CN109447068A - A method of it separating seal from image and calibrates seal - Google Patents
A method of it separating seal from image and calibrates seal Download PDFInfo
- Publication number
- CN109447068A CN109447068A CN201811257669.3A CN201811257669A CN109447068A CN 109447068 A CN109447068 A CN 109447068A CN 201811257669 A CN201811257669 A CN 201811257669A CN 109447068 A CN109447068 A CN 109447068A
- Authority
- CN
- China
- Prior art keywords
- seal
- image
- identified
- shape detection
- original
- 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
Classifications
-
- 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
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- 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
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The present invention discloses a kind of method for separating seal from image and calibrating seal, and the method includes the steps of: establishing the data set of original official seal；Slant correction is carried out to image to be identified；SHAPE DETECTION is carried out to image using oval, round and three kinds of SHAPE DETECTION algorithms of rectangle, to position official seal, and official seal is separated from image to be identified；Preliminary registration is carried out, consistent seal and suspicious seal are tentatively identified as.The invention can tentatively realize the authenticity of seal.Method of the invention can quickly and effectively seal present in detection image, have many advantages, such as that detection accuracy is high, speed is fast, strong interference immunity.
Description
Technical field
The present invention relates to pictographs to identify field, and in particular to a kind of side for separating seal from image and calibrate seal
Method.
Background technique
With the continuous development of computer technology, the difficulty of falsification of seal substantially reduces, and causes so as to cause seal is forged
Criminal activity remain incessant after repeated prohibition, automate seal authenticity authentication technique research it is most important in modern society.The positioning of seal
Be registrated the speed and correctness that judging result is directly related to as the committed step for judging the seal true and false.How efficiently
Realize the positioning of seal be registrated as identifying stamp true and false urgent problem to be solved.
Summary of the invention
The method that in view of the deficiencies of the prior art, the present invention proposes a kind of to separate seal from image and calibrate seal, should
Method specifically comprises the following steps:
Step 1: establishing the data set of original official seal；
Step 2: obtain original image in image to be identified maximum enclosure frame profile, to image to be identified into
Line tilt correction；
Step 3: by image to be identified by RGB color model conversation to HSI color space model, using threshold value control
Preparation method extracts red component, and color image gray processing；
Step 4: shape is carried out using image of oval, the round and three kinds of SHAPE DETECTION algorithms of rectangle to step 3 gray processing
Detection, to position the position for obtaining the smallest rectangular profile and official seal of surrounding official seal in image to be identified, and will packet
The smallest rectangular profile for enclosing official seal is separated from image to be identified；
Step 5: using the method based on Harris corner feature to the seal image extracted in original seal and step 4 into
Then the preliminary registration that line position is set carries out rotation and translation to two seals again in small angle range, search for optimum position,
Complete accuracy registration；
Step 6: by principal-employment and minus tolerance quantification registration result, it is true tentatively to judge seal by calculating difference image
Seal to be measured is divided into consistent seal and suspicious seal by puppet.
Preferably, in the step 4 specifically includes the following steps:
(1) gray level image for obtaining step 3 is converted into bianry image；
(2) image thinning algorithm is used, obtains skeleton drawing from bianry image；
(3) oval, round and three kinds of SHAPE DETECTION algorithms of rectangle are respectively adopted, SHAPE DETECTION are carried out to skeleton drawing, wherein
The SHAPE DETECTION of rectangular seal is detected to the criterion of digital straight line and the feature of digital straight line, is minimum single with line segment member
Position construction straight line, after detecting all straight lines, the rectangle in image is quickly oriented by comparing the length of straight line and direction；
The SHAPE DETECTION of elliptical seal is detected using the thought divided based on curve arc, according to connectivity mutual between profile point
Line trace is clicked through to the contour pixel in refined image, profile is divided into segmental arc from point of intersection, in each continuous profile
Stochastical sampling, which takes, in segmental arc a little brings elliptic equation into and finds out parameter value；The SHAPE DETECTION of circular stamp and the shape of elliptical seal are examined
The method of survey is identical.
(4) seal is found out the location of in image to be identified, and single seal is separated.
Preferably, the step 5 specifically includes the following steps:
(1) the Harris angle point for extracting the seal image extracted in original seal and step 4, is matched, according to matching
Angle point to transformation matrix is found out, complete preliminary registration；
(2) two seal images are subjected in small angle range rotation and translation, search for optimum position, completed essence and match
It is quasi-.
Preferably, the principal-employment in the step 6 refers to number of pixels of the original seal image more than seal image to be measured, bears
Difference refers to the original seal image number of pixels fewer than seal image to be measured.
Preferably, it in the step 2, is obtained using se ed filling algorithm maximum in the image to be identified in original image
Surround the profile of frame.
Beneficial effects of the present invention:
The present invention proposes a kind of method for separating seal from image and calibrating seal, realizes that seal is separated with image, energy
The preliminary judgement seal true and false enough automated.
Detailed description of the invention
Fig. 1 is the separation seal of the invention from image and calibrates seal work flow diagram.
Specific embodiment
Below according to attached drawing and preferred embodiment the present invention is described in detail, the objects and effects of the present invention will become brighter
White, below in conjunction with drawings and examples, the present invention will be described in further detail.It should be appreciated that described herein specific
Embodiment is only used to explain the present invention, is not intended to limit the present invention.
As shown in Figure 1, a kind of method for separating seal from image and calibrating seal, specifically comprises the following steps:
Step 1: establishing the data set of original official seal；
A plurality of types of images of high quality are obtained by way of scanning or taking pictures, the official seal image in interception image
Rectangular profile establishes the data set of original official seal；
Step 2: the profile of the maximum enclosure frame of the image to be identified in original image is obtained using se ed filling algorithm, it is right
Image to be identified carries out slant correction；
The all of the profile of maximum enclosure frame in original image to be identified are extracted by the method that Hough transform detects straight line
Straight line, the minimum angle of all straight lines and horizontal direction of choosing the profile of maximum enclosure frame are that rotation angle is corrected；
Step 3: by image to be identified by RGB color model conversation to HSI color space model, using threshold value control
Preparation method extracts red component, and color image gray processing；
In HSI spatial model, red component coloration variation be 0 ° to 20 ° and 340 ° to 360 °, when angle this two
When in a section, the cosine value of coloration is greater than 0.94.
If all pixels point comes out, in the image after red component extraction process comprising seal image and other
Red interference information, such as red text, red icon.In addition to seal feature angle point also has others in image
Feature angle point is detected, if directly extracting angle point on such an image as registration foundation, it will seriously affect registration
Precision, so being limited to image angle point grid region before registration operation execution, needing to be accurately positioned out seal and surveying
Attempt the position as in, to reduce the interference of noise as far as possible.
Step 4: shape is carried out using image of oval, the round and three kinds of SHAPE DETECTION algorithms of rectangle to step 3 gray processing
Detection, to position the position for obtaining the smallest rectangular profile and official seal of surrounding official seal in image to be identified, and will packet
The smallest rectangular profile for enclosing official seal is separated from image to be identified；
(1) gray level image for obtaining step 3 is converted into bianry image；
(2) image thinning algorithm is used, obtains skeleton drawing from bianry image；
(3) oval, round and three kinds of SHAPE DETECTION algorithms of rectangle are respectively adopted, SHAPE DETECTION are carried out to skeleton drawing, wherein
The SHAPE DETECTION of rectangular seal is detected to the criterion of digital straight line and the feature of digital straight line, is minimum single with line segment member
Position construction straight line, after detecting all straight lines, the rectangle in image is quickly oriented by comparing the length of straight line and direction；
The SHAPE DETECTION of elliptical seal is detected using the thought divided based on curve arc, according to connectivity mutual between profile point
Line trace is clicked through to the contour pixel in refined image, profile is divided into segmental arc from point of intersection, in each continuous profile
Stochastical sampling, which takes, in segmental arc a little brings elliptic equation into and finds out parameter value；The SHAPE DETECTION of circular stamp and the shape of elliptical seal are examined
The method of survey is identical.
(4) seal is found out the location of in image to be identified, and single seal is separated.
Seal positioning refers to the geometric characteristic according to seal, determines seal present position in the picture, obtains single
Seal image, the positioning of seal image can reduce the number of useless feature angle point, greatly reduce the calculation amount of subsequent processing,
Improve the accuracy and speed of registration operation.
Step 5: using the method based on Harris corner feature to the seal image extracted in original seal and step 4 into
Then the preliminary registration that line position is set carries out rotation and translation to two seals again in small angle range, search for optimum position,
Complete accuracy registration；
(1) the Harris angle point for extracting the seal image extracted in original seal and step 4, is matched, according to matching
Angle point to transformation matrix is found out, complete preliminary registration；
(2) two seal images are subjected in small angle range rotation and translation, search for optimum position, completed essence and match
It is quasi-.
The position of seal image to be measured and reserved seal image is not corresponding, so directly cannot be compared and divide
Analysis.Seal registration refers to the point in seal image to be measured according to certain space reflection relationship map into reserved seal image.
Certain existing rotation and translation relation between seal to be measured and reserved seal after extraction, in the identification for carrying out seal to be measured
Before, first this two images is registrated.What the precision of seal image registration directly determined subsequent seal similarity calculation can
By property.
Step 6: by principal-employment and minus tolerance quantification registration result, it is true tentatively to judge seal by calculating difference image
Seal to be measured is divided into consistent seal and suspicious seal by puppet.
Preset threshold value is both less than by setting principal-employment and minus tolerance, is calculated difference image and is tentatively judged the seal true and false, it will be to
It surveys seal and is divided into consistent seal and suspicious seal.Principal-employment refers to number of pixels of the reserved seal image more than seal image to be measured,
Minus tolerance refers to the reserved seal image number of pixels fewer than seal image to be measured.
It will appreciated by the skilled person that being not used to limit the foregoing is merely the preferred embodiment of invention
System invention, although invention is described in detail referring to previous examples, for those skilled in the art, still
It can modify to the technical solution of aforementioned each case history or equivalent replacement of some of the technical features.It is all
Within the spirit and principle of invention, modification, equivalent replacement for being made etc. be should be included within the protection scope of invention.
Claims (5)
1. a kind of method for separating seal from image and calibrating seal, which is characterized in that this method comprises the following steps:
Step 1: establishing the data set of original official seal；
Step 2: obtaining the profile of the maximum enclosure frame of the image to be identified in original image, incline to image to be identified
Tiltedly correction；
Step 3: by image to be identified by RGB color model conversation to HSI color space model, using threshold value control methods
Red component is extracted, and color image gray processing；
Step 4: SHAPE DETECTION is carried out using image of oval, the round and three kinds of SHAPE DETECTION algorithms of rectangle to step 3 gray processing,
To position the position for obtaining the smallest rectangular profile and official seal of surrounding official seal in image to be identified, and official seal will be surrounded
The smallest rectangular profile separated from image to be identified；
Step 5: position is carried out to the seal image extracted in original seal and step 4 using the method based on Harris corner feature
Then the preliminary registration set carries out rotation and translation to two seals again in small angle range, search for optimum position, completes
Accuracy registration；
Step 6: by principal-employment and minus tolerance quantification registration result, the seal true and false tentatively is judged by calculating difference image, it will
Seal to be measured is divided into consistent seal and suspicious seal.
2. the method according to claim 1 for separating seal from image and calibrating seal, which is characterized in that the step
In rapid 4 specifically includes the following steps:
(1) gray level image for obtaining step 3 is converted into bianry image；
(2) image thinning algorithm is used, obtains skeleton drawing from bianry image；
(3) oval, round and three kinds of SHAPE DETECTION algorithms of rectangle are respectively adopted, SHAPE DETECTION is carried out to skeleton drawing, wherein rectangle
The SHAPE DETECTION of seal is detected to the criterion of digital straight line and the feature of digital straight line, using line segment member as minimum unit structure
Straight line is made, after detecting all straight lines, the rectangle in image is quickly oriented by comparing the length of straight line and direction；It is oval
The SHAPE DETECTION of seal is detected using the thought divided based on curve arc, according to connectivity mutual between profile point to thin
The contour pixel changed in image clicks through line trace, profile is divided into segmental arc from point of intersection, in each continuous profile segmental arc
Middle stochastical sampling, which takes, a little brings elliptic equation into and finds out parameter value；The SHAPE DETECTION of the SHAPE DETECTION and elliptical seal of circular stamp
Method is identical.
(4) seal is found out the location of in image to be identified, and single seal is separated.
3. a kind of extraction separation method based on official seal on bill classification and bill according to claim 1, feature
Be: the step 5 specifically includes the following steps:
(1) the Harris angle point for extracting the seal image extracted in original seal and step 4, is matched, according to matched angle
Point completes preliminary registration to transformation matrix is found out；
(2) two seal images are subjected in small angle range rotation and translation, search for optimum position, complete essence registration.
4. the method according to claim 1 for separating seal from image and calibrating seal, it is characterised in that: the step
Principal-employment in rapid 6 refers to that number of pixels of the original seal image more than seal image to be measured, minus tolerance refer to original seal image than to be measured
The few number of pixels of seal image.
5. the method according to claim 1 for separating seal from image and calibrating seal, it is characterised in that: the step
In rapid 2, the profile of maximum enclosure frame in the image to be identified in original image is obtained using se ed filling algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811257669.3A CN109447068A (en) | 2018-10-26 | 2018-10-26 | A method of it separating seal from image and calibrates seal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811257669.3A CN109447068A (en) | 2018-10-26 | 2018-10-26 | A method of it separating seal from image and calibrates seal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109447068A true CN109447068A (en) | 2019-03-08 |
Family
ID=65548640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811257669.3A Pending CN109447068A (en) | 2018-10-26 | 2018-10-26 | A method of it separating seal from image and calibrates seal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109447068A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084229A (en) * | 2019-03-25 | 2019-08-02 | 科大讯飞股份有限公司 | A kind of seal detection method, device, equipment and readable storage medium storing program for executing |
| CN110472623A (en) * | 2019-06-29 | 2019-11-19 | 华为技术有限公司 | Image detecting method, equipment and system |
| CN110765992A (en) * | 2019-09-23 | 2020-02-07 | 厦门大学 | Seal identification method, medium, equipment and device |
| CN111191657A (en) * | 2019-11-19 | 2020-05-22 | 泰康保险集团股份有限公司 | Character recognition method and device and computer readable storage medium |
| CN111291757A (en) * | 2020-02-17 | 2020-06-16 | 江苏诚印科技有限公司 | Method for identifying uniqueness of seal |
| CN111325722A (en) * | 2020-02-17 | 2020-06-23 | 江苏诚印科技有限公司 | Stamp image accurate identification method, stamp image identification processing method and stamp image identification system |
| CN111507338A (en) * | 2020-04-15 | 2020-08-07 | 广西科技大学 | Chinese chess piece identification method based on binary image skeleton similarity calculation |
| CN111950353A (en) * | 2020-06-30 | 2020-11-17 | 深圳市雄帝科技股份有限公司 | Seal text recognition method and device and electronic equipment |
| CN111950355A (en) * | 2020-06-30 | 2020-11-17 | 深圳市雄帝科技股份有限公司 | Seal identification method and device and electronic equipment |
| CN112257712A (en) * | 2020-10-29 | 2021-01-22 | 湖南星汉数智科技有限公司 | Train ticket image rectification method and device, computer device and computer readable storage medium |
| CN113469888A (en) * | 2021-07-08 | 2021-10-01 | 江西金格科技股份有限公司 | Method and device for correcting inclination angle of circular electronic seal |
| CN113486901A (en) * | 2021-06-23 | 2021-10-08 | 内江师范学院 | Novel high-imitation round seal identification method |
| CN113705330A (en) * | 2021-07-08 | 2021-11-26 | 厦门科路德科技有限公司 | Seal authenticity identification method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101008985A (en) * | 2007-01-18 | 2007-08-01 | 章毅 | Seal identification system and controlling method thereof |
| CN101533517A (en) * | 2009-04-15 | 2009-09-16 | 北京联合大学 | Structure feature based on Chinese painting and calligraphy seal image automatic extracting method |
| CN102054168A (en) * | 2010-12-23 | 2011-05-11 | 武汉大学苏州研究院 | Method for recognizing circular seal on valuable bill |
| CN104008369A (en) * | 2014-05-16 | 2014-08-27 | 四川大学 | Method and device for recognizing authenticity of seal |
| CN104239870A (en) * | 2014-09-25 | 2014-12-24 | 哈尔滨工业大学 | Curve arc segmentation based ellipse detection method |
| CN105574521A (en) * | 2016-02-25 | 2016-05-11 | 民政部国家减灾中心 | House contour extraction method and apparatus thereof |
| CN107710229A (en) * | 2016-10-20 | 2018-02-16 | 深圳配天智能技术研究院有限公司 | Shape recognition process, device, equipment and computer-readable storage medium in image |
-
2018
- 2018-10-26 CN CN201811257669.3A patent/CN109447068A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101008985A (en) * | 2007-01-18 | 2007-08-01 | 章毅 | Seal identification system and controlling method thereof |
| CN101533517A (en) * | 2009-04-15 | 2009-09-16 | 北京联合大学 | Structure feature based on Chinese painting and calligraphy seal image automatic extracting method |
| CN102054168A (en) * | 2010-12-23 | 2011-05-11 | 武汉大学苏州研究院 | Method for recognizing circular seal on valuable bill |
| CN104008369A (en) * | 2014-05-16 | 2014-08-27 | 四川大学 | Method and device for recognizing authenticity of seal |
| CN104239870A (en) * | 2014-09-25 | 2014-12-24 | 哈尔滨工业大学 | Curve arc segmentation based ellipse detection method |
| CN105574521A (en) * | 2016-02-25 | 2016-05-11 | 民政部国家减灾中心 | House contour extraction method and apparatus thereof |
| CN107710229A (en) * | 2016-10-20 | 2018-02-16 | 深圳配天智能技术研究院有限公司 | Shape recognition process, device, equipment and computer-readable storage medium in image |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110084229B (en) * | 2019-03-25 | 2021-10-08 | 科大讯飞股份有限公司 | Seal detection method, device and equipment and readable storage medium |
| CN110084229A (en) * | 2019-03-25 | 2019-08-02 | 科大讯飞股份有限公司 | A kind of seal detection method, device, equipment and readable storage medium storing program for executing |
| CN110472623A (en) * | 2019-06-29 | 2019-11-19 | 华为技术有限公司 | Image detecting method, equipment and system |
| CN110472623B (en) * | 2019-06-29 | 2022-08-09 | 华为技术有限公司 | Image detection method, device and system |
| CN110765992A (en) * | 2019-09-23 | 2020-02-07 | 厦门大学 | Seal identification method, medium, equipment and device |
| CN110765992B (en) * | 2019-09-23 | 2023-03-24 | 厦门大学 | Seal identification method, medium, equipment and device |
| CN111191657A (en) * | 2019-11-19 | 2020-05-22 | 泰康保险集团股份有限公司 | Character recognition method and device and computer readable storage medium |
| CN111191657B (en) * | 2019-11-19 | 2023-08-18 | 泰康保险集团股份有限公司 | Character recognition method, device and computer readable storage medium |
| CN111325722A (en) * | 2020-02-17 | 2020-06-23 | 江苏诚印科技有限公司 | Stamp image accurate identification method, stamp image identification processing method and stamp image identification system |
| CN111291757B (en) * | 2020-02-17 | 2023-08-15 | 江苏诚印科技有限公司 | Method for uniquely identifying seal |
| CN111325722B (en) * | 2020-02-17 | 2024-02-20 | 江苏诚印科技有限公司 | Seal image accurate identification method and system and seal image identification processing method |
| CN111291757A (en) * | 2020-02-17 | 2020-06-16 | 江苏诚印科技有限公司 | Method for identifying uniqueness of seal |
| CN111507338A (en) * | 2020-04-15 | 2020-08-07 | 广西科技大学 | Chinese chess piece identification method based on binary image skeleton similarity calculation |
| CN111950353A (en) * | 2020-06-30 | 2020-11-17 | 深圳市雄帝科技股份有限公司 | Seal text recognition method and device and electronic equipment |
| CN111950355A (en) * | 2020-06-30 | 2020-11-17 | 深圳市雄帝科技股份有限公司 | Seal identification method and device and electronic equipment |
| CN111950353B (en) * | 2020-06-30 | 2024-04-19 | 深圳市雄帝科技股份有限公司 | Seal text recognition method and device and electronic equipment |
| CN112257712A (en) * | 2020-10-29 | 2021-01-22 | 湖南星汉数智科技有限公司 | Train ticket image rectification method and device, computer device and computer readable storage medium |
| CN112257712B (en) * | 2020-10-29 | 2024-02-27 | 湖南星汉数智科技有限公司 | Train ticket image alignment method and device, computer device and computer readable storage medium |
| CN113486901B (en) * | 2021-06-23 | 2023-05-02 | 内江师范学院 | Novel high imitation round seal identification method |
| CN113486901A (en) * | 2021-06-23 | 2021-10-08 | 内江师范学院 | Novel high-imitation round seal identification method |
| CN113705330A (en) * | 2021-07-08 | 2021-11-26 | 厦门科路德科技有限公司 | Seal authenticity identification method and system |
| CN113705330B (en) * | 2021-07-08 | 2023-12-01 | 厦门科路德科技有限公司 | Seal authenticity identification method and system |
| CN113469888A (en) * | 2021-07-08 | 2021-10-01 | 江西金格科技股份有限公司 | Method and device for correcting inclination angle of circular electronic seal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109447068A (en) | A method of it separating seal from image and calibrates seal | |
| CN105913093B (en) | A kind of template matching method for Text region processing | |
| CN107688806B (en) | Affine transformation-based free scene text detection method | |
| CN109034047A (en) | A kind of method for detecting lane lines and device | |
| CN109426814B (en) | Method, system and equipment for positioning and identifying specific plate of invoice picture | |
| CN111814686A (en) | Vision-based power transmission line identification and foreign matter invasion online detection method | |
| CN103824091B (en) | A kind of licence plate recognition method for intelligent transportation system | |
| CN110298281B (en) | Video structuring method and device, electronic equipment and storage medium | |
| Xu | Robust traffic sign shape recognition using geometric matching | |
| CN110032946B (en) | Aluminum/aluminum blister packaging tablet identification and positioning method based on machine vision | |
| CN109829458B (en) | Method for automatically generating log file for recording system operation behavior in real time | |
| CN110378351B (en) | Seal identification method and device | |
| TWI745204B (en) | High-efficiency LiDAR object detection method based on deep learning | |
| CN103699876B (en) | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images | |
| CN110119742A (en) | A kind of recognition methods of container number, device and mobile terminal | |
| CN112784835A (en) | Method and device for identifying authenticity of circular seal, electronic equipment and storage medium | |
| CN110675442A (en) | Local stereo matching method and system combined with target identification technology | |
| CN109753981B (en) | Image recognition method and device | |
| CN112396582B (en) | Mask RCNN-based equalizing ring skew detection method | |
| US9727780B2 (en) | Pedestrian detecting system | |
| Khin et al. | License plate detection of Myanmar vehicle images captured from the dissimilar environmental conditions | |
| CN113053164A (en) | Parking space identification method using look-around image | |
| CN106845498A (en) | With reference to the single width mountain range remote sensing images landslide detection method of elevation | |
| CN110969135A (en) | Vehicle logo recognition method in natural scene | |
| CN104408430B (en) | License plate positioning method and device |
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: Xinyada technology building, 3888 Jiangnan Avenue, Binjiang District, Hangzhou City, Zhejiang Province 310051 Applicant after: Sinyada Technology Co.,Ltd. Address before: Xinyada technology building, 3888 Jiangnan Avenue, Binjiang District, Hangzhou City, Zhejiang Province 310051 Applicant before: SUNYARD SYSTEM ENGINEERING Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |
|
| RJ01 | Rejection of invention patent application after publication |