CN109115775A - A kind of betel nut level detection method based on machine vision - Google Patents

A kind of betel nut level detection method based on machine vision Download PDF

Info

Publication number
CN109115775A
CN109115775A CN201810894870.6A CN201810894870A CN109115775A CN 109115775 A CN109115775 A CN 109115775A CN 201810894870 A CN201810894870 A CN 201810894870A CN 109115775 A CN109115775 A CN 109115775A
Authority
CN
China
Prior art keywords
betel nut
membership function
image
betel
indicate
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.)
Granted
Application number
CN201810894870.6A
Other languages
Chinese (zh)
Other versions
CN109115775B (en
Inventor
张辉
李志恒
刘理
赵淼
邓广
熊镇林
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.)
Changsha University of Science and Technology
Original Assignee
Changsha University of Science and Technology
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 Changsha University of Science and Technology filed Critical Changsha University of Science and Technology
Priority to CN201810894870.6A priority Critical patent/CN109115775B/en
Publication of CN109115775A publication Critical patent/CN109115775A/en
Application granted granted Critical
Publication of CN109115775B publication Critical patent/CN109115775B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • 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
    • G01N2021/8411—Application to online plant, process monitoring
    • 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
    • G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Image Analysis (AREA)

Abstract

The betel nut level detection method based on machine vision that the invention discloses a kind of, this method utilizes betel nut feature of image, pass through connective region search, edge detection effectively is carried out to effectively obtain the characteristic parameters such as long axis, short axle, perimeter, area, elongation, circularity, the rectangular degree of betel nut to betel nut image, and the grade of each parameter of each betel nut is obtained based on membership function stage division, further according to the grade of weighting algorithm Comprehensive Assessment betel nut.The computation complexity of method of the invention is low, it is easy to accomplish, suitable for the quick real-time grading of betel nut, and the classification of 4 kinds of betel nuts is realized, it is widely applicable.

Description

A kind of betel nut level detection method based on machine vision
Technical field
The invention belongs to field of image processing more particularly to a kind of betel nut level detection methods based on machine vision.
Background technique
The overall merit of the quality evaluation system primary evaluation betel nut of betel nut has shape, size and circularity etc..Currently, During Production of fruit and operation, some fruit detection methods remain in the manual classification stage, classify by naked eyes identification, The labour cost of its great work intensity, transfer fee is high, and low efficiency, nicety of grading is not high, and compared with automatic-grading device, this will be tight The development of recasting about betel nut industry, and this method has randomness, because individual is different the understanding of standard, to betel nut Evaluation be a lack of stability, and it is scientific not strong.Computer Image Processing carry out large-scale product quality inspection and Classification, overcomes the influence of individual physiology and psychological factor, and can obtain quick, accurate, non-destructive and other artificial institute's nothings Analogous effect, and people can be made to free from heavy manual labor, therefore, technical bottleneck is brought to enterprise, Urgently find a kind of effective solution approach.The computation complexity of method of the invention is low, it is easy to accomplish, suitable for the quick of betel nut Real-time graded, and 4 kinds of grades classification of betel nut is realized, it is widely applicable.
Explanation of nouns:
1. single channel operates: i.e. single channel figure is commonly called as grayscale image, and each pixel can only have a value to indicate color, Its pixel value is between 0 to 255, and 0 is black, and 255 be white, and median is some different grades of grey.
2. binarization operation: i.e. the binaryzation of image exactly sets 0 or 255 for the gray value of the pixel on image, Namely whole image is showed and significantly there was only black and white visual effect.
Summary of the invention
The betel nut level detection method based on machine vision that the invention discloses a kind of, the present invention overcomes produce in betel nut During operation, classify by naked eyes identification, the labour cost of great work intensity, transfer fee is high, low efficiency, classification essence Not high problem is spent, quick, accurate, the nondestructive grade for obtaining betel nut of energy, the visible detection method is simple, accurately, surely It is fixed, meet the real-time online testing requirements of production line.
To achieve the goals above, technical scheme is as follows:
A kind of betel nut level detection method based on machine vision, comprising the following steps:
Step 1: acquisition is located at the betel nut image on production line, is denoted as Image0；
Step 2: single channel operation is carried out to betel nut image Image0, obtains image Image1；
Step 3: binarization operation is carried out to betel nut image Image1, obtains bianry image Image2；
Betel nut is split from background image, T1 be binarization segmentation threshold value, Image1 (x, y) be image in (x, Y) gray value of position pixel: x indicates that the coordinate of betel nut image X-axis, y show the coordinate of betel nut image Y-axis；Then
Step 4: connective region search operation is carried out to binary image Image2, searches out the maximum connected domain of area Blob, and empty filling is carried out to Blob；
Step 5: the connected domain Blob obtained in step 4 is split out, obtains betel nut region RegionDiff, The as profile of betel nut；
Step 6: betel nut characteristic parameter is extracted, that is, calculates major axis A, the short axle B, perimeter of betel nut region RegionDiff P, area S, elongation E, circularity C, rectangular degree R；Specific step is as follows:
Step 6.1: extracting the major axis A of betel nut region RegionDiff, the feature of short axle B, to region RegionDiff structure Build minimum circumscribed rectangle, the long side of minimum circumscribed rectangle, short side, that is, corresponding major axis A, short axle B；
Step 6.2: extracting the feature of perimeter P, perimeter refers to the profile length of betel nut
Step 6.3: extracting the feature of area S, betel nut area describes the size of betel nut contour area, i.e., owns in image The pixel number for belonging to betel nut, for the RegionDiff of region, if the length of each pixel is unit 1, then area Are as follows:
S=∑(x, y) ∈ Q1
In formula: Q indicates betel nut region RegionDiff
Step 6.4: the extraction of elongation E, circularity C, rectangular degree R,
E=A/B
C=4 π S/P2
R=S/ (A*B)；
Step 7: collect 200 the first estate betel nut characteristics, respectively to the major axis A of betel nut region RegionDiff, Seven short axle B, perimeter P, area S, elongation E, circularity C, rectangular degree R characteristic parameters establish membership function；It determines different etc. The characteristic value of grade betel nut sample；
The membership function of long axis:
The membership function of short axle:
The membership function of perimeter:
The membership function of area:
The membership function of elongation:
The membership function of circularity:
The membership function of rectangular degree:
Wherein, μiFor the characteristic value of i-th of particle in sample,It is the mean value of betel nut feature in 200 master samples, σ is The square error of each sample average in 200 master samples.
A(μi) indicate the membership function established to betel nut long axis；Exp [] is indicated in higher mathematics using natural constant e the bottom of as Exponential function；B(μi) indicate the membership function established to betel nut short axle；P(μi) indicate to be subordinate to letter to what betel nut perimeter was established Number, because perimeter is indicated with P, and is about μiFunction, so with P (μi) indicate；S(μi) indicate to establish betel nut area Membership function；E(μi) indicate the membership function established to betel nut elongation；C(μi) indicate to be subordinate to letter to what betel nut circularity was established Number；R(μi) indicate the membership function established to betel nut rectangular degree；
Step 8: if the characteristic value and standard of sample to be tested are closer to the characteristic value of sample, the similar journey of betel nut It spends higher: on the contrary, the similarity degree of betel nut is lower；According to membership function, the corresponding betel nut grade of each parameter is obtained；
Step 9: according to each betel nut grade, each feature gives n different score, and weights to score；It is each after weighting The gross score that score is added determines the score of betel nut, and the grade of betel nut is then divided according to the score of betel nut.
It is further to improve, in the step 6.2, betel nut length: P=sqrt (2) * Nd+NX is obtained with chain rule +NY；Sqrt () indicates evolution；
It is further to improve, in the step 9, n=100, in A:B:P:S:E:C:R=3:1:1:1:2:1:1 ratio pair Score is weighted.
Use the mode of Image Acquisition for trigger-type acquisition in step 1.
[when betel nut is close to optoelectronic switch, optoelectronic switch triggers industrial CCD camera at once and acquires a frame image；]
Image Acquisition is carried out using high brightness diffusing reflection light source, brightness range is 10000~20000lux.
[ensure the high speed acquisition of image.]
The light source is the dome diffusing reflection light source that radius is 6cm.
Compared with prior art, advantages of the present invention is embodied in the following:
(1) present invention employs the hierarchical algorithms based on membership function to betel nut long axis, short axle, area, circularity, rectangle 7 degree, elongation characteristic values are classified, and the grade of each characteristic parameter is obtained, and are carried out synthesis finally by weighting algorithm and are sentenced Determine betel nut grade, total algorithm is simple, efficient, 93.6% accurate detection betel nut grade；
(2) compared with existing manual method, which has that detection accuracy is high, speed is fast, the advantages such as reproducible, Meets the needs of existing production line real-time online detection, reliable and stable.The influence of individual physiology and psychological factor is overcome, thus The accuracy that the classification of betel nut is generated.
Detailed description of the invention
Fig. 1 is structure chart of the invention；
Fig. 2 is the respective image after the process flow chart that betel nut extracts and processing, wherein (a) is original graph to be fractionated Picture；It (b) is the single channel image of (a) figure；It (c) is the binary image of (b) figure；
(d) connected domain screening is carried out for (c) figure；
It (e) is the effect picture after (d) totem culture；(f) edge detecting operation is carried out for (e) figure, detects the profile of betel nut； (g) betel nut corresponds to minimum circumscribed rectangle；
Fig. 3 is that betel nut extracts figure；
Fig. 4 is based on the betel nut hierarchical block diagram for being subordinate to algorithm；
Fig. 5 is part betel nut sample
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples.The present invention is detected with rail surface defects It is illustrated for example, but the present invention is not limited thereto.
Camera uses resolution ratio for the face of 1080*960 battle array kilomega network CCD camera (Baumer TXG12) in this example, Camera lens is 6mm wide viewing angle Computar camera lens, and light source is the dome diffusing reflection light source (LTS-FM12030-WQ) that radius is 6cm；
As shown in Figure 1, a kind of betel nut level detection method based on machine vision, comprising the following steps:
Step 1: acquisition is located at the betel nut image on production line, Image0 is denoted as, as shown in Fig. 2 (a)；
Step 2: single channel operation being carried out to betel nut image Image0, obtains image Image1；As shown in Fig. 2 (b)
Step 3: binarization operation being carried out to betel nut image Image1, obtains bianry image Image2；As shown in Fig. 2 (c)
Betel nut is split from background image, T1 be binarization segmentation threshold value, Image1 (x, y) be image in (x, Y) gray value of position pixel:
Step 3: connective region search operation is carried out to binary image Image2, it is shown to search out area most such as Fig. 2 (d) Big connected domain Blob, and empty filling is carried out to Blob, as shown in Fig. 2 (e)；
[different processing condiment, and complex contour are contained in betel nut surface, and therefore, simple binary image operation can not be protected It is solid to demonstrate,prove connected domain Blob, and needs to use in the present invention and betel nut image area feature is classified betel nut, so, to protect The accuracy for demonstrate,proving betel nut image area, need to carry out holes filling.]
Step 4: the connected domain Blob obtained in step 3 being split out, obtains betel nut region RegionDiff, i.e., For the profile of betel nut, as shown in Fig. 2 (f)；
Step 5: extract betel nut characteristic parameter, that is, calculate the major axis A of betel nut region RegionDiff, short axle B, perimeter P, Area S, elongation E, circularity C, rectangular degree R, as shown in Figure 3；
Step 5.1: major axis A, the feature extraction of short axle B construct minimum circumscribed rectangle to region RegionDiff, minimum outer Meet the long side of rectangle, short side, that is, corresponding major axis A, short axle B, as shown in Fig. 2 (g)；
Step 5.2: the feature extraction of perimeter P, perimeter refer to the profile length of betel nut, obtain betel nut with chain rule Length:
P=sqrt (2) * Nd+NX+NY
Step 5.3: the feature extraction of area S, betel nut area describe the size of betel nut contour area, i.e., own in image The pixel number for belonging to betel nut, for the RegionDiff of region, if the length of each pixel is unit 1, then area Are as follows:
In formula: Q --- betel nut region RegionDiff.
Step 5.4: the extraction of elongation E, circularity C, rectangular degree R,
E=A/B
C=4 π S/P2
R=S/ (A*B)
Step 6: as shown in figure 4, being hierarchical algorithms structure chart, 200 the first estate betel nut characteristics are collected, it is right respectively 7 characteristic parameters establish membership function；
The membership function of long axis:
The membership function of short axle:
The membership function of perimeter:
The membership function of area:
The membership function of elongation:
The membership function of circularity:
The membership function of rectangular degree:
Wherein, μiFor the characteristic value of i-th of particle in sample,It is the mean value of betel nut feature in 200 master samples, σ is The square error of each sample average in 200 master samples.
Step 7: if the characteristic value and standard of sample to be tested are closer to the characteristic value of sample, the similarity degree of betel nut It is higher: on the contrary, the similarity degree of betel nut is lower；According to membership function, the corresponding betel nut grade of each parameter is obtained；
[wherein long axis makes an exception, and when the sample parameter of measurement is less than master sample average value, selected normal state is subordinate to letter Number.When sample parameter measurement is greater than master sample mean value, normal membership function cannot be selected, because of normal membership function Value begin to decline and another expression formula should be used to make the value of sample parameter and standard sample continues to increase and objective law Unanimously, i.e. the bigger quality of long axis parameter value of betel nut is higher.]
Step 8: and according to each grade, 100 different scores are given, and weight according to score.Since long axis is to betel nut Influence it is maximum, by A:B:P:S:E:C:R=3:1:1:1:2:1:1 proportion weighted, obtain comprehensive judgement betel nut grade to the end；
Use the mode of Image Acquisition for trigger-type acquisition in step 1.
[when betel nut is close to optoelectronic switch, optoelectronic switch triggers industrial CCD camera at once and acquires a frame image；]
Image Acquisition is carried out using high brightness diffusing reflection light source, brightness range is 10000~20000lux.[ensure image High speed acquisition.]
The grade of betel nut is sent to controller, controller issues grade and instructs to classification mechanism, corresponds to when betel nut reaches When rank position, betel nut classification is completed.This kind of method is simple, quick, and stability is good.Classification accuracy reaches 93.6%.
The betel nut sample detection result of Fig. 5 is as shown in Table 1:
Table one
Although the principle of the present invention is described in detail above in conjunction with the preferred embodiment of the present invention, this field skill Art personnel are it should be understood that above-described embodiment is only the explanation to exemplary implementation of the invention, not to present invention packet Restriction containing range.Details in embodiment is simultaneously not meant to limit the scope of the invention, without departing substantially from spirit of the invention and In the case where range, any equivalent transformation based on technical solution of the present invention, simple replacement etc. obviously change, and all fall within Within the scope of the present invention.

Claims (3)

1. a kind of betel nut level detection method based on machine vision, which comprises the following steps:
Step 1: acquisition is located at the betel nut image on production line, is denoted as Image0；
Step 2: single channel operation is carried out to betel nut image Image0, obtains image Image1；
Step 3: binarization operation is carried out to betel nut image Image1, obtains bianry image Image2；By betel nut from background image In split, T1 be binarization segmentation threshold value, Image1 (x, y) be image in the position (x, y) pixel gray value: x indicate The coordinate of betel nut image X-axis, y show the coordinate of betel nut image Y-axis；Then
Step 4: carrying out connective region search operation to binary image Image2, search out the maximum connected domain Blob of area, and Empty filling is carried out to Blob；
Step 5: the connected domain Blob obtained in step 4 is split out, obtains betel nut region RegionDiff, as The profile of betel nut；
Step 6: betel nut characteristic parameter is extracted, that is, calculates major axis A, the short axle B, perimeter P, face of betel nut region RegionDiff Product S, elongation E, circularity C, rectangular degree R；Specific step is as follows:
Step 6.1: extracting the major axis A of betel nut region RegionDiff, the feature of short axle B constructs most region RegionDiff Small boundary rectangle, the long side of minimum circumscribed rectangle, short side, that is, corresponding major axis A, short axle B；
Step 6.2: extracting the feature of perimeter P, perimeter refers to the profile length of betel nut
Step 6.3: extracting the feature of area S, betel nut area describes the size of betel nut contour area, i.e., all in image to belong to The pixel number of betel nut, for the RegionDiff of region, if the length of each pixel is unit 1, then area are as follows:
S=∑(x, y)∈Q1
In formula: Q indicates betel nut region RegionDiff
Step 6.4: the extraction of elongation E, circularity C, rectangular degree R,
E=A/B
C=4 π S/P2
R=S/ (A*B)；
Step 7: 200 the first estate betel nut characteristics are collected, respectively to betel nut region
Seven major axis A of RegionDiff, short axle B, perimeter P, area S, elongation E, circularity C, rectangular degree R characteristic parameters are built Vertical membership function；Determine the characteristic value of different brackets betel nut sample；
The membership function of long axis:
The membership function of short axle:
The membership function of perimeter:
The membership function of area:
The membership function of elongation:
The membership function of circularity:
The membership function of rectangular degree:
Wherein, μiFor the characteristic value of i-th of particle in sample,It is the mean value of betel nut feature in 200 master samples, σ is 200 The square error of each sample average in a master sample.
A(μi) indicate the membership function established to betel nut long axis；Exp [] is indicated in higher mathematics using natural constant e as the finger at bottom Number function；B(μi) indicate the membership function established to betel nut short axle；P(μi) indicate the membership function established to betel nut perimeter, because It is indicated for perimeter with P, and is about μiFunction, so with P (μi) indicate；S(μi) indicate to be subordinate to letter to what betel nut area was established Number；E(μi) indicate the membership function established to betel nut elongation；C(μi) indicate the membership function established to betel nut circularity；R (μi) indicate the membership function established to betel nut rectangular degree；
Step 8: if the characteristic value and standard of sample to be tested are closer to the characteristic value of sample, the similarity degree of betel nut is just It is higher: on the contrary, the similarity degree of betel nut is lower；According to membership function, the corresponding betel nut grade of each parameter is obtained；
Step 9: according to each betel nut grade, each feature gives n different score, and weights to score；Each score after weighting The gross score of addition determines the score of betel nut, and the grade of betel nut is then divided according to the score of betel nut.
2. the betel nut level detection method based on machine vision as described in claim 1, which is characterized in that the step 6.2 In, betel nut length is obtained with chain rule:
P=sqrt (2) * Nd+NX+NY；Sqrt () indicates evolution.
3. the betel nut level detection method based on machine vision as described in claim 1, which is characterized in that the step 9 In, n=100 is weighted score in A:B:P:S:E:C:R=3:1:1:1:2:1:1 ratio.
CN201810894870.6A 2018-08-08 2018-08-08 Betel nut grade detection method based on machine vision Active CN109115775B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810894870.6A CN109115775B (en) 2018-08-08 2018-08-08 Betel nut grade detection method based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810894870.6A CN109115775B (en) 2018-08-08 2018-08-08 Betel nut grade detection method based on machine vision

Publications (2)

Publication Number Publication Date
CN109115775A true CN109115775A (en) 2019-01-01
CN109115775B CN109115775B (en) 2021-05-07

Family

ID=64853121

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810894870.6A Active CN109115775B (en) 2018-08-08 2018-08-08 Betel nut grade detection method based on machine vision

Country Status (1)

Country Link
CN (1) CN109115775B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109724978A (en) * 2019-01-02 2019-05-07 广州南颐贸易有限公司 A kind of swallow small cup accurate intelligent assortment device
CN109827971A (en) * 2019-03-19 2019-05-31 湖州灵粮生态农业有限公司 A kind of method of non-destructive testing fruit surface defect
CN110110810A (en) * 2019-05-17 2019-08-09 北京禾泽方圆智能科技有限公司 A kind of squid credit rating identification method for separating
CN114882499A (en) * 2022-07-08 2022-08-09 南通海扬食品有限公司 Fruit acid-sweetness classification method and system based on artificial intelligence

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7298897B1 (en) * 2004-02-11 2007-11-20 United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration Optimal binarization of gray-scaled digital images via fuzzy reasoning
CN103164695A (en) * 2013-02-26 2013-06-19 中国农业大学 Fruit identification method based on multi-source image information fusion
CN203155561U (en) * 2013-04-25 2013-08-28 株洲广博自动化设备有限公司 Raw areca nut screening line
CN104463804A (en) * 2014-12-12 2015-03-25 中国科学院武汉物理与数学研究所 Image enhancement method based on intuitional fuzzy set
CN104537671A (en) * 2015-01-04 2015-04-22 长沙理工大学 Cigarette filter online counting and quality detecting method based on machine vision
CN105404869A (en) * 2015-11-20 2016-03-16 陕西科技大学 Computer vision based fruit shape grading method
US20160300363A1 (en) * 2015-03-12 2016-10-13 Raytheon Company Apparatus and processes for corn moisture analysis and prediction of optimum harvest date
CN106097308A (en) * 2016-05-31 2016-11-09 长沙理工大学 A kind of New energy electric vehicle based on machine vision charging hole detection and localization method
CN106204589A (en) * 2016-07-11 2016-12-07 陕西科技大学 A kind of fruit type quality stage division based on Digital Image Processing
KR20170027746A (en) * 2017-01-20 2017-03-10 유진인스텍 주식회사 Surface treatment degree detecting method of material and the system
CN207280962U (en) * 2017-08-31 2018-04-27 惠州市三协精密有限公司 A kind of CCD detection devices for areca nut food processing
CN108051449A (en) * 2018-01-30 2018-05-18 华中农业大学 The online visible detection method of Salted duck egg face crack based on morphologic edge detection
CN207487588U (en) * 2017-10-26 2018-06-12 湖南远见视觉科技有限责任公司 A kind of betel nut vision inspection apparatus
CN108279238A (en) * 2018-01-30 2018-07-13 深圳春沐源控股有限公司 A kind of fruit maturity judgment method and device

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7298897B1 (en) * 2004-02-11 2007-11-20 United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration Optimal binarization of gray-scaled digital images via fuzzy reasoning
CN103164695A (en) * 2013-02-26 2013-06-19 中国农业大学 Fruit identification method based on multi-source image information fusion
CN203155561U (en) * 2013-04-25 2013-08-28 株洲广博自动化设备有限公司 Raw areca nut screening line
CN104463804A (en) * 2014-12-12 2015-03-25 中国科学院武汉物理与数学研究所 Image enhancement method based on intuitional fuzzy set
CN104537671A (en) * 2015-01-04 2015-04-22 长沙理工大学 Cigarette filter online counting and quality detecting method based on machine vision
US20160300363A1 (en) * 2015-03-12 2016-10-13 Raytheon Company Apparatus and processes for corn moisture analysis and prediction of optimum harvest date
CN105404869A (en) * 2015-11-20 2016-03-16 陕西科技大学 Computer vision based fruit shape grading method
CN106097308A (en) * 2016-05-31 2016-11-09 长沙理工大学 A kind of New energy electric vehicle based on machine vision charging hole detection and localization method
CN106204589A (en) * 2016-07-11 2016-12-07 陕西科技大学 A kind of fruit type quality stage division based on Digital Image Processing
KR20170027746A (en) * 2017-01-20 2017-03-10 유진인스텍 주식회사 Surface treatment degree detecting method of material and the system
CN207280962U (en) * 2017-08-31 2018-04-27 惠州市三协精密有限公司 A kind of CCD detection devices for areca nut food processing
CN207487588U (en) * 2017-10-26 2018-06-12 湖南远见视觉科技有限责任公司 A kind of betel nut vision inspection apparatus
CN108051449A (en) * 2018-01-30 2018-05-18 华中农业大学 The online visible detection method of Salted duck egg face crack based on morphologic edge detection
CN108279238A (en) * 2018-01-30 2018-07-13 深圳春沐源控股有限公司 A kind of fruit maturity judgment method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
NUDTHAPONG TONGKHAM: "Dragon fruit peel pectin: Microwave-assisted extraction and fuzzy assessment", 《AGRICULTURE AND NATURAL RESOURCES》 *
许月明: "基于计算机视觉的槟榔分级研究", 《食品与机械》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109724978A (en) * 2019-01-02 2019-05-07 广州南颐贸易有限公司 A kind of swallow small cup accurate intelligent assortment device
CN109827971A (en) * 2019-03-19 2019-05-31 湖州灵粮生态农业有限公司 A kind of method of non-destructive testing fruit surface defect
CN110110810A (en) * 2019-05-17 2019-08-09 北京禾泽方圆智能科技有限公司 A kind of squid credit rating identification method for separating
CN110110810B (en) * 2019-05-17 2021-03-26 北京禾泽方圆智能科技有限公司 Squid quality grade identification and sorting method
CN114882499A (en) * 2022-07-08 2022-08-09 南通海扬食品有限公司 Fruit acid-sweetness classification method and system based on artificial intelligence
CN114882499B (en) * 2022-07-08 2022-09-20 南通海扬食品有限公司 Fruit acid-sweetness classification method and system based on artificial intelligence

Also Published As

Publication number Publication date
CN109115775B (en) 2021-05-07

Similar Documents

Publication Publication Date Title
CN109269951B (en) Image-based flotation tailing ash content, concentration and coarse particle content detection method
CN104794491B (en) Based on the fuzzy clustering Surface Defects in Steel Plate detection method presorted
CN109115775A (en) A kind of betel nut level detection method based on machine vision
Omid et al. An expert egg grading system based on machine vision and artificial intelligence techniques
CN109977808A (en) A kind of wafer surface defects mode detection and analysis method
CN110276386A (en) A kind of apple grading method and system based on machine vision
CN109684906B (en) Method for detecting red fat bark beetles based on deep learning
CN101059425A (en) Method and device for identifying different variety green tea based on multiple spectrum image texture analysis
CN103593670A (en) Copper sheet and strip surface defect detection method based on-line sequential extreme learning machine
CN102221559A (en) Online automatic detection method of fabric defects based on machine vision and device thereof
CN111242899B (en) Image-based flaw detection method and computer-readable storage medium
CN109668909A (en) A kind of glass defect detection method
CN110135271A (en) A kind of cell sorting method and device
CN112184648A (en) Piston surface defect detection method and system based on deep learning
CN107730499A (en) A kind of leucocyte classification method based on nu SVMs
CN113421230B (en) Visual detection method for defects of vehicle-mounted liquid crystal display light guide plate based on target detection network
CN110096980A (en) Character machining identifying system
CN114119526A (en) Steel plate surface defect detection and identification system and method based on machine vision
CN107330478A (en) A kind of cherry tomato sorting technique, system and cherry tomato on-line sorting system
CN106872473A (en) A kind of potato defects detection identifying system design based on machine vision
CN111161237A (en) Fruit and vegetable surface quality detection method, storage medium and sorting device thereof
CN109598681A (en) The reference-free quality evaluation method of image after a kind of symmetrical Tangka repairs
CN106340007A (en) Image processing-based automobile body paint film defect detection and identification method
Xu et al. A defect inspection for explosive cartridge using an improved visual attention and image-weighted eigenvalue
Xiao et al. Defect detection and classification of galvanized stamping parts based on fully convolution neural network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant