CN111160091B - Intelligent image comparison system and method for supply chain - Google Patents
Intelligent image comparison system and method for supply chain Download PDFInfo
- Publication number
- CN111160091B CN111160091B CN201911156893.8A CN201911156893A CN111160091B CN 111160091 B CN111160091 B CN 111160091B CN 201911156893 A CN201911156893 A CN 201911156893A CN 111160091 B CN111160091 B CN 111160091B
- Authority
- CN
- China
- Prior art keywords
- image
- comparison
- supply chain
- platform
- comparison result
- 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
Images
Classifications
-
- 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
- G06V30/413—Classification of content, e.g. text, photographs or tables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/5846—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using extracted text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Character Discrimination (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a supply chain intelligent image comparison system and a supply chain intelligent image comparison method, wherein a sample library, a project information list and a right-confirming bill of materials are collected through a first platform and pushed to an open platform; a set path pushed to a supply chain server by using a back-end service of an open platform; the method comprises the steps that a supply chain server scans by adopting a timing service, a file list obtained by scanning is stored in a database, an image obtaining request is initiated, and the image obtaining request downloads an image piece from a cloud server of a first platform through an open platform gateway; the supply chain server receives the image piece, invokes the image intelligent recognition service through the ESB enterprise bus to perform image comparison, obtains a comparison result, returns the comparison result to the supply chain server, stores the comparison result, and transmits the comparison result to the first platform through the open platform. The OCR intelligent recognition comparison is adopted, so that the flow requirement of manual offline auditing of face videos and signature photo materials is eliminated, and the labor cost and time cost are greatly reduced.
Description
Technical Field
The invention relates to the technical field of intelligent identification, in particular to a supply chain intelligent image comparison system and method.
Background
Image recognition
The Chinese OCR and optical symbol recognition technology is an automatic input mode of Chinese character manuscript, and through the cooperation of optical scanner and computer, the image data is converted into computer internal code after being calculated and classified by OCR software, so that the intensity of data input work can be greatly reduced, and the data input speed can be raised. The research work of China in the aspect of OCR technology is relatively late, traditional text type OCR software mainly comprises Qinghua text TH-OCR, beixin BI-OCR, chinese self ICR, shenyang Automation SY-OCR, beijing eosin NI-OCR and the like, and a matched scanner is a flat bed scanner on the market.
Traditional OCR image recognition is limited by recognition scenes at first, and the current technology is more limited by the recognition of scanning pieces; the scene photographed by the mobile phone on the existing service cannot be well processed, and a proprietary camera is matched with the scene photographed by the mobile phone on the existing service, so that the definition and format of an input image are ensured; secondly, the method is limited by the number of grabbing features, compared with feature grabbing of a neural network, the traditional technology has poor precision, and the recognition precision of nonstandard files with complex interference, handwriting and the like is low; furthermore, the problems of the image such as the format and the direction are limited, the traditional technology can only process the text type recognition of a fixed format, and the method is very limited for scenes of various formats.
For example, patent document CN109543614a discloses a full text difference comparison method, which includes the following steps: the comparison part and the original part recognize the characters through an OCR recognition engine and generate a recognition text, wherein the recognition text comprises coordinates corresponding to the characters; the identification text adopts a text comparison algorithm to compare the difference text, and the coordinates of the difference text are obtained; the difference text is located and then marked in the comparison.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a supply chain intelligent image comparison system and method.
The invention provides a supply chain intelligent image comparison system, which comprises:
sample module: collecting a sample library, a project information list and a right-confirming bill of materials through a first platform, pushing the sample library, the project information list and the right-confirming bill of materials to an open platform, and storing the sample library, the project information list and the right-confirming bill of materials as file lists;
and the pushing module is used for: pushing the file list to a set path of a supply chain server by utilizing a back-end service of the open platform;
a request module: the method comprises the steps that a supply chain server scans a file list by adopting a timing service, stores the scanned file list into a database, and initiates an image acquisition request according to an address in the file list, wherein the image acquisition request downloads an image piece from a cloud server of a first platform through an open platform gateway;
comparison module: the supply chain server receives the image piece, invokes the image intelligent recognition service through the ESB enterprise bus to perform image comparison, obtains a comparison result, returns the comparison result to the supply chain server, stores the comparison result, and transmits the comparison result to the first platform through the open platform.
Preferably, the supply chain intelligent image comparison system further comprises a display module for displaying the comparison result aiming at each transaction in the file list, displaying the comparison result in a list mode, and providing detailed information of the second-level menu viewing comparison result.
Preferably, the comparison module includes:
and (5) accessing the comparison module: receiving an image piece, downloading an image to be confirmed to an image platform according to the ID of the file to be confirmed of the image piece, and associating an image sample in the image piece with the image to be confirmed;
task scheduling module: decoupling the dependence degree of the comparison algorithm by an RPC series scheduling comparison algorithm, and realizing synchronous or asynchronous interface call according to the requirement;
and a pretreatment module: based on detection, rotation and classification of the image area of deep learning, processing the right-confirming image and providing a first RPC interface call;
signature detection module: based on the detection of the deep-learning handwriting signature area, signature detection is carried out on the right-confirming image, the detected signature and corresponding position information are returned, and a second RPC interface call is provided;
signature comparison module: based on the text recognition of the deep learning, performing text region recognition on the right-confirming image to obtain text content, and providing a third RPC interface call;
and a result output module: outputting the comparison result obtained by detection in the form of structured data, and providing a fourth RPC interface call.
Preferably, the image piece received by the supply chain server is uploaded to the image platform in a load balancing mode, and the image platform returns an image ID to the supply chain server after storing the image piece, wherein the image ID is a unique identification mark of the image piece.
Preferably, after receiving the image piece, the supply chain server provides version management for the image sample in the image piece, wherein the version management comprises adding, modifying, deleting and checking details; the comparison results comprise consistency, inconsistency and need to be checked manually.
The invention provides a supply chain intelligent image comparison method, which comprises the following steps:
sample steps: collecting a sample library, a project information list and a right-confirming bill of materials through a first platform, pushing the sample library, the project information list and the right-confirming bill of materials to an open platform, and storing the sample library, the project information list and the right-confirming bill of materials as file lists;
pushing: pushing the file list to a set path of a supply chain server by utilizing a back-end service of the open platform;
the request steps are as follows: the method comprises the steps that a supply chain server scans a file list by adopting a timing service, stores the scanned file list into a database, and initiates an image acquisition request according to an address in the file list, wherein the image acquisition request downloads an image piece from a cloud server of a first platform through an open platform gateway;
and (3) comparison: the supply chain server receives the image piece, invokes the image intelligent recognition service through the ESB enterprise bus to perform image comparison, obtains a comparison result, returns the comparison result to the supply chain server, stores the comparison result, and transmits the comparison result to the first platform through the open platform.
Preferably, the method for comparing the intelligent images of the supply chain further comprises a display step, wherein the comparison result is displayed for each transaction in the file list, and is displayed in a list mode, and the detailed information of the comparison result is viewed through a secondary menu.
Preferably, the step of comparing includes:
and (3) access comparison: receiving an image piece, downloading an image to be confirmed to an image platform according to the ID of the file to be confirmed of the image piece, and associating an image sample in the image piece with the image to be confirmed;
task scheduling: decoupling the dependence degree of the comparison algorithm by an RPC series scheduling comparison algorithm, and realizing synchronous or asynchronous interface call according to the requirement;
pretreatment: based on detection, rotation and classification of the image area of deep learning, processing the right-confirming image and providing a first RPC interface call;
signature detection: based on the detection of the deep-learning handwriting signature area, signature detection is carried out on the right-confirming image, the detected signature and corresponding position information are returned, and a second RPC interface call is provided;
signature comparison: based on the text recognition of the deep learning, performing text region recognition on the right-confirming image to obtain text content, and providing a third RPC interface call;
and outputting a result: outputting the comparison result obtained by detection in the form of structured data, and providing a fourth RPC interface call.
Compared with the prior art, the invention has the following beneficial effects:
1. the OCR intelligent recognition is adopted, 360-degree rotation recognition can be carried out, the correlation comparison can be set for the sample and carried out according to the corresponding relation, the video comparison adopts the frame capturing technology to screen the face and carry out the comparison, the flow requirement of checking the face video and signing photo materials under the manual line is avoided, and the labor cost and the time cost are greatly reduced.
2. The supply chain sample information management function is adopted to solve the problem of sample change management, including the addition, modification, deletion and detail viewing of the image samples.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a schematic diagram of a system framework of the present invention;
fig. 2 is a schematic diagram of a data architecture according to the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present invention.
Aiming at the videos of the project sample library and the project site right-confirming handwriting signature, the photos and the signatures of the right-confirming person are intercepted from the site videos, and are compared with the photos and the bank seal of the right-confirming person in the sample library based on an AI algorithm, and a comparison result which is consistent, inconsistent and needs to be checked manually is returned. The processing procedure of the AI algorithm mainly comprises three modules: hand-written signature detection and comparison, dynamic face detection and comparison, hand-written receipt recognition and structured output: developing a handwritten signature of a receipt, a detection and comparison model of a handwritten text based on Fast R-CNN, performing special training on the signature, the face and the handwritten font through a specific data set, and accurately completing signature region positioning through three processes of feature extraction, interest point retrieval, classification and regression; and comparing the characteristic values and checking the consistency through an ArcFace algorithm, and outputting a service judgment result.
The method comprises the steps that a first platform collects a sample library, a project information list and a right-confirming bill of materials, and pushes the sample library, the project information list and the right-confirming bill of materials to an open platform to be stored as a file list; pushing the file list to a set path of a supply chain server by utilizing a back-end service of the open platform; the method comprises the steps that a supply chain server scans a file list by adopting a timing service, stores the scanned file list into a database, and initiates an image acquisition request according to an address in the file list, wherein the image acquisition request downloads an image piece from a cloud server of a first platform through an open platform gateway; the supply chain server receives the image piece, invokes the image intelligent recognition service through the ESB enterprise bus to perform image comparison, obtains a comparison result, returns the comparison result to the supply chain server, stores the comparison result, and transmits the comparison result to the first platform through the open platform.
In specific use, the first platform adopts a partner platform, the cloud server of the first platform adopts an Arian cloud, as shown in fig. 1, the partner platform pushes a sample library, a project information list and a confirmation bill of materials to an open platform, a back-end server of the open platform pushes a file list containing image project information to be compared to a specific path of a supply chain, the project information comprises project ID, payment bill number, bill number and file URL information, the supply chain adopts a timing task to scan a file and stores the file into a database on the own side, and meanwhile, an image acquisition request is initiated according to an address in the list, and the request downloads an image part from the Arian cloud through a gateway of the open platform.
The method comprises the steps that a supply chain uploads downloaded samples and right-confirming images, one or more samples belong to a sample library, the samples are regarded as reference standards for comparison, the right-confirming images are images to be compared, the images downloaded from an Arian cloud comprise the samples and the right-confirming images, and the samples and the right-confirming images have association relations. The supply chain uploads the image to the server through load balancing of the image platform and returns image ID information, specifically, the supply chain uploads the image to the image platform and acquires its generated image ID, and the supply chain database stores the image ID but does not store the image itself. The image ID information is used for being provided for an image intelligent recognition service by a supply chain, the image intelligent recognition service downloads images on an image platform according to the image ID information and then is used for comparison, the image intelligent recognition service adopts an OCR service, and the OCR service is a specific application in the aspect of face recognition of characters and videos.
The supply chain calls the intelligent image recognition service through the ESB enterprise bus to perform image comparison, as shown in fig. 2, in a service layer, the intelligent image recognition service forwards a request to a service layer scheduling module through business process access, signature detection and comparison, face detection and comparison are adopted to perform comparison processing on face videos and signature photos, images are obtained according to image IDs during the comparison processing, an actual matching result, an AI matching result and intermediate/result data are obtained and stored in a database, and the database adopts a MySQL database. In the service layer, the task scheduling module schedules each algorithm submodule in series through the RPC, decouples the mutual dependence of the submodules, improves the utilization rate of computing resources, and realizes a synchronous or asynchronous interface calling mode according to the requirement. The preprocessing module comprises functions of image region detection, rotation, classification and the like based on a deep learning model, and provides RPC interface calling. The handwriting signature/human face detection is based on deep learning handwriting signature region detection, detected signatures and corresponding position information are returned, and RPC interface calling is provided. The signature comparison module is based on a text recognition sub-module of deep learning, recognizes text content for a given text region, and provides RPC interface calling. And the structured output module outputs structured data based on the result of detecting the handwritten signature and the feature comparison, and provides RPC interface calling, wherein the structured data adopts JSON character strings. The data layer comprises an algorithm model, a knowledge base and a database. The base layer is configured with a network, a server, and a hardware store.
The image intelligent recognition service returns the comparison result (whether match) to the supply chain through the enterprise service bus ESB, and the supply chain stores the result information and simultaneously transmits the image comparison result to the partner through the open platform. The supply chain can display the comparison result aiming at each transaction in the file list, display the comparison result in a list mode and provide detailed information of the comparison result for the second-level menu.
Those skilled in the art will appreciate that the systems, apparatus, and their respective modules provided herein may be implemented entirely by logic programming of method steps such that the systems, apparatus, and their respective modules are implemented as logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc., in addition to the systems, apparatus, and their respective modules being implemented as pure computer readable program code. Therefore, the system, the apparatus, and the respective modules thereof provided by the present invention may be regarded as one hardware component, and the modules included therein for implementing various programs may also be regarded as structures within the hardware component; modules for implementing various functions may also be regarded as being either software programs for implementing the methods or structures within hardware components.
The foregoing describes specific embodiments of the present invention. It is to be understood that the invention is not limited to the particular embodiments described above, and that various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the invention. The embodiments of the present application and features in the embodiments may be combined with each other arbitrarily without conflict.
Claims (10)
1. A supply chain intelligent image comparison system, comprising:
sample module: collecting a sample library, a project information list and a right-confirming bill of materials through a first platform, pushing the sample library, the project information list and the right-confirming bill of materials to an open platform, and storing the sample library, the project information list and the right-confirming bill of materials as file lists;
and the pushing module is used for: pushing the file list to a set path of a supply chain server by utilizing a back-end service of the open platform;
a request module: the method comprises the steps that a supply chain server scans a file list by adopting a timing service, stores the scanned file list into a database, and initiates an image acquisition request according to an address in the file list, wherein the image acquisition request downloads an image piece from a cloud server of a first platform through an open platform gateway;
comparison module: the supply chain server receives the image piece, invokes the image intelligent recognition service through the ESB enterprise bus to perform image comparison, obtains a comparison result, returns the comparison result to the supply chain server, stores the comparison result, and transmits the comparison result to the first platform through the open platform.
2. The supply chain intelligent image comparison system according to claim 1, further comprising a display module for displaying the comparison result for each transaction in the file list, displaying the comparison result in a list manner, and providing detailed information of the second-level menu viewing comparison result.
3. The supply chain intelligent image comparison system of claim 1, wherein the comparison module comprises:
and (5) accessing the comparison module: receiving an image piece, downloading an image to be confirmed to an image platform according to the ID of the file to be confirmed of the image piece, and associating an image sample in the image piece with the image to be confirmed;
task scheduling module: decoupling the dependence degree of the comparison algorithm by an RPC series scheduling comparison algorithm, and realizing synchronous or asynchronous interface call according to the requirement;
and a pretreatment module: based on detection, rotation and classification of the image area of deep learning, processing the right-confirming image and providing a first RPC interface call;
signature detection module: based on the detection of the deep-learning handwriting signature area, signature detection is carried out on the right-confirming image, the detected signature and corresponding position information are returned, and a second RPC interface call is provided;
signature comparison module: based on the text recognition of the deep learning, performing text region recognition on the right-confirming image to obtain text content, and providing a third RPC interface call;
and a result output module: outputting the comparison result obtained by detection in the form of structured data, and providing a fourth RPC interface call.
4. The intelligent image comparison system of claim 1, wherein the image received by the supply chain server is uploaded to the image platform in a load balancing manner, and the image platform returns an image ID to the supply chain server after storing the image ID, wherein the image ID is a unique identification of the image.
5. The supply chain intelligent image comparison system according to claim 1, wherein after receiving the image pieces, the supply chain server provides version management for the image samples in the image pieces, wherein the version management comprises adding, modifying, deleting and viewing details; the comparison results comprise consistency, inconsistency and need to be checked manually.
6. A supply chain intelligent image comparison method, comprising:
sample steps: collecting a sample library, a project information list and a right-confirming bill of materials through a first platform, pushing the sample library, the project information list and the right-confirming bill of materials to an open platform, and storing the sample library, the project information list and the right-confirming bill of materials as file lists;
pushing: pushing the file list to a set path of a supply chain server by utilizing a back-end service of the open platform;
the request steps are as follows: the method comprises the steps that a supply chain server scans a file list by adopting a timing service, stores the scanned file list into a database, and initiates an image acquisition request according to an address in the file list, wherein the image acquisition request downloads an image piece from a cloud server of a first platform through an open platform gateway;
and (3) comparison: the supply chain server receives the image piece, invokes the image intelligent recognition service through the ESB enterprise bus to perform image comparison, obtains a comparison result, returns the comparison result to the supply chain server, stores the comparison result, and transmits the comparison result to the first platform through the open platform.
7. The method of claim 6, further comprising displaying the comparison results for each transaction in the file list, displaying the results in a list, and providing detailed information of the second-level menu viewing comparison results.
8. The method of claim 6, wherein the step of comparing comprises:
and (3) access comparison: receiving an image piece, downloading an image to be confirmed to an image platform according to the ID of the file to be confirmed of the image piece, and associating an image sample in the image piece with the image to be confirmed;
task scheduling: decoupling the dependence degree of the comparison algorithm by an RPC series scheduling comparison algorithm, and realizing synchronous or asynchronous interface call according to the requirement;
pretreatment: based on detection, rotation and classification of the image area of deep learning, processing the right-confirming image and providing a first RPC interface call;
signature detection: based on the detection of the deep-learning handwriting signature area, signature detection is carried out on the right-confirming image, the detected signature and corresponding position information are returned, and a second RPC interface call is provided;
signature comparison: based on the text recognition of the deep learning, performing text region recognition on the right-confirming image to obtain text content, and providing a third RPC interface call;
and outputting a result: outputting the comparison result obtained by detection in the form of structured data, and providing a fourth RPC interface call.
9. The intelligent image comparison method of the supply chain according to claim 6, wherein the image pieces received by the supply chain server are uploaded to the image platform in a load balancing manner, and the image platform returns an image ID to the supply chain server after storing the image ID, wherein the image ID is a unique identification of the image pieces.
10. The supply chain intelligent image comparison method according to claim 6, wherein after the supply chain server receives the image pieces, version management is provided for the image samples in the image pieces, and the version management comprises adding, modifying, deleting and viewing details; the comparison results comprise consistency, inconsistency and need to be checked manually.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911156893.8A CN111160091B (en) | 2019-11-22 | 2019-11-22 | Intelligent image comparison system and method for supply chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911156893.8A CN111160091B (en) | 2019-11-22 | 2019-11-22 | Intelligent image comparison system and method for supply chain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111160091A CN111160091A (en) | 2020-05-15 |
| CN111160091B true CN111160091B (en) | 2023-06-02 |
Family
ID=70556107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911156893.8A Active CN111160091B (en) | 2019-11-22 | 2019-11-22 | Intelligent image comparison system and method for supply chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111160091B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010478A (en) * | 2021-03-15 | 2021-06-22 | 北京金山云网络技术有限公司 | List file generation method and device, electronic equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541022A (en) * | 2012-01-19 | 2012-07-04 | 重庆市鹏创道路材料有限公司 | Intelligent road tunnel overhaul and management system based on Internet of things and three-dimensional (3D) geographic information system (GIS) |
| CN108833405A (en) * | 2018-06-13 | 2018-11-16 | 深圳市云识科技有限公司 | A kind of the cloud identification service processing platform and method of intelligent camera table |
| WO2019209008A1 (en) * | 2018-04-24 | 2019-10-31 | 주식회사 지디에프랩 | System for improving video quality by using changed macroblock extraction technique |
-
2019
- 2019-11-22 CN CN201911156893.8A patent/CN111160091B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541022A (en) * | 2012-01-19 | 2012-07-04 | 重庆市鹏创道路材料有限公司 | Intelligent road tunnel overhaul and management system based on Internet of things and three-dimensional (3D) geographic information system (GIS) |
| WO2019209008A1 (en) * | 2018-04-24 | 2019-10-31 | 주식회사 지디에프랩 | System for improving video quality by using changed macroblock extraction technique |
| CN108833405A (en) * | 2018-06-13 | 2018-11-16 | 深圳市云识科技有限公司 | A kind of the cloud identification service processing platform and method of intelligent camera table |
Non-Patent Citations (1)
| Title |
|---|
| 劳卫伦 ; 刘 ; 洪慧君 ; .面向财务共享服务的电子影像系统设计.大众用电.2016,(S2),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111160091A (en) | 2020-05-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170111532A1 (en) | Real-time processing of video streams captured using mobile devices | |
| US10078781B2 (en) | Automatically organizing images | |
| US9558401B2 (en) | Scanbox | |
| CN110569341B (en) | Method and device for configuring chat robot, computer equipment and storage medium | |
| US9619701B2 (en) | Using motion tracking and image categorization for document indexing and validation | |
| US11743216B2 (en) | Digital file recognition and deposit system | |
| US10482393B2 (en) | Machine-based learning systems, methods, and apparatus for interactively mapping raw data objects to recognized data objects | |
| CN116052193B (en) | RPA interface dynamic form picking and matching method and system | |
| TW201539210A (en) | Personal information management service system | |
| EP2864906A2 (en) | Searching for events by attendants | |
| WO2017172421A1 (en) | Image action based on automatic feature extraction | |
| CN113963147A (en) | Key information extraction method and system based on semantic segmentation | |
| CN111160091B (en) | Intelligent image comparison system and method for supply chain | |
| CN112052702A (en) | Method and device for identifying two-dimensional code | |
| CN114283416A (en) | Processing method and device for vehicle insurance claim settlement pictures | |
| CN104142955A (en) | Method and terminal for recommending learning courses | |
| US11620038B2 (en) | Restoring full online documents from scanned paper fragments | |
| CN111339939B (en) | Attendance checking method and device based on image recognition | |
| CN110853115B (en) | Creation method and device of development flow page | |
| US20150030241A1 (en) | Method and system for data identification and extraction using pictorial representations in a source document | |
| CN111931687A (en) | Bill identification method and device | |
| WO2015012820A1 (en) | Method and system for data identification and extraction using pictorial representations in a source document | |
| CN117058432B (en) | Image duplicate checking method and device, electronic equipment and readable storage medium | |
| CN117689935A (en) | Certificate information identification method, device and system, electronic equipment and storage medium | |
| CN115841291A (en) | Online verification method, system and storage medium for information of remote warehouse of dealer |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200803 Address after: Unit 01 and 02, 1st floor, 1239 Century Avenue, Pudong New Area, Shanghai, 200122 Applicant after: Shanghai Huarui bank Limited by Share Ltd. Address before: 200137 Room 302, No. 34, Lane 688, Datong Road, Pudong New Area, Shanghai Applicant before: Zhang Hong |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |