CN110276281A - A kind of screenshotss picture and text identification extracting method and system towards mobile terminal - Google Patents
A kind of screenshotss picture and text identification extracting method and system towards mobile terminal Download PDFInfo
- Publication number
- CN110276281A CN110276281A CN201910494709.4A CN201910494709A CN110276281A CN 110276281 A CN110276281 A CN 110276281A CN 201910494709 A CN201910494709 A CN 201910494709A CN 110276281 A CN110276281 A CN 110276281A
- Authority
- CN
- China
- Prior art keywords
- picture
- text
- screenshot capture
- mobile terminal
- image
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000005516 engineering process Methods 0.000 claims abstract description 8
- 239000000284 extract Substances 0.000 claims abstract description 6
- 230000008569 process Effects 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 238000003012 network analysis Methods 0.000 claims description 4
- 230000002093 peripheral effect Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims 1
- 238000012015 optical character recognition Methods 0.000 description 3
- 230000010365 information processing Effects 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/414—Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Image Analysis (AREA)
- Character Input (AREA)
Abstract
A kind of screenshotss picture and text identification extracting method towards mobile terminal, mobile terminal obtains image to be analyzed, and verifies whether input picture is mobile device screen screenshot with whether the length-width ratio of mobile device screen matches according to image;Screenshot capture to be analyzed is pre-processed, background colour is filled around screenshot capture, it is ensured that original image boundary not with current screen overlapping margins;The profile that picture in screenshot capture is detected by rectangle identification technology, using the region in profile as the picture recognized;Detection screenshot capture includes the region of middle text information and merges adjacent area, is identified respectively to the text information in each region, and text data is generated;Extract the picture and text data for saving and identifying.Based on the method, a kind of screenshotss picture and text identification extraction system towards mobile terminal is given.The present invention is efficiently convenient, enables mobile device user from screenshot capture quick obtaining picture and text information.
Description
Technical field
The present invention relates to mobile terminal field of information processing and pictograph to identify field, in particular to one kind is towards mobile terminal
Screenshotss picture and text identification extracting method and system.
Background technique
Becoming increasingly popular and develop with mobile device, all kinds of mobile applications have also appeared in daily life, this
So that people begin to focus on software quality and user experience.Nowadays most mobile application supports more matchmakers of the forms such as picture and text
Body information, this largely meets the demand that user information is received and expressed, however, many applications do not support picture and text to believe
The extraction and preservation of breath, the user experience and convenient degree that this reduces users in terms of information processing.For example, day any active ues
The up to ten million Instagram application program of number does not allow user to save picture and text directly from the information of publication.
In reality, in order to solve the problems, such as that mobile terminal picture and text extract, user is generally required by other operations and third party's work
Tool.Such as pass through the interface of interception application program and cut image manually from screenshot capture, using with OCR (Optical
Character Recognition, optical character identification) application program of function retrieves text.This mode is time-consuming, and logical
It often needs to network to support, is not easy to user's use.
Summary of the invention
The shortcomings that in order to overcome existing method complicated for operation, low efficiency, poor user experience, the invention proposes a kind of efficient
Easily screenshotss picture and text based on mobile terminal extract with identification extracting method and system, enable mobile device user from screen
Screenshot quick obtaining picture and text information.
In order to achieve the above object, the technical scheme adopted by the invention is that:
A kind of screenshotss picture and text identification extraction and recognition methods towards mobile terminal, comprising the following steps:
Step 1, mobile terminal obtain image to be analyzed, and according to the length-width ratio of image and mobile device screen whether
Match to verify whether input picture is mobile device screen screenshot;
Step 2, mobile terminal pre-process screenshot capture to be analyzed, background colour are filled around screenshot capture, really
Protect original image boundary not with current screen overlapping margins;
Step 3 detects the profile of picture in screenshot capture by rectangle identification technology, using the region in profile as knowledge
The picture being clipped to;
Step 4, detection screenshot capture includes the region of text information and merges adjacent area, respectively in each region
Text information is identified, text data is generated;
Step 5 extracts the picture and text data for saving and identifying.
Further, in the step 2, the pretreated process of screenshot capture are as follows: the main body at interface where detection screenshot capture
Background colour fills the frame of the color in screen shot image surrounding.Due to utilizing screen area as far as possible in mobile device
Domain, image often reach in length or width with the consistent maximum value of screen, therefore the purpose of the process is avoided because of screenshot
In picture boundary and screen coincident and reduce the performance of subsequent rectangular recognizer.
Further, when screenshot capture pre-processes, the process of screenshot capture main body background colour is detected are as follows: statistical screens screenshot
Pixel value, construct image color histogram, select color frequency highest as main body background colour.
Further, in the step 3, the process of rectangle identification are as follows: first by Hough transformation detect two pairs it is parallel straight
Line is mutually perpendicular between each pair of straight line;4 intersecting point coordinates of 4 straight lines are calculated again, and the region that line is constituted is
Rectangle to be detected.
Preferably, the Hough transformation uses polar coordinate transform, and the image of X-Y plane is transformed to p- θ plane treatment,
Equation are as follows: p=xcos θ+ysin θ, wherein p is distance of the origin to straight line, and θ is the normal of straight line and the angle of axis.
A kind of screenshotss picture and text identification extraction system towards mobile terminal, comprising:
Screenshot capture obtains module, and for obtaining image from mobile end system photograph album, and whether authentication image is mobile
Device screen screenshot;
Screenshot preprocessing module, for being pre-processed to the image analyzed, in the main back of image peripheral filling original image
Scenery frame;
Picture recognition module is based on rectangle identification technology, for identification picture present in pretreated screenshot capture
Region;
Text identification module merges adjacent area, and know for detecting the character area in pretreated screenshot capture
Text data in other region;
Display module, for showing the picture and character area that detect on the graphic user interface of mobile terminal;
Extraction module, picture and word content for obtaining identification are extracted and preserved.
Further, the system also includes:
Memory module, for storing screenshot capture to be analyzed and saving the picture obtained after network analysis identifies
And text data, and text copy function is provided.
Method and system of the present invention analyze screenshot capture based on mobile terminal, being capable of automatic identification extraction
Picture present in screenshot and text information out can not save picture for some mobile applications and replicate asking for text
Topic, compared to conventional method, the operation is more convenient, and recognition accuracy is higher.
Detailed description of the invention
Fig. 1 identifies extraction system structure chart towards the screenshotss picture and text of mobile terminal.
Fig. 2 identifies extracting method flow chart towards the screenshotss picture and text of mobile terminal.
Specific embodiment
The present invention will be described in detail with attached drawing With reference to embodiment.
Referring to Figures 1 and 2, a kind of screenshotss picture and text towards mobile terminal identify that extraction system, including screenshot capture obtain mould
Block S01, screenshot preprocessing module S02, picture recognition module S03, text identification module S04, display module S05, extraction module
S06, memory module S07.Specifically:
Screenshot capture obtains module S01, and for obtaining image from mobile end system photograph album, and whether authentication image is shifting
Dynamic device screen screenshot;
Screenshot preprocessing module S02, for being pre-processed to the image analyzed, in the master of image peripheral filling original image
Background colour frame;
Picture recognition module S03 is based on rectangle identification technology, schemes present in pretreated screenshot capture for identification
Panel region;
Text identification module S04 merges adjacent area for detecting the character area in pretreated screenshot capture,
And the text data in identification region;
Display module S05, for showing the picture and character area that detect on the graphic user interface of mobile terminal;
Extraction module S06, picture and word content for obtaining identification are extracted and preserved;
Memory module S07 is obtained after network analysis identifies for storing screenshot capture to be analyzed and saving
Picture and text data, and text copy function is provided.
Referring to Fig. 2, a kind of screenshotss picture and text identification extracting method towards mobile terminal, comprising the following steps:
Step 1, mobile terminal obtain module S01 by screenshot capture and obtain image to be analyzed, are stored in memory module
In S07, and verify whether input picture is mobile device screen with whether the length-width ratio of mobile device screen matches according to image
Curtain screenshot;
Step 2, mobile terminal pre-processes screenshot capture to be analyzed by screenshot preprocessing module S02, in screen
Background colour is filled around screenshot, it is ensured that original image boundary not with current screen overlapping margins;
Step 3, by detecting the profile of picture in screenshot capture in picture recognition module S03, which is known based on rectangle
Other technology is realized, using the region in profile as the picture recognized.Rectangle frame will be marked around the picture recognized, by aobvious
Show that module S05 is presented to the user on a graphical user interface;
Step 4 detects the region that screenshot capture includes middle text information by text identification module S04, by showing mould
Block S05 is presented to the user on a graphical user interface.For adjacent area, module thinks that it belongs to same section of text and carries out area
Domain merges, and identifies respectively to the text information in each region, generates text data;
Step 5 is extracted by extraction module S06 and saves the picture identified and text data into memory module S07.
Further, in the step 2, the pretreated process of screenshot capture are as follows: the main body at interface where detection screenshot capture
Background colour fills the frame of the color in screen shot image surrounding.The purpose of the process is the picture boundary avoided in screenshot
The performance of subsequent rectangular recognizer is reduced with screen coincident.
Further, when screenshot capture pre-processes, the process of screenshot capture main body background colour is detected are as follows: statistical screens screenshot
Pixel value, construct image color histogram, select color frequency highest as main body background colour.Due to being in mobile device
Screen area is utilized as far as possible, and image often reaches in length or width and the consistent maximum value of screen, therefore the process
Purpose the performance of subsequent rectangular recognizer is reduced due to be the picture boundary that avoids because in screenshot and screen coincident.
Further, in the step 3, the process of rectangle identification are as follows: first by Hough transformation detect two pairs it is parallel straight
Line is mutually perpendicular between each pair of straight line.4 intersecting point coordinates of 4 straight lines are calculated again, and the region that line is constituted is
Rectangle to be detected.
Preferably, the Hough transformation uses polar coordinate transform, and the image of X-Y plane is transformed to p- θ plane treatment,
Linear equation are as follows: p=x cose+y sine, wherein p is the citing of origin to straight line, and θ is the normal of straight line and the angle of axis.
Screenshotss picture and text identification extracting method and system based on mobile terminal can have following specific embodiments:
The screenshotss picture and text based on mobile terminal in the present invention are realized with iOS standard software development kit and Objective-C language
Identify extraction system in the concrete application program of iOS platform.Application testing environment is the Apple with following characteristics
8 mobile device of iPhone: Apple A11Bionic chip, 2GB memory, 64G internal storage space, test software environment are
12 operating system of iOS.
Specific system in the embodiment includes that screenshot capture obtains module S01, screenshot preprocessing module S02, and picture is known
Other module S03, text identification module S04, display module S05, extraction module S06, memory module S07.
Screenshot capture obtains module S01, for obtaining image from mobile end system photograph album, and according to image length-width ratio come
Verify whether it is mobile device screen screenshot;
Screenshot preprocessing module S02 further includes main background colour detection unit for pre-processing to the image analyzed
The highest color of frequency in background is calculated as main background colour, in the main background colour frame of image peripheral filling original image,;
Picture recognition module S03, based on the rectangle identification technology in iOS Vision Development Framework, after identifying pretreatment
Screenshot capture present in picture region;
Text identification module S04 merges adjacent area for detecting the character area in pretreated screenshot capture,
And the text data in identification region, in the present embodiment, text detection and identification are realized based on Tesseract OCR engine;
Display module S05, for showing the picture and character area that detect on the graphic user interface of mobile terminal, with side
Wire mark display;
Extraction module S06, picture and word content for obtaining identification are extracted and preserved;
Memory module S07 is obtained after network analysis identifies for storing screenshot capture to be analyzed and saving
Picture and text data, and text copy function is provided.
In conclusion a kind of screenshotss picture and text identification extracting method and system towards mobile terminal provided by the invention, it can
Mobile device screen screenshot is obtained in mobile terminal, after being pre-processed to screenshot, picture present in automatic detection identification screenshot
And text data, and extract preservation.
Above-described specific descriptions have carried out further specifically the purpose of invention, technical scheme and beneficial effects
It is bright, it should be understood that above is only a specific embodiment of the present invention, being used to explain the present invention, it is not used to limit this
The protection scope of invention, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should all
It is included within protection scope of the present invention.
Claims (7)
1. a kind of screenshotss picture and text towards mobile terminal identify extracting method, it is characterised in that: the described method comprises the following steps:
Step 1, mobile terminal obtain image to be analyzed, and according to image and the length-width ratio of mobile device screen whether match come
Verify whether input picture is mobile device screen screenshot;
Step 2, mobile terminal pre-process screenshot capture to be analyzed, and background colour is filled around screenshot capture, it is ensured that former
Figure boundary not with current screen overlapping margins;
Step 3 detects the profile of picture in screenshot capture by rectangle identification technology, using the region in profile as recognizing
Picture;
Step 4, detection screenshot capture includes the region of middle text information and merges adjacent area, respectively to the text in each region
This information is identified, text data is generated;
Step 5 extracts the picture and text data for saving and identifying.
2. a kind of screenshotss picture and text towards mobile terminal as described in claim 1 identify extracting method, it is characterised in that: the step
In rapid two, the pretreated process of screenshot capture are as follows: the main body background colour at interface where detection screenshot capture, in screen shot image
Surrounding fills the frame of the color.
3. a kind of screenshotss picture and text towards mobile terminal as claimed in claim 2 identify extracting method, it is characterised in that: screen is cut
When figure pretreatment, the process of screenshot capture main body background colour is detected are as follows: the pixel value of statistical screens screenshot, construction color of image are straight
Fang Tu selects color frequency highest as main body background colour.
4. a kind of screenshotss picture and text towards mobile terminal as described in one of claims 1 to 3 identify that extracting method, feature exist
In: in the step 3, the process of rectangle identification are as follows: two pairs of parallel straight lines are first detected by Hough transformation, each pair of straight line it
Between be mutually perpendicular to;4 intersecting point coordinates of 4 straight lines are calculated again, and the region that line is constituted is rectangle to be detected.
5. a kind of screenshotss picture and text towards mobile terminal as claimed in claim 4 identify extracting method, it is characterised in that: it is described suddenly
Husband's transformation uses polar coordinate transform, and the image of X-Y plane is transformed to p- θ plane treatment, linear equation are as follows: and p=x cos θ+
Y sin θ, wherein p is the citing of origin to straight line, and θ is the normal of straight line and the angle of axis.
6. a kind of system for realizing the screenshotss picture and text identification extracting method towards mobile terminal as described in claim 1, feature exist
In, the system comprises:
Screenshot capture obtains module, and for obtaining image from mobile end system photograph album, and whether authentication image is mobile device
Screenshot capture;
Screenshot preprocessing module, for being pre-processed to the image analyzed, in the main background colour of image peripheral filling original image
Frame;
Picture recognition module is based on rectangle identification technology, for identification picture region present in pretreated screenshot capture;
Text identification module merges adjacent area and cog region for detecting the character area in pretreated screenshot capture
Text data in domain;
Display module, for showing the picture and character area that detect on the graphic user interface of mobile terminal;
Extraction module, picture and word content for obtaining identification are extracted and preserved.
7. system as claimed in claim 6, which is characterized in that the system also includes:
Memory module, for storing screenshot capture to be analyzed and saving the picture and text that obtain after network analysis identifies
Notebook data, and text copy function is provided.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910494709.4A CN110276281A (en) | 2019-06-10 | 2019-06-10 | A kind of screenshotss picture and text identification extracting method and system towards mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910494709.4A CN110276281A (en) | 2019-06-10 | 2019-06-10 | A kind of screenshotss picture and text identification extracting method and system towards mobile terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110276281A true CN110276281A (en) | 2019-09-24 |
Family
ID=67960535
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910494709.4A Pending CN110276281A (en) | 2019-06-10 | 2019-06-10 | A kind of screenshotss picture and text identification extracting method and system towards mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110276281A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111597966A (en) * | 2020-05-13 | 2020-08-28 | 北京达佳互联信息技术有限公司 | Expression image recognition method, device and system |
CN113286139A (en) * | 2020-02-19 | 2021-08-20 | 福建天泉教育科技有限公司 | Method and system for testing video or real-time screen sharing interaction capability |
CN113723401A (en) * | 2021-08-23 | 2021-11-30 | 上海千映智能科技有限公司 | Song menu extraction method based on morphological method |
CN114296842A (en) * | 2021-07-26 | 2022-04-08 | 海信视像科技股份有限公司 | Display device and scrolling text detection method |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102216941A (en) * | 2008-08-19 | 2011-10-12 | 数字标记公司 | Methods and systems for content processing |
CN106844785A (en) * | 2017-03-15 | 2017-06-13 | 浙江工业大学 | A kind of CBIR method based on conspicuousness segmentation |
CN107977652A (en) * | 2017-12-21 | 2018-05-01 | 维沃移动通信有限公司 | The extracting method and mobile terminal of a kind of screen display content |
CN108416018A (en) * | 2018-03-06 | 2018-08-17 | 北京百度网讯科技有限公司 | Screenshotss searching method, device and intelligent terminal |
CN108509343A (en) * | 2018-04-04 | 2018-09-07 | 浙江小泰科技有限公司 | Automated testing method based on image recognition technology and system |
CN108595107A (en) * | 2018-05-02 | 2018-09-28 | 维沃移动通信有限公司 | A kind of interface content processing method and mobile terminal |
CN109190617A (en) * | 2018-08-09 | 2019-01-11 | 腾讯科技(深圳)有限公司 | A kind of rectangle detection method of image, device and storage medium |
CN109710140A (en) * | 2018-12-25 | 2019-05-03 | 清创网御(合肥)科技有限公司 | A kind of smart phone social application automatic data collection method |
CN109783759A (en) * | 2019-01-15 | 2019-05-21 | 北京智融网络科技有限公司 | Page screenshot automatic generating method, equipment and readable storage medium storing program for executing |
-
2019
- 2019-06-10 CN CN201910494709.4A patent/CN110276281A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102216941A (en) * | 2008-08-19 | 2011-10-12 | 数字标记公司 | Methods and systems for content processing |
CN106844785A (en) * | 2017-03-15 | 2017-06-13 | 浙江工业大学 | A kind of CBIR method based on conspicuousness segmentation |
CN107977652A (en) * | 2017-12-21 | 2018-05-01 | 维沃移动通信有限公司 | The extracting method and mobile terminal of a kind of screen display content |
CN108416018A (en) * | 2018-03-06 | 2018-08-17 | 北京百度网讯科技有限公司 | Screenshotss searching method, device and intelligent terminal |
CN108509343A (en) * | 2018-04-04 | 2018-09-07 | 浙江小泰科技有限公司 | Automated testing method based on image recognition technology and system |
CN108595107A (en) * | 2018-05-02 | 2018-09-28 | 维沃移动通信有限公司 | A kind of interface content processing method and mobile terminal |
CN109190617A (en) * | 2018-08-09 | 2019-01-11 | 腾讯科技(深圳)有限公司 | A kind of rectangle detection method of image, device and storage medium |
CN109710140A (en) * | 2018-12-25 | 2019-05-03 | 清创网御(合肥)科技有限公司 | A kind of smart phone social application automatic data collection method |
CN109783759A (en) * | 2019-01-15 | 2019-05-21 | 北京智融网络科技有限公司 | Page screenshot automatic generating method, equipment and readable storage medium storing program for executing |
Non-Patent Citations (1)
Title |
---|
邓超等: "《数字图像处理与模式识别研究》", 30 June 2018, 地质出版社 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113286139A (en) * | 2020-02-19 | 2021-08-20 | 福建天泉教育科技有限公司 | Method and system for testing video or real-time screen sharing interaction capability |
CN111597966A (en) * | 2020-05-13 | 2020-08-28 | 北京达佳互联信息技术有限公司 | Expression image recognition method, device and system |
CN111597966B (en) * | 2020-05-13 | 2023-10-10 | 北京达佳互联信息技术有限公司 | Expression image recognition method, device and system |
CN114296842A (en) * | 2021-07-26 | 2022-04-08 | 海信视像科技股份有限公司 | Display device and scrolling text detection method |
CN113723401A (en) * | 2021-08-23 | 2021-11-30 | 上海千映智能科技有限公司 | Song menu extraction method based on morphological method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110276281A (en) | A kind of screenshotss picture and text identification extracting method and system towards mobile terminal | |
CN109359575B (en) | Face detection method, service processing method, device, terminal and medium | |
US20140286542A1 (en) | Methods and systems for determining image processing operations relevant to particular imagery | |
CN105450411B (en) | The method, apparatus and system of authentication are carried out using card feature | |
US10713514B2 (en) | Identification method and electronic device | |
CN111582085B (en) | Document shooting image recognition method and device | |
US11244157B2 (en) | Image detection method, apparatus, device and storage medium | |
US20200065460A1 (en) | Method and computer readable storage medium for remote interview signature | |
JP2019519844A (en) | Image quality evaluation of documents | |
CN110796646A (en) | Method and device for detecting defects of screen area of electronic device | |
CN110414352A (en) | The method and relevant device of PPT the file information are extracted from video file | |
AU2015318386A1 (en) | Intelligent scoring method and system for text objective question | |
CN111709414A (en) | AR device, character recognition method and device thereof, and computer-readable storage medium | |
US8897565B1 (en) | Extracting documents from a natural scene image | |
EP3273388A1 (en) | Image information recognition processing method and device, and computer storage medium | |
US20210271857A1 (en) | Method and apparatus for identity verification, electronic device, computer program, and storage medium | |
CN111259891B (en) | Method, device, equipment and medium for identifying identity card in natural scene | |
CN109993075B (en) | Chat application session content storage method, system and device | |
KR101034117B1 (en) | A method and apparatus for recognizing the object using an interested area designation and outline picture in image | |
CN106709488A (en) | Business card identification method and device | |
CN112686257A (en) | Storefront character recognition method and system based on OCR | |
CN113781356A (en) | Training method of image denoising model, image denoising method, device and equipment | |
CN114359932B (en) | Text detection method, text recognition method and device | |
CN105224919B (en) | Texture characteristic extracting method and device | |
CN107992872B (en) | Method for carrying out text recognition on picture and mobile terminal |
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: 20190924 |