CN109903174B - Insurance policy input system and method based on mobile terminal camera shooting - Google Patents
Insurance policy input system and method based on mobile terminal camera shooting Download PDFInfo
- Publication number
- CN109903174B CN109903174B CN201910222268.2A CN201910222268A CN109903174B CN 109903174 B CN109903174 B CN 109903174B CN 201910222268 A CN201910222268 A CN 201910222268A CN 109903174 B CN109903174 B CN 109903174B
- Authority
- CN
- China
- Prior art keywords
- detection
- picture
- insurance policy
- contour
- text
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 117
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000007797 corrosion Effects 0.000 claims description 6
- 238000005260 corrosion Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
Abstract
The application discloses an insurance policy input system and method based on mobile terminal shooting, a cloud server is respectively communicated with a mobile terminal and a computer terminal, the mobile terminal comprises a camera and an insurance policy picture feature detection module, the camera shoots an insurance policy and captures a frame image, the insurance policy picture feature detection module detects the frame image, the cloud server comprises an insurance policy information analysis module, the cloud server is used for receiving the insurance policy picture passing through the detection, the insurance policy information analysis module analyzes text information in the insurance policy picture and stores the text information as insurance policy data, and the computer terminal or the mobile terminal is used for accessing the insurance policy data stored by the cloud server. The average speed is 20 seconds/share, compared with manual input, the input efficiency is greatly improved, and based on the insurance policy picture feature detection module, the picture which is possibly insurance is identified, and the resolution accuracy of the cloud server side to the insurance policy information is greatly improved.
Description
Technical Field
The application relates to the technical field of insurance policy entry, in particular to an insurance policy entry system and method based on mobile terminal shooting.
Background
The insurance policy is abbreviated as "policy" and is a written proof that an insurance person and an applicant have signed an insurance contract. The main contents of the insurance policy include: (1) The description of the related items of the insurance targets comprises the name of the insured person, the name of the insurance target and the storage place or state thereof, the insurance amount, the insurance period, the insurance fee and the like. (2) Rights and obligations of both parties, such as responsibility and unexplained responsibility, etc. (3) The remark condition refers to the insurance clause or other conditions agreed by both parties, and matters such as policy change, transfer and cancellation. Insurance policies are the primary manifestations of the contracting insurance. The currently known modes of entering insurance policies are all manually entered. The system is manually entered based on information of the insurance policy. This mode needs a large amount of manpowers, and the logging time is long, and the average logging time of passing the test is 20 minutes per share insurance policy, inefficiency.
Disclosure of Invention
In view of the above-mentioned defects or shortcomings in the prior art, it is desirable to provide a system and a method for entering an insurance policy based on mobile terminal shooting, so as to greatly improve the entering efficiency and the resolution accuracy of insurance policy information.
According to the technical scheme provided by the embodiment of the application, in one aspect, the system for entering the insurance policy based on the camera shooting of the mobile terminal comprises the mobile terminal, a cloud server and a computer terminal, wherein the cloud server is respectively communicated with the mobile terminal and the computer terminal, the mobile terminal comprises a camera and an insurance policy picture feature detection module, the camera shoots the insurance policy and captures a frame image, the insurance policy picture feature detection module detects the frame image, the cloud server comprises an insurance policy information analysis module, the cloud server is used for receiving the insurance policy picture passing through the detection, the insurance policy information analysis module analyzes text information in the insurance policy picture and stores the text information as insurance policy data, and the computer terminal or the mobile terminal is used for accessing the insurance policy data stored by the cloud server.
In the application, the insurance policy picture feature detection module comprises brightness detection, definition detection, inclination detection, character size and integrity detection, and the insurance policy information analysis module adopts an OCR recognition algorithm.
On the other hand, providing a safety bill input method based on mobile terminal shooting, wherein a safety bill picture feature detection module respectively carries out brightness detection, definition detection, gradient detection, character size and integrity detection on frame images captured by a camera, if the detection is passed, shooting is stopped, the passed safety bill pictures are remotely sent to a cloud server, if the detection is not passed, error information is prompted, picture frames are continuously captured, and the detection is continued until the detection is passed, and the brightness detection comprises the following steps of S1 and picture graying; s2, calculating the gray average value cp of all pixel points of the picture,wherein x is n The gray value of the pixel points N is the total number of the pixel points of the picture; s3, setting a threshold value, wherein the threshold value can be adjusted, the overdue threshold value pd= -60 and the overdue threshold value pl= 60; s4, detecting, when pa<When pd is too dark, the detection is not passed, when pa>When pl is too bright, the detection is not passed, and when pd<＝pa<When=pl, detect pass; the definition detection comprises the following steps of S10, graying the picture; s20, calculating an average gray-scale meanG of the picture by using a Tenengard function; s30, calculating a threshold value ct according to the size of the picture, wherein ct=c1-c 2xmaxl, c1 is a constant, c1 is changeable according to test setting of 3.10, c2 is a constant, c2 is changeable according to test setting of 0.0019, and maxl is the total number of pixels at the longest edge of the picture; s40, detecting, namely, meanG>When=ct, the picture sharpness detection passes, when means g<When ct, the picture definition detection is not passed; the gradient detection comprises the following steps of S100, graying a picture, and then binarizing; s200, extracting all straight line sets L in the picture through Hough standard transformation; and S300, removing unreasonable straight lines, and defining the minimum straight line length (miml), wherein miml=wl is 0.3, and wl is the width of the picture, and removing straight lines with the length smaller than minl from the set L. S400, calculating average gradient ms, < >>S500, detecting, setting a inclination angle threshold value (msd) which is msd=15, can be changed, does not pass detection if the set L element is 0, and is when |ms| if the set L element is more than 0<When=msd, then the detection passes, when |ms|>In msd, the detection is not passed; the text size and integrity detection comprises the following steps of S1000, graying of pictures, and binarization; s2000, performing corrosion once by using an error function of OpenCV, and performing expansion once by using a dialite function of OpenCv, wherein the parameters of corrosion and expansion are the core shape MORPH_RECT rectangle, the core size and the core size are 14x2; s3000, extracting a text region contour set T, and extracting a text region contour by using a finContours function of OpenCV. Parameters are profile type, RETR_CCOMP all profiles, profile approximation method, CHAIN_APPROX_SIMPLE, only the inflection point information of the contour is saved; s4000, removing abnormal contour data, wherein the abnormal contour comprises a contour with a too small area and a long and narrow area, and the minimum area threshold value minu=80, the minu can be changed, the contour area is a, and when the contour area a is<At mina, the contour is removed from T, when a>At=spt, the contour is preserved; removing the long and narrow profile, and calculating the profile height-width ratio sp, sp=h/w; where h is the length of the profile and w is the width of the profile; setting a minimum proportional threshold spt, spt=1.25, which can be changed when sp>At spt, the contour is removed from T, when sp<At=spt, the contour is preserved.
In the application, the character size and integrity detection comprises character size detection and character integrity detection, wherein the character size detection comprises the following steps of S10000, calculating average height mh,s20000, defining a threshold, a minimum height of words minh=10.5, which can be changed, and a maximum height of words maxh 16.8, which can be changed; s30000, detection, when mh<minh or mh>In the case of maxh, the detection is not passed, when the reaction is minh<＝mh<When=maxh, detection passes; the text integrity detection uses the steps of S100000, calculating left (txl) and right (txr) x coordinates of each outline, txl = tx, txr = tx + tw; where tx is the relative picture to x coordinate of the contour t in the picture and tw is the width of the contour; s200000, defining a threshold, a boundary minimum distance mins, mins=4, which mins can be modified; s300000, detecting, namely, detecting the integrity of the characters for each contour set T, if one of the contour sets T does not pass, the integrity of the characters does not pass, and if all the contour sets T pass, the integrity of the characters passes; s40000, text integrity test for each outline T, as txl>mins and txr<(pw-mins) and the profilometer pass, otherwise do not, where pw is the width of the picture.
In summary, the application has the following beneficial effects: the mobile phone is used for shooting and identifying, the average speed is 20 seconds/share, compared with manual input, the input efficiency is greatly improved, and based on the insurance policy picture feature detection module, the picture frames in shooting are checked, the picture which is possibly insurance is identified, and the analysis accuracy of the cloud server side to the insurance policy information is greatly improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:
FIG. 1 is a schematic diagram of a system architecture of the present application;
FIG. 2 is a system flow diagram of the present application;
FIG. 3 is a flowchart of the insurance policy picture feature detection module of the present application.
Reference numerals in fig. 1: 10. a mobile terminal; 20. the cloud server; 30. and a computer terminal.
Detailed Description
The application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be noted that, for convenience of description, only the portions related to the application are shown in the drawings.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
Referring to fig. 1 and 2, an insurance policy entry system based on mobile terminal shooting includes a mobile terminal 10, a cloud server 20 and a computer terminal 30, the cloud server 20 is respectively connected with the mobile terminal 10 and the computer terminal 30, the mobile terminal 10 includes a camera and an insurance policy picture feature detection module, the camera shoots and captures a frame image of an insurance policy, the insurance policy picture feature detection module detects the frame image, the cloud server 20 includes an insurance policy information analysis module, the cloud server 20 is configured to receive an insurance policy picture through detection, the insurance policy information analysis module analyzes text information in the insurance policy picture and stores the text information as insurance policy data, and the computer terminal 30 or the mobile terminal 10 is configured to access the insurance policy data stored by the cloud server 20. The insurance policy picture feature detection module comprises brightness detection, definition detection, inclination detection, character size and integrity detection, and the insurance policy information analysis module adopts an OCR recognition algorithm.
Examples: as shown in fig. 3, in the method for entering a security document based on mobile terminal image capturing, a security document image feature detection module performs brightness detection, definition detection, inclination detection, text size and integrity detection on a frame image captured by a camera, the detection items can exchange detection sequences, if the detection is passed, image capturing is stopped, and a passed security document image is remotely sent to a cloud server, if the detection is not passed, error information is prompted, and capturing of an image frame is continued, and the detection is continued until the detection is passed, wherein the brightness detection comprises the following steps of S1 and image graying; s2, calculating the gray average value cp of all pixel points of the picture,wherein x is n The gray value of the pixel points N is the total number of the pixel points of the picture; s3, setting a threshold value, wherein the threshold value can be adjusted, the overdue threshold value pd= -60 and the overdue threshold value pl= 60; s4, detecting, when pa<When pd is too dark, the detection is not passed, when pa>When pl is too bright, the detection is not passed, and when pd<＝pa<When=pl, detect pass; the definition detection comprises the following steps of S10, graying the picture; s20, calculating an average gray-scale meanG of the picture by using a Tenengard function; s30, calculating a threshold value ct according to the size of the picture, wherein ct=c1-c 2xmaxl, c1 is a constant, c1 is changeable according to test setting of 3.10, c2 is a constant, c2 is changeable according to test setting of 0.0019, and maxl is the total number of pixels at the longest edge of the picture; s40, detecting, namely, meanG>When=ct, the picture sharpness detection passes, when means g<When ct, the picture definition detection is not passed; the gradient detection comprises the following steps of S100, graying a picture, and then binarizing; s200, extracting all straight line sets L in the picture through Hough standard transformation; s300. The unreasonable straight line is removed, defining a minimum straight line length (miml) of miml=wl 0.3, where wl is the width of the picture, and from this set L, the straight line with a length less than minl is removed. S400, calculating the average gradient ms,s500, detecting, setting a inclination angle threshold value (msd) which is msd=15, can be changed, does not pass detection if the set L element is 0, and is when |ms| if the set L element is more than 0<When=msd, then the detection passes, when |ms|>In msd, the detection is not passed; the text size and integrity detection comprises the following steps of S1000, graying of pictures, and binarization; s2000, performing corrosion once by using an error function of OpenCV, and performing expansion once by using a dialite function of OpenCv, wherein the parameters of corrosion and expansion are the core shape MORPH_RECT rectangle, the core size and the core size are 14x2; s3000, extracting a text region contour set T, and extracting a text region contour by using a finContours function of OpenCV. Parameters are profile type, RETR_CCOMP all profiles, profile approximation method, CHAIN_APPROX_SIMPLE, and only the inflection point information of the profile is saved; s4000, removing abnormal contour data, wherein the abnormal contour comprises a contour with a too small area and a long and narrow area, and the minimum area threshold value minu=80, the minu can be changed, the contour area is a, and when the contour area a is<At mina, the contour is removed from T, when a>At=spt, the contour is preserved; removing the long and narrow profile, and calculating the profile height-width ratio sp, sp=h/w; where h is the length of the profile and w is the width of the profile; setting a minimum proportional threshold spt, spt=1.25, which can be changed when sp>At spt, the contour is removed from T, when sp<At=spt, the contour is preserved. The character size and integrity detection comprises character size detection and character integrity detection, wherein the character size detection comprises the following steps of S10000, calculating average height mh and->S20000, defining a threshold, a minimum height of words minh=10.5, which can be changed, and a maximum height of words maxh 16.8, which can be changed; s30000, detectionWhen mh<minh or mh>In the case of maxh, the detection is not passed, when the reaction is minh<＝mh<When=maxh, detection passes; the text integrity detection uses the steps of S100000, calculating left (txl) and right (txr) x coordinates of each outline, txl = tx, txr = tx + tw; where tx is the relative picture to x coordinate of the contour t in the picture and tw is the width of the contour; s200000, defining a threshold, a boundary minimum distance mins, mins=4, which mins can be modified; s300000, detecting, namely, detecting the integrity of the characters for each contour set T, if one of the contour sets T does not pass, the integrity of the characters does not pass, and if all the contour sets T pass, the integrity of the characters passes; s40000, text integrity test for each outline T, as txl>mins and txr<(pw-mins) and the profilometer pass, otherwise do not, where pw is the width of the picture.
The above description is only illustrative of the preferred embodiments of the application and the technical principles employed. Meanwhile, the scope of the application is not limited to the technical scheme formed by the specific combination of the technical features, and other technical schemes formed by any combination of the technical features or the equivalent features thereof without departing from the inventive concept are also covered. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
Claims (1)
1. A insurance policy input system based on mobile terminal shooting is characterized in that: the system comprises a mobile terminal (10), a cloud server (20) and a computer terminal (30), wherein the cloud server (20) is respectively communicated with the mobile terminal (10) and the computer terminal (30), the mobile terminal (10) comprises a camera and a insurance policy picture feature detection module, the camera is used for shooting an insurance policy and capturing a frame image, the insurance policy picture feature detection module is used for detecting the frame image, the cloud server (20) comprises an insurance policy information analysis module, the cloud server (20) is used for receiving an insurance policy picture which passes through the detection, the insurance policy information analysis module is used for analyzing text information in the insurance policy picture and storing the text information as insurance policy data, and the computer terminal (30) or the mobile terminal (10) is used for accessing the insurance policy data stored by the cloud server (20);
the insurance policy picture feature detection module comprises brightness detection, definition detection, inclination detection, character size and integrity detection, and the insurance policy information analysis module adopts an OCR recognition algorithm;
the insurance policy picture feature detection module respectively carries out brightness detection, definition detection, inclination detection, character size and integrity detection on the frame image captured by the camera, if the detection is passed, the camera shooting is stopped, the passed insurance policy picture is remotely sent to the cloud server, if the detection is not passed, error information is prompted, the capturing of picture frames is continued, the detection is continued until the passing, the brightness detection comprises the following steps,
s1, graying a picture;
s2, calculating the gray average value cp of all pixel points of the picture,wherein xn is the gray value of pixel N, N is the total number of pixel points of the picture;
s3, setting a threshold value, wherein the threshold value is adjusted as required, the overdue threshold value pd= -60 and the overdue threshold value pl= 60;
s4, detecting the sample, wherein the sample is subjected to detection,
pa is the gray average value, which is calculated after a certain photographing in the step S2,
when cp < pd, too dark, the detection does not pass,
when cp > pl, too bright, the detection does not pass,
when pd < = cp < = pl, detection passes;
the sharpness detection comprises the steps of,
s10, graying the picture;
s20, calculating an average gray-scale meanG of the picture by using a Tenengard function;
s30, calculating a threshold value ct according to the size of the picture, wherein ct=c1-c 2xmaxl, c1 is a constant, c1 is set to 3.10 according to the test, c1 is changed according to the requirement, c2 is a constant, c2 is set to 0.0019 according to the test, and maxl is the total number of pixels at the longest edge of the picture according to the requirement;
s40, detecting the position of the sample,
when means > =ct, the picture sharpness detection passes,
when means < ct, the picture definition detection does not pass;
the inclination detection comprises the steps of,
s100, graying the picture, and then binarizing;
s200, extracting all straight line sets L in the picture through Hough standard transformation;
s300, removing unreasonable straight lines, defining the minimum straight line length mi, wherein mi=wl is 0.3,
where wl is the width of the picture, from this set L, the straight line with a length less than minl is removed;
s400, calculating the average gradient ms,wherein Ln is the offset angle of the nth straight line and the horizontal axis, the values of the 1 st and 3 rd quadrants are 0 to 90, the values of the 2 nd and 4 th quadrants are 0 to-90, and n is the total number of the straight lines;
s500, detecting, setting a inclination angle threshold msd, msd=15, which is changed as needed,
if the set L element is 0, the detection does not pass,
if the set L element is greater than 0,
when |ms| < =msd, then the detection passes,
when |ms| > msd, then the detection does not pass;
the text size and integrity detection includes the steps of,
s1000, graying the picture, and then binarizing;
s2000, performing corrosion once by using an error function of OpenCV, and performing expansion once by using a dialite function of OpenCv, wherein the parameters of corrosion and expansion are the core shape MORPH_RECT rectangle, the core size and the core size are 14x2;
s3000, extracting a character area outline set T, and extracting character area outline by using a finContours function of OpenCV, wherein parameters required to be extracted by the character area outline are as follows: profile type, RETR_CCOMP all profiles, profile approximation method, CHAIN_APPROX_SIMPLE, then only the inflection point information of the profile is saved;
s4000, removing abnormal contour data, wherein the abnormal contour comprises an excessively small and long area,
removing a contour with an excessively small area, wherein a minimum area threshold value minu=80, the minu is changed as required, the contour area is a, when the contour area a < minu, the contour is removed from T, and when a > =minu, the contour is reserved;
removing the long and narrow profile, and calculating the profile height-width ratio sp, sp=h/w; where h is the length of the profile and w is the width of the profile; setting a minimum proportional threshold spt, spt=1.25, which is modified as needed, removing the profile from T when sp > spt, and retaining the profile when sp < = spt;
the text size and integrity detection includes text size detection and text integrity detection,
the word size detection uses the following steps,
s10000, calculating the average height mh,tn is the height of the nth contour, n is the total number of contours;
s20000, defining a threshold, and changing the minimum height minh=10.5 of the text, wherein the minh is changed according to the need, and the maximum height maxh of the text;
s30000, detecting the position of the object,
when mh < minh or mh > maxh, the detection does not pass,
detecting passing when minh < = mh < = maxh;
the text integrity detection uses the following steps,
s100000, calculate left side x coordinate txl and right side x coordinate txr for each contour, txl =tx, txr =tx+tw; where tx is the relative picture to x coordinate of the contour t in the picture and tw is the width of the contour;
s200000, defining a threshold, a boundary minimum distance mins, mins=4, which mins is modified as needed;
s300000, detecting, namely, detecting the integrity of the characters for each contour set T, if one of the contour sets T does not pass, the integrity of the characters does not pass, and if all the contour sets T pass, the integrity of the characters passes;
s400000, text integrity detection of each outline T, when txl > mins and txr < (pw-mins), the outline text integrity detection passes, otherwise, the outline text integrity detection does not pass, wherein pw is the width of the picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910222268.2A CN109903174B (en) | 2019-03-22 | 2019-03-22 | Insurance policy input system and method based on mobile terminal camera shooting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910222268.2A CN109903174B (en) | 2019-03-22 | 2019-03-22 | Insurance policy input system and method based on mobile terminal camera shooting |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109903174A CN109903174A (en) | 2019-06-18 |
| CN109903174B true CN109903174B (en) | 2023-11-24 |
Family
ID=66952536
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910222268.2A Active CN109903174B (en) | 2019-03-22 | 2019-03-22 | Insurance policy input system and method based on mobile terminal camera shooting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109903174B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376281A (en) * | 2014-10-29 | 2015-02-25 | 上海天涛智能科技有限公司 | Surface receipt recognizing system based on mobile network |
| CN105243592A (en) * | 2015-11-06 | 2016-01-13 | 东莞市创世纪保险代理有限公司 | Intelligent car insurance quotation and insurance system and method |
| CN106557747A (en) * | 2016-11-15 | 2017-04-05 | 平安科技（深圳）有限公司 | The method and device of identification insurance single numbers |
| CN107944791A (en) * | 2017-11-23 | 2018-04-20 | 上海最会保网络科技有限公司 | A kind of declaration form delivery system based on cloud data service |
| CN109062926A (en) * | 2018-06-06 | 2018-12-21 | 成都中通信通科技有限公司 | A kind of car insurance data collection system |
-
2019
- 2019-03-22 CN CN201910222268.2A patent/CN109903174B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104376281A (en) * | 2014-10-29 | 2015-02-25 | 上海天涛智能科技有限公司 | Surface receipt recognizing system based on mobile network |
| CN105243592A (en) * | 2015-11-06 | 2016-01-13 | 东莞市创世纪保险代理有限公司 | Intelligent car insurance quotation and insurance system and method |
| CN106557747A (en) * | 2016-11-15 | 2017-04-05 | 平安科技（深圳）有限公司 | The method and device of identification insurance single numbers |
| CN107944791A (en) * | 2017-11-23 | 2018-04-20 | 上海最会保网络科技有限公司 | A kind of declaration form delivery system based on cloud data service |
| CN109062926A (en) * | 2018-06-06 | 2018-12-21 | 成都中通信通科技有限公司 | A kind of car insurance data collection system |
Non-Patent Citations (3)
| Title |
|---|
| "基于TesseractOCR的驾驶证识别系统设计与实现";李亮;《中国优秀硕士论文全文数据库 工程科技Ⅱ辑》;C034-74 * |
| 余辉.《印刷工艺》.重庆大学出版社,2018,31. * |
| 单证识别领域的OCR技术应用探索;贾旸;《金融电子化》;20180415(第04期);第48-49页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109903174A (en) | 2019-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11599861B2 (en) | Systems and methods for mobile automated clearing house enrollment | |
| US11544945B2 (en) | Systems and methods for mobile image capture and content processing of driver's licenses | |
| US11798302B2 (en) | Mobile image quality assurance in mobile document image processing applications | |
| US8000514B2 (en) | Methods for mobile image capture and processing of checks | |
| US9298979B2 (en) | Systems and methods for mobile image capture and content processing of driver's licenses | |
| WO2020147398A1 (en) | Reproduced image detection method and device, computer device and storage medium | |
| US20100033603A1 (en) | Method for extracting raw data from an image resulting from a camera shot | |
| CN109766778A (en) | Invoice information input method, device, equipment and storage medium based on OCR technique | |
| CN111259891B (en) | Method, device, equipment and medium for identifying identity card in natural scene | |
| CN104866847A (en) | Rapid and robust answering card identifying method | |
| CN115170567A (en) | Method for detecting defects of waterproof steel plate for ship | |
| CN108021913A (en) | Certificate photograph information identifying method and device | |
| CN107977648A (en) | A kind of method of discrimination and system of the identity card clarity based on recognition of face | |
| CN109447942B (en) | Image ambiguity determining method, apparatus, computer device and storage medium | |
| CN109903174B (en) | Insurance policy input system and method based on mobile terminal camera shooting | |
| KR102102403B1 (en) | Code authentication method of counterfeit print image and its application system | |
| KR102161315B1 (en) | Automatic identification monitoring system of container | |
| US9536162B2 (en) | Method for detecting an invisible mark on a card | |
| CN114820621B (en) | Bolt loss defect detection method, system and device | |
| US20160275345A1 (en) | Camera systems with enhanced document capture | |
| CN113792677B (en) | Table identification method and device, computer equipment and storage medium | |
| CN115908319A (en) | Micro-graph code light reflection detection method and device based on grey level histogram discreteness | |
| CN115578729B (en) | AI intelligent process arrangement method for digital staff | |
| CN115604567A (en) | Method and device for detecting camera shading by green leaves and computer equipment | |
| CN113255638A (en) | Character correction detection method, device, equipment and 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 | ||
| CB02 | Change of applicant information |
Address after: No. 2, 30th Floor, Unit 1, Building 1, No. 28, North Section of Tianfu Avenue, High tech Zone, Chengdu City, Sichuan Province, 610000 Applicant after: Chengdu Sure Technology Co.,Ltd. Address before: No. 4, 13th Floor, Building 3, No. 666 Jitai Road, Chengdu High tech Zone, Chengdu (Sichuan) Pilot Free Trade Zone, Sichuan 610000 Applicant before: CHENGDU SHENGKUN TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |