CN112560955A - Image recognition system for red date sorting - Google Patents
Image recognition system for red date sorting Download PDFInfo
- Publication number
- CN112560955A CN112560955A CN202011491574.5A CN202011491574A CN112560955A CN 112560955 A CN112560955 A CN 112560955A CN 202011491574 A CN202011491574 A CN 202011491574A CN 112560955 A CN112560955 A CN 112560955A
- Authority
- CN
- China
- Prior art keywords
- red
- time sequence
- red dates
- image recognition
- server device
- 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
- 230000000007 visual effect Effects 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 9
- 206010027146 Melanoderma Diseases 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000007619 statistical method Methods 0.000 claims description 3
- 240000008866 Ziziphus nummularia Species 0.000 claims 1
- 238000012216 screening Methods 0.000 abstract description 13
- 241001247821 Ziziphus Species 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The utility model discloses an image recognition system for red date sorting, which belongs to the field of red date sorting and comprises a plurality of visual camera devices and a server device which is in network connection with each of the visual camera devices; a new comparison library is established for each red date through the vision camera device and the server device, primary screening is completed through comparison of a plurality of characteristics with time sequences in the comparison library, secondary classification screening is performed when the primary screening accords with set parameters, and classification sorting of the red dates is completed through secondary screening of the established database, so that the sorting accuracy of the red dates is guaranteed.
Description
Technical Field
The disclosure belongs to the field of red date sorting, and particularly relates to an image recognition system for red date sorting.
Background
When red dates for food are frequently made, the size and the quality of the red dates need to be screened, the red dates with the same size and quality cannot be accurately screened due to individual subjective consciousness of manual screening of the red dates, the red dates are damaged due to inaccurate holding force, impurities on hands and the like can pollute the red dates, the manual screening efficiency is low, and the requirement of screening the red dates for food production in large batches cannot be met, so that red date sorting equipment is frequently used at present;
the existing red date sorting equipment mainly adopts an image recognition mode to realize red date screening, and only the existing image recognition system has the problems of single comparison mode, high data acquisition volatility, incapability of ensuring the accuracy of screening and classification and the like.
BRIEF SUMMARY OF THE PRESENT DISCLOSURE
Aiming at the defects of the prior art, the purpose of the present disclosure is to provide an image recognition system for red date sorting, which solves the problem of poor red date image sorting accuracy in the prior art.
The purpose of the disclosure can be realized by the following technical scheme:
an image recognition system for sorting red dates, the image recognition system comprising a plurality of visual camera devices and a server device connected to each of the plurality of visual camera devices via a network, each of the plurality of visual camera devices comprising: an acquisition unit that acquires time-series images captured by the acquisition unit in time series; the first image recognition part is used for carrying out image recognition processing on the time sequence images, processing a single time sequence image, recognizing the characteristics of a plurality of red dates in the single time sequence image and labeling the newly appeared red dates;
the server device establishes an independent comparison library for identifying the plurality of red dates in the single time sequence image, archives the characteristics of the plurality of red dates in the single time sequence image in the corresponding label comparison library according to the time sequence, and processes the characteristics of the plurality of red dates in the label comparison library to obtain independent comprehensive characteristic parameters of each red date and compares whether the independent comprehensive characteristic parameters of each red date have a specified phenomenon or not; the server device marks red dates having a predetermined phenomenon for each individual integrated characteristic parameter, and transmits the marked red dates to a plurality of vision camera devices, wherein the vision camera devices are provided with a second image recognition unit which performs image recognition processing on the marked red dates at a higher progress level, and estimates whether or not the predetermined phenomenon occurs in the red dates.
Further, the server device further includes a classification sorting unit that sets the predetermined different characteristic parameters and classifies the red dates based on the module parameters, and the classification result is: no jujube, black spot, broken peel, split, peel, level four, level three, level two, level one and special.
Further, the server device further includes a counting unit that performs a unique number for each newly appearing red date in the first image recognition unit, the unique number being performed in a numerical order.
Further, the server device may further include a deep learning unit configured to estimate whether or not the predetermined phenomenon has occurred in the imaging target.
Furthermore, the server device is also provided with a data processing part for carrying out statistical analysis on the classification result, converting the analysis result into a CPK icon form and outputting the CPK icon form, and the server device carries out alarm reminding on the abnormal fluctuation of the CPK.
Furthermore, the time sequence image collection of the first image recognition part and the second image recognition part is 1-30 times per second.
Further, the system comprises the following working steps:
the first step is as follows: a first image identification part of the visual camera device is used for installing time sequence intervals to shoot and sending shot time sequence images to first image identification, the first image identification part processes the received time sequence images, compares the time sequence images of the previous period to number newly appeared red dates, and processes and records the characteristics of the red dates in the time sequence images;
the second step is that: and establishing a new independent comparison library for the newly appeared serial numbers in the first step, and storing the characteristic installation time marks of each red date in the first step in the corresponding comparison library.
The third step: the server device analyzes the change condition of the red date features of each comparison library, the analysis result is the current grading feature of each red date, the server device marks the serial number of each red date when the current grading feature of each red date is in accordance with the specified phenomenon, and the grading feature of each red date changes along with the increase of time sequence images;
the fourth step: and (3) establishing a new independent second comparison library for the red dates marked in the third step, identifying the time sequence images and processing and recording the characteristics of the red dates in the time sequence images by the second image identification part, storing the characteristic parameters of the red dates in the second comparison library corresponding to the characteristic parameters of the red dates identified by the second image identification part, analyzing the characteristics in the second comparison library by the server device, and when the number of the characteristic parameters in the second comparison library is 10, obtaining the final grading characteristic of each red date.
The beneficial effect of this disclosure:
the quality of the red dates is dynamically identified and sorted, so that the sorting accuracy is guaranteed.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below, and it should be understood that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
An image recognition system for sorting red dates, the image recognition system comprising a plurality of visual camera devices and a server device connected to each of the plurality of visual camera devices via a network, each of the plurality of visual camera devices comprising: an acquisition unit that acquires time-series images captured by the acquisition unit in time series; the first image recognition part is used for carrying out image recognition processing on the time sequence images, processing a single time sequence image, recognizing the characteristics of a plurality of red dates in the single time sequence image and labeling the newly appeared red dates;
the server device establishes an independent comparison library for identifying the plurality of red dates in the single time sequence image, archives the characteristics of the plurality of red dates in the single time sequence image in the corresponding label comparison library according to the time sequence, and processes the characteristics of the plurality of red dates in the label comparison library to obtain independent comprehensive characteristic parameters of each red date and compares whether the independent comprehensive characteristic parameters of each red date have a specified phenomenon or not; the server device marks red dates having a predetermined phenomenon for each individual integrated characteristic parameter, and transmits the marked red dates to a plurality of vision camera devices, wherein the vision camera devices are provided with a second image recognition unit which performs image recognition processing on the marked red dates at a higher progress level, and estimates whether or not the predetermined phenomenon occurs in the red dates.
In some publications, the server device further includes a classification unit configured to set the predetermined different characteristic parameters and classify the red dates based on the module parameters, and the classification result is: no jujube, black spot, broken peel, split, peel, level four, level three, level two, level one and special.
In some publications, the server device further includes a counting section that performs a unique number in numerical order by assigning a unique number to each newly appearing red date in the first image recognition section.
In some publications, the server device further includes a deep learning unit configured to estimate whether or not the predetermined phenomenon has occurred in the imaging target.
In some disclosures, the server device further includes a data processing unit configured to perform statistical analysis on the classification result, convert the analysis result into a CPK icon form, and output the CPK icon form, and the server device performs alarm reminding on abnormal fluctuation of the CPK.
In some disclosures, the system operates as follows:
the first step is as follows: a first image identification part of the visual camera device is used for installing time sequence intervals to shoot and sending shot time sequence images to first image identification, the first image identification part processes the received time sequence images, compares the time sequence images of the previous period to number newly appeared red dates, and processes and records the characteristics of the red dates in the time sequence images;
the second step is that: and establishing a new independent comparison library for the newly appeared serial numbers in the first step, and storing the characteristic installation time marks of each red date in the first step in the corresponding comparison library.
The third step: the server device analyzes the change condition of the red date features of each comparison library, the analysis result is the current grading feature of each red date, the server device marks the serial number of each red date when the current grading feature of each red date is in accordance with the specified phenomenon, and the grading feature of each red date changes along with the increase of time sequence images;
the fourth step: and (3) establishing a new independent second comparison library for the red dates marked in the third step, identifying the time sequence images and processing and recording the characteristics of the red dates in the time sequence images by the second image identification part, storing the characteristic parameters of the red dates in the second comparison library corresponding to the characteristic parameters of the red dates identified by the second image identification part, analyzing the characteristics in the second comparison library by the server device, and when the number of the characteristic parameters in the second comparison library is 10, obtaining the final grading characteristic of each red date.
Principle of operation
Establishing a new comparison library for each red date, completing primary screening by comparing a plurality of characteristics with time sequences in the comparison library, performing secondary classification screening when the primary screening meets set parameters, and completing classification and sorting of the red dates by performing secondary screening through the established database.
In the description herein, references to the description of "one embodiment," "an example," "a specific example," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the disclosure. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing illustrates and describes the general principles, principal features, and advantages of the present disclosure. It will be understood by those skilled in the art that the present disclosure is not limited to the embodiments described above, which are presented solely for purposes of illustrating the principles of the disclosure, and that various changes and modifications may be made to the disclosure without departing from the spirit and scope of the disclosure, which is intended to be covered by the claims.
Claims (7)
1. An image recognition system for sorting red dates, the image recognition system comprising a plurality of visual camera devices and a server device connected to each of the plurality of visual camera devices via a network, wherein each of the plurality of visual camera devices comprises: an acquisition unit that acquires time-series images captured by the acquisition unit in time series; the first image recognition part is used for carrying out image recognition processing on the time sequence images, processing a single time sequence image, recognizing the characteristics of a plurality of red dates in the single time sequence image and labeling the newly appeared red dates;
the server device establishes an independent comparison library for identifying the plurality of red dates in the single time sequence image, archives the characteristics of the plurality of red dates in the single time sequence image in the corresponding label comparison library according to the time sequence, and processes the characteristics of the plurality of red dates in the label comparison library to obtain independent comprehensive characteristic parameters of each red date and compares whether the independent comprehensive characteristic parameters of each red date have a specified phenomenon or not; the server device marks red dates having a predetermined phenomenon for each individual integrated characteristic parameter, and transmits the marked red dates to a plurality of vision camera devices, wherein the vision camera devices are provided with a second image recognition unit which performs image recognition processing on the marked red dates at a higher progress level, and estimates whether or not the predetermined phenomenon occurs in the red dates.
2. The system according to claim 1, wherein the server device further comprises a classification unit configured to set the predetermined different characteristic parameters, classify the red dates according to the module parameters, and classify the red dates as follows: no jujube, black spot, broken peel, split, peel, level four, level three, level two, level one and special.
3. The image recognition system for red date sorting according to claim 2, wherein the server device further comprises a counting unit for performing a unique number for each newly appearing red date in the first image recognition unit, the unique number being performed in numerical order.
4. The system according to claim 3, wherein the server device further comprises a deep learning unit configured to estimate whether or not the predetermined phenomenon has occurred in the subject.
5. The image recognition system for red date sorting according to claim 4, wherein the server device further comprises a data processing unit that performs statistical analysis on the sorting result, converts the analysis result into a CPK icon form, and outputs the CPK icon form, and the server device gives an alarm to prompt for abnormal fluctuation of the CPK.
6. The image recognition system for red date sorting according to claim 5, wherein the time sequence image collection of the first image recognition part and the second image recognition part is 1-30 times per second.
7. The red date sorting image recognition system according to claim 6, wherein the system operates as follows:
the first step is as follows: a first image identification part of the visual camera device is used for installing time sequence intervals to shoot and sending shot time sequence images to first image identification, the first image identification part processes the received time sequence images, compares the time sequence images of the previous period to number newly appeared red dates, and processes and records the characteristics of the red dates in the time sequence images;
the second step is that: and establishing a new independent comparison library for the newly appeared serial numbers in the first step, and storing the characteristic installation time marks of each red date in the first step in the corresponding comparison library.
The third step: the server device analyzes the change condition of the red date features of each comparison library, the analysis result is the current grading feature of each red date, the server device marks the serial number of each red date when the current grading feature of each red date is in accordance with the specified phenomenon, and the grading feature of each red date changes along with the increase of time sequence images;
the fourth step: and (3) establishing a new independent second comparison library for the red dates marked in the third step, identifying the time sequence images and processing and recording the characteristics of the red dates in the time sequence images by the second image identification part, storing the characteristic parameters of the red dates in the second comparison library corresponding to the characteristic parameters of the red dates identified by the second image identification part, analyzing the characteristics in the second comparison library by the server device, and when the number of the characteristic parameters in the second comparison library is 10, obtaining the final grading characteristic of each red date.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011491574.5A CN112560955A (en) | 2020-12-16 | 2020-12-16 | Image recognition system for red date sorting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011491574.5A CN112560955A (en) | 2020-12-16 | 2020-12-16 | Image recognition system for red date sorting |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112560955A true CN112560955A (en) | 2021-03-26 |
Family
ID=75064318
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011491574.5A Pending CN112560955A (en) | 2020-12-16 | 2020-12-16 | Image recognition system for red date sorting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112560955A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106483135A (en) * | 2016-10-12 | 2017-03-08 | 河北农业大学 | Corn kernel detection and identification device and method based on machine vision under complex background |
| CN110073405A (en) * | 2016-12-06 | 2019-07-30 | 柯尼卡美能达株式会社 | Image identification system and image-recognizing method |
| CN110378761A (en) * | 2019-06-21 | 2019-10-25 | 珠海威泓急救云科技有限公司 | It is a kind of to take object control system and its method automatically |
| CN111940339A (en) * | 2020-08-18 | 2020-11-17 | 合肥金果缘视觉科技有限公司 | Red date letter sorting system based on artificial intelligence |
| CN111967440A (en) * | 2020-09-04 | 2020-11-20 | 郑州轻工业大学 | Comprehensive identification and treatment method for crop diseases |
-
2020
- 2020-12-16 CN CN202011491574.5A patent/CN112560955A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106483135A (en) * | 2016-10-12 | 2017-03-08 | 河北农业大学 | Corn kernel detection and identification device and method based on machine vision under complex background |
| CN110073405A (en) * | 2016-12-06 | 2019-07-30 | 柯尼卡美能达株式会社 | Image identification system and image-recognizing method |
| CN110378761A (en) * | 2019-06-21 | 2019-10-25 | 珠海威泓急救云科技有限公司 | It is a kind of to take object control system and its method automatically |
| CN111940339A (en) * | 2020-08-18 | 2020-11-17 | 合肥金果缘视觉科技有限公司 | Red date letter sorting system based on artificial intelligence |
| CN111967440A (en) * | 2020-09-04 | 2020-11-20 | 郑州轻工业大学 | Comprehensive identification and treatment method for crop diseases |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826538B (en) | Abnormal off-duty identification system for electric power business hall | |
| CN110738127B (en) | Helmet identification method based on unsupervised deep learning neural network algorithm | |
| CN111181939B (en) | Network intrusion detection method and device based on ensemble learning | |
| CN111507376B (en) | Single-index anomaly detection method based on fusion of multiple non-supervision methods | |
| CN108711148B (en) | Tire defect intelligent detection method based on deep learning | |
| CN101661004B (en) | Visible detection method of welding quality of circuit board based on support vector machine | |
| CN114219799A (en) | Intelligent manufacturing defective product analysis method and system | |
| CN116363573A (en) | Transformer substation equipment state anomaly identification method and system | |
| CN114066848A (en) | FPCA appearance defect visual inspection system | |
| CN108510487A (en) | A kind of photovoltaic module remote monitoring device | |
| CN114895634A (en) | Product production line automatic control system based on machine vision | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN117277566B (en) | Power grid data analysis power dispatching system and method based on big data | |
| CN110309737A (en) | A kind of information processing method applied to cigarette sales counter, apparatus and system | |
| CN113850773A (en) | Detection method, device, equipment and computer readable storage medium | |
| CN117851184A (en) | Alarm grading system and method based on machine learning | |
| CN117372956A (en) | Method and device for detecting state of substation screen cabinet equipment | |
| CN112560955A (en) | Image recognition system for red date sorting | |
| CN109598724B (en) | Cloth label detection and identification method | |
| CN109829887B (en) | Image quality evaluation method based on deep neural network | |
| CN115936389A (en) | Big data technology-based method for matching evaluation experts with evaluation materials | |
| WO2022262013A1 (en) | Method and system for collecting and monitoring vehicle state information | |
| CN113052821B (en) | Quality evaluation method for power equipment inspection picture | |
| CN115392663A (en) | Data acquisition and processing method based on big data | |
| CN108460119A (en) | A kind of system for supporting efficiency using machine learning lift technique |
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 |