CN111842216A - Agricultural product quality detection automatic sorting management system based on machine vision - Google Patents
Agricultural product quality detection automatic sorting management system based on machine vision Download PDFInfo
- Publication number
- CN111842216A CN111842216A CN202010869834.1A CN202010869834A CN111842216A CN 111842216 A CN111842216 A CN 111842216A CN 202010869834 A CN202010869834 A CN 202010869834A CN 111842216 A CN111842216 A CN 111842216A
- Authority
- CN
- China
- Prior art keywords
- odor
- agricultural products
- agricultural
- agricultural product
- separation
- 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.)
- Withdrawn
Links
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
- B07C5/34—Sorting according to other particular properties
- B07C5/3416—Sorting according to other particular properties according to radiation transmissivity, e.g. for light, x-rays, particle radiation
-
- 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
-
- 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
- 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
- B07C5/38—Collecting or arranging articles in groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Abstract
The invention discloses an automatic sorting management system for agricultural product quality detection based on machine vision, which comprises a conveying module, an image acquisition module, an image processing module, a shape detection module, a shape analysis module, a smell detection module, a smell analysis module, a cloud server, a master control center, a display terminal and a storage database, wherein the conveying module is used for conveying agricultural products; according to the invention, gray level images of all bagged agricultural products detected under x-rays and odor indexes emitted by all agricultural products are detected, gray level values of different areas in the gray level images of all agricultural products are analyzed, whether all agricultural products are damaged or not is judged, the numbers of the separation grooves corresponding to the damaged agricultural products are counted, whether the odor indexes emitted by all agricultural products exceed the standard or not is judged, the numbers of the separation grooves corresponding to the agricultural products with the odor indexes exceeding the standard are counted, agricultural products with unqualified quality and agricultural products with defective products are screened, and the agricultural products are stored in corresponding storage areas, so that the labor force is reduced, and the detection efficiency and accuracy are improved.
Description
Technical Field
The invention relates to the field of agricultural product quality detection management, in particular to an automatic sorting management system for agricultural product quality detection based on machine vision.
Background
With the improvement of living standard of people, the attention of consumers to agricultural products is converted from quantity to quality, the bagging cultivation technology is one of the widely adopted technologies for producing pollution-free high-quality agricultural products at present, and the problem that the quality of the bagged agricultural products needs to be accurately detected in order to guarantee the physical health of the consumers is urgently solved.
At present, current bagging agricultural product quality detection technique ubiquitous some are not enough, traditional bagging agricultural product quality detection adopts artifical naked eye detection mode basically, open the bagging of agricultural product at random through the manual work, rely on whether the naked eye detects the agricultural product surface and damages, can't detect whether the agricultural product is inside rotten, the accuracy is not high, and judge whether bagging agricultural product gives off peculiar smell gas according to artificial smell sense, so not only need a large amount of hand labor, and reduce the efficiency of detecting the agricultural product quality, the workman is after long-time work, because visual fatigue, produce the mistake easily and carry out wrong letter sorting with the fruit of existing problem, influence the consumer to the reputation evaluation of trade company easily, in order to solve above problem, an agricultural product quality detection automated sorting management system based on machine vision now designs.
Disclosure of Invention
The invention aims to provide an automatic sorting management system for quality detection of agricultural products based on machine vision, which detects gray level images of all bagged agricultural products under x-rays through a shape detection module, analyzes the gray level values of different areas in the gray level images of all agricultural products, comparing and judging whether each agricultural product is damaged, counting the number of the separation groove corresponding to the damaged agricultural product, detecting the index of the odor emitted by each agricultural product through the odor detection module, comparing to obtain whether the index of the odor gas emitted by each agricultural product exceeds the standard, counting the number of the corresponding separation groove, the agricultural products with unqualified quality and the agricultural products with defective products are compared and screened out through the cloud server, and are stored in the corresponding storage area, meanwhile, the influence coefficient of the qualified quality of the agricultural products is calculated and displayed, and the problems in the background technology are solved.
The purpose of the invention can be realized by the following technical scheme:
an automatic sorting management system for quality detection of agricultural products based on machine vision comprises a conveying module, an image acquisition module, an image processing module, a shape detection module, a shape analysis module, a smell detection module, a smell analysis module, a cloud server, a master control center, a display terminal and a storage database;
the cloud server is respectively connected with the appearance analysis module, the odor analysis module, the master control center and the display terminal, the storage database is respectively connected with the conveying module, the appearance analysis module and the odor analysis module, the image processing module is respectively connected with the image acquisition module, the appearance analysis module and the odor analysis module, the appearance detection module is connected with the appearance analysis module, and the odor detection module is connected with the odor analysis module;
the conveying module adopts conveying belts which are provided with separating grooves and are provided with skirt edges and are used for quantitatively conveying and transporting agricultural products, the separating grooves on each conveying belt are numbered in sequence, the number is 1,2, a.
The image acquisition module comprises a high-definition camera, wherein the high-definition camera is respectively arranged above the appearance detection area and the smell detection area and is used for respectively acquiring images of each separation tank passing through the appearance detection area and the smell detection area on the conveying belt and sending the acquired images of each separation tank to the image processing module;
the image processing module is used for receiving each separating groove image which is sent by the image acquisition module and passes through the shape detection area and each separating groove image which passes through the odor detection area, carrying out image segmentation on each received separating groove image, selecting a minimum area wrapping each separating groove number, strengthening the image high-frequency component of the minimum area, respectively obtaining an enhanced image of each separating groove number which passes through the shape detection area and the odor detection area, extracting the corresponding separating groove number in each enhanced image, sending each separating groove number which passes through the shape detection area to the shape analysis module, and sending each separating groove number which passes through the odor detection area to the odor analysis module;
the shape detection module comprises a shell and an x-ray detector, wherein the shell is of a shell structure with an opening at the lower end and the size of the shell structure corresponds to that of the separation groove, the x-ray detector is arranged above the inside of the shell and used for detecting a gray level image of an agricultural product in the separation groove reaching the shape detection area on the conveying belt, extracting an absorption value of each pixel point in the received gray level image of the agricultural product in each separation groove, and sending the absorption value of each pixel point in the detected gray level image of the agricultural product in each separation groove to the shape analysis module;
the appearance analysis module is used for receiving the serial numbers of the separation grooves passing through the appearance detection area and sent by the image processing module, receiving the absorption values of pixel points in the gray level image of the agricultural product in the separation grooves reaching the appearance detection area and sent by the appearance detection module, calculating the gray level value corresponding to the pixel points in the gray level image of the agricultural product in each division groove, counting the areas corresponding to the same gray level value in the gray level image of the agricultural product in each division groove, and forming a gray level value set W of different areas in the gray level image of the agricultural product in each separation groovenRf(w1rf,w2rf,...,wirf,...,wnrf)，wirfExpressing the gray values as the gray value of the f-th area in the gray image of the agricultural product in the ith separating groove, wherein f is 1,2, 1 and x, extracting the gray value range of different areas in the standard gray image detected by the agricultural product under the x-ray stored in the storage database, comparing the gray value of different areas in the gray image of the agricultural product in each separating groove reaching the shape detection area with the gray value range of the corresponding area in the standard gray image detected by the corresponding agricultural product under the x-ray, if the gray value of a certain area in the gray image of the agricultural product in a certain separating groove is out of the gray value range of the corresponding area in the standard gray image, indicating that the agricultural product is damaged, counting the numbers of the separating grooves corresponding to the agricultural products with damage, and forming a separating groove number set A corresponding to the agricultural products with damagem(a1,a2,...,aj,...,am),m≤n，ajIndicating that damaged agricultural products exist in the jth separation groove, and sending a separation groove number set corresponding to each damaged agricultural product to a cloud server;
the odor detection module comprises a closed shell and an odor sensor, wherein the closed shell is a shell structure with an opening at the lower end and corresponding to the size of the separation grooveThe odor sensor is arranged above the inside of the closed shell and used for detecting odor gas indexes emitted by the agricultural products in the separation grooves reaching the odor detection area on the conveyor belt, counting the odor gas indexes emitted by the agricultural products in the separation grooves reaching the odor detection area, and forming an odor gas index set Q emitted by the agricultural products in the separation groovesn(q1,q2,...,qi,...,qn)，qiExpressing the index of the odor gas emitted by the agricultural product in the ith separation groove, and sending the index set of the odor gas emitted by the agricultural product in each separation groove to an odor analysis module;
the odor analysis module is used for receiving the serial numbers of the separation grooves which are sent by the image processing module and pass through the odor detection area, receiving the odor gas index set sent by the odor detection module and emitted by the agricultural products in the separation grooves, extracting and storing the qualified odor gas index range emitted by the agricultural products stored in the database, comparing the odor gas index emitted by the agricultural products in the separation grooves reaching the odor detection area with the qualified odor gas index range emitted by the corresponding agricultural products, if the odor gas index emitted by the agricultural products in the separation grooves reaching the odor detection area is within the qualified odor gas index range emitted by the corresponding agricultural products, indicating that the odor gas index emitted by the agricultural products is normal, and if the odor gas index emitted by the agricultural products in the division grooves reaching the odor detection area is outside the qualified odor gas index range emitted by the corresponding agricultural products, the index of the odor gas emitted by the agricultural products exceeds the standard, the number of the separation groove corresponding to each agricultural product with the index of the odor gas exceeding the standard is counted, and a collection B of the number of the separation groove corresponding to each agricultural product with the index of the odor gas exceeding the standard is formedk(b1,b2,...,bl,...,bk),k≤n，blThe agricultural products with the odor emission indexes exceeding the standard in the first separation groove are represented, and the separation groove number set corresponding to each agricultural product with the odor emission indexes exceeding the standard is sent to the cloud server;
the cloud server is used for receiving a separation groove number set which is sent by the appearance analysis module and corresponds to each damaged agricultural product, receiving a separation groove number set which is sent by the odor analysis module and corresponds to each agricultural product with an excessive odor emission index, comparing the received separation groove number set which corresponds to each damaged agricultural product with the separation groove number set which corresponds to each agricultural product with an excessive odor emission index, screening separation grooves with the same number in the two sets, indicating that the quality of the agricultural products in the separation grooves is unqualified, sending the separation groove numbers corresponding to the agricultural products with unqualified quality to the master control center, counting the separation grooves with the residual numbers in the two sets, indicating that the agricultural products in the residual separation grooves are defective products, and sending the separation groove numbers corresponding to the agricultural products with the defective products to the master control center; meanwhile, the cloud server comprehensively calculates the qualified quality influence coefficient of the agricultural products and sends the qualified quality influence coefficient of the agricultural products to the display terminal;
the main control center is used for receiving the number of the separation grooves corresponding to the agricultural products with unqualified quality and the number of the separation grooves corresponding to the agricultural products with defective products, which are sent by the cloud server, when the separation grooves corresponding to the agricultural products with unqualified quality or the separation grooves corresponding to the agricultural products with defective products reach the tail end of the conveying belt, the main control center respectively pushes the agricultural products with unqualified quality or the agricultural products with defective products onto the conveying belt of the corresponding quality inspection channel by controlling the material pushing manipulator, stores the agricultural products with unqualified quality or the agricultural products with defective products in the corresponding storage area, and informs related personnel of carrying out secondary detection on the area of the agricultural products storing the defective products;
the display terminal is used for receiving the influence coefficient of the qualified quality of the agricultural product sent by the cloud server and displaying the influence coefficient;
the storage database is used for receiving the serial numbers of the separation grooves on the conveying belts sent by the conveying module, storing the gray value ranges of different areas in the standard gray image detected by the agricultural products under the X-ray and storing the qualified odor index ranges emitted by the agricultural products;
further, a gray value calculation formula corresponding to each pixel point in the gray image of the agricultural product in the segmentation groove is as follows
ryExpressed as the gray value R corresponding to the y-th pixel point in the gray image of the agricultural product in the cutting groovey,Gy,ByRespectively expressing the values as the absorption values of the red primary color, the green primary color and the blue primary color in the y-th pixel point in the gray level image of the agricultural product in the segmentation groove;
further, the calculation formula of the qualified quality influence coefficient of the agricultural products is
wjrfExpressing the gray value of the f-th area in the gray image of the damaged agricultural product in the j-th separation groove, wherein f is 1,2lExpressed as index of odor gas of agricultural product with excessive odor gas index in the first separation groove, qmaxAnd q isminExpressed as the maximum and minimum values, w, of the acceptable odorous gas index range emitted by the agricultural productirfExpressed as the gray value of the f area in the gray image of the agricultural product in the i separating groove, qiExpressed as index of off-flavor gas emitted by the produce in the ith compartment.
Has the advantages that:
(1) according to the automatic sorting management system for detecting the quality of the agricultural products based on the machine vision, the gray level images of all bagged agricultural products detected under the X-ray are detected through the shape detection module, the gray level values of different areas in the gray level images of all the agricultural products are analyzed, whether all the agricultural products are damaged or not is judged through comparison, therefore, the detection accuracy is improved, the numbers of the separation grooves corresponding to the damaged agricultural products are counted, meanwhile, the odor gas indexes emitted by all the agricultural products are detected through the odor detection module, whether the odor gas indexes emitted by all the agricultural products exceed the standard or not is obtained through comparison, the detection efficiency is improved, the manual labor force is greatly reduced, the numbers of the corresponding separation grooves are counted, and a reliable reference basis is provided for later-stage statistics and agricultural product quality distinguishing.
(2) According to the invention, the agricultural products with unqualified quality and the agricultural products with defective products are screened out through the comparison of the cloud server, meanwhile, the pushing manipulator is controlled by the master control center to respectively push the agricultural products with unqualified quality or the agricultural products with defective products onto the conveyer belts of the corresponding quality inspection channels, and store the agricultural products onto the corresponding storage areas, and related personnel are informed to carry out secondary detection on the areas of the agricultural products storing the defective products, so that the cost loss of the agricultural products is reduced, the detection error rate is reduced, the credit evaluation of consumers to merchants is improved, meanwhile, the influence coefficient of the qualified quality of the agricultural products is calculated and displayed, and the management personnel can conveniently and visually know the qualified quality condition of the agricultural products.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of the connection relationship between modules according to the present invention;
FIG. 2 is a partial front view of the automated sorting apparatus of the present invention;
FIG. 3 is a partial top plan view of the automated sorting apparatus of the present invention;
fig. 4 is a cross-sectional view of a profile detection module and an odor detection module of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an automatic sorting management system for quality inspection of agricultural products based on machine vision comprises a conveying module, an image acquisition module, an image processing module, a shape inspection module, a shape analysis module, a smell inspection module, a smell analysis module, a cloud server, a master control center, a display terminal and a storage database;
the cloud server is respectively connected with the appearance analysis module, the odor analysis module, the master control center and the display terminal, the storage database is respectively connected with the conveying module, the appearance analysis module and the odor analysis module, the image processing module is respectively connected with the image acquisition module, the appearance analysis module and the odor analysis module, the appearance detection module is connected with the appearance analysis module, and the odor detection module is connected with the odor analysis module;
the conveying module adopts conveying belts which are provided with separating grooves and are provided with skirt edges and are used for quantitatively conveying and transporting agricultural products, the separating grooves on each conveying belt are numbered in sequence, the number is 1,2, a.
The image acquisition module comprises a high-definition camera, wherein the high-definition camera is respectively arranged above the appearance detection area and the smell detection area and is used for respectively acquiring images of each separation tank passing through the appearance detection area and the smell detection area on the conveying belt and sending the acquired images of each separation tank to the image processing module;
the image processing module is used for receiving the images of the separation grooves passing through the shape detection area and the images of the separation grooves passing through the odor detection area, which are sent by the image acquisition module, carrying out image segmentation on the received images of the separation grooves, selecting the minimum area wrapping the serial numbers of the separation grooves, strengthening the high-frequency components of the images of the minimum area, respectively obtaining the enhanced images of the serial numbers of the separation grooves passing through the shape detection area and the odor detection area, extracting the corresponding serial numbers of the separation grooves in the enhanced images, sending the serial numbers of the separation grooves passing through the shape detection area to the shape analysis module, and sending the serial numbers of the separation grooves passing through the odor detection area to the odor analysis module.
The shape detection module comprises a shell and an x-ray detector, wherein the shell is of a shell structure with an opening at the lower end and the size of the shell structure corresponds to that of the separation groove, the x-ray detector is arranged above the inside of the shell and used for detecting a gray level image of an agricultural product in the separation groove reaching the shape detection area on the conveying belt, extracting an absorption value of each pixel point in the received gray level image of the agricultural product in each separation groove, and sending the absorption value of each pixel point in the detected gray level image of the agricultural product in each separation groove to the shape analysis module;
the appearance analysis module is used for receiving the serial numbers of the separation grooves passing through the appearance detection area and sent by the image processing module, receiving the absorption values of the pixel points in the gray level image of the agricultural product in the separation grooves reaching the appearance detection area and sent by the appearance detection module, calculating the gray level value corresponding to the pixel points in the gray level image of the agricultural product in each partition groove, and the gray level value calculation formula corresponding to the pixel points in the gray level image of the agricultural product in the partition groove is as follows
ryExpressed as the gray value R corresponding to the y-th pixel point in the gray image of the agricultural product in the cutting groovey,Gy,ByRespectively expressing the absorption values of the red primary color, the green primary color and the blue primary color in the y-th pixel point in the gray level image of the agricultural product in each partition groove, counting the areas corresponding to the same gray level value in the gray level image of the agricultural product in each partition groove, and forming a gray level value set W of different areas in the gray level image of the agricultural product in each partition groovenRf(w1rf,w2rf,...,wirf,...,wnrf)，wirfExpressing the gray values as the gray value of the f-th area in the gray image of the agricultural product in the i-th separation groove, wherein f is 1,2, 1, x, extracting the gray value range of different areas in the standard gray image detected by the agricultural product under the x-ray stored in the storage database, comparing the gray value of different areas in the gray image of the agricultural product in each separation groove reaching the shape detection area with the gray value range of the corresponding area in the standard gray image detected by the corresponding agricultural product under the x-ray, thereby improving the detection accuracy, and if the gray value of a certain area in the gray image of the agricultural product in a certain separation groove is in the gray value range of the corresponding area in the standard gray imageIf the value is out of the range, the agricultural products are damaged, the number of the separation groove corresponding to each damaged agricultural product is counted, a reliable reference basis is provided for later-stage counting and agricultural product quality distinguishing, and a separation groove number set A corresponding to each damaged agricultural product is formedm(a1,a2,...,aj,...,am),m≤n，ajAnd when the damaged agricultural products exist in the jth separation groove, sending the separation groove number set corresponding to each damaged agricultural product to the cloud server.
The odor detection module comprises a closed shell cover and an odor sensor, wherein the closed shell cover is of a shell structure with an opening at the lower end and corresponding to the size of the separation groove, the closed shell cover is used for sealing and surrounding the agricultural products reaching the position right below the odor detection area on the conveying belt, the odor sensor is arranged above the inner portion of the closed shell cover and used for detecting odor gas indexes emitted by the agricultural products in the separation grooves reaching the odor detection area on the conveying belt, counting the odor gas indexes emitted by the agricultural products in the separation grooves reaching the odor detection area, and forming an odor gas index set Q emitted by the agricultural products in each separation grooven(q1,q2,...,qi,...,qn)，qiExpressing the index of the odor gas emitted by the agricultural product in the ith separation groove, and sending the index set of the odor gas emitted by the agricultural product in each separation groove to an odor analysis module;
the odor analysis module is used for receiving the serial numbers of the separation grooves which are sent by the image processing module and pass through the odor detection area, receiving the odor gas index set sent by the odor detection module and emitted by the agricultural products in the separation grooves, extracting the qualified odor gas index range emitted by the agricultural products stored in the storage database, comparing the odor gas index emitted by the agricultural products in the separation grooves reaching the odor detection area with the qualified odor gas index range emitted by the corresponding agricultural products, if the odor gas index emitted by the agricultural products in the separation grooves reaching the odor detection area is within the qualified odor gas index range emitted by the corresponding agricultural products, indicating that the odor gas index emitted by the agricultural products is normal, and if the odor gas index reaches the separation grooves of the odor detection area, indicating that the odor gas index emitted by the agricultural products is normalThe odor gas index emitted by the agricultural products in the cutting is out of the range of the qualified odor gas index emitted by the corresponding agricultural products, and the odor gas index emitted by the agricultural products exceeds the standard, so that the detection efficiency is improved, the manual labor is greatly reduced, the number of the separation grooves corresponding to the agricultural products with the odor gas index exceeding the standard is counted, reliable reference basis is provided for later-stage counting and distinguishing the quality of the agricultural products, and a separation groove number set B corresponding to the agricultural products with the odor gas index exceeding the standard is formedk(b1,b2,...,bl,...,bk),k≤n，blAnd (4) expressing the agricultural products with the odor emission indexes exceeding the standard in the first separation groove, and sending the separation groove number set corresponding to each agricultural product with the odor emission indexes exceeding the standard to the cloud server.
The cloud server is used for receiving a separation groove number set which is sent by the appearance analysis module and corresponds to each damaged agricultural product, receiving a separation groove number set which is sent by the odor analysis module and corresponds to each agricultural product with an excessive odor emission index, comparing the received separation groove number set which corresponds to each damaged agricultural product with the separation groove number set which corresponds to each agricultural product with an excessive odor emission index, screening separation grooves with the same number in the two sets, indicating that the quality of the agricultural products in the separation grooves is unqualified, sending the separation groove numbers corresponding to the agricultural products with unqualified quality to the master control center, counting the separation grooves with the residual numbers in the two sets, indicating that the agricultural products in the residual separation grooves are defective products, and sending the separation groove numbers corresponding to the agricultural products with the defective products to the master control center; meanwhile, the cloud server comprehensively calculates the qualified quality influence coefficient of the agricultural products, and the calculation formula of the qualified quality influence coefficient of the agricultural products is
wjrfExpressing the gray value of the f-th area in the gray image of the damaged agricultural product in the j-th separation groove, wherein f is 1,2lExpressed as index of odor gas of agricultural product with excessive odor gas index in the first separation groove, qmaxAnd q isminExpressed as the maximum and minimum values, w, of the acceptable odorous gas index range emitted by the agricultural productirfExpressed as the gray value of the f area in the gray image of the agricultural product in the i separating groove, qiThe index is expressed as the index of the odor gas emitted by the agricultural products in the ith separation groove, and the qualified quality influence coefficient of the agricultural products is sent to the display terminal.
The main control center is used for receiving the number of the separation grooves corresponding to the unqualified agricultural products and the number of the separation grooves corresponding to the defective agricultural products, which are sent by the cloud server, when the separation grooves corresponding to the unqualified agricultural products or the separation grooves corresponding to the defective agricultural products reach the tail end of the conveying belt, the main control center respectively pushes the unqualified agricultural products or the defective agricultural products onto the conveying belt corresponding to the quality inspection channel by controlling the material pushing manipulator, stores the unqualified agricultural products or the defective agricultural products in the corresponding storage area, and informs related personnel of carrying out secondary detection on the area of the stored defective agricultural products, so that the cost loss of the agricultural products is reduced, the detection error rate is reduced, and the credit evaluation of consumers on merchants is improved.
The display terminal is used for receiving the influence coefficient of the qualified quality of the agricultural products sent by the cloud server and displaying the influence coefficient, so that management personnel can know the qualified quality of the agricultural products visually.
The storage database is used for receiving the serial numbers of the separation grooves on the conveying belts sent by the conveying module, storing the gray value ranges of different areas in the standard gray image detected by the agricultural products under the X-ray and storing the qualified odor index ranges emitted by the agricultural products.
The foregoing is merely exemplary and illustrative of the principles of the present invention and various modifications, additions and substitutions of the specific embodiments described herein may be made by those skilled in the art without departing from the principles of the present invention or exceeding the scope of the claims set forth herein.
Claims (3)
1. The utility model provides an agricultural product quality testing automation letter sorting management system based on machine vision which characterized in that: the system comprises a conveying module, an image acquisition module, an image processing module, a shape detection module, a shape analysis module, an odor detection module, an odor analysis module, a cloud server, a master control center, a display terminal and a storage database;
the cloud server is respectively connected with the appearance analysis module, the odor analysis module, the master control center and the display terminal, the storage database is respectively connected with the conveying module, the appearance analysis module and the odor analysis module, the image processing module is respectively connected with the image acquisition module, the appearance analysis module and the odor analysis module, the appearance detection module is connected with the appearance analysis module, and the odor detection module is connected with the odor analysis module;
the conveying module adopts conveying belts which are provided with separating grooves and are provided with skirt edges and are used for quantitatively conveying and transporting agricultural products, the separating grooves on each conveying belt are numbered in sequence, the number is 1,2, a.
The image acquisition module comprises a high-definition camera, wherein the high-definition camera is respectively arranged above the appearance detection area and the smell detection area and is used for respectively acquiring images of each separation tank passing through the appearance detection area and the smell detection area on the conveying belt and sending the acquired images of each separation tank to the image processing module;
the image processing module is used for receiving each separating groove image which is sent by the image acquisition module and passes through the shape detection area and each separating groove image which passes through the odor detection area, carrying out image segmentation on each received separating groove image, selecting a minimum area wrapping each separating groove number, strengthening the image high-frequency component of the minimum area, respectively obtaining an enhanced image of each separating groove number which passes through the shape detection area and the odor detection area, extracting the corresponding separating groove number in each enhanced image, sending each separating groove number which passes through the shape detection area to the shape analysis module, and sending each separating groove number which passes through the odor detection area to the odor analysis module;
the shape detection module comprises a shell and an x-ray detector, wherein the shell is of a shell structure with an opening at the lower end and the size of the shell structure corresponds to that of the separation groove, the x-ray detector is arranged above the inside of the shell and used for detecting a gray level image of an agricultural product in the separation groove reaching the shape detection area on the conveying belt, extracting an absorption value of each pixel point in the received gray level image of the agricultural product in each separation groove, and sending the absorption value of each pixel point in the detected gray level image of the agricultural product in each separation groove to the shape analysis module;
the appearance analysis module is used for receiving the serial numbers of the separation grooves passing through the appearance detection area and sent by the image processing module, receiving the absorption values of pixel points in the gray level image of the agricultural product in the separation grooves reaching the appearance detection area and sent by the appearance detection module, calculating the gray level value corresponding to the pixel points in the gray level image of the agricultural product in each division groove, counting the areas corresponding to the same gray level value in the gray level image of the agricultural product in each division groove, and forming a gray level value set W of different areas in the gray level image of the agricultural product in each separation groovenRf(w1rf,w2rf,...,wirf,...,wnrf)，wirfExpressing the gray values as the gray value of the f-th area in the gray image of the agricultural product in the ith separating groove, wherein f is 1,2, 1 and x, extracting the gray value range of different areas in the standard gray image detected by the agricultural product under the x-ray stored in the storage database, comparing the gray value of different areas in the gray image of the agricultural product in each separating groove reaching the shape detection area with the gray value range of the corresponding area in the standard gray image detected by the corresponding agricultural product under the x-ray, if the gray value of a certain area in the gray image of the agricultural product in a certain separating groove is out of the gray value range of the corresponding area in the standard gray image, indicating that the agricultural product is damaged, counting the numbers of the separating grooves corresponding to the agricultural products with damage, and forming a separating groove number set A corresponding to the agricultural products with damagem(a1,a2,...,aj,...,am),m≤n，ajExpressing that damaged agricultural products exist in the jth separation groove, and collecting the number of the separation grooves corresponding to the damaged agricultural productsSending the data to a cloud server;
the odor detection module comprises a closed shell cover and an odor sensor, wherein the closed shell cover is of a shell structure with an opening at the lower end and corresponding to the size of the separation groove, the closed shell cover is used for sealing and surrounding the agricultural products reaching the position right below the odor detection area on the conveying belt, the odor sensor is arranged above the inner portion of the closed shell cover and used for detecting odor gas indexes emitted by the agricultural products in the separation grooves reaching the odor detection area on the conveying belt, counting the odor gas indexes emitted by the agricultural products in the separation grooves reaching the odor detection area, and forming an odor gas index set Q emitted by the agricultural products in each separation grooven(q1,q2,...,qi,...,qn)，qiExpressing the index of the odor gas emitted by the agricultural product in the ith separation groove, and sending the index set of the odor gas emitted by the agricultural product in each separation groove to an odor analysis module;
the odor analysis module is used for receiving the serial numbers of the separation grooves which are sent by the image processing module and pass through the odor detection area, receiving the odor gas index set sent by the odor detection module and emitted by the agricultural products in the separation grooves, extracting and storing the qualified odor gas index range emitted by the agricultural products stored in the database, comparing the odor gas index emitted by the agricultural products in the separation grooves reaching the odor detection area with the qualified odor gas index range emitted by the corresponding agricultural products, if the odor gas index emitted by the agricultural products in the separation grooves reaching the odor detection area is within the qualified odor gas index range emitted by the corresponding agricultural products, indicating that the odor gas index emitted by the agricultural products is normal, and if the odor gas index emitted by the agricultural products in the division grooves reaching the odor detection area is outside the qualified odor gas index range emitted by the corresponding agricultural products, the index of the odor gas emitted by the agricultural products exceeds the standard, the number of the separation groove corresponding to each agricultural product with the index of the odor gas exceeding the standard is counted, and a collection B of the number of the separation groove corresponding to each agricultural product with the index of the odor gas exceeding the standard is formedk(b1,b2,...,bl,...,bk),k≤n，blDenoted as the first dividing groove inner powderSending the number set of the separation grooves corresponding to the agricultural products with the odor-emitting gas indexes exceeding the standard to a cloud server;
the cloud server is used for receiving a separation groove number set which is sent by the appearance analysis module and corresponds to each damaged agricultural product, receiving a separation groove number set which is sent by the odor analysis module and corresponds to each agricultural product with an excessive odor emission index, comparing the received separation groove number set which corresponds to each damaged agricultural product with the separation groove number set which corresponds to each agricultural product with an excessive odor emission index, screening separation grooves with the same number in the two sets, indicating that the quality of the agricultural products in the separation grooves is unqualified, sending the separation groove numbers corresponding to the agricultural products with unqualified quality to the master control center, counting the separation grooves with the residual numbers in the two sets, indicating that the agricultural products in the residual separation grooves are defective products, and sending the separation groove numbers corresponding to the agricultural products with the defective products to the master control center; meanwhile, the cloud server comprehensively calculates the qualified quality influence coefficient of the agricultural products and sends the qualified quality influence coefficient of the agricultural products to the display terminal;
the main control center is used for receiving the number of the separation grooves corresponding to the agricultural products with unqualified quality and the number of the separation grooves corresponding to the agricultural products with defective products, which are sent by the cloud server, when the separation grooves corresponding to the agricultural products with unqualified quality or the separation grooves corresponding to the agricultural products with defective products reach the tail end of the conveying belt, the main control center respectively pushes the agricultural products with unqualified quality or the agricultural products with defective products onto the conveying belt of the corresponding quality inspection channel by controlling the material pushing manipulator, stores the agricultural products with unqualified quality or the agricultural products with defective products in the corresponding storage area, and informs related personnel of carrying out secondary detection on the area of the agricultural products storing the defective products;
the display terminal is used for receiving the influence coefficient of the qualified quality of the agricultural product sent by the cloud server and displaying the influence coefficient;
the storage database is used for receiving the serial numbers of the separation grooves on the conveying belts sent by the conveying module, storing the gray value ranges of different areas in the standard gray image detected by the agricultural products under the X-ray and storing the qualified odor index ranges emitted by the agricultural products.
2. The machine-vision-based agricultural product quality inspection automated sorting management system of claim 1, wherein: the gray value calculation formula corresponding to each pixel point in the gray image of the agricultural product in the division groove is
ryExpressed as the gray value R corresponding to the y-th pixel point in the gray image of the agricultural product in the cutting groovey,Gy,ByRespectively expressed as the absorption values of the red primary color, the green primary color and the blue primary color in the y-th pixel point in the gray level image of the agricultural product in the partition groove.
3. The machine-vision-based agricultural product quality inspection automated sorting management system of claim 1, wherein: the calculation formula of the qualified quality influence coefficient of the agricultural products is
wjrfExpressing the gray value of the f-th area in the gray image of the damaged agricultural product in the j-th separation groove, wherein f is 1,2lExpressed as index of odor gas of agricultural product with excessive odor gas index in the first separation groove, qmaxAnd q isminExpressed as the maximum and minimum values, w, of the acceptable odorous gas index range emitted by the agricultural productirfExpressed as the gray value of the f area in the gray image of the agricultural product in the i separating groove, qiExpressed as index of off-flavor gas emitted by the produce in the ith compartment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010869834.1A CN111842216A (en) | 2020-08-26 | 2020-08-26 | Agricultural product quality detection automatic sorting management system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010869834.1A CN111842216A (en) | 2020-08-26 | 2020-08-26 | Agricultural product quality detection automatic sorting management system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111842216A true CN111842216A (en) | 2020-10-30 |
Family
ID=72968306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010869834.1A Withdrawn CN111842216A (en) | 2020-08-26 | 2020-08-26 | Agricultural product quality detection automatic sorting management system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111842216A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116465888A (en) * | 2023-03-17 | 2023-07-21 | 南通锐越信息科技有限公司 | Agricultural product quality Internet of things monitoring method and device based on machine visual effect, electronic equipment and computer readable storage medium |
-
2020
- 2020-08-26 CN CN202010869834.1A patent/CN111842216A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116465888A (en) * | 2023-03-17 | 2023-07-21 | 南通锐越信息科技有限公司 | Agricultural product quality Internet of things monitoring method and device based on machine visual effect, electronic equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110238078B (en) | Sorting method, device, system and storage medium | |
| Sahu et al. | Defect identification and maturity detection of mango fruits using image analysis | |
| US20060081135A1 (en) | Industrial overline imaging system and method | |
| CN115272341A (en) | Packaging machine defect product detection method based on machine vision | |
| CN102246186B (en) | Method and system for item identification | |
| CN108109137A (en) | The Machine Vision Inspecting System and method of vehicle part | |
| CN110648069B (en) | Vegetable quality analysis system based on transport vehicle | |
| CN115018844B (en) | Plastic film quality evaluation method based on artificial intelligence | |
| CN111552243B (en) | Intelligent spinning and packaging production line fault detection system | |
| CN210059040U (en) | Based on RGB fruit sorter | |
| CN111582735B (en) | Intelligent warehouse logistics commercial commodity quality monitoring and management system based on big data | |
| CN110434090A (en) | A kind of carrot surface flaw detecting method | |
| CN109239073A (en) | A kind of detection method of surface flaw for body of a motor car | |
| CN103394472A (en) | Method for detecting and grading greening potatoes based on machine vision | |
| CN111842216A (en) | Agricultural product quality detection automatic sorting management system based on machine vision | |
| Thong et al. | Mango classification system uses image processing technology and artificial intelligence | |
| EP3896650A1 (en) | Quality control system for series production | |
| CN110813795B (en) | Device and method for detecting breakage of chemical fiber spindle paper tube on line | |
| CN111482381B (en) | Full-automatic sorting system and method | |
| Thong et al. | Mango sorting mechanical system combines image processing | |
| CN117274623A (en) | Identification method and system for intelligent retrieval and identification of forbidden articles | |
| CN110639832A (en) | Tobacco leaf processing method and system | |
| CN111077146A (en) | Vegetable quality evaluation system | |
| CN107243461B (en) | Automatic grading device | |
| CN115564990A (en) | Agricultural product visual identification platform |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201030 |