CN106971134A - It is a kind of can error correction pattern recognition device and method - Google Patents
It is a kind of can error correction pattern recognition device and method Download PDFInfo
- Publication number
- CN106971134A CN106971134A CN201610025160.0A CN201610025160A CN106971134A CN 106971134 A CN106971134 A CN 106971134A CN 201610025160 A CN201610025160 A CN 201610025160A CN 106971134 A CN106971134 A CN 106971134A
- Authority
- CN
- China
- Prior art keywords
- target image
- image signal
- unit
- recognition result
- error correction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of pattern recognition device, it is adaptable to intelligent electronic device, including:Image acquisition units, to gather a target image and export target image formation target image signal;Unit is transmitted wirelessly, target image signal to be sent;Radio receiving unit, to receive the target image signal of radio-cell transmission, and exports target image signal;Feature extraction unit, to extracting characteristic information in target image signal, and is exported;Recognition unit, according to characteristic information, target image to be identified, and exports recognition result;Input block, when the recognition result mistake, correct recognition result is inputted by the input block.The beneficial effect of its technical scheme is:The image for needing to recognize can be identified, and when recognition result malfunctions, can carry out correcting the correct recognition result of input, overcome the defect that existing identification image can not be corrected in time.
Description
Technical field
The present invention relates to intelligent electronic device field, more particularly to it is a kind of can error correction pattern recognition device and
Method.
Background technology
Pattern recognition device can easily make identification to the image for needing to recognize, but during identification
Often occur that identification is not accurate enough, or the result identified is very close to the image to be recognized, and it is right
Identify and stagger the time, for example recognize a milk box when, may mistake be identified as soapbox or others
Packing box, now user, which would generally take, repeatedly recognizes untill the result of identification is accurate, but this
Sample requires a great deal of time operation, therefore brings bad usage experience to user.
The content of the invention
Above mentioned problem for recognizing image in the prior art, now provides one kind and aims at raising identification standard
Exactness, can quickly recognize the raising image recognition precision device and method of image.
Concrete technical scheme is as follows:
It is a kind of can error correction pattern recognition device, it is adaptable to intelligent electronic device, including:
Image acquisition units, to gather a target image and the target image is formed into target image signal
Output;
Unit is transmitted wirelessly, is connected with described image collecting unit, the target image signal to be sent;
Radio receiving unit, is connected with the wireless transmission unit 2, is sent to receive the radio-cell
The target image signal, and export the target image signal;
Feature extraction unit, is connected with the radio receiving unit, to being carried in the target image signal
Characteristic information is taken out, and the characteristic information is exported;
Recognition unit, is connected with the characteristic extracting module, to according to the characteristic information, to described
Target image is identified, and exports recognition result;
Input block, is connected with the recognition unit, when the recognition result mistake, by described defeated
Enter unit and input correct recognition result.
It is preferred that, wherein described image collecting unit includes:
Photographing module, to obtain target image and be converted to target image signal;
Controller, is connected with the photographing module, the collection for the target image.
It is preferred that, the photographing module is minisize pick-up head.
It is preferred that, the extraction unit includes:
Processing module, to recognize calculating, inquiry and show;
Extraction module, is connected with the processing module, for extracting the spy in the target image signal
Reference ceases.
It is preferred that, wherein the special recognition unit includes:
Be stored with picture and the introduction that is associated with picture in picture database, the picture database;
Recognizer module, to according to the characteristic information, to the target in the picture database
Image is identified.
It is preferred that, in addition to display is connected with the recognition unit, for show the recognition result and
Operation indicating.
It is preferred that, wherein the display is LCD display.
It is preferred that, the input block includes a voice typing module, by the voice typing module for making
The correct recognition result of user's typing.
Also include it is a kind of can error correction image-recognizing method, comprise the following steps:
Step S1, one image acquisition units of offer, pass through described image collecting unit and gather a target image
The target image is converted into target image signal and exported;
Step S2, by one wireless transmission unit the target image signal is sent to a wireless receiving list
Member;
Step S3, the characteristic information for extracting in the target image signal target image signal
And export;
Step S4, according to the characteristic information, the target image is identified and the identification is exported
As a result;
Step S5, according to the recognition result, the recognition result is fed back.
Above-mentioned technical proposal has the following advantages that or beneficial effect:Above-mentioned technical proposal have the following advantages that or
Beneficial effect:The image for needing to recognize can be identified, and when recognition result malfunctions, can carried out
The correct recognition result of input is corrected, the defect that existing identification image can not be corrected in time is overcome.
Brief description of the drawings
With reference to appended accompanying drawing, more fully to describe embodiments of the invention.However, appended accompanying drawing is only
For illustrating and illustrating, and it is not meant to limit the scope of the invention.
Fig. 1 for the present invention it is a kind of can error correction pattern recognition device embodiment theory diagram;
Fig. 2 for the present invention is a kind of can be in the pattern recognition device embodiment of error correction, on image acquisition units
Structural representation;
Fig. 3 for the present invention is a kind of can be in the pattern recognition device embodiment of error correction, on feature extraction unit
Structural representation;
Fig. 4 for the present invention is a kind of can be in the pattern recognition device embodiment of error correction, on recognition unit
Structural representation;
Fig. 5 for the present invention it is a kind of can error correction image-recognizing method embodiment flow chart.
1st, image acquisition units;2nd, unit 2 is transmitted wirelessly;3rd, radio receiving unit;4th, feature is carried
Take unit;5th, recognition unit;6th, input block;41st, processing module;42nd, extraction module;51、
Picture database;52nd, recognizer module.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out
Clearly and completely describe, it is clear that described embodiment is only a part of embodiment of the invention, and
The embodiment being not all of.Based on the embodiment in the present invention, those of ordinary skill in the art are not making
The every other embodiment obtained on the premise of going out creative work, belongs to the scope of protection of the invention.
It should be noted that in the case where not conflicting, the embodiment in the present invention and the spy in embodiment
Levying to be mutually combined.
The invention will be further described with specific embodiment below in conjunction with the accompanying drawings, but not as the present invention's
Limit.
The present invention including it is a kind of can error correction pattern recognition device.
As shown in Figure 1 it is a kind of can error correction pattern recognition device, it is adaptable to intelligent electronic device, including:
Image acquisition units 1, to gather a target image and target image is formed into target image signal defeated
Go out;
Unit 2 is transmitted wirelessly, is connected with image acquisition units 1, target image signal to be sent;
Radio receiving unit 3, is connected with wireless transmission unit 2, the target to receive radio-cell transmission
Picture signal, and export target image signal;
Feature extraction unit 4, is connected with radio receiving unit 3, to being extracted in target image signal
Characteristic information, and characteristic information is exported;
Recognition unit 5, is connected with feature extraction unit 4, to according to characteristic information, to target image
It is identified, and exports recognition result;
Input block 6, is connected with identification module, is connected with recognition unit, when recognition result mistake,
Correct recognition result is inputted by input block.
In above-mentioned technical proposal, target image is gathered by image acquisition units 1 and target image is formed
Signal, is sent picture signal to radio receiving unit 3, wireless receiving list by transmitting wirelessly unit 2
Member 3 transmits target image signal to feature extraction unit 4, by extraction unit to target image signal
Characteristic information at extraction, and characteristic information is exported to recognition unit 5, recognition unit 5 is believed according to feature
Target image is identified breath, and recognition result is exported, and passes through 6 pairs of identification errors of input block
Recognition result inputs correct recognition result, and then identification can be made more accurate.
It is preferred that, as shown in Fig. 2 wherein image acquisition units 1 include:
Photographing module, to obtain target image and be converted to target image signal;
Controller, is connected with photographing module, the collection for target image.
In a kind of preferably embodiment, photographing module is minisize pick-up head.
In a kind of preferably embodiment, as shown in figure 3, extraction unit includes:
Processing module 41, to recognize calculating, inquiry and show;
Extraction module 42, is connected with processing module 41, for extracting the characteristic information in target image signal.
In a kind of preferably embodiment, as shown in figure 4, wherein special recognition unit 5 includes:
Be stored with picture and the introduction that is associated with picture in picture database 51, picture database;
Recognizer module 52, according to characteristic information, to be carried out in picture database to target image
Identification.
In a kind of preferably embodiment, in addition to display, it is connected with recognition unit 5, for showing
Recognition result and operation indicating.
In a kind of preferably embodiment, wherein display is LCD display.
In a kind of preferably embodiment, the input block includes a voice typing module, by described
Voice typing module supplies the correct recognition result of user's typing.
In technical scheme, in addition to it is a kind of can error correction image-recognizing method, as shown in figure 5,
Comprise the following steps:
Step S1, one image acquisition units 1 of offer, gathering a target image by image acquisition units 1 will
Target image is converted into target image signal and exported;
Step S2, by one wireless transmission unit 2 target image signal is sent to a radio receiving unit 3;
Step S3, the characteristic information of extraction target image signal and output in target image signal;
Step S4, according to characteristic information, target image is identified and recognition result is exported;
Step S5, the recognition result to identification error, progress are corrected and the correct recognition result of typing.
In a particular embodiment, when needing the image to commodity to be identified, by using image recognition
Unit 5, is shot to the image for needing to recognize and by the target image formation target image signal of shooting,
Target image signal is sent to radio receiving unit 33, wireless receiving list by transmitting wirelessly unit 22
Member 33 exports target image signal to feature extraction unit 4, by feature extraction unit 4 from target figure
Exported as extracting characteristic information in signal, and by characteristic information to recognition unit 5, pass through recognition unit 5
In recognizer module target image is identified from image data base according to characteristic information, and will
Recognition result is by showing that display is shown, user judges recognition result according to the recognition result of display
If whether correctly identification mistake can input correct identification information by input block 6 and be preserved, work as knowledge
Other unit 5 is re-recognized, and can accurately identify target image, so identifying system can be carried out perfect.
Above-mentioned technical proposal has the following advantages that or beneficial effect:The image for needing to recognize can be identified,
And when recognition result malfunctions, it can carry out correcting the correct recognition result of input, overcome existing identification
The defect that image can not be corrected in time.
Preferred embodiments of the present invention are these are only, embodiments of the present invention and protection is not thereby limited
Scope, to those skilled in the art, should can appreciate that all utilization description of the invention and figure
Show the equivalent substitution made by content and the scheme obtained by obvious change, should be included in this
In the protection domain of invention.
Claims (9)
1. it is a kind of can error correction pattern recognition device, it is adaptable to intelligent electronic device, it is characterised in that bag
Include:
Image acquisition units, to gather a target image and the target image is formed into target image signal
Output;
Unit is transmitted wirelessly, is connected with described image collecting unit, the target image signal to be sent;
Radio receiving unit, is connected with the wireless transmission unit, is sent to receive the radio-cell
The target image signal, and export the target image signal;
Feature extraction unit, is connected with the radio receiving unit, to being carried in the target image signal
Characteristic information is taken out, and the characteristic information is exported;
Recognition unit, is connected with the characteristic extracting module, to according to the characteristic information, to described
Target image is identified, and exports recognition result;
Input block, is connected with the recognition unit, when the recognition result mistake, by described defeated
Enter unit and input correct recognition result.
2. it is according to claim 1 it is a kind of can error correction pattern recognition device, it is characterised in that the figure
As collecting unit includes:
Photographing module, to obtain target image and be converted to target image signal;
Controller, is connected with the photographing module, the collection for the target image.
3. pattern recognition device according to claim 1, the photographing module is minisize pick-up head.
4. it is according to claim 1 it is a kind of can error correction pattern recognition device, it is characterised in that institute
Stating feature extraction unit includes:
Processing module, to recognize calculating, inquiry and show;
Extraction module, is connected with the processing module, for extracting the spy in the target image signal
Reference ceases.
5. it is according to claim 1 it is a kind of can error correction pattern recognition device, it is characterised in that institute
Stating special recognition unit includes:
Be stored with picture and the introduction that is associated with picture in picture database, the picture database;
Recognizer module, to according to the characteristic information, to the target in the picture database
Image is identified.
6. it is according to claim 1 it is a kind of can error correction pattern recognition device, it is characterised in that also
Including display, it is connected with the recognition unit, for showing the recognition result and operation indicating.
7. it is according to claim 5 it is a kind of can error correction pattern recognition device, it is characterised in that institute
Display is stated for LCD display.
8. it is according to claim 1 it is a kind of can error correction pattern recognition device, it is characterised in that institute
Stating input block includes a voice typing module, correct for user's typing by the voice typing module
Recognition result.
9. it is a kind of can error correction image-recognizing method, it is characterised in that comprise the following steps:
Step S1, one image acquisition units of offer, pass through described image collecting unit and gather a target image
The target image is converted into target image signal and exported;
Step S2, by one wireless transmission unit the target image signal is sent to a wireless receiving list
Member;
Step S3, the characteristic information for extracting in the target image signal target image signal
And export;
Step S4, according to the characteristic information, the target image is identified and the identification is exported
As a result;
Step S5, the recognition result to the identification error, are corrected and typing are correctly recognized
As a result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610025160.0A CN106971134A (en) | 2016-01-14 | 2016-01-14 | It is a kind of can error correction pattern recognition device and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610025160.0A CN106971134A (en) | 2016-01-14 | 2016-01-14 | It is a kind of can error correction pattern recognition device and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106971134A true CN106971134A (en) | 2017-07-21 |
Family
ID=59334351
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610025160.0A Pending CN106971134A (en) | 2016-01-14 | 2016-01-14 | It is a kind of can error correction pattern recognition device and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106971134A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107545391A (en) * | 2017-09-07 | 2018-01-05 | 安徽共生物流科技有限公司 | A kind of logistics document intellectual analysis and automatic storage method based on image recognition |
CN109335744A (en) * | 2018-11-06 | 2019-02-15 | 宁波大榭招商国际码头有限公司 | A kind of dock container handling intellectual broadcast system |
CN110619354A (en) * | 2019-08-27 | 2019-12-27 | 广州伊思高科技有限公司 | Image recognition system and method for unmanned sales counter |
CN112561902A (en) * | 2020-12-23 | 2021-03-26 | 天津光电通信技术有限公司 | Chip inverse reduction method and system based on deep learning |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102023971A (en) * | 2009-09-11 | 2011-04-20 | 韩国电子通信研究院 | User-interactive automatic translation device and method for mobile device |
CN102073849A (en) * | 2010-08-06 | 2011-05-25 | 中国科学院自动化研究所 | Target image identification system and method |
CN103279743A (en) * | 2013-05-28 | 2013-09-04 | 深圳市中兴移动通信有限公司 | Business card recognition method and device |
CN103377287A (en) * | 2012-04-25 | 2013-10-30 | 腾讯科技(深圳)有限公司 | Method and device for putting in item information |
-
2016
- 2016-01-14 CN CN201610025160.0A patent/CN106971134A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102023971A (en) * | 2009-09-11 | 2011-04-20 | 韩国电子通信研究院 | User-interactive automatic translation device and method for mobile device |
CN102073849A (en) * | 2010-08-06 | 2011-05-25 | 中国科学院自动化研究所 | Target image identification system and method |
CN103377287A (en) * | 2012-04-25 | 2013-10-30 | 腾讯科技(深圳)有限公司 | Method and device for putting in item information |
CN103279743A (en) * | 2013-05-28 | 2013-09-04 | 深圳市中兴移动通信有限公司 | Business card recognition method and device |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107545391A (en) * | 2017-09-07 | 2018-01-05 | 安徽共生物流科技有限公司 | A kind of logistics document intellectual analysis and automatic storage method based on image recognition |
CN109335744A (en) * | 2018-11-06 | 2019-02-15 | 宁波大榭招商国际码头有限公司 | A kind of dock container handling intellectual broadcast system |
CN110619354A (en) * | 2019-08-27 | 2019-12-27 | 广州伊思高科技有限公司 | Image recognition system and method for unmanned sales counter |
CN112561902A (en) * | 2020-12-23 | 2021-03-26 | 天津光电通信技术有限公司 | Chip inverse reduction method and system based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106971134A (en) | It is a kind of can error correction pattern recognition device and method | |
CN104573637B (en) | License plate recognition method based on multiple cameras | |
CN103996239B (en) | A kind of bill positioning identifying method merged based on multi thread and system | |
CN109858476B (en) | Tag expansion method and electronic equipment | |
WO2017092224A1 (en) | Rfid-based gesture recognition method and system | |
US20140358465A1 (en) | Yield analysis system and method using sensor data of fabrication equipment | |
CN105447437A (en) | Fingerprint identification method and device | |
CN106971133A (en) | One kind improves image recognition precision device and method | |
EP3255617A1 (en) | Folded bill identification method and device | |
JP7036401B2 (en) | Learning server, image collection support system for insufficient learning, and image estimation program for insufficient learning | |
CN102982305A (en) | Information processing apparatus and method of processing information, storage medium and program | |
CN103500337A (en) | Quadrangular side frame identifying method and device applied to intelligent wireless communication terminal | |
CN107958443A (en) | A kind of fingerprint image joining method based on crestal line feature and TPS deformation models | |
CN104063701B (en) | Fast electric television stations TV station symbol recognition system and its implementation based on SURF words trees and template matches | |
CN110245087A (en) | The state detection method and device at the human customer end for sample audit | |
WO2020237480A1 (en) | Control method and device based on image recognition | |
CN102194106A (en) | Human face recognition method used in door access system | |
CN103886296A (en) | Fingerprint identification method and device based on feedback | |
US20200150628A1 (en) | Defect detection during an automated production process | |
US20210136450A1 (en) | Electronic device and method for controlling the same, and storage medium | |
CN111476070A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
CN103248955A (en) | Identity recognition method and device based on intelligent remote control system | |
CN112418204A (en) | Text recognition method, system and computer medium based on paper document | |
CN110459206A (en) | A kind of speech recognition system and method based on track planning of dual robots identification | |
CN106682676A (en) | Image test method and image test device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170721 |