CN112580648A - Method for realizing image information identification based on image segmentation technology - Google Patents
Method for realizing image information identification based on image segmentation technology Download PDFInfo
- Publication number
- CN112580648A CN112580648A CN202011467194.8A CN202011467194A CN112580648A CN 112580648 A CN112580648 A CN 112580648A CN 202011467194 A CN202011467194 A CN 202011467194A CN 112580648 A CN112580648 A CN 112580648A
- Authority
- CN
- China
- Prior art keywords
- image
- information
- target
- standard
- segmentation
- 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 23
- 238000003709 image segmentation Methods 0.000 title claims abstract description 17
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- 230000011218 segmentation Effects 0.000 claims abstract description 28
- 238000007781 pre-processing Methods 0.000 claims description 14
- 230000008030 elimination Effects 0.000 claims description 11
- 238000003379 elimination reaction Methods 0.000 claims description 11
- 238000012937 correction Methods 0.000 claims description 9
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000000638 solvent extraction Methods 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Input (AREA)
Abstract
The invention relates to a method for realizing image information identification based on an image segmentation technology, which comprises the steps of partitioning each feature or information in a standard image according to the type of the standard image to obtain a segmentation model of each partitioned feature or information; determining a target identified by the target image information, and determining corresponding block characteristics or information according to the target; according to the segmentation model of the block characteristics or the information, segmenting the preprocessed target image according to the corresponding segmentation line, and extracting the required image block; the invention divides the boundary region based on the target image type, divides the boundary region into a plurality of regions with independent information or characteristics, and only needs to be in the image of the plate block of the corresponding region when the image is identified, thereby greatly reducing the image processing time and improving the image identification speed.
Description
Technical Field
The invention relates to the field of image recognition, in particular to a method for realizing image information recognition based on an image segmentation technology.
Background
Image recognition, which refers to a technique for processing, analyzing and understanding images by a computer to recognize various different patterns of objects and objects, is a practical application of applying a deep learning algorithm. The image recognition technology at the present stage is generally divided into face recognition and commodity recognition, wherein the face recognition is mainly applied to security inspection, identity verification and mobile payment, and the commodity recognition is mainly applied to the commodity circulation process, in particular to the field of unmanned retail such as unmanned goods shelves and intelligent retail cabinets. The traditional image identification process is divided into four steps: image acquisition → image preprocessing → feature extraction → image recognition. The image recognition software is represented by the health and the endurance and the like at foreign countries, and is represented by the map intelligence, the deep sea science and technology and the like at home. In addition, the technology refers to the technology for classifying remote sensing images in geography.
At present, when image feature extraction is performed, image content must be identified, that is, image preprocessing is performed, and features are performed according to feature models in full image information, which makes preprocessing of images necessary to include the entire content of images, which makes the amount of image preprocessing information excessively large, and especially, image identification under some images and data with large pictures causes a large computational load, and also reduces the speed of image identification.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for realizing image information identification based on an image segmentation technology.
The purpose of the invention is realized by the following technical scheme:
a method for realizing image information identification based on an image segmentation technology comprises the following steps:
s100: constructing an image segmentation model, segmenting each feature or information in the standard image according to the type of the standard image, segmenting the standard image according to the position relation of each segmented feature or information in the standard image, and determining a segmentation line corresponding to each segmented feature or information to obtain a segmentation model of each segmented feature or information;
s200: preprocessing a target image, namely scaling the target image needing information identification to form a preprocessed target image with the size consistent with that of a standard object;
s300: determining a target identified by the target image information, and determining corresponding block characteristics or information according to the target;
s400: according to the segmentation model of the block characteristics or the information, segmenting the preprocessed target image according to the corresponding segmentation line, and extracting the required image block;
s500: and carrying out information identification on the image blocks to obtain target information.
Further, the scaling in S200 is to put the target image and the standard image in the same coordinate system to be scaled according to a 1:1 ratio.
Further, the target image preprocessing in S200 further includes an image interference elimination, where the image interference elimination includes image angle correction, image background or peripheral information elimination, image incomplete completion, and sharpness correction.
Further, the image angle correction means that the target image is rotated to be identical to the standard image and located at the same coordinate point in the same coordinate system.
Further, the image background or surrounding information elimination refers to deleting information or features irrelevant to the standard image content.
Further, the image incomplete filling refers to filling the incomplete part in the image, and the filled part mainly comprises general images and characters in the target image.
Further, in the step S400, the segmentation of the pre-processing target image is performed by extracting and segmenting coordinates of each end point of a segmentation line enclosing the image blocks.
The invention has the beneficial effects that: according to the scheme, the original target image is segmented according to the required information to obtain a part of image only containing the target information, so that the calculation amount in the subsequent image identification process is reduced, meanwhile, the interference is greatly reduced because only the required image part is extracted, the segmentation of the image is realized based on the coordinate position, the content in the image does not need to be identified, the segmentation mode is simple and easy to realize in operation, and the calculation amount is further reduced.
Detailed Description
The technical solution of the present invention is further described in detail with reference to the following specific examples, but the scope of the present invention is not limited to the following.
A method for realizing image information identification based on an image segmentation technology comprises the following steps:
s100: constructing an image segmentation model, segmenting each feature or information in the standard image according to the type of the standard image, segmenting the standard image according to the position relation of each segmented feature or information in the standard image, and determining a segmentation line corresponding to each segmented feature or information to obtain a segmentation model of each segmented feature or information;
s200: preprocessing a target image, namely scaling the target image needing information identification to form a preprocessed target image with the size consistent with that of a standard object;
s300: determining a target identified by the target image information, and determining corresponding block characteristics or information according to the target;
s400: according to the segmentation model of the block characteristics or the information, segmenting the preprocessed target image according to the corresponding segmentation line, and extracting the required image block;
s500: and carrying out information identification on the image blocks to obtain target information.
In one embodiment, a method for implementing image information identification based on an image segmentation technology, S100: constructing an image segmentation model, segmenting each feature or information in the standard image according to the type of the standard image, segmenting the standard image according to the position relation of each segmented feature or information in the standard image, and determining a segmentation line corresponding to each segmented feature or information to obtain a segmentation model of each segmented feature or information;
s200: preprocessing a target image, namely scaling the target image needing information identification to form a preprocessed target image with the size consistent with that of a standard object; the zooming in the scheme is to put the target image and the standard image in the same coordinate system to zoom according to the proportion of 1:1
S300: determining a target identified by the target image information, and determining corresponding block characteristics or information according to the target;
s400: according to the segmentation model of the block characteristics or the information, segmenting the preprocessed target image according to the corresponding segmentation line, and extracting the required image block;
s500: and carrying out information identification on the image blocks to obtain target information.
In one embodiment, a method for implementing image information identification based on an image segmentation technology, S100: constructing an image segmentation model, segmenting each feature or information in the standard image according to the type of the standard image, segmenting the standard image according to the position relation of each segmented feature or information in the standard image, and determining a segmentation line corresponding to each segmented feature or information to obtain a segmentation model of each segmented feature or information;
s200: preprocessing a target image, namely scaling the target image needing information identification to form a preprocessed target image with the size consistent with that of a standard object; the scaling in the scheme is to put the target image and the standard image in the same coordinate system to scale according to the proportion of 1: 1. The target image preprocessing also comprises image interference elimination, wherein the image interference elimination comprises image angle correction, image background or peripheral information elimination, image incomplete completion and definition correction.
S300: determining a target identified by the target image information, and determining corresponding block characteristics or information according to the target;
s400: according to the segmentation model of the block characteristics or the information, segmenting the preprocessed target image according to the corresponding segmentation line, and extracting the required image block;
s500: optionally, the image angle correction refers to rotating the target image to the same coordinate point in the same coordinate system as the standard image.
Optionally, in the method for implementing image information identification based on the image segmentation technology, the image background or surrounding information removal refers to deletion of information or features irrelevant to the standard image content.
Optionally, the image incomplete filling refers to filling the incomplete part in the image, the filled part mainly includes general images and characters in the target image, such as national emblem patterns in an identity card, and the character filling matches based on a standard character model to fill the incomplete part of the characters, so as to enhance the accuracy in the subsequent information acquisition process.
Optionally, in the method for realizing image information identification based on an image segmentation technology, the step of segmenting the preprocessing target image in S400 is to extract and segment according to coordinates of each endpoint of a segmentation line enclosing the image blocks.
The foregoing is illustrative of the preferred embodiments of this invention, and it is to be understood that the invention is not limited to the precise form disclosed herein and that various other combinations, modifications, and environments may be resorted to, falling within the scope of the concept as disclosed herein, either as described above or as apparent to those skilled in the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. A method for realizing image information identification based on an image segmentation technology is characterized by comprising the following steps:
s100: constructing an image segmentation model, segmenting each feature or information in the standard image according to the type of the standard image, segmenting the standard image according to the position relation of each segmented feature or information in the standard image, and determining a segmentation line corresponding to each segmented feature or information to obtain a segmentation model of each segmented feature or information;
s200: preprocessing a target image, namely scaling the target image needing information identification to form a preprocessed target image with the size consistent with that of a standard object;
s300: determining a target identified by the target image information, and determining corresponding block characteristics or information according to the target;
s400: according to the segmentation model of the block characteristics or the information, segmenting the preprocessed target image according to the corresponding segmentation line, and extracting the required image block;
s500: and carrying out information identification on the image blocks to obtain target information.
2. The method of claim 1, wherein the scaling in S200 is scaling at a ratio of 1:1 by placing the target image and the standard image in the same coordinate system.
3. The method according to claim 2, wherein the target image preprocessing in S200 further includes image interference elimination, and the image interference elimination includes image angle correction, image background or peripheral information elimination, image incomplete completion, and sharpness correction.
4. The method of claim 3, wherein the image angle correction is performed by rotating the target image to be identical to the standard image and located at the same coordinate point in the same coordinate system.
5. The method of claim 4, wherein the image background or surrounding information elimination refers to deleting information or features irrelevant to standard image content.
6. The method of claim 5, wherein the image incomplete filling is performed on a incomplete part in the image, and the complete part mainly includes common images and characters in the target image.
7. The method of claim 6, wherein the step of segmenting the pre-processed target image in the step S400 is to extract and segment the pre-processed target image according to the coordinates of each end point of a segment line surrounding the image block.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011467194.8A CN112580648A (en) | 2020-12-14 | 2020-12-14 | Method for realizing image information identification based on image segmentation technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011467194.8A CN112580648A (en) | 2020-12-14 | 2020-12-14 | Method for realizing image information identification based on image segmentation technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112580648A true CN112580648A (en) | 2021-03-30 |
Family
ID=75134814
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011467194.8A Pending CN112580648A (en) | 2020-12-14 | 2020-12-14 | Method for realizing image information identification based on image segmentation technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112580648A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102096821A (en) * | 2010-04-15 | 2011-06-15 | 西安理工大学 | Number plate identification method under strong interference environment on basis of complex network theory |
CN103116902A (en) * | 2011-11-16 | 2013-05-22 | 华为软件技术有限公司 | Three-dimensional virtual human head image generation method, and method and device of human head image motion tracking |
CN103839058A (en) * | 2012-11-21 | 2014-06-04 | 方正国际软件(北京)有限公司 | Information locating method for document image based on standard template |
CN104091348A (en) * | 2014-05-19 | 2014-10-08 | 南京工程学院 | Multi-target tracking method integrating obvious characteristics and block division templates |
CN105139004A (en) * | 2015-09-23 | 2015-12-09 | 河北工业大学 | Face expression identification method based on video sequences |
CN106529429A (en) * | 2016-10-27 | 2017-03-22 | 中国计量大学 | Image recognition-based facial skin analysis system |
CN109034266A (en) * | 2018-08-16 | 2018-12-18 | 新智数字科技有限公司 | A kind of target image detection method, apparatus and system |
CN110414507A (en) * | 2019-07-11 | 2019-11-05 | 和昌未来科技(深圳)有限公司 | Licence plate recognition method, device, computer equipment and storage medium |
CN111325092A (en) * | 2019-12-26 | 2020-06-23 | 湖南星汉数智科技有限公司 | Bullet train ticket identification method and device, computer device and computer readable storage medium |
-
2020
- 2020-12-14 CN CN202011467194.8A patent/CN112580648A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102096821A (en) * | 2010-04-15 | 2011-06-15 | 西安理工大学 | Number plate identification method under strong interference environment on basis of complex network theory |
CN103116902A (en) * | 2011-11-16 | 2013-05-22 | 华为软件技术有限公司 | Three-dimensional virtual human head image generation method, and method and device of human head image motion tracking |
CN103839058A (en) * | 2012-11-21 | 2014-06-04 | 方正国际软件(北京)有限公司 | Information locating method for document image based on standard template |
CN104091348A (en) * | 2014-05-19 | 2014-10-08 | 南京工程学院 | Multi-target tracking method integrating obvious characteristics and block division templates |
CN105139004A (en) * | 2015-09-23 | 2015-12-09 | 河北工业大学 | Face expression identification method based on video sequences |
CN106529429A (en) * | 2016-10-27 | 2017-03-22 | 中国计量大学 | Image recognition-based facial skin analysis system |
CN109034266A (en) * | 2018-08-16 | 2018-12-18 | 新智数字科技有限公司 | A kind of target image detection method, apparatus and system |
CN110414507A (en) * | 2019-07-11 | 2019-11-05 | 和昌未来科技(深圳)有限公司 | Licence plate recognition method, device, computer equipment and storage medium |
CN111325092A (en) * | 2019-12-26 | 2020-06-23 | 湖南星汉数智科技有限公司 | Bullet train ticket identification method and device, computer device and computer readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109934110B (en) | Method for identifying illegal buildings near river channel | |
CN110334762B (en) | Feature matching method based on quad tree combined with ORB and SIFT | |
CN110348264A (en) | A kind of QR image in 2 D code bearing calibration and system | |
CN110991258B (en) | Face fusion feature extraction method and system | |
CN105069754A (en) | System and method for carrying out unmarked augmented reality on image | |
CN110502977B (en) | Building change classification detection method, system, device and storage medium | |
CN110503682B (en) | Rectangular control identification method and device, terminal and storage medium | |
CN111680690A (en) | Character recognition method and device | |
CN113989604A (en) | Tire DOT information identification method based on end-to-end deep learning | |
CN113378837A (en) | License plate shielding identification method and device, electronic equipment and storage medium | |
CN116798041A (en) | Image recognition method and device and electronic equipment | |
CN111968104A (en) | Machine vision-based steel coil abnormity identification method, system, equipment and medium | |
CN109191489B (en) | Method and system for detecting and tracking aircraft landing marks | |
CN112580648A (en) | Method for realizing image information identification based on image segmentation technology | |
CN111079749A (en) | End-to-end commodity price tag character recognition method and system with attitude correction function | |
CN112183556B (en) | Port ore heap contour extraction method based on spatial clustering and watershed transformation | |
CN112749713A (en) | Big data image recognition system and method based on artificial intelligence | |
Milevskiy et al. | A fast algorithm for korean text extraction and segmentation from subway signboard images utilizing smartphone sensors | |
CN114330708A (en) | Neural network training method, system, medium and device based on point cloud data | |
CN111079792A (en) | Power equipment identification method and device | |
CN102938156B (en) | Planar note configuration method based on integral images | |
CN110737364A (en) | Control method for touch writing acceleration under android systems | |
CN114782459B (en) | Spliced image segmentation method, device and equipment based on semantic segmentation | |
CN112232348B (en) | Oracle identification method and system based on machine vision | |
CN117037049B (en) | Image content detection method and system based on YOLOv5 deep learning |
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: 20210330 |