CN114653612A - Red date letter sorting system based on machine vision - Google Patents
Red date letter sorting system based on machine vision Download PDFInfo
- Publication number
- CN114653612A CN114653612A CN202210356257.5A CN202210356257A CN114653612A CN 114653612 A CN114653612 A CN 114653612A CN 202210356257 A CN202210356257 A CN 202210356257A CN 114653612 A CN114653612 A CN 114653612A
- Authority
- CN
- China
- Prior art keywords
- sorting
- red
- module
- image
- red date
- 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
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 239000012535 impurity Substances 0.000 claims description 10
- 238000013500 data storage Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 210000000078 claw Anatomy 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/04—Sorting according to size
- B07C5/10—Sorting according to size measured by light-responsive means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/0081—Sorting of food items
Abstract
A red date sorting system based on machine vision comprises a sorting table, a sorting identification module and a classification processing module; the method comprises the steps that an image acquisition module in a sorting identification module is used for acquiring and preprocessing images on a conveyor belt in real time, the processed images are sent to a feature processing module in a classifying processing module, the feature processing module firstly judges whether the images are red dates or not by using a feature comparison unit, if the images are the red dates, the red dates in the images are detected by size measuring nodes, color identification nodes and flaw detection nodes in a red date classifying unit, the grade of the red dates is judged by using a preset standard, and the classifying sorting module controls a mechanical claw to sort the red dates on the conveyor belt; the device has the advantages of simple structure, convenient operation, easy realization and accurate grading.
Description
Technical Field
The invention belongs to the technical field of food sorting, and particularly relates to a red date sorting system based on machine vision.
Background
The red dates become main products in partial areas of China and are main economic sources of the partial areas, most of the sorted red dates on the market pass through a meshed slope or a meshed roller sieve, the red dates in different sizes can only be sorted roughly in a sorting mode, and when the red dates and impurities are separated, the impurities can only be separated by means of manual operation on the sieve, the sorting standard is single, the efficiency is low, and the time is wasted.
A multistage red date sorting machine with publication number CN201920712066.1, including controller and frame, the frame upside has set gradually material loading chute, blanking conveyer trough, shadow machine, blanking machine and conveyer, and the conveyer includes drive arrangement and two about the letter sorting conveyer belt of interval arrangement. Above-mentioned scheme is obvious to the red date letter sorting effect of equidimension not, has got rid of impurity such as sand and soil, leaf automatically to a certain extent in the letter sorting process. However, the scheme can only sort the red dates according to the sizes of the red dates, and the red dates cannot be accurately graded in the sorting process.
Disclosure of Invention
In order to solve the problems in the prior art, the invention aims to provide a red date sorting system based on machine vision, which collects images on a conveyor belt in real time through an image collecting module, sends the images to a characteristic processing module after preprocessing, compares the characteristics, sequentially identifies the color, detects the flaws and measures and sorts the red dates in size, accurately sorts the red dates through a preset sorting standard, and finally accurately sorts the red dates through a sorting module.
In order to achieve the purpose, the invention can be realized by the following technical scheme:
a red date sorting system based on machine vision comprises a sorting table 2, a sorting identification module and a classification processing module;
the sorting identification module comprises a conveyor belt 1 arranged on the table surface of a sorting table 2, and an image acquisition module is erected above the conveyor belt 1 through an auxiliary support 7 on the periphery of the sorting table 2;
categorised processing module includes red date classification case 4 that 2 middle sections one side of letter sorting platform set up, and the impurity case 5 that 2 stroke ends of letter sorting platform set up, on the auxiliary stand 7 and 2 one side tops of letter sorting platform are equipped with triaxial truss manipulator 8 along 2 stroke directions of letter sorting platform.
The image acquisition module includes the bar light source 6 that letter sorting platform 2 both sides set up, and bar light source 6 top is equipped with industry camera 9, and industry camera passes through camera support 10 to be installed on auxiliary stand 7.
And a control processing module 3 is arranged on one side of the sorting table 2.
The control processing module 3 comprises a characteristic processing module, a grading sorting module and a data storage module; the characteristic processing module receives image information acquired by the image acquisition module, then preprocesses the image, compares and classifies the image according to a profile characteristic library with preset standards, controls the three-axis truss manipulator 8 by the classification and sorting module to classify and pick up red dates into red date classification boxes 4 with different grades, and stores statistical data of the red dates in each grade in unit time to the data storage module.
The control processing module 3 employs a computer comprising Anaconda software of a library of machine vision algorithms.
The image preprocessing comprises gray processing, image normalization processing, image enhancement processing and image binarization processing of the collected images.
The characteristic processing module comprises a characteristic comparison unit and a red date grading unit; the characteristic comparison unit comprises a preset standard outline characteristic library and an outline detection node, the outline detection node identifies the image outline data acquired by the image acquisition module, the identified outline is matched with the data in the outline characteristic library, if the matching is successful, the outline is red dates and enters sorting treatment, if the matching is unsuccessful, the characteristic processing module sends an unidentified instruction, and the conveyor belt 1 sends the unidentified objects to the impurity box 5.
The red date grading unit comprises a color identification node, a flaw detection node and a size measurement node; and identifying the red dates in the image by the color identification node, marking the identification result as O, if the identification result is red, judging that O is equal to '1', judging that the grabbing is met, and if not, judging that O is equal to '0', and not meeting the grabbing.
And detecting the red dates in the image by the defect detection node, marking the detection result as P, judging that the P is equal to 1 if the red dates in the detection result have no defect, judging that the grabbing is met, and otherwise, judging that the P is equal to 0, and not meeting the grabbing.
After the red date grading unit receives the image, measuring the long diameter of the red dates through a size measuring node, and marking a measuring result as D; according to the grading standard of the dried red dates, the grabbing instructions are sent to the red dates with different diameters, and the grading sorting module controls the three-shaft truss manipulator 8 to grab the red dates with different grades into the red date sorting box 4.
Compared with the prior art, the invention has the beneficial effects that:
1. the image acquisition module is used for acquiring images on the conveyor belt in real time through the industrial camera, the images are preprocessed and then sent to the characteristic processing module, and the light source is arranged in the image acquisition module, so that the quality of the acquired images is guaranteed, the cost is saved, and the working efficiency is improved.
2. The invention is provided with a characteristic processing module, the characteristic processing module receives the preprocessed image, firstly determines a red date target on a conveyor belt through a characteristic comparison unit, then identifies red dates in the image through a color identification node, detects the red dates in the image through a flaw detection node, measures the major diameter of the red dates through a size measurement node in a red date grading unit, and finally grades the red dates accurately through the range of the major diameter.
Drawings
FIG. 1 is a system block diagram of the present invention.
Fig. 2 is a schematic diagram of the circuit structure of the present invention.
Fig. 3 is a schematic diagram of the operation of the system.
In the figure: 1. a conveyor belt; 2. a sorting table; 3. a control processing module; 4. a red date classification box; 5. an impurity box; 6. a strip light source; 7. an auxiliary support; 8. a three-axis truss manipulator; 9. an industrial camera; 10. a camera support.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, a red date sorting system based on machine vision comprises a sorting table 2, a sorting identification module and a classification processing module;
the sorting identification module comprises a conveyor belt 1 arranged on the table surface of a sorting table 2, and an image acquisition module is erected above the conveyor belt 1 through an auxiliary support 7 on the periphery of the sorting table 2;
categorised processing module includes red date classification case 4 that 2 middle sections one side of letter sorting platform set up, and the impurity case 5 that 2 stroke ends of letter sorting platform set up, on the auxiliary stand 7 and 2 one side tops of letter sorting platform are equipped with triaxial truss manipulator 8 along 2 stroke directions of letter sorting platform.
And a control processing module 3 is also arranged on one side of the sorting table 2.
The image acquisition module comprises bar-shaped light sources 6 arranged on two sides of the sorting table, an industrial camera 9 is arranged above the bar-shaped light sources 6, and the industrial camera is installed on the auxiliary support 7 through a camera support 10.
Referring to fig. 2 and 3, the control processing module 3 includes a feature processing module, a grading sorting module and a data storage module; the characteristic processing module receives image information acquired by the image acquisition module, then preprocesses the image, compares and classifies the image according to a profile characteristic library with preset standards, controls the three-axis truss manipulator 8 by the classification and sorting module to classify and pick up red dates into red date classification boxes 4 with different grades, and stores statistical data of the red dates in each grade in unit time to the data storage module.
The control processing module 3 employs a computer containing the Anaconda software of a machine vision algorithm library.
The image preprocessing comprises gray processing, image normalization processing, image enhancement processing and image binarization processing of the collected images.
The characteristic processing module comprises a characteristic comparison unit and a red date grading unit; the characteristic comparison unit comprises a preset standard outline characteristic library and outline detection nodes, the outline detection nodes identify the outline data of the image acquired by the image acquisition module, the identified outline is matched with the data in the outline characteristic library, if the matching is successful, the outline is red dates and enters sorting processing, if the matching is unsuccessful, the characteristic processing module sends an unidentified instruction, and the conveyor belt 1 sends the unidentified object to the impurity box 5.
The red date grading unit comprises a color identification node, a flaw detection node and a size measurement node; the color identification node identifies the red dates in the image, the identification result is marked as O, if the identification result is red, the O is equal to '1', the grasping is judged to be met, and if not, the O is equal to '0', the grasping is not met;
detecting the red dates in the image by using a flaw detection node, marking a detection result as P, if the red dates in the detection result have no flaws, judging that P is equal to '1', and judging that the picking is met, otherwise, judging that P is equal to '0', and not meeting the picking;
after the red date grading unit receives the image, measuring the long diameter of the red dates through a size measuring node, and marking a measuring result as D; according to the grading standard of the dried red dates, a grabbing instruction is sent to the red dates with different diameters, and the grading sorting module controls the three-axis truss manipulator 8 to grab the red dates with different grades into the red date sorting box 4.
Grading standard of dried red dates: when D is larger than 50mm, the red dates are divided into special grades, when D is larger than 47.1mm and is smaller than or equal to 50.0mm, the red dates are divided into first grades, when D is larger than 42.1mm and is smaller than or equal to 47.0mm, the red dates are divided into second grades, when D is larger than 36.1mm and is smaller than or equal to 42.0mm, the red dates are divided into third grades, when D is larger than 31.0mm and is smaller than or equal to 36.0mm, the red dates are divided into fourth grades, the red dates are respectively grabbed into corresponding special-grade red date classification boxes according to the special grades, the first grades, the second grades, the third grades and the fourth grades, the total number of the special-grade red dates, the first grades, the second grades, the third grades and the fourth grades in unit time is respectively counted, and the total number of the special-grade red dates, the first grade, the second grade, the third grades and the fourth grades is sent to the data storage module.
The three-axis truss manipulator 8 is an existing device.
The working principle of the invention is as follows:
the method comprises the steps of collecting images on a conveyor belt 1 in real time through an image collection module, carrying out gray level processing, image normalization processing, image enhancement processing and image binarization processing on the collected images, sending the processed images to a feature processing module, judging whether the images are red dates or not by using a feature comparison unit by the feature processing module, detecting the red dates in the images through size measurement nodes, color identification nodes and flaw detection nodes in a red date grading unit if the images are red dates, judging the grade of the red dates by using a preset standard, controlling a three-axis truss manipulator 8 to sort the red dates on the conveyor belt by the grading sorting module, and respectively grabbing corresponding special-grade red date sorting boxes 4, first-grade red date sorting boxes, second-grade red date sorting boxes, third-grade red date sorting boxes, three-grade red date sorting boxes, and four-grade red dates to corresponding special-grade red date sorting boxes 4, first-grade red date sorting boxes, second-grade red dates, third-grade red date sorting boxes, three-grade red date sorting boxes, Four-level red date sorting box.
Claims (8)
1. A red date sorting system based on machine vision comprises a sorting table (2), a sorting identification module and a classification processing module; the method is characterized in that:
the sorting identification module comprises a conveyor belt (1) arranged on the table surface of the sorting table (2), and an image acquisition module is erected above the conveyor belt (1) through an auxiliary support (7) on the periphery of the sorting table (2);
categorised processing module is equipped with triaxial truss manipulator (8) along letter sorting platform (2) stroke direction including categorised case (4) of red date that letter sorting platform (2) middle section one side set up, letter sorting platform (2) stroke end impurity case (5) that set up, auxiliary stand (7) are gone up and letter sorting platform (2) one side top.
2. The machine vision based red date sorting system according to claim 1, wherein: the image acquisition module comprises bar-shaped light sources (6) arranged on two sides of the sorting table (2), an industrial camera (9) is arranged above the bar-shaped light sources (6), and the industrial camera is installed on the auxiliary support (7) through a camera support (10).
3. The machine vision based red date sorting system according to claim 1, wherein: and a control processing module (3) is also arranged on one side of the sorting table (2).
4. The machine vision based red date sorting system according to claim 3, wherein: the control processing module (3) comprises a characteristic processing module, a grading sorting module and a data storage module; the characteristic processing module receives image information acquired by the image acquisition module, then preprocesses the image, compares and classifies the image according to a profile characteristic library with preset standards, controls a three-axis truss manipulator (8) by the classification and sorting module to classify and pick up red dates into red date classification boxes (4) of different grades, and stores statistical data of each grade of red dates in unit time to the data storage module.
5. The machine vision based red date sorting system according to claim 3, wherein: the control processing module (3) adopts a computer of Anaconda software containing a machine vision algorithm library.
6. The machine vision-based red date sorting system according to claim 4, wherein: the image preprocessing comprises gray processing, image normalization processing, image enhancement processing and image binarization processing of the collected images.
7. The machine vision-based red date sorting system according to claim 4, wherein: the characteristic processing module comprises a characteristic comparison unit and a red date grading unit; the characteristic comparison unit comprises a preset standard outline characteristic library and outline detection nodes, the outline detection nodes identify the image outline data acquired by the image acquisition module, the identified outline is matched with the data in the outline characteristic library, if the matching is successful, the outline is red dates and enters sorting processing, if the matching is unsuccessful, the characteristic processing module sends an unidentified instruction, and the conveyor belt (1) sends the unidentified object to the impurity box (5).
8. The machine vision based red date sorting system according to claim 7, wherein: the red date grading unit comprises a color identification node, a flaw detection node and a size measurement node; the color identification node identifies the red dates in the image, the identification result is marked as O, if the identification result is red, the O is equal to '1', the grasping is judged to be met, and if not, the O is equal to '0', the grasping is not met;
detecting the red dates in the image by using a flaw detection node, marking a detection result as P, if the red dates in the detection result have no flaws, judging that P is equal to '1', and judging that the picking is met, otherwise, judging that P is equal to '0', and not meeting the picking;
after the red date grading unit receives the image, measuring the long diameter of the red dates through a size measuring node, and marking a measuring result as D; according to the grading standard of the dried red dates, a grabbing instruction is sent to the red dates with different diameters, and the grading sorting module controls the three-axis truss manipulator (8) to grab the red dates with different grades into the red date sorting box (4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210356257.5A CN114653612A (en) | 2022-04-06 | 2022-04-06 | Red date letter sorting system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210356257.5A CN114653612A (en) | 2022-04-06 | 2022-04-06 | Red date letter sorting system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114653612A true CN114653612A (en) | 2022-06-24 |
Family
ID=82035976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210356257.5A Pending CN114653612A (en) | 2022-04-06 | 2022-04-06 | Red date letter sorting system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114653612A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11165134A (en) * | 1997-12-07 | 1999-06-22 | Shikoku Instrumentation Co Ltd | Automatic sorting method for lettuce and the like |
| CN201041551Y (en) * | 2007-01-11 | 2008-03-26 | 浙江大学 | A real time detection and classification system for pearl based on machine vision |
| CN109332215A (en) * | 2018-12-17 | 2019-02-15 | 华东交通大学 | A kind of classification and grading plant for jujube sorting machine |
| 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 |
| CN113145492A (en) * | 2021-05-14 | 2021-07-23 | 河北工业大学 | Visual grading method and grading production line for pear appearance quality |
| CN113319013A (en) * | 2021-07-08 | 2021-08-31 | 陕西科技大学 | Apple intelligent sorting method based on machine vision |
-
2022
- 2022-04-06 CN CN202210356257.5A patent/CN114653612A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11165134A (en) * | 1997-12-07 | 1999-06-22 | Shikoku Instrumentation Co Ltd | Automatic sorting method for lettuce and the like |
| CN201041551Y (en) * | 2007-01-11 | 2008-03-26 | 浙江大学 | A real time detection and classification system for pearl based on machine vision |
| CN109332215A (en) * | 2018-12-17 | 2019-02-15 | 华东交通大学 | A kind of classification and grading plant for jujube sorting machine |
| 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 |
| CN113145492A (en) * | 2021-05-14 | 2021-07-23 | 河北工业大学 | Visual grading method and grading production line for pear appearance quality |
| CN113319013A (en) * | 2021-07-08 | 2021-08-31 | 陕西科技大学 | Apple intelligent sorting method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN107486415B (en) | Thin bamboo strip defect online detection system and detection method based on machine vision | |
| CN112893159B (en) | Coal gangue sorting method based on image recognition | |
| CN108287010B (en) | Crab multi-index grading device and method | |
| CN111940339B (en) | Red date letter sorting system based on artificial intelligence | |
| CN107185858B (en) | Fruit detection and classification system and method | |
| CN112808603B (en) | Fresh cut flower sorting device and method based on RealSense camera | |
| CN111545483B (en) | Chopstick sorting detection device and detection algorithm thereof | |
| CN113145492A (en) | Visual grading method and grading production line for pear appearance quality | |
| CN104056789A (en) | Carrot defect image quantitative detection method and carrot sorting apparatus | |
| CN110586502B (en) | Green plum sorting device and sorting method | |
| WO2023134286A1 (en) | Online automatic quality testing and classification method for cathode copper | |
| CN110813795B (en) | Device and method for detecting breakage of chemical fiber spindle paper tube on line | |
| CN111330874A (en) | Detection device and detection method for pollution or impurity defects of bottom area of medicine bottle | |
| CN114522900A (en) | Lotus seed core removing and defective product sorting device and sorting method | |
| CN111805541B (en) | Deep learning-based traditional Chinese medicine decoction piece cleaning and selecting device and cleaning and selecting method | |
| CN113333327A (en) | Automatic conveying and sorting system based on industrial robot | |
| CN114653612A (en) | Red date letter sorting system based on machine vision | |
| CN106991667A (en) | A kind of prawn integrality method of discrimination for building characteristics of image spectrum | |
| CN217165388U (en) | Unqualified glove classifying screen device | |
| CN113560214B (en) | Intelligent sorting system for pearls and application method thereof | |
| CN213529709U (en) | Fruit sorting machine | |
| CN111723861B (en) | Gangue percentage identification method for coal mine control baffle | |
| CN209271938U (en) | A kind of improvement device of jujube pickout apparatus | |
| CN111563519B (en) | Tea impurity identification method and sorting equipment based on Stacking weighting integrated learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |