CN113706483A - Detection method and detection system for pork quality - Google Patents

Detection method and detection system for pork quality Download PDF

Info

Publication number
CN113706483A
CN113706483A CN202110936171.5A CN202110936171A CN113706483A CN 113706483 A CN113706483 A CN 113706483A CN 202110936171 A CN202110936171 A CN 202110936171A CN 113706483 A CN113706483 A CN 113706483A
Authority
CN
China
Prior art keywords
pork
detection
region
muscle
sample
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
Application number
CN202110936171.5A
Other languages
Chinese (zh)
Inventor
邓仲平
凌雄娟
陈湘青
黄利荣
何静
田钧
林常威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Foshan Polytechnic
Original Assignee
Foshan Polytechnic
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Foshan Polytechnic filed Critical Foshan Polytechnic
Priority to CN202110936171.5A priority Critical patent/CN113706483A/en
Publication of CN113706483A publication Critical patent/CN113706483A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • A—HUMAN NECESSITIES
    • A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
    • A23L—FOODS, FOODSTUFFS, OR NON-ALCOHOLIC BEVERAGES, NOT COVERED BY SUBCLASSES A21D OR A23B-A23J; THEIR PREPARATION OR TREATMENT, e.g. COOKING, MODIFICATION OF NUTRITIVE QUALITIES, PHYSICAL TREATMENT; PRESERVATION OF FOODS OR FOODSTUFFS, IN GENERAL
    • A23L13/00—Meat products; Meat meal; Preparation or treatment thereof
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/01—Arrangements or apparatus for facilitating the optical investigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/02—Food
    • G01N33/12—Meat; fish
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/01—Arrangements or apparatus for facilitating the optical investigation
    • G01N2021/0106—General arrangement of respective parts
    • G01N2021/0112—Apparatus in one mechanical, optical or electronic block
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Food Science & Technology (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Nutrition Science (AREA)
  • Polymers & Plastics (AREA)
  • Quality & Reliability (AREA)
  • Signal Processing (AREA)
  • Medicinal Chemistry (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention discloses a detection method and a detection system for pork quality, wherein the detection method comprises the following steps: acquiring pork sample images of the same pork sample fed back by the detection mechanism under different height values, wherein the plurality of pork sample images form a sample image group; performing region segmentation on each pork sample image in the sample image group to obtain a pork sample region, wherein a plurality of pork sample regions form a muscle subset; carrying out gray processing and weight giving on each pork sample region in the muscle subset to obtain a first muscle characteristic; according to the detection method, the images of the pork samples under different height values are collected, gray level processing and weight giving are carried out on the pork sample area, muscle tissues of the pork samples can be effectively identified, the first muscle characteristics are used for confirming the muscle size and the muscle density of the pork samples, data support is provided for pork quality judgment, workers can quickly judge the pork quality according to the data, and the detection efficiency is improved.

Description

Detection method and detection system for pork quality
Technical Field
The invention relates to the technical field of detection methods based on machine vision, in particular to a detection method and a detection system for pork quality.
Background
At present, the quality detection of pork is mainly manual detection, workers compare standard maps of pork to be detected and pork color to evaluate the quality of the pork, and due to high subjectivity of manual judgment, quantitative standards cannot be formed, so that effective development of detection operation is influenced; in addition, when the amount of comparison work is large, it is difficult to evaluate the quality of pork quickly and accurately, and the determination result has a problem of large error.
In the prior art of detecting the quality of livestock meat by machine vision, a method for detecting the freshness of pork by adopting a near infrared spectrum exists, but the method only establishes a relation between spectral information and a volatile basic nitrogen index to predict the freshness of pork, the index is too single, and the error of the obtained detection result of the freshness of pork is large.
It is seen that improvements and enhancements to the prior art are needed.
Disclosure of Invention
In view of the defects of the prior art, the invention aims to provide a method for detecting pork quality, which can effectively obtain the muscle tissue of a pork sample, quickly confirm the size and density of the muscle and provide data support for judging the pork quality.
In order to achieve the purpose, the invention adopts the following technical scheme:
a detection method of pork quality is provided, a detection system for realizing the detection method comprises a control device and a detection mechanism electrically connected with the control device, the detection mechanism is used for acquiring pork sample images of the same pork sample under different height values, and the detection method comprises the following steps:
acquiring pork sample images of the same pork sample fed back by the detection mechanism under different height values, wherein the plurality of pork sample images form a sample image group;
performing region segmentation on each pork sample image in the sample image group to obtain a pork sample region, wherein a plurality of pork sample regions form a muscle subset;
performing gray scale processing and weight giving on each pork sample region in the muscle subset to obtain a first muscle characteristic.
In the method for detecting pork quality, after the pork sample area is obtained, the method further comprises the following steps:
performing region selection on each pork sample region in the muscle subset to obtain a second muscle characteristic;
selecting a pixel p in a range adjacent to the second muscle featurezWith pzTaking a region with radius r as a circle center, and setting the region as a characteristic region;
acquiring the snowflake degree of the pork according to the number of pixels in the characteristic region and the color vector of each pixel;
and acquiring the roughness of the pork according to the area of the characteristic region and the snowflake degree.
In the method for detecting pork quality, the region segmentation is performed on each pork sample image in the sample image group to obtain a pork sample region, and the method specifically comprises the following steps:
establishing a mapping relation between the identification block and the pixel points to obtain the coordinates of the identification block corresponding to the pixel points;
counting the number of the motion pixel points judged in the pork sample image;
and comparing the number of the motion pixel points with the total number of the pixel points, and acquiring a pork sample area according to a comparison result.
In the method for detecting pork quality, gray level processing and weight giving are carried out on each pork sample region in the muscle subset to obtain first muscle characteristics Muscles,
Figure BDA0003212938160000021
Figure BDA0003212938160000022
wherein G (x) ═ G (G)p-gc)；gcThe gray value of the detection point position; gpIs given as gcAs the same angle at intervals on the circumference of which the circle center R is the radius
Figure BDA0003212938160000031
The gray values of the p pixel points.
In the method for detecting pork quality, region selection is performed on each pork sample region in the muscle subset to obtain a second muscle characteristic, and the method specifically comprises the following steps:
selecting a region with the boundary of 1 and the region of omega, wherein f (x, y) exists,
Figure BDA0003212938160000032
let the second muscle characteristic be D,
Figure BDA0003212938160000033
wherein alpha is a calibration parameter, and the value range is 0.5-2 times of the area of the region omega.
The invention also correspondingly provides a pork quality detection system, which comprises a control device, and an induction mechanism and a detection mechanism which are respectively electrically connected with the control device, wherein the induction mechanism is used for detecting whether the pork quality is normal; the detection mechanism comprises a detection part and a lifting part, the lifting part is used for adjusting the height distance between the detection part and the pork to be detected, and the detection part is used for acquiring the image of the pork sample of the pork to be detected.
The pork quality detection system further comprises a storage mechanism and a cutting mechanism which are respectively connected with the control device, wherein the storage mechanism comprises a storage cavity, the cutting mechanism is arranged in the storage cavity, and the cutting mechanism is used for cutting the pork to be detected.
In the detection system for the pork quality, the cutting mechanism comprises a cutting part and a clamping part, the cutting part is used for cutting the pork to be detected, and the clamping part is used for clamping the pork to be detected; the cutting part comprises a cutting groove for placing the pork to be detected, the cutting groove is arranged in the storage cavity, and the inner walls of two sides of the cutting groove are respectively provided with a clamping part; the storage mechanism further comprises a limiting part, the limiting part is arranged in the storage cavity, and the limiting part is used for limiting the moving position of the cutting groove.
In the detection system for pork quality, the sensing mechanism comprises a sensing part and a supply part, the supply part is used for supplying detection test paper, the sensing part is used for identifying the detection test paper, and the sensing part is fixedly connected with the supply part.
The pork quality detection system further comprises a collection device electrically connected with the control device, and the collection device is used for collecting the odor of the pork to be detected.
Has the advantages that:
the invention provides a pork quality detection method, which is characterized in that pork sample images under different height values are collected, and gray level processing and weight endowing are carried out on regions of the pork samples, so that muscle tissues of the pork samples can be effectively identified, first muscle characteristics are used for confirming the muscle size and the muscle density of the pork samples, data support is provided for pork quality judgment, workers can quickly judge the pork quality according to the data, the detection efficiency is improved, and the accuracy of detection results is high.
Drawings
FIG. 1 is a first logic flow diagram of a detection method provided by the present invention;
FIG. 2 is a second logic flow diagram of a detection method provided by the present invention;
FIG. 3 is a schematic perspective view of the sensing part and the supplying part according to the present invention;
FIG. 4 is an enlarged view of portion A of FIG. 3;
FIG. 5 is a side view of the sensing part and the supplying part provided in the present invention;
FIG. 6 is a cross-sectional view of a support device provided by the present invention;
FIG. 7 is a schematic structural view of a cutting mechanism and a clamping mechanism provided in the present invention;
FIG. 8 is a cross-sectional view of a cutting head, cutting bar and cutting drive provided by the present invention;
FIG. 9 is a schematic perspective view of a cutting mechanism provided in the present invention;
FIG. 10 is a schematic structural diagram of a collecting device provided by the present invention;
fig. 11 is an enlarged view of a portion B of fig. 10.
Description of the main element symbols: 11-induction rod, 12-induction head, 13-test paper, 131-pulling head, 14-transmission switch, 21-supply box, 211-supply port, 22-support rod, 221-return spring, 222-sliding block, 23-limiting wheel, 24-connecting rod, 25-fixed seat, 26-first rotating wheel, 27-second rotating wheel, 3-storage cavity, 41-cutting groove, 42-cutting head, 421-blade, 43-cutting rod, 44-telescopic driving device, 45-clamping rod, 46-clamping plate, 47-clamping driving device, 48-cutting track, 51-measuring rod, 511-through hole, 512-connecting hole, 52-contact test paper and 53-fixed part.
Detailed Description
The invention provides a method and a system for detecting pork quality, and in order to make the purpose, technical scheme and effect of the invention clearer and clearer, the invention is further described in detail by referring to the attached drawings and embodiments.
In the description of the present invention, it is to be understood that the terms "mounted," "connected," and the like are to be interpreted broadly, and those skilled in the art can understand the specific meanings of the above terms in the present invention according to specific situations.
Referring to fig. 1 and 2, the present invention provides a method for detecting pork quality, wherein a detection system for implementing the detection method includes a control device and a detection mechanism electrically connected to the control device, the detection mechanism is configured to obtain images of pork samples of the same pork sample at different height values, and the detection method includes the steps of:
s100, acquiring pork sample images of the same pork sample fed back by a detection mechanism under different height values, wherein the plurality of pork sample images form a sample image group;
s200, carrying out region segmentation on each pork sample image in the sample image group to obtain a pork sample region, wherein a plurality of pork sample regions form a muscle subset;
s310, carrying out gray processing and weight endowing on each pork sample region in the muscle subset to obtain a first muscle characteristic.
According to the detection method, the images of the pork samples under different height values are collected, gray level processing and weight giving are carried out on the pork sample region, muscle tissues of the pork samples can be effectively identified, the first muscle characteristics are used for confirming the muscle size and the muscle density of the pork samples, data support is provided for pork quality judgment, workers can quickly judge the pork quality according to the data, the detection efficiency is improved, and the accuracy of detection results is high.
Further, referring to fig. 2, after the pork sample region is obtained, the method further includes the steps of:
s321, carrying out region selection on each pork sample region in the muscle subset to obtain second muscle characteristics;
s322, selecting a pixel p in the range adjacent to the second muscle featurezWith pzIs a circleA center, which is a region with a radius of r and is set as a characteristic region; further limiting the second muscle characteristic by setting a characteristic area; the area is chosen and cut off by the selection of the radius r to obtain the characteristic area,
Figure BDA0003212938160000061
wherein μ is the pixel p in the neighborhoodzThe number accounts for the percentage of the total number of pixels of the whole pork sample area, and the proximity is preset by a worker to be within a distance range; u and V are the height and width of the pork sample area, respectively.
S323, acquiring the snowflake degree of the pork according to the number of pixels in the characteristic region and the color vector of each pixel; specifically, the snowflake degree is set as Qx，
Figure BDA0003212938160000062
Figure BDA0003212938160000063
Wherein N is the total number of pixels in the feature region, CiA color vector for the ith pixel in the muscle feature;
Figure BDA0003212938160000064
is represented by CiAnd
Figure BDA0003212938160000065
the euclidean distance between; the snowflake degree can be used as a reference for evaluating pork quality.
S324, acquiring the roughness of the pork according to the area of the characteristic region and the snowflake degree, and specifically setting the roughness as Quality，
Figure BDA0003212938160000071
Wherein M is the area of the characteristic region; counting the calculated roughness and sorting the calculated roughness from large to small, removing one fifth of the pixels in sequence, and particularly, when U, V are all smaller than 100, not executing the operation of roughness filtering; the roughness is filtered, so that the accuracy of a detection result can be improved; the staff can further evaluate the pork quality through the snowflake degree and the roughness, so that effective data support is provided for the detection of the pork quality, the detection efficiency is improved, and the detection accuracy is improved.
Further, the region segmentation is performed on each pork sample image in the sample image group to obtain a pork sample region, and the method specifically includes the steps of:
establishing a mapping relation between the identification block and the pixel points to obtain the coordinates of the identification block corresponding to the pixel points; specifically, the area of the identification block is set to be w × h, wherein w is the width and h is the height; if the coordinates of the pixel point are (x, y) and the coordinates of the identification block are (i, j), the following mapping relationship exists:
Figure BDA0003212938160000072
wherein, wk、hkThe coordinates of the identification block can be obtained for the height and width of the pork sample.
Counting the number of the motion pixel points judged in the pork sample image;
comparing the number of the motion pixel points with the total number of the pixel points, and acquiring a pork sample area according to a comparison result; specifically, if the number of the motion pixel points is greater than or equal to one fourth of the total number of the pixel points, the identification block is considered as a pork sample, and otherwise, the identification block is a background.
Further, performing gray scale processing and weight assignment on each pork sample region in the muscle subset to obtain first muscle characteristics Muscles,
Figure BDA0003212938160000073
Figure BDA0003212938160000074
wherein G (x) ═ G (G)p-gc)；gcThe gray value of the detection point position; gpIs given as gcAs the same angle at intervals on the circumference of which the circle center R is the radius
Figure BDA0003212938160000081
The gray values of the p pixel points; the detection point positions are randomly selected positions in the pork sample area, and the areas adjacent to the detection point positions can be filtered by determining the gray value of the detection point positions, so that the cross-section image muscles of the detection point positions can be displayed; and each pixel point is assigned a corresponding 2pThe weight of the pork sample is determined, so that the muscle tissues of the pork sample are all identified, and the size and the density of the muscle are conveniently confirmed; the weight 2pThe correlation with the pixel value of the pork sample image is obtained by a Gaussian (kernel) function.
Further, the region selection is performed on each pork sample region in the muscle subset to obtain a second muscle characteristic, specifically:
selecting a region with the boundary of 1 and the region of omega, wherein f (x, y) exists,
Figure BDA0003212938160000082
let the second muscle characteristic be D,
Figure BDA0003212938160000083
wherein alpha is a calibration parameter, and the value range is 0.5-2 times of the area of the region omega.
Referring to fig. 3 to 11, the present invention further provides a pork quality detection system, which includes a control device, and an induction mechanism and a detection mechanism electrically connected to the control device, respectively, wherein the induction mechanism is used for detecting whether the pork quality is normal; the detection mechanism comprises a detection part and a lifting part, the lifting part is used for adjusting the height distance between the detection part and the pork to be detected, and the detection part is used for acquiring the image of the pork sample of the pork to be detected.
In one embodiment, the detection part comprises a detection cavity and a detection probe, the lifting part and the detection probe are arranged in the detection cavity, and the lifting part is in transmission connection with the detection transmission device and used for adjusting the height distance between the detection probe and the pork to be detected; after the pork sample to be detected is cut, a worker places the pork sample to be detected in the detection cavity, and the control device adjusts the working state of the lifting part to obtain images of the pork sample under different height values; the detection probe can be a camera, a video camera, a visual sensor and the like.
In one embodiment, the lifting part comprises a lifting rod, a lifting driving mechanism and a height detection device, one end of the lifting rod is in transmission connection with the lifting driving mechanism, the other end of the lifting rod is in transmission connection with the detection probe, the lifting driving mechanism is fixedly connected with the upper wall of the detection cavity, and the detection probe faces the lower wall of the detection cavity; the height detection device is used for confirming the height of the detection probe so as to confirm the height distance between the detection probe and the pork sample to be detected, and the image of the pork sample corresponds to the height value; the lifting driving mechanism can be an air cylinder, the lifting rod can be a telescopic rod, and the height detection device can be a photoelectric sensor.
In one embodiment, the detection part further comprises a first wireless communication chip arranged in the detection probe, the first wireless communication chip is electrically connected with the control device, and the detection probe feeds back the image of the pork sample to the control device through the first wireless communication chip; the first wireless communication chip can be a wifi chip or a bluetooth chip.
In one embodiment, referring to fig. 3 to 6, the sensing mechanism includes a sensing portion and a supplying portion, the supplying portion is used for supplying the test paper 13, the sensing portion is used for identifying the test paper 13, and the sensing portion is fixedly connected to the supplying portion; when the pork to be detected is placed in the detection cavity, the worker can obtain the chemical substances on the surface of the pork sample to be detected through the detection test paper 13 so as to judge whether the meat quality of the pork sample to be detected is normal.
In one embodiment, referring to fig. 3 to 6, a pulling head 131 is disposed on one side of the test strip 13, and the pulling head 131 is disposed on the bottom side of the test strip 13; the sensing part comprises a sensing head 12 and a sensing rod 11, the sensing head 12 is arranged at one end of the sensing rod 11 and faces the detection test paper 13, and the sensing head 12 can be a camera, a video camera, a visual sensor and the like and is used for recording the color of the detection test paper 13; the supply part comprises a supply box 21, a limiting piece and a supporting device, wherein the supply box 21 and the limiting piece are respectively arranged at two sides of the induction rod 11; the two supporting devices are arranged on the induction rod 11 and are respectively positioned at two sides of the induction head 12; a supply cavity is formed in the supply box 21, the test paper 13 is arranged in the supply cavity, a supply opening 211 is formed in the supply box 21, the test paper 13 passes through the supply opening 211 and is connected with the limiting piece, the limiting piece limits the test paper 13, and the supporting device is positioned on a moving path of the test paper 13 and can support the test paper 13, so that the test paper 13 is always in a tight state; when the test paper 13 needs to be used, the pulling head 131 arranged on the test paper 13 is pulled to pull the test paper 13 toward the direction of the limiting piece, and the test paper 13 and the limiting piece are connected to complete the installation of the test paper 13.
In one embodiment, the supply box 21 includes a storage disk, an upper box and a bottom cover, the bottom cover is fixedly connected with the sensing rod 11, and the upper box is clamped with the bottom cover; the storage disc is arranged in the bottom cover and is detachably connected with the bottom cover, and the detection test paper 13 is nested in the storage disc; when the test paper 13 runs out, the worker can disassemble the upper box, then disassemble the storage disc from the bottom cover, place the new test paper 13 in the storage disc, and then reassemble the storage disc and the upper box to complete the replacement of the test paper 13.
In one embodiment, the supporting device comprises a supporting rod 22, a limiting wheel 23 and a connecting rod 24, the connecting rod 24 is fixedly arranged on one side of the supporting rod 22, and the limiting wheel 23 is arranged around the supporting rod 22; a support cavity is formed in the support rod 22, a sliding block 222 and a return spring 221 are arranged in the support cavity, one end of the return spring 221 is abutted against the inner wall of the support cavity, and the other end of the return spring 221 is connected with one end of the sliding block 222; a connecting port is formed in the supporting rod 22 and is communicated with the supporting cavity; the other end of the slider 222 abuts against the limiting wheel 23 through the connection port; the return spring 221 is used for providing elastic force to enable the other end of the sliding block 222 to clamp the limiting wheel 23; the width of the test paper 13 is greater than the width of the limiting wheel 23.
When an operator detects the pork sample to be detected by using the sensing mechanism, the operator holds the sensing rod 11 by hand to enable the detection test paper 13 to be in contact with the surface of the pork sample to be detected, and during the period, the reset spring 221 deforms to enable the detection test paper 13 to be kept in a tight state; in the process of detecting the pork sample to be detected by the detection test paper 13, different types of detection test paper 13 can be used for detecting different indexes; the detection test paper 13 can be heavy metal rapid detection test paper 13, clenbuterol hydrochloride rapid detection test paper 13, ractopamine rapid detection test paper 13, salbutamol rapid detection test paper 13 or PH test paper; the color change of the detection test paper 13 is collected through the induction head 12 and fed back to the control device, and the control device compares the color result of the detection test paper 13 with a standard colorimetric range preset in the control device, so that the detection result can be rapidly output, and the detection accuracy is improved.
In one embodiment, the sensing mechanism further comprises a transmission switch 14 and a second wireless communication chip, the transmission switch 14 is arranged on the sensing rod 11, the second wireless communication chip is arranged in the sensing rod 11, and when an operator triggers the transmission switch 14, the second wireless communication chip transmits detection data to the control device; the second wireless communication chip may be a wifi chip or a bluetooth chip, and the transmission switch 14 may be a reset button.
In one embodiment, referring to fig. 4 and 5, the limiting member includes a fixed seat 25, a first rotating wheel 26 and a second rotating wheel 27, the fixed seat 25 is fixedly connected to the sensing rod 11, the first rotating wheel 26 and the second rotating wheel 27 are respectively rotatably disposed in the fixed seat 25, and a gap between the first rotating wheel 26 and the second rotating wheel 27 is used to limit a moving position of the test paper 13, that is, the test paper 13 output from the supply box 21 passes through the gap between the first rotating wheel 26 and the second rotating wheel 27, so as to fix the test paper 13.
Further, referring to fig. 7 to 9, the detection system further includes a storage mechanism and a cutting mechanism respectively connected to the control device, the storage mechanism includes a storage cavity 3, the cutting mechanism is disposed in the storage cavity 3, and the cutting mechanism is configured to cut the pork to be detected.
Further, referring to fig. 7 to 9, the cutting mechanism includes a cutting portion and a clamping portion, the cutting portion is used for cutting the pork to be detected, and the clamping portion is used for clamping the pork to be detected; the cutting part comprises a cutting groove 41 for placing the pork to be detected, the cutting groove 41 is arranged in the storage cavity 3, and the inner walls of two sides of the cutting groove 41 are respectively provided with a clamping part; the storage mechanism further comprises a limiting part, the limiting part is arranged in the storage cavity 3, and the limiting part is used for limiting the moving position of the cutting groove 41.
Before the pork quality is detected, the pork to be detected is placed in the cutting groove 41 to cut the pork sample; in one embodiment, referring to fig. 7 to 9, the cutting part includes a cutting head 42, a cutting rod 43 and a telescopic driving device 44, and a blade 421 is disposed at the bottom of the cutting head 42; the two cutting rods 43 are respectively arranged at two ends of the top of the cutting head 42, the telescopic driving device 44 is arranged in the cutting head 42, the telescopic driving device 44 is in transmission connection with one end of the cutting rod 43, and the other end of the cutting rod 43 is positioned outside the cutting head 42; the cutting rod 43 is matched with the telescopic driving device 44, so that the height of the cutting head 42 can be adjusted; when the telescopic driving device 44 works, the telescopic rod extends upwards and is abutted against the upper wall of the storage cavity 3, and the cutting head 42 moves downwards under the reverse acting force of the upper wall to cut the pork to be detected; the cutting rod 43 may be a telescopic rod, and the telescopic driving device 44 may be an air cylinder.
In an embodiment, referring to fig. 7, the clamping portion includes a clamping rod 45, a clamping plate 46, a first pressure detection device and a clamping driving device 47, the clamping driving device 47 is fixedly disposed in the cutting groove 41, the clamping driving device 47 is fixedly connected to one end of the clamping rod 45, the other end of the clamping rod 45 is fixedly connected to the clamping plate 46, the clamping plate 46 is provided with the first pressure detection device, and the first pressure detection device is configured to detect a force of the clamping plate 46 clamping the pork; when the pork is extruded, if the pressure data fed back by the first pressure detection device is greater than or equal to a first pressure threshold value preset in the control device, the control device controls the clamping driving device 47 to stop working, so that the clamping plate 46 is maintained in the clamping state; after the cutting of the pork to be detected is finished, the control device controls the clamping driving device 47, and the clamping driving device 47 drives the clamping rod 45 and the clamping plate 46 to retract, namely, returns to the original position; the clamping rod 45 may be an expansion rod, the clamping driving device 47 may be an air cylinder, and the first pressure detecting device may be a pressure sensor.
In one embodiment, please refer to fig. 9, the cutting portion further includes a cutting track 48 and a stroke detection member, the cutting track 48 is respectively disposed on the inner walls of two sides of the cutting groove 41, two sides of the cutting head 42 are respectively provided with a fixture block, and the fixture block is connected to the cutting track 48 in a matching manner; when the telescopic driving device 44 drives the cutting rod 43 to move, the cutting head 42 slides along the cutting track 48; the top and the bottom of the cutting track 48 are respectively provided with a stroke detection piece, the stroke detection pieces, the cutting rod 43 and the telescopic driving device 44 form a closed loop, when the stroke detection pieces at the bottom detect the cutting head 42, the control device outputs a retraction signal to the telescopic driving device 44, and the telescopic driving device 44 drives the cutting rod 43 to retract; when the stroke detection piece at the top detects the cutting head 42, the control device outputs a retraction signal to the telescopic driving device 44, and the telescopic driving device 44 drives the cutting rod 43 to extend out; the cutting of the pork to be detected is realized through the conversion of the two states of the cutting rod 43, the contact frequency of the hand of a worker and the surface of the pork to be detected is effectively reduced, the influence of human factors on the detection result is reduced, and the accuracy of the detection result is improved; the formation detection member may be a photoelectric sensor.
In one embodiment, the first pressure detection device and the stroke detection piece feed back detection signals to the control device in a wireless communication mode.
In one embodiment, the limiting part comprises a limiting rod, a second pressure detection device and a limiting driving device, the limiting driving device is fixedly arranged in the storage cavity 3, the limiting driving device is in transmission connection with one end of the limiting rod, and the second pressure detection device is arranged at the other end of the limiting rod; limiting holes are formed in the outer walls of the two sides of the cutting groove 41 respectively, and the other end of the limiting rod is connected with the limiting holes in a matched mode; when the cutting groove 41 needs to be locked, the limiting driving device drives the limiting rod to extend out, the limiting rod is inserted into the limiting hole, at the moment, the second pressure detection device arranged at the end part of the limiting rod is extruded, and when the threshold value fed back by the second pressure detection device is larger than or equal to the second pressure threshold value preset in the control device, the control device controls the limiting driving device to stop working, so that the limiting rod keeps the extending state to limit the cutting groove 41; when the cutting groove 41 needs to be replaced, the control device controls the limiting driving device to work, the limiting driving device drives the limiting rod to retract, the limiting rod returns to the original position, and the limiting of the cutting groove 41 is released; the second pressure detection device can be a pressure sensor, and the limit driving device can be an air cylinder.
Further, referring to fig. 10 and 11, the detection system further includes a collecting device electrically connected to the control device, and the collecting device is configured to collect the odor of the pork to be detected; whether there is the pollutant on the pork surface that detects through response mechanism detection and waits to detect, whether the rethread collection system detects the pork surface that detects and waits to have the peculiar smell, can ensure the new freshness and the health degree of the pork that detects, avoids the testing result of pork meat to receive external factor to disturb, improves testing result's rate of accuracy.
In one embodiment, the collecting device comprises a pair of measuring rods 51, a contact test paper 52, a fixing part 53 and an odor sensor, wherein the contact test paper 52 is fixedly arranged at one end of the measuring rods 51 through the fixing part 53; the odor sensor is arranged in the measuring rod 51 and positioned on the inner side of the contact test paper 52, the odor sensor is used for detecting whether the pork sample to be detected has abnormal odor, and the odor sensor is electrically connected with the control device; one end of the measuring rod 51, which is provided with the contact test paper 52, is provided with a plurality of through holes 511, and the through holes 511 are used for transmitting the odor to the odor sensor; the odor sensor may be an odor sensor that is sensitive to pH changes.
In one embodiment, a connection hole 512 is formed at an end of the measuring rod 51, the fixing portion 53 is disposed in the connection hole 512, the fixing portion 53 includes a first fixing rod group and a second fixing rod group respectively disposed at two ends of the connection hole 512, the first fixing rod group includes a first rotating rod and a second rotating rod rotatably disposed in the connection hole 512, the second fixing rod group includes a third rotating rod and a fourth rotating rod rotatably disposed in the connection hole 512, and a gap between the first rotating rod and the second rotating rod and a gap between the third rotating rod and the fourth rotating rod are used for fixing the contact test paper 52; the contact test paper 52 enters from an opening at one end of the connecting hole 512, passes through a gap between the first rotating rod and the second rotating rod, then passes through a gap between the third rotating rod and the fourth rotating rod, and is output from the other port of the connecting hole 512, so that the contact test paper 52 can be quickly disassembled and assembled.
It should be understood that equivalents and modifications of the technical solution and inventive concept thereof may occur to those skilled in the art, and all such modifications and alterations should fall within the protective scope of the present invention.

Claims (10)

1. The detection method of pork quality is characterized in that a detection system for realizing the detection method comprises a control device and a detection mechanism electrically connected with the control device, wherein the detection mechanism is used for acquiring pork sample images of the same pork sample under different height values, and the detection method comprises the following steps:
acquiring pork sample images of the same pork sample fed back by the detection mechanism under different height values, wherein the plurality of pork sample images form a sample image group;
performing region segmentation on each pork sample image in the sample image group to obtain a pork sample region, wherein a plurality of pork sample regions form a muscle subset;
performing gray scale processing and weight giving on each pork sample region in the muscle subset to obtain a first muscle characteristic.
2. The method for detecting pork quality of claim 1, wherein the method further comprises the following steps after the pork sample region is obtained:
performing region selection on each pork sample region in the muscle subset to obtain a second muscle characteristic; selecting a pixel p in a range adjacent to the second muscle featurezWith pzTaking a region with radius r as a circle center, and setting the region as a characteristic region;
acquiring the snowflake degree of the pork according to the number of pixels in the characteristic region and the color vector of each pixel;
and acquiring the roughness of the pork according to the area of the characteristic region and the snowflake degree.
3. The method for detecting pork quality according to claim 2, wherein the step of performing region segmentation on each pork sample image in the sample image group to obtain a pork sample region comprises the steps of:
establishing a mapping relation between the identification block and the pixel points to obtain the coordinates of the identification block corresponding to the pixel points;
counting the number of the motion pixel points judged in the pork sample image;
and comparing the number of the motion pixel points with the total number of the pixel points, and acquiring a pork sample area according to a comparison result.
4. The method of claim 3, wherein each pork sample region in the subset of Muscles is processed with gray scale and assigned with weight to obtain a first muscle characteristic, Muscles,
Figure FDA0003212938150000021
Figure FDA0003212938150000022
wherein G (x) ═ G (G)p-gc)；gcThe gray value of the detection point position; gpIs given as gcAs the same angle at intervals on the circumference of which the circle center R is the radius
Figure FDA0003212938150000023
The gray values of the p pixel points.
5. The method for detecting pork quality according to claim 1, wherein the region selection is performed on each pork sample region in the muscle subset to obtain a second muscle characteristic, specifically:
selecting a region with the boundary of 1 and the region of omega, wherein f (x, y) exists,
Figure FDA0003212938150000024
let the second muscle characteristic be D,
Figure FDA0003212938150000025
wherein alpha is a calibration parameter, and the value range is 0.5-2 times of the area of the region omega.
6. The pork quality detection system is characterized by comprising a control device, and an induction mechanism and a detection mechanism which are respectively and electrically connected with the control device, wherein the induction mechanism is used for detecting whether pork quality is normal or not; the detection mechanism comprises a detection part and a lifting part, the lifting part is used for adjusting the height distance between the detection part and the pork to be detected, and the detection part is used for acquiring the image of the pork sample of the pork to be detected.
7. The pork quality detection system of claim 6, further comprising a storage mechanism and a cutting mechanism respectively connected to the control device, wherein the storage mechanism comprises a storage cavity, the cutting mechanism is disposed in the storage cavity, and the cutting mechanism is used for cutting pork to be detected.
8. The system for detecting pork quality of claim 7, wherein the cutting mechanism comprises a cutting part and a clamping part, the cutting part is used for cutting the pork to be detected, and the clamping part is used for clamping the pork to be detected; the cutting part comprises a cutting groove for placing the pork to be detected, the cutting groove is arranged in the storage cavity, and the inner walls of two sides of the cutting groove are respectively provided with a clamping part; the storage mechanism further comprises a limiting part, the limiting part is arranged in the storage cavity, and the limiting part is used for limiting the moving position of the cutting groove.
9. The system of claim 6, wherein the sensing mechanism comprises a sensing part and a supplying part, the supplying part is used for supplying test paper, the sensing part is used for identifying the test paper, and the sensing part is fixedly connected with the supplying part.
10. The system of claim 6, further comprising a collection device electrically connected to the control device, wherein the collection device is configured to collect the odor of the pork to be detected.
CN202110936171.5A 2021-08-16 2021-08-16 Detection method and detection system for pork quality Pending CN113706483A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110936171.5A CN113706483A (en) 2021-08-16 2021-08-16 Detection method and detection system for pork quality

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110936171.5A CN113706483A (en) 2021-08-16 2021-08-16 Detection method and detection system for pork quality

Publications (1)

Publication Number Publication Date
CN113706483A true CN113706483A (en) 2021-11-26

Family

ID=78653096

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110936171.5A Pending CN113706483A (en) 2021-08-16 2021-08-16 Detection method and detection system for pork quality

Country Status (1)

Country Link
CN (1) CN113706483A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116359142A (en) * 2023-03-27 2023-06-30 山东千禧农牧发展有限公司 Evaluation method for chicken quality

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101561402A (en) * 2009-05-07 2009-10-21 浙江大学 Machine vision-based real-time detection and grading method and machine vision-based real-time detection and grading device for pork appearance quality
CN201508328U (en) * 2009-05-07 2010-06-16 浙江大学 Machine vision-based real-time detecting and grading device for pork appearance quality
CN105701805A (en) * 2016-01-07 2016-06-22 中国农业大学 Pork intramuscular fat content nondestructive testing method based on computer vision
CN111175230A (en) * 2020-02-11 2020-05-19 山东省产品质量检验研究院 Pork detection equipment
CN112634274A (en) * 2021-03-10 2021-04-09 广东省农业科学院动物科学研究所 Machine vision-based fattening pork quality evaluation method and system
CN113057598A (en) * 2021-04-20 2021-07-02 中国农业大学 Meat quality grading method and system for animal living body slaughterless

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101561402A (en) * 2009-05-07 2009-10-21 浙江大学 Machine vision-based real-time detection and grading method and machine vision-based real-time detection and grading device for pork appearance quality
CN201508328U (en) * 2009-05-07 2010-06-16 浙江大学 Machine vision-based real-time detecting and grading device for pork appearance quality
CN105701805A (en) * 2016-01-07 2016-06-22 中国农业大学 Pork intramuscular fat content nondestructive testing method based on computer vision
CN111175230A (en) * 2020-02-11 2020-05-19 山东省产品质量检验研究院 Pork detection equipment
CN112634274A (en) * 2021-03-10 2021-04-09 广东省农业科学院动物科学研究所 Machine vision-based fattening pork quality evaluation method and system
CN113057598A (en) * 2021-04-20 2021-07-02 中国农业大学 Meat quality grading method and system for animal living body slaughterless

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
于铂: "基于图像处理技术的猪肉无损定级系统", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116359142A (en) * 2023-03-27 2023-06-30 山东千禧农牧发展有限公司 Evaluation method for chicken quality
CN116359142B (en) * 2023-03-27 2024-03-22 山东千禧农牧发展有限公司 Evaluation method for chicken quality

Similar Documents

Publication Publication Date Title
US6031930A (en) Method and apparatus for testing a progression of neoplasia including cancer chemoprevention testing
CN105021529B (en) Fusion spectrum and the crop disease and insect of image information identify and distinguish between method
CN104155312B (en) Grain intragranular portion pest detection method and apparatus based on near-infrared computer vision
JP2003511702A5 (en)
US8803673B2 (en) System and method for evaluating surface finish of tire retread
CA2723452C (en) Systems, methods and devices for use in assessing carcass grading
WO1981003080A1 (en) Method and apparatus for measuring mean cell volume of red blood cells
JP2010112887A (en) Principal component analysis method, principal component analyzer, different kind article detection device, principal component analysis program, and recording medium for recording the principal component analysis program
CN115684208B (en) Automatic feeding and discharging control system of AVI detection machine
CN202421024U (en) Broken rice rate on-line detection system
CN113706483A (en) Detection method and detection system for pork quality
CN102494977B (en) Method and system for detecting broken rice rate on line
JP5095440B2 (en) Residual deposit measuring device
CN108007945A (en) A kind of assay method that thick stalk rate and length stalk rate in offal are quantitatively detected based on X-ray transmission image
CN112465741B (en) Defect detection method and device for suspension spring and valve spring and storage medium
CN107797517B (en) Method and system for realizing steel belt punching processing detection by adopting machine vision
US20150130926A1 (en) Method And Apparatus For Mapping And Analyzing Surface Gradients
US8472675B2 (en) Systems, methods and devices for use in filter-based assessment of carcass grading
CN115266906A (en) Nondestructive testing device for parts
CN111950351B (en) Agricultural machinery strain early diagnosis inspection system based on terahertz and visible light
CN206563717U (en) A kind of full automatic cell image detection and diagnosis system
CN103076164B (en) The method of automotive ventilation mouth Aulomatizeted Detect and equipment thereof
CN107462221B (en) Automatic measuring method for fisheye characteristics
WO2005026660A1 (en) Sheet-surface analyser and method of analysing a sheet-surface
CN111359892A (en) Device and method for detecting and grading appearance of Tianbao honey pomelos based on machine vision

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20211126

RJ01 Rejection of invention patent application after publication