CN112871746B - Automatic red date screening method - Google Patents
Automatic red date screening method Download PDFInfo
- Publication number
- CN112871746B CN112871746B CN202110048903.7A CN202110048903A CN112871746B CN 112871746 B CN112871746 B CN 112871746B CN 202110048903 A CN202110048903 A CN 202110048903A CN 112871746 B CN112871746 B CN 112871746B
- Authority
- CN
- China
- Prior art keywords
- red date
- red
- gray value
- images
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012216 screening Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000007547 defect Effects 0.000 claims abstract description 12
- 235000015277 pork Nutrition 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 9
- 230000009194 climbing Effects 0.000 claims description 6
- 206010000496 acne Diseases 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 239000000284 extract Substances 0.000 abstract 1
- 230000002950 deficient Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 241001247821 Ziziphus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- B07C5/34—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
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- 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
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/009—Sorting of fruit
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/90—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in food processing or handling, e.g. food conservation
Landscapes
- Sorting Of Articles (AREA)
Abstract
The application relates to the technical field of red date sorting, and discloses an automatic red date screening method, which comprises the following steps: s1, automatic feeding, S2, image acquisition, S3, image screening, S4 and sorting, wherein in the image screening, image processing software arranged in a computer extracts gray values of four images in the circumferential direction of red dates, the gray values reserved at the same place of the red dates shot in the four images are compared, the images with gray value changes within a set threshold are marked as normal dates, the images with gray value changes smaller than the set threshold are marked as cracks, and the images with gray value changes larger than the set threshold are marked as pork skin deformation cracks. The application has the following advantages and effects: for two defect parts of red date breakage and crack, the gray value change degree of the red date is obviously different from the gray value change of the normal red date, and the defect type of the red date can be accurately judged through the gray value change difference value.
Description
Technical Field
The application relates to the technical field of red date sorting, in particular to an automatic red date screening method.
Background
The intelligent red date sorting machine is mainly used for sorting the defects and grade sizes of jujubes and gray dates, and a fruit size sorting machine detection technology based on computer vision is mature, but the defect detection of fruit surfaces is a difficulty in fruit classification, and it is difficult to accurately and rapidly detect different defects such as blackheads, rotten damages, cracks and deformation on the surfaces of the red dates.
The Chinese patent publication No. CN 105268659B discloses a red date screening machine based on vision technology, which comprises: the system comprises a defective product removing system capable of identifying defective products of red dates and removing the identified defective products of the red dates, a red date conveying system for conveying the red dates to the defective product removing system, and a red date grading system which is connected with the defective product removing system and can store the red dates with the defective products removed according to the sizes. This application adopts to dial the wheel and turns over to the red date, compares the detection to the red date through two pictures of taking the different angles of red date, dials the wheel and dials the red date, and red date pivoted angle is uncertain, can not necessarily shoot the whole outer peripheral face of red date completely, and the red date both ends produce blackhead and rotten damage easiest, and the circumference of red date can only be shot to this application, is difficult to gather and screen the image at red date both ends.
Disclosure of Invention
The application aims to provide an automatic red date screening method which has the effects of high screening accuracy and high screening efficiency.
2. The technical aim of the application is realized by the following technical scheme: the method comprises the following steps:
s1, automatic feeding: red dates are placed in a storage hopper of a climbing machine, the red dates are transmitted to a distribution hopper through the climbing machine, the distribution hopper divides the red dates into two parts and respectively fall into a V-shaped groove, the red dates are arranged end to end in the V-shaped groove by vibration of a vibration motor and then fall onto a conveying roller of a transmission assembly one by one, and the conveying roller rotates under the action of a hairbrush, so that the red dates on the conveying roller are parallel to the conveying roller and are relatively fixed between the two conveying rollers;
s2, image acquisition: four images are collected by a CCD camera in the image collection unit according to a preset time interval in the circumferential direction of the red date, left and right side views are collected at two ends of the red date, and the collected image information is transmitted to a computer;
s3, image screening: extracting gray values of four images in the circumferential direction of the red date by using image processing software in the computer, taking a gray value range with the largest proportion in the red date as a gray value of a red date smooth surface, setting the gray value of the red date smooth surface to 0, regarding the gray value as a crease of the red date when the gray value is larger than the range, and reserving the original gray value; comparing the gray values reserved at the same place of the red dates shot in the four images, marking the images with gray value changes within a set threshold as normal dates, marking the images with gray value changes smaller than the set threshold as cracks, and marking the images with gray value changes larger than the set threshold as pork skin deformation cracks;
s4, sorting: and the processing result of the image processing software built in the computer is transmitted to the PLC, the PLC control cavity controls the action of the electromagnetic valve according to the processing result, the corresponding red dates are subjected to real-time sorting processing, and the red dates of different damage types and the red dates of different grades are sent out from the corresponding sorting channels.
The application is further provided with: in the step S2, the photographing interval time of the CCD camera is equal to the time of 1/4 turn of the red date.
The application is further provided with: in the step S3, the left side view and the right side view of the red date are extracted by the built-in image processing software of the computer, the RGB image model acquired by the CCD camera is converted into the HIS image model, and the HIS color model is adopted to screen the blackhead rotten damage of the red date.
The application is further provided with: in the step S3, four images of the red date in the circumferential direction are extracted by the built-in image processing software of the computer, the long-diameter and short-diameter pixel values of the red date in the images are extracted by adopting a four-line scanning method, the functional relation between the real values of the long-diameter and short-diameter of the red date and the pixel values is fitted, a red date size grading model is established, and the red date is divided into special grade, first grade, second grade and third grade according to the values of different long-diameter and short-diameter.
The application is further provided with: and (3) the set threshold in the step (S3) is trained by a large number of samples, and the distribution rule of the sample values is observed to obtain the threshold for measuring the red date defect types.
The application is further provided with: in the step S3, after the image is extracted by the image processing software built in the computer, the image is first subjected to threshold segmentation by using a maximum variance threshold method, and the red date area image is separated from the background.
The beneficial effects of the application are as follows:
1. adopt the transfer roller to transmit the red date, set up the CCD camera in the transfer roller both sides and can gather the image at red date both ends, the transfer roller can be rotated under the effect of brush to drive 360 rotations of red date, the rotational speed is comparatively invariable, through adjusting the frequency of shooing of CCD camera, can shoot four images on the red date global, can not have the dead angle to the surface and the both ends of red date and detect, guarantees the accuracy of screening result.
2. The computer is internally provided with image processing software to analyze four images in the circumferential direction of the red date, one image can be acquired every 90 degrees of rotation of the red date, 180 degrees of images of the upper surface of the red date can be shot in each image, namely 50% of two adjacent images acquired by the CCD camera are overlapped parts, the red date with different rotation angles obtains different shadows of the images due to the fact that the angle of a light source in the illumination phase is fixed, the gray values of the same part of the red date are different under different rotation angles, the gray value change degree of the red date is obviously different from that of the red date at two defect parts of the red date breakage and the red date crack, the gray value change degree of the red date is smaller under different illumination due to the fact that pulp is exposed at the red date breakage part, the illumination angle is different at the crack part, the gray value change of the crack part is larger, the defect type of the red date can be accurately judged through the gray value change difference value, the screening method is simple, and the accuracy is high.
3. According to the application, the gray value of the smooth surface of the red date is set to 0, the numerical value of the red date can be denoised, the screening accuracy is improved, the gray values of the crease and the deformed crack of the red date are relatively close, the gray values of the crease and the deformed crack of the red date are difficult to distinguish only by the gray values, the gray values of the crease of the red date are reserved, and then the gray value difference values of the crease and the deformed crack of the adjacent photo are compared, so that the crease and the deformed crack can be effectively distinguished.
4. According to the automatic red date screening method, the defect condition of the red dates is judged through the comparison of the gray values of the same red date at different angles, the different defects of the red dates can be accurately screened out without complex calculation, and the accuracy rate and the screening efficiency of red date screening can be greatly improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic process diagram of the method of the present application.
Detailed Description
The technical scheme of the present application will be clearly and completely described in connection with specific embodiments. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Examples: an automatic red date screening method comprises the following steps:
s1, automatic feeding: red dates are placed in a storage hopper of a climbing machine, the red dates are transmitted to a distribution hopper through the climbing machine, the distribution hopper divides the red dates into two parts and respectively fall into a V-shaped groove, the red dates are arranged end to end in the V-shaped groove by vibration of a vibration motor and then fall onto a conveying roller of a transmission assembly one by one, and the conveying roller rotates under the action of a hairbrush, so that the red dates on the conveying roller are parallel to the conveying roller and are relatively fixed between the two conveying rollers;
s2, image acquisition: four images are collected by a CCD camera in the image collection unit according to a preset time interval in the circumferential direction of the red date, left and right side views are collected at two ends of the red date, and the collected image information is transmitted to a computer, wherein the photographing interval time of the CCD camera is equal to the time of 1/4 turn of the red date;
s3, image screening:
s301, extracting gray values of four images in the circumferential direction of the red date by using image processing software arranged in a computer;
s302, after an image is extracted by image processing software arranged in a computer, firstly, threshold segmentation is carried out on the image by adopting a maximum variance threshold method, and a red date area image is separated from a background;
s303, taking the gray value range with the largest ratio in the red dates as the gray value of the red date smooth surface, setting the gray value of the red date smooth surface to 0, and regarding the gray value larger than the range as the crease of the red dates, reserving the original gray value;
s304, comparing gray values reserved at the same place of the red dates shot in the four images;
s305, marking an image with the gray value change within a set threshold value as a normal date, marking an image with the gray value change smaller than the set threshold value as a crack, and marking an image with the gray value change larger than the set threshold value as a pork skin deformation crack;
setting a threshold value, training a large number of samples, and observing the distribution rule of the sample values to obtain a threshold value for measuring the types of the red date defects;
extracting left and right side views of the red date by built-in image processing software of a computer, converting an RGB image model acquired by a CCD camera into an HIS image model, and screening the blackhead rotten damage of the red date by adopting the HIS color model;
extracting four images in the circumferential direction of the red dates by using image processing software built in a computer, extracting long-diameter and short-diameter pixel values of the red dates in the images by using a four-line scanning method, fitting the functional relation between the true values of the long-diameter and short-diameter of the red dates in the bar and the pixel values, establishing a red date size grading model, and dividing the red dates into special grades, one grade, two grades and three grades according to the values of the different long-diameter and short-diameter;
s4, sorting: and the processing result of the image processing software built in the computer is transmitted to the PLC, the PLC control cavity controls the action of the electromagnetic valve according to the processing result, the corresponding red dates are subjected to real-time sorting processing, and the red dates of different damage types and the red dates of different grades are sent out from the corresponding sorting channels.
Claims (6)
1. An automatic red date screening method is characterized in that: the method comprises the following steps:
s1, automatic feeding: red dates are placed in a storage hopper of a climbing machine, the red dates are transmitted to a distribution hopper through the climbing machine, the distribution hopper divides the red dates into two parts and respectively fall into a V-shaped groove, the red dates are arranged end to end in the V-shaped groove by vibration of a vibration motor and then fall onto a conveying roller of a transmission assembly one by one, and the conveying roller rotates under the action of a hairbrush, so that the red dates on the conveying roller are parallel to the conveying roller and are relatively fixed between the two conveying rollers;
s2, image acquisition: four images are collected by a CCD camera in the image collection unit according to a preset time interval in the circumferential direction of the red date, left and right side views are collected at two ends of the red date, and the collected image information is transmitted to a computer;
s3, image screening: extracting gray values of four images in the circumferential direction of the red date by using image processing software in the computer, taking a gray value range with the largest proportion in the red date as a gray value of a red date smooth surface, setting the gray value of the red date smooth surface to 0, regarding the gray value as a crease of the red date when the gray value is larger than the range, and reserving the original gray value; comparing the gray values reserved at the same place of the red dates shot in the four images, marking the images with gray value changes within a set threshold as normal dates, marking the images with gray value changes smaller than the set threshold as cracks, and marking the images with gray value changes larger than the set threshold as pork skin deformation cracks;
s4, sorting: and the processing result of the image processing software built in the computer is transmitted to the PLC, the PLC control cavity controls the action of the electromagnetic valve according to the processing result, the corresponding red dates are subjected to real-time sorting processing, and the red dates of different damage types and the red dates of different grades are sent out from the corresponding sorting channels.
2. The automated red date screening method according to claim 1, wherein: in the step S2, the photographing interval time of the CCD camera is equal to the time of 1/4 turn of the red date.
3. The automated red date screening method according to claim 1, wherein: in the step S3, the left side view and the right side view of the red date are extracted by the built-in image processing software of the computer, the RGB image model acquired by the CCD camera is converted into the HIS image model, and the HIS color model is adopted to screen the blackhead rotten damage of the red date.
4. The automated red date screening method according to claim 1, wherein: in the step S3, four images of the red date in the circumferential direction are extracted by the built-in image processing software of the computer, the long-diameter and short-diameter pixel values of the red date in the images are extracted by adopting a four-line scanning method, the true values of the long-diameter and short-diameter of the red date in the bar are fitted with the functional relation of the pixel values, a red date size grading model is established, and the red date is divided into special grade, first grade, second grade and third grade according to the values of different long-diameter and short-diameter.
5. The automated red date screening method according to claim 1, wherein: and (3) the set threshold in the step (S3) is trained by a large number of samples, and the distribution rule of the sample values is observed to obtain the threshold for measuring the red date defect types.
6. The automated red date screening method according to claim 1, wherein: in the step S3, after the image is extracted by the image processing software built in the computer, the image is first subjected to threshold segmentation by using a maximum variance threshold method, and the red date area image is separated from the background.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110048903.7A CN112871746B (en) | 2021-01-14 | 2021-01-14 | Automatic red date screening method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110048903.7A CN112871746B (en) | 2021-01-14 | 2021-01-14 | Automatic red date screening method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112871746A CN112871746A (en) | 2021-06-01 |
| CN112871746B true CN112871746B (en) | 2023-10-20 |
Family
ID=76048734
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110048903.7A Active CN112871746B (en) | 2021-01-14 | 2021-01-14 | Automatic red date screening method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112871746B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103185609A (en) * | 2011-12-29 | 2013-07-03 | 机械科学研究总院先进制造技术研究中心 | Image detecting method for grading of tomatoes |
| KR101635460B1 (en) * | 2015-03-20 | 2016-07-01 | 최병훈 | Fruit sorting machine |
| CN106311628A (en) * | 2016-08-29 | 2017-01-11 | 安徽兆晨农业科技发展有限公司 | Red jujube grading device |
| CN108526043A (en) * | 2018-06-29 | 2018-09-14 | 天津工业大学 | A kind of machine classification equipment for jujube quality-screening based on deep learning |
| CN112200826A (en) * | 2020-10-15 | 2021-01-08 | 北京科技大学 | Industrial weak defect segmentation method |
-
2021
- 2021-01-14 CN CN202110048903.7A patent/CN112871746B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103185609A (en) * | 2011-12-29 | 2013-07-03 | 机械科学研究总院先进制造技术研究中心 | Image detecting method for grading of tomatoes |
| KR101635460B1 (en) * | 2015-03-20 | 2016-07-01 | 최병훈 | Fruit sorting machine |
| CN106311628A (en) * | 2016-08-29 | 2017-01-11 | 安徽兆晨农业科技发展有限公司 | Red jujube grading device |
| CN108526043A (en) * | 2018-06-29 | 2018-09-14 | 天津工业大学 | A kind of machine classification equipment for jujube quality-screening based on deep learning |
| CN112200826A (en) * | 2020-10-15 | 2021-01-08 | 北京科技大学 | Industrial weak defect segmentation method |
Non-Patent Citations (1)
| Title |
|---|
| 基于HSV色彩空间的红枣叶片病斑分割方法;李新疆;王赏贵;王丹;李扬;李疆;;安徽农学通报(第04期);第213-218页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112871746A (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110403232B (en) | Cigarette quality detection method based on secondary algorithm | |
| CN110044910B (en) | Automobile cup box part detection system and detection method | |
| CN110648364B (en) | Multi-dimensional space solid waste visual detection positioning and identification method and system | |
| CN107966454A (en) | A kind of end plug defect detecting device and detection method based on FPGA | |
| CN108596880A (en) | Weld defect feature extraction based on image procossing and welding quality analysis method | |
| CN107402221A (en) | A kind of defects of display panel recognition methods and system based on machine vision | |
| CN111266315A (en) | Ore material online sorting system and method based on visual analysis | |
| CN104056789B (en) | Carrot defect image quantitative detection method | |
| CN112184648A (en) | Piston surface defect detection method and system based on deep learning | |
| CN205538710U (en) | Inductance quality automatic check out system based on machine vision | |
| CN1664568A (en) | Fruit quality detection system based on image information fusion technology | |
| CN104048966B (en) | The detection of a kind of fabric defect based on big law and sorting technique | |
| Samarawickrama et al. | Matlab based automated surface defect detection system for ceremic tiles using image processing | |
| CN107328781A (en) | A kind of columnar product detection method of surface flaw and device based on machine vision | |
| CN106872473A (en) | A kind of potato defects detection identifying system design based on machine vision | |
| CN104952754A (en) | Coated silicon chip sorting method based on machine vision | |
| CN110858395A (en) | Method for detecting dirty yarn defect of coiled filament | |
| CN113894055A (en) | Hardware surface defect detection and classification system and method based on machine vision | |
| CN111667475A (en) | Machine vision-based Chinese date grading detection method | |
| CN114113129B (en) | Lens micro defect recognition and grabbing system and method | |
| CN112801965A (en) | Sintering belt foreign matter monitoring method and system based on convolutional neural network | |
| CN112871746B (en) | Automatic red date screening method | |
| CN109596620A (en) | Product surface shape defect detection method and system based on machine vision | |
| CN117214178A (en) | Intelligent identification method for appearance defects of package on packaging production line | |
| CN116740449A (en) | Shaving form detection method and system based on AI (advanced technology attachment) computer vision technology |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |