition Applications | |
| US20190354791A1 (en) | Character recognition method | |
| Reina et al. | Adaptive traffic road sign panels text extraction | |
| CN115147409A (en) | Mobile phone shell production quality detection method based on machine vision | |
| CN108182691B (en) | Method and device for identifying speed limit sign and vehicle | |
| CN111062919B (en) | Bearing ring appearance defect detection method | |
| JP2018120445A (en) | Car number recognition apparatus | |
| CN111667475B (en) | Machine vision-based Chinese date grading detection method | |
| KR101613703B1 (en) | detection of vehicle video and license plate region extraction method | |
| CN111898605A (en) | Set top box information detection method and system based on image OCR recognition | |
| CN108877030B (en) | Image processing method, device, terminal and computer readable storage medium | |
| JP5887242B2 (en) | Image processing apparatus, image processing method, and program | |
| CN114220102A (en) | Virtual server information detection method and system based on image OCR recognition | |
| Ouji et al. | Chromatic/achromatic separation in noisy document images | |
| US20190205752A1 (en) | Method for training a neural network for recognition of a character sequence and associated recognition method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201106 |