CN113627849A - Method and system for improving automatic goods customer information acquisition recognition rate - Google Patents
Method and system for improving automatic goods customer information acquisition recognition rate Download PDFInfo
- Publication number
- CN113627849A CN113627849A CN202110923147.8A CN202110923147A CN113627849A CN 113627849 A CN113627849 A CN 113627849A CN 202110923147 A CN202110923147 A CN 202110923147A CN 113627849 A CN113627849 A CN 113627849A
- Authority
- CN
- China
- Prior art keywords
- goods
- characters
- pictures
- identification
- recognition
- 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 28
- 238000012795 verification Methods 0.000 claims abstract description 8
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 abstract description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/67—Focus control based on electronic image sensor signals
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Signal Processing (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Multimedia (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Character Discrimination (AREA)
Abstract
The invention relates to a method for improving the automatic goods customer information acquisition recognition rate, which comprises the following steps: generating a plurality of sets of identification numbers consisting of client identification codes for clients, and distributing the client identification codes in the goods identification in a one-to-one correspondence manner according to the set characters which are not easy to be confused; when goods labels are identified, a plurality of cameras are adopted to collect shot pictures with different depths of field, pictures meeting OCR identification conditions are screened and obtained, OCR identification is carried out on the screened pictures, characters without client identification codes are replaced by approximate characters in the characters which are not easy to be confused according to setting, and then client verification is carried out; by the method, pictures meeting OCR recognition conditions and characters recognized by OCR are collected by the industrial cameras for correction, and meanwhile, the goods label adopts two or more customer recognition codes, so that the recognition probability of the goods corresponding to the customer information is finally improved.
Description
Technical Field
The invention relates to the technical field of image-text recognition, in particular to a method and a system for improving the automatic goods customer information acquisition recognition rate.
Background
In the automatic application process of the logistics and warehousing industry, the bar codes of the goods and the information of the customers are mostly subjected to correlation identification, and the corresponding weight and volume of the goods are collected through equipment, so that the system cannot normally operate if the correlation between the bar codes of the goods and the customers is not preserved in advance;
in the process of identifying the information with the client number in the warehousing label or the express bill by applying an image-text identification technology (OCR), because of different cargo specifications, a camera is required to shoot a visual range and shoot the depth of field to be randomly adjusted. Therefore, the problems of too small proportion of the goods labels in the picture and different depth of field definition can be caused by shooting the picture by the industrial camera, and the recognition success rate through OCR is not high; in addition, the image-text recognition technology (OCR) has probability problem and has requirement on the definition of the photographed characters, and in conclusion, the final success rate is low, so that the significance of automatic operation is lost; therefore, a method and a system for improving the recognition probability of the customer identification code to realize the automatic warehousing of goods are needed.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method and a system for increasing the automatic goods customer information acquisition and identification rate, aiming at the above-mentioned defects of the prior art.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a method for improving the customer information acquisition recognition rate is constructed, wherein the realization method comprises the following steps:
generating a plurality of sets of identification numbers consisting of client identification codes for clients, and distributing the client identification codes in the goods identification in a one-to-one correspondence manner according to the set characters which are not easy to be confused;
when goods labels are identified, shooting pictures with different depths of field are collected by adopting a plurality of cameras, pictures meeting OCR identification conditions are screened and obtained, OCR identification is carried out on the screened pictures, characters without client identification codes are replaced by approximate characters in the characters which are not easy to be confused according to setting, and then client verification is carried out.
The method for improving the customer information acquisition recognition rate, provided by the invention, is characterized in that the customer identification code comprises one or more of numbers, letters and symbols.
According to the method for improving the client information acquisition and identification rate, when the plurality of cameras are used for acquiring shot pictures with different depths of field, the plurality of cameras adopt fixed focal lengths and are provided with lenses with different focal lengths.
According to the method for improving the customer information acquisition and identification rate, visual ranges of the multiple cameras for acquiring pictures are different.
The method for improving the customer information acquisition recognition rate is characterized in that a plurality of identification numbers respectively correspond to different identifications on goods.
A system for improving customer information acquisition and recognition rate is used for realizing the method for improving customer information acquisition and recognition rate, and comprises an identification code generation module, a shooting module, a processing module and an OCR recognition module;
the identification code generation module is used for generating a plurality of sets of identification numbers consisting of client identification codes for clients and distributing the client identification codes in one-to-one correspondence only according to the set characters which are not easy to be confused in the goods identification;
the shooting module comprises a plurality of cameras for shooting pictures with different depths of field and is used for acquiring goods pictures;
the processing module is used for screening out the pictures which accord with the OCR recognition conditions from the pictures collected by the shooting module, sending the screened pictures to the OCR recognition module for OCR recognition, replacing characters which are not distributed with the client recognition codes in the recognized characters with approximate characters in the characters which are not easy to be confused according to the setting, and then carrying out client verification.
The system for improving the automatic cargo customer information acquisition recognition rate is characterized in that a plurality of cameras of the shooting module all adopt fixed focal lengths, and are provided with lenses with different focal lengths.
The system for improving the automatic goods customer information acquisition recognition rate is characterized in that the visual ranges of the pictures acquired by the cameras of the shooting module are different.
The system for improving the automatic goods customer information acquisition recognition rate comprises a customer identification code, a customer identification code and a control module.
The system for improving the automatic goods customer information acquisition recognition rate is characterized in that a plurality of identification numbers correspond to different identifications on goods respectively.
The invention has the beneficial effects that: by the method, pictures meeting OCR recognition conditions and characters recognized by OCR are collected by the industrial cameras and corrected, and meanwhile, the goods label adopts two or more customer identification numbers, so that the recognition probability of the corresponding customer information of the goods is finally improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be further described with reference to the accompanying drawings and embodiments, wherein the drawings in the following description are only part of the embodiments of the present invention, and for those skilled in the art, other drawings can be obtained without inventive efforts according to the accompanying drawings:
FIG. 1 is a flow chart of a method for increasing automated goods customer information collection recognition rate in accordance with a preferred embodiment of the present invention;
fig. 2 is a schematic block diagram of a system for increasing the recognition rate of automatic goods customer information collection according to a preferred embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without inventive step, are within the scope of the present invention.
The method for improving the automatic goods customer information acquisition recognition rate of the preferred embodiment of the invention, as shown in fig. 1, comprises the following implementation methods:
s01: generating a plurality of sets of identification numbers consisting of client identification codes for clients, and distributing the client identification codes in the goods identification in a one-to-one correspondence manner according to the set characters which are not easy to be confused;
s02: when the goods label is identified, a plurality of cameras are adopted to collect shot pictures with different depths of field, and pictures meeting OCR identification conditions are obtained through screening;
s03: performing OCR recognition on the screened picture, replacing characters without the client identification codes into approximate characters in the characters which are not easy to be confused according to the setting, and then performing client verification;
by the method, pictures meeting OCR recognition conditions and characters recognized by OCR are collected by the industrial cameras for correction, and meanwhile, the goods label adopts two or more customer recognition codes, so that the recognition probability of the goods corresponding to the customer information is finally improved;
preferably, the customer identification code is a number, letter or symbol; commonly used are arabic numerals, english letters (size), common symbols, and characters of some other languages, etc.;
for example, in practical application, image-text recognition confusion of 0 and D, O, Q, 1 and I, J, L, E and F, C and G, M and N, W and V occurs, and 10 characters of the large and small letters C, D, F, I, J, L, N, O, Q, V can be set without participating in the client id code allocation;
after OCR recognition, converting characters distributed with client recognition codes into corresponding client recognition codes in all recognized characters, converting characters not distributed with client recognition codes into approximate characters in the characters distributed with client recognition codes, converting the client recognition codes, and then verifying;
such as: 0 and D, O, Q, 0 is the character allocated by the system, D, O, Q is the character which is not allocated by the system, if D, O, Q characters appear after recognition, it is automatically replaced by 0, and the verification is carried out.
Preferably, when a plurality of cameras are used for collecting shot pictures with different depths of field, the plurality of cameras adopt fixed focal lengths and are provided with lenses with different focal lengths;
industrial cameras are basically fixed in focal length (zoom cameras have a problem in life), so the shooting angle and the shooting depth of field of each camera are fixed;
for example, one industrial camera used a 30mm lens, focused at 90cm, tested with a depth of field in the range of 80cm to 100cm, and a capture vision in the range of 130cm by 190cm to 160cm by 240 cm; an industrial camera using a 12mm lens is focused at 80cm, tested depth of field is in the range of 55cm to 100cm, and shooting visual range is in the range of 230cm to 340cm to 410cm to 610 cm;
after the shooting visual range of a plurality of different industrial cameras is tested like this, the combination is carried out to cover the surface area to be shot of the actual goods as much as possible, and the visual range of the cameras is kept when the cameras collect the pictures, so that the definition and the success rate of picture collection can be guaranteed.
Preferably, the plurality of identification numbers correspond to different identifications on the goods respectively;
two or more identification numbers are generated for the client, and the identification probability is improved. Such as: generating a pure number and a pure capital letter number, and matching the pure number and the pure capital letter number with a warehousing label or express bill receiving information and the like; by adopting the client numbers of two groups of different classified characters, the number can not have letter number, and judgment basis is provided for OCR recognition data correction.
A system for improving customer information acquisition recognition rate is used for realizing the method for improving customer information acquisition recognition rate, as shown in FIG. 2, and comprises an identification code generation module 1, a shooting module 2, a processing module 3 and an OCR recognition module 4;
the identification code generation module 1 is used for generating a plurality of sets of identification numbers consisting of client identification codes for clients and distributing the client identification codes in one-to-one correspondence only according to characters which are set and are not easy to be confused in goods identification;
the shooting module 2 comprises a plurality of cameras for shooting pictures with different depths of field and is used for acquiring goods pictures;
the processing module 3 is used for screening out pictures meeting OCR recognition conditions from the pictures collected by the shooting module, sending the screened pictures to the OCR recognition module 4 for OCR recognition, replacing characters which are not distributed with client recognition codes in the recognized characters with approximate characters in the characters which are not easy to be confused according to setting, and then carrying out client verification;
the pictures meeting the OCR recognition conditions and the characters recognized by the OCR are collected by the multiple cameras to be corrected, and the overall recognition probability of the system is improved by matching with the recognition of multiple client numbers.
Preferably, a plurality of cameras of the shooting module all adopt fixed focal lengths, and are provided with lenses with different focal lengths; the visual ranges of pictures acquired by a plurality of cameras of the shooting module are different; a plurality of cameras are selected to be matched with lenses with different focal lengths, so that pictures with different depth of field and suitable for OCR technology recognition can be acquired.
Preferably, the customer identification code is a number, letter or symbol.
Preferably, the plurality of identification numbers correspond to different identifications on the goods respectively; by adopting the client numbers of two groups of different classified characters, the number can not have letter number, and judgment basis is provided for OCR recognition data correction.
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined in the appended claims.
Claims (10)
1. A method for improving the automatic goods customer information acquisition recognition rate is characterized by comprising the following steps:
generating a plurality of sets of identification numbers consisting of client identification codes for clients, and distributing the client identification codes in the goods identification in a one-to-one correspondence manner according to the set characters which are not easy to be confused;
when goods labels are identified, shooting pictures with different depths of field are collected by adopting a plurality of cameras, pictures meeting OCR identification conditions are screened and obtained, OCR identification is carried out on the screened pictures, characters without client identification codes are replaced by approximate characters in the characters which are not easy to be confused according to setting, and then client verification is carried out.
2. The method for increasing the recognition rate of the automated goods customer information collection according to claim 1, wherein the customer identification code comprises one or more of numbers, letters and symbols.
3. The method for increasing the automatic cargo customer information collection recognition rate according to claim 1 or 2, wherein when a plurality of cameras are used for collecting the shot pictures with different depths of field, the plurality of cameras are fixed in focal length and are provided with lenses with different focal lengths.
4. The method for increasing the recognition rate of the automatic goods customer information acquisition according to claim 3, wherein the visual ranges of the plurality of cameras for acquiring the pictures are different.
5. The method for increasing the recognition rate of the automatic cargo customer information collection according to claim 1 or 2, wherein a plurality of the recognition numbers respectively correspond to different identifications on the cargo.
6. A system for improving the automatic goods customer information acquisition recognition rate is used for realizing the method for improving the automatic goods customer information acquisition recognition rate as claimed in any one of claims 1 to 5, and is characterized by comprising an identification code generation module, a shooting module, a processing module and an OCR recognition module;
the identification code generation module is used for generating a plurality of sets of identification numbers consisting of client identification codes for clients and distributing the client identification codes in one-to-one correspondence only according to the set characters which are not easy to be confused in the goods identification;
the shooting module comprises a plurality of cameras for shooting pictures with different depths of field and is used for acquiring goods pictures;
the processing module is used for screening out the pictures which accord with the OCR recognition conditions from the pictures collected by the shooting module, sending the screened pictures to the OCR recognition module for OCR recognition, replacing characters which are not distributed with the client recognition codes in the recognized characters with approximate characters in the characters which are not easy to be confused according to the setting, and then carrying out client verification.
7. The system for improving the recognition rate of automatic cargo customer information collection according to claim 6, wherein the cameras of the shooting module all adopt fixed focal lengths, and are configured with lenses with different focal lengths.
8. The system for improving the recognition rate of automatic cargo customer information collection according to claim 6, wherein the plurality of cameras of the photographing module collect pictures with different visual ranges.
9. The system of claim 6, wherein the customer identification code comprises one or more of a number, a letter, and a symbol.
10. The system for increasing automated goods customer information collection recognition rate of claim 6, wherein a plurality of the identification numbers correspond to different identifications on the goods respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110923147.8A CN113627849A (en) | 2021-08-12 | 2021-08-12 | Method and system for improving automatic goods customer information acquisition recognition rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110923147.8A CN113627849A (en) | 2021-08-12 | 2021-08-12 | Method and system for improving automatic goods customer information acquisition recognition rate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113627849A true CN113627849A (en) | 2021-11-09 |
Family
ID=78384788
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110923147.8A Pending CN113627849A (en) | 2021-08-12 | 2021-08-12 | Method and system for improving automatic goods customer information acquisition recognition rate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113627849A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504545A (en) * | 2014-12-02 | 2015-04-08 | 广州宝钢南方贸易有限公司 | Device and method for sold goods warehousing confirmation based on the Internet-of-things technology |
| CN106682671A (en) * | 2016-12-29 | 2017-05-17 | 成都数联铭品科技有限公司 | Image character recognition system |
| CN107045678A (en) * | 2017-02-08 | 2017-08-15 | 陈东 | Automatic batch quickly matches somebody with somebody goods system and method |
| CN108416412A (en) * | 2018-01-23 | 2018-08-17 | 浙江瀚镪自动化设备股份有限公司 | A kind of logistics compound key recognition methods based on multitask deep learning |
| CN108875725A (en) * | 2018-06-05 | 2018-11-23 | 华南理工大学 | A kind of the mail automatic sorting device and method of view-based access control model identification |
| WO2019080513A1 (en) * | 2017-10-27 | 2019-05-02 | 君泰创新（北京）科技有限公司 | Optical character recognition vision-based recognition system |
| KR20190119464A (en) * | 2018-04-12 | 2019-10-22 | 한국전자통신연구원 | Method and apparatus for Logistics by using reusable RFID tag |
| CN110516663A (en) * | 2019-07-15 | 2019-11-29 | 平安普惠企业管理有限公司 | Test method, device, computer equipment and the storage medium of OCR recognition accuracy |
| CN110659704A (en) * | 2019-09-29 | 2020-01-07 | 西安邮电大学 | Logistics express mail information identification system and method |
| CN110717347A (en) * | 2019-10-08 | 2020-01-21 | 珠海格力智能装备有限公司 | Method and device for acquiring cargo information |
| CN111369198A (en) * | 2020-03-23 | 2020-07-03 | 深圳市全景世纪科技有限公司 | Intelligent logistics control method, device, equipment and storage medium |
| CN211604160U (en) * | 2020-05-14 | 2020-09-29 | 四川华西集采电子商务有限公司 | Goods detection device based on OCR character recognition |
-
2021
- 2021-08-12 CN CN202110923147.8A patent/CN113627849A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504545A (en) * | 2014-12-02 | 2015-04-08 | 广州宝钢南方贸易有限公司 | Device and method for sold goods warehousing confirmation based on the Internet-of-things technology |
| CN106682671A (en) * | 2016-12-29 | 2017-05-17 | 成都数联铭品科技有限公司 | Image character recognition system |
| CN107045678A (en) * | 2017-02-08 | 2017-08-15 | 陈东 | Automatic batch quickly matches somebody with somebody goods system and method |
| WO2019080513A1 (en) * | 2017-10-27 | 2019-05-02 | 君泰创新（北京）科技有限公司 | Optical character recognition vision-based recognition system |
| CN108416412A (en) * | 2018-01-23 | 2018-08-17 | 浙江瀚镪自动化设备股份有限公司 | A kind of logistics compound key recognition methods based on multitask deep learning |
| KR20190119464A (en) * | 2018-04-12 | 2019-10-22 | 한국전자통신연구원 | Method and apparatus for Logistics by using reusable RFID tag |
| CN108875725A (en) * | 2018-06-05 | 2018-11-23 | 华南理工大学 | A kind of the mail automatic sorting device and method of view-based access control model identification |
| CN110516663A (en) * | 2019-07-15 | 2019-11-29 | 平安普惠企业管理有限公司 | Test method, device, computer equipment and the storage medium of OCR recognition accuracy |
| CN110659704A (en) * | 2019-09-29 | 2020-01-07 | 西安邮电大学 | Logistics express mail information identification system and method |
| CN110717347A (en) * | 2019-10-08 | 2020-01-21 | 珠海格力智能装备有限公司 | Method and device for acquiring cargo information |
| CN111369198A (en) * | 2020-03-23 | 2020-07-03 | 深圳市全景世纪科技有限公司 | Intelligent logistics control method, device, equipment and storage medium |
| CN211604160U (en) * | 2020-05-14 | 2020-09-29 | 四川华西集采电子商务有限公司 | Goods detection device based on OCR character recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107153817B (en) | Pedestrian re-identification data labeling method and device | |
| CN107067006B (en) | Verification code identification method and system serving for data acquisition | |
| CN108986086A (en) | The detection of typographical display panel inkjet printing picture element flaw and classification method and its device | |
| CN109635620B (en) | Self-service terminal (SST) face authentication process | |
| MX2014004073A (en) | Device and method for automatically identifying a qr code. | |
| CN111582126B (en) | Pedestrian re-recognition method based on multi-scale pedestrian contour segmentation fusion | |
| CN109413411B (en) | Black screen identification method and device of monitoring line and server | |
| CN113989794B (en) | License plate detection and recognition method | |
| TW202215296A (en) | System and method for license plate recognition and method for extracting character segments in a license plate | |
| CN103605982A (en) | Cigarette case 32-bit bar code acquisition system and 32-bit bar code identification method | |
| CN111524083A (en) | Active and passive combined underwater aerial imaging image recovery method based on structured light | |
| CN112001200A (en) | Identification code identification method, device, equipment, storage medium and system | |
| CN115314713A (en) | Method, system and device for extracting target segment in real time based on accelerated video | |
| CN109558798B (en) | Face recognition method and system based on convolution feature map matching | |
| CN113627849A (en) | Method and system for improving automatic goods customer information acquisition recognition rate | |
| PirahanSiah et al. | Adaptive image segmentation based on peak signal-to-noise ratio for a license plate recognition system | |
| Arsenovic et al. | Deep learning driven plates recognition system | |
| CN115909351B (en) | Container number identification method and device based on deep learning | |
| CN201522724U (en) | Detonator safety tracking management device | |
| CN108345895A (en) | Advertising image recognition methods and advertising image identifying system | |
| CN110781811A (en) | Abnormal work order identification method and device, readable storage medium and computer equipment | |
| CN108734158B (en) | Real-time train number identification method and device | |
| EP0632404B1 (en) | Pattern recognition by generating and using zonal features and anti-features | |
| CN110569692A (en) | multi-vehicle identification method, device and equipment | |
| CN114332983A (en) | Face image definition detection method, face image definition detection device, electronic equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |