CN111257339B - Preserved egg crack online detection method and detection device based on machine vision - Google Patents

Preserved egg crack online detection method and detection device based on machine vision Download PDF

Info

Publication number
CN111257339B
CN111257339B CN202010117474.XA CN202010117474A CN111257339B CN 111257339 B CN111257339 B CN 111257339B CN 202010117474 A CN202010117474 A CN 202010117474A CN 111257339 B CN111257339 B CN 111257339B
Authority
CN
China
Prior art keywords
image
preserved egg
preserved
egg
detection
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010117474.XA
Other languages
Chinese (zh)
Other versions
CN111257339A (en
Inventor
王巧华
龚帅斌
汤文权
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.)
Huazhong Agricultural University
Original Assignee
Huazhong Agricultural University
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 Huazhong Agricultural University filed Critical Huazhong Agricultural University
Priority to CN202010117474.XA priority Critical patent/CN111257339B/en
Publication of CN111257339A publication Critical patent/CN111257339A/en
Application granted granted Critical
Publication of CN111257339B publication Critical patent/CN111257339B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/95Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan 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
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KGRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for recognising patterns
    • G06K9/62Methods or arrangements for pattern recognition using electronic means
    • G06K9/6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G06K9/6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KGRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for recognising patterns
    • G06K9/62Methods or arrangements for pattern recognition using electronic means
    • G06K9/6267Classification techniques
    • G06K9/6268Classification techniques relating to the classification paradigm, e.g. parametric or non-parametric approaches
    • G06K9/6269Classification techniques relating to the classification paradigm, e.g. parametric or non-parametric approaches based on the distance between the decision surface and training patterns lying on the boundary of the class cluster, e.g. support vector machines
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan 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
    • G01N2021/8854Grading and classifying of flaws
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan 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
    • G01N2021/8887Scan 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

Abstract

The invention discloses a preserved egg crack online detection method and device based on machine vision. The detection device comprises a conveyor belt, a camera bellows, a light source, an industrial camera, an electromagnetic valve, a controller and a computer. The method comprises the following steps: firstly, acquiring preserved egg images; automatically cutting the preserved egg image; thirdly, preprocessing preserved egg images; extracting relevant characteristic parameters; establishing a crack discrimination model; sixthly, judging whether cracks exist on the surface of the preserved egg. The method utilizes machine vision to detect, can realize online detection and classification of preserved egg cracks, has low requirement on application environment, low equipment cost and high selection freedom, and has better application and popularization prospects compared with acoustic detection; turning the preserved eggs by using an industrial camera to take pictures in multiple angles, and having a full detection range; the Haar feature detection is utilized, the region is automatically selected in a frame mode, and the method is real-time, concise and accurate and has high flexibility; the image is efficiently processed, a discrimination model is established, and an effective detection method is provided for the vacant part in online detection and comparison of preserved egg cracks.

Description

Preserved egg crack online detection method and detection device based on machine vision
Technical Field
The invention relates to the technical field of nondestructive testing of agricultural products, in particular to an online preserved egg crack detection method and device based on machine vision.
Background
During the production process of preserved eggs (preserved eggs), the preserved eggs are easy to be damaged due to common reasons such as production processes, operation of workers and the like, and once the shells are damaged and cracked, toxic and harmful substances in preserved egg marinades can enter the preserved eggs. Thus, cracked preserved eggs are inedible and must be removed before shipment to avoid the introduction of harmful products into the market.
In the production process of preserved eggs in China, the most manual mode is still adopted for controlling the quality of the preserved eggs, time and labor are wasted, errors are prone to occurring after long-time work, efficiency is low, and labor cost is high. The online detection method for researching the preserved egg cracks has important theoretical value and practical production significance.
Currently, researchers have conducted studies on the detection of cracks in eggs. The royal jelly and the like adopt natural light and polarized light to collect preserved egg images to respectively carry out static preserved egg crack detection, and the detection precision is improved by combining two detection methods and fusing multiple characteristics; the method comprises the following steps of sorting cracked eggs by the Wang navy and the like in an acoustic mode, extracting acoustic signal characteristics related to the cracks of the eggs, constructing a discrimination model by utilizing an artificial neural network, designing an on-line egg crack detection system based on FPGA and DSP, and exploring the discrimination effect of the on-line egg detection system on intact eggs and cracked eggs; the Pan Lei Qing and the like are fused with computer vision and acoustic signals to realize nondestructive detection and classification of the surface cracks of the eggs, wherein in the aspect of computer vision, images are analyzed and processed, geometric characteristic parameters of crack areas and noise areas are extracted, a three-layer BP neural network model based on MATLAB is established, and the cracks are identified and the eggs are automatically classified.
The existing detection technology through relevant retrieval has the following problems:
1. due to the need for online crack detection in an actual production line, the strong interference of the machine equipment makes the acoustic detection means unsuitable for the actual online detection of preserved eggs. 2. At present, the crack detection of the poultry egg mainly takes the crack of a fresh egg as a main part, and the adopted method mainly comprises the steps of placing a light source under a transmission mode to illuminate a target egg. The preserved eggs are cured and gelled, so that light is extremely difficult to transmit, and cracks cannot be highlighted through transmission. 3. At present, the static crack detection of domestic preserved eggs is available, and the dynamic online detection method is blank. 4. Most detection methods are complex in algorithm and large in calculation amount. Therefore, medium and small poultry egg processing enterprises need simple, direct and high-cost-performance image detection technology and equipment to replace manpower urgently.
Disclosure of Invention
The invention aims to provide a preserved egg crack online detection method and a preserved egg crack online detection device based on machine vision, which are used for solving the problems in the prior art.
In order to achieve the purpose, the invention provides the following scheme: the invention provides a preserved egg crack online detection method based on machine vision, which comprises the following steps:
acquisition of preserved egg image
Continuously acquiring real-time image information of different angles of the preserved eggs to be detected, wherein the real-time images form full-surface image information;
automatic cutting of preserved egg image
A. Obtaining a shot real-time image containing preserved eggs, and identifying the image by using a trained cascade classifier based on Haar characteristics;
B. cutting the original image according to the obtained result to obtain an original image I1 containing a single preserved egg;
thirdly, preprocessing the preserved egg image
A. The G component of the original image I1 is extracted to obtain a grayscale image I2. Performing edge detection through an edge detection operator to obtain an edge information binary image BW1 of the original image;
B. fixedly filling a full-black ellipse in the center of the binary image BW1, and covering an area of 50% -60% of the inner central area of the edge of the preserved egg to obtain a binary image BW 2;
C. removing a connected domain occupying 1-1.5 per mill of area in BW2, performing ellipse fitting to obtain a preserved egg shaped binary image BW3, and performing dot multiplication operation on the binary image BW3 and a gray level image I2 to obtain a background removed image I3;
D. carrying out gray level enhancement on the image I3, and then carrying out high-pass filtering operation to obtain a gray level image I4;
judging whether the preserved egg has cracks
A. Calculating and extracting three characteristic parameters of average gray value, smoothness and uniformity from the obtained image I4;
B. inputting the average gray value, smoothness and uniformity characteristic parameters of the image I4 into an SVM (support vector machine) discrimination model for calculation discrimination;
C. if one or more images are determined to be a crack, the preserved egg is determined to be a cracked egg.
Preferably, a large number of preserved egg image samples and non-preserved egg image samples are collected, harr characteristics of the image samples are extracted, an Adaboost algorithm is used for training a classifier to distinguish preserved eggs from non-preserved eggs, the classifier is cascaded together by using screening type cascade, training is carried out layer by layer, all cascade layers are trained until the false positive rate is not higher than 5%, the classifier is stored, and the cascade classifier based on the Haar characteristics is obtained.
Preferably, the collected normal egg image samples and the collected cracked egg image samples form a training set according to the proportion of 1:1, average gray value, smoothness and uniformity characteristic parameters of the samples are respectively extracted and input into an SVM (support vector machine) for two-classification training, the optimal parameters are found out, and a support vector machine model is stored to obtain the SVM discrimination model.
Detection apparatus for preserved egg crackle on-line measuring method based on machine vision, including conveyer belt, camera bellows, light source, industry camera, solenoid valve, controller and computer the conveyer belt top sets up the camera bellows, the light source is placed between two parties in the camera bellows top, set up the camera hole directly over the camera bellows and place the industry camera, the industry camera passes through data transmission line and links to each other with the computer, the controller passes through signal line and solenoid valve and computer connection respectively, and the solenoid valve is installed conveyer belt outlet egg mouth one side.
Preferably, the conveyer belt is provided with an egg support, and the egg support is black or other colors with larger discrimination with the preserved egg shell.
Preferably, the dark box is a cubic hollow stainless steel box body.
Preferably, the light source is a ring light source.
Preferably, the computer is provided with image processing software.
The invention discloses the following technical effects:
1. the machine vision is used for detection, online detection and classification of preserved egg cracks can be realized, the requirement on application environment is low, the equipment cost is low, and the application and popularization prospects are better compared with acoustic detection;
2. the model is simple and effective, the calculation speed is high, and the requirements on the accuracy and speed of online detection can be met.
3. An effective detection method is provided for the vacant part of online detection of preserved egg cracks, the robustness is strong, and the frame can be applied to online detection of other poultry eggs or similar products by slight modification.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described 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 to obtain other drawings without inventive exercise.
FIG. 1 is a schematic diagram of the structure of the device of the present invention, in which:
a conveyor belt 1; 2, preserved eggs; a dark box 3; a light source 4; an industrial camera 5; an electromagnetic valve 6; a controller 7; a computer 8;
fig. 2 is a flowchart of the image processing process and image processing software of the present invention, wherein fig. 2-1 is a picture formed by the image processing process and fig. 2-2 is a flowchart of the image processing software.
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.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Referring to fig. 1, the invention provides an online preserved egg crack detection device based on vision, which comprises a conveyor belt 1, a camera 3, a light source 4, an industrial camera 5, an electromagnetic valve 6, a controller 7 and a computer 8. Set up camera bellows 3 above conveyer belt 1, light source 4 is placed between two parties in camera bellows 3 top, set up the camera hole directly over the camera bellows and place industry camera 5, industry camera 5 passes through data transmission line and links to each other with computer 8, controller 7 is connected with solenoid valve 6 and computer 8 through the signal line respectively, solenoid valve 6 is installed 1 egg outlet one side of conveyer belt.
Further optimization scheme, conveyer belt 1 is the device of the transport preserved egg 2 in the actual production, and conveyer belt 1 is provided with the egg and holds in the palm, and the egg holds in the palm and need be black or other colors different with the preserved egg shell, the subsequent image processing operation of being convenient for. Its function is to convey and tumble preserved eggs 2;
in a further optimized scheme, the camera bellows 3 is a cubic hollow stainless steel box body, and a camera hole is formed right above the camera bellows, so that the industrial camera 5 is convenient to mount and fix;
in a further preferred embodiment, the light source 4 is a general purpose item available from commercial sources, such as an LED ring light source, which functions to illuminate the preserved egg 2 to be tested while ensuring uniform illumination.
In a further optimized scheme, the industrial camera 5 is a general outsourcing part, for example, a Basler industrial camera is selected, and the function of the industrial camera is to collect the original image of the preserved egg 2;
according to a further optimized scheme, the electromagnetic valve 6 is a target egg removing device and has the function of jumping once immediately after being electrified and pushing a previous preserved egg 2 out of the track of the conveyor belt 1;
in a further optimized scheme, the controller 7 is a general-purpose outsourced component, for example, an S7-200PLC is selected, and the controller has the function of receiving signals of the picture processing result of the computer 8 and controlling the action of the electromagnetic valve 6.
In a further optimized scheme, the computer 8 is a general-purpose outsourced component, such as a CPU AMDR536003.60GHz/memory 16G and Windows 10 system. The computer can be according to the demand of detection through changing the discontinuous settlement of time come to carry out arbitrary adjustment to specific every turn-over angle of preserved egg and a week of processing number of times of motion, has great flexibility and controllability.
In a further optimization scheme, the computer 8 is internally provided with image processing software, and the work flow is as follows according to the figure 2-2:
a. collecting an original image;
b. automatically cutting and segmenting the original image through Haar characteristic detection to obtain a single preserved egg original image I1;
c. extracting a G component of the image I1 to obtain a gray image I2;
d. performing edge detection through an edge detection operator to obtain an edge information binary image BW1 of the original image;
e. filling all 0 ellipses with constant sizes into the BW1 to obtain a binary image BW 2;
f. after removing the connected domain with a smaller area in the BW2, carrying out ellipse fitting to obtain a binary image BW 3;
g. multiplying the fitted ellipse BW3 with the gray level image I2 to obtain a background-removed gray level image I3;
h. carrying out gray level enhancement on the image I3, and then carrying out high-pass filtering operation to obtain an enhanced crack image I4;
i. calculating three characteristic parameters of average gray value, smoothness and uniformity of the image I4;
j. calculating and distinguishing by using the trained SVM distinguishing model;
k. if one or more image discrimination results are cracks, the preserved egg is discriminated as a cracked egg;
and l, ending.
The method for carrying out online detection on the preserved egg cracks by using the detection device comprises the following steps:
step one acquisition of preserved egg image
Continuously acquiring real-time image information of different angles of the preserved eggs to be detected, wherein the real-time images form full-surface image information;
step two, automatic cutting of preserved egg image
A. Obtaining a shot real-time image containing preserved eggs, identifying the image by using a trained cascade classifier based on Haar features, extracting the features of the image once for each frame in the captured image, and obtaining a group of return value arrays with stored coordinates and width and height if the images can be judged by a cascade strong classifier;
B. cutting on an original drawing according to the obtained real-time preserved egg position coordinates and width and height information to obtain an original drawing I1 containing a single preserved egg;
three-step preserved egg image preprocessing
A. The G component of the image I1 is extracted, and a grayscale image I2 is obtained. Then, edge detection is carried out through an edge detection operator to obtain an edge contour information binary image BW1 of the original image;
B. an ellipse with a constant size is fixedly filled in the binary image BW1, after edge detection, the edge of a larger crack can be difficult to work by a method of removing a small-area connected domain, so that a completely black ellipse is generated to cover a central area with a larger area, the size of the ellipse accounts for 50% -60% of the area of a preserved egg, and a binary image BW2 is obtained, so that the detected noise profile with the larger area is prevented from influencing the subsequent ellipse fitting operation;
C. removing a connected domain occupying 1-1.5 per mill of area in BW2, performing ellipse fitting to obtain a binary image BW3, and performing point multiplication operation on the fitted ellipse and a gray image I2 to obtain a background-removed gray image I3;
D. carrying out gray level enhancement on the image I3, and then carrying out high-pass filtering operation to obtain an enhanced crack image I4;
step four, judging whether the preserved eggs have cracks or not
A. And (5) carrying out operation of extracting three characteristic parameters of average gray value, smoothness and uniformity on the obtained I4. The average gray value is the average brightness of the picture at the moment, the smoothness is the excessive smoothness of the picture, namely the variance after variable standardization, and the uniformity is the measurement consistency of the picture and is the sum of squares of all elements of the gray histogram.
C. Judging by using the trained SVM judgment model;
D. if one or more image discrimination results are the cracked egg pictures, the preserved egg is discriminated as a cracked egg.
The method further comprises the steps of collecting a large number of preserved egg image samples and non-preserved egg image samples, extracting harr-like characteristics of pictures, training a strong classifier by using an Adaboost algorithm, distinguishing preserved eggs from non-preserved eggs, and cascading the strong classifier together by using screening type cascading, so that the detection accuracy is improved. And training the cascade classifiers layer by layer, and only when the false detection rate of one layer is not higher than 5%, entering the next layer to train all cascade layers, and storing the classifiers after training is finished to obtain the trained cascade classifier based on the Haar features.
And further optimizing the scheme, collecting a large number of normal egg image samples and cracked egg image samples, forming a training set by the collected normal egg image samples and cracked egg image samples according to a ratio of 1:1, respectively extracting average gray value, smoothness and uniformity characteristic parameters of the samples, inputting the parameters into an SVM (support vector machine) for two-class training, finding out optimal parameters, and storing a support vector machine model to obtain a trained SVM discrimination model.
The preserved egg image processing process according to fig. 2-1 is as follows:
1. FIG. 2-1-1 is an automatic cropping segmentation map of an original image;
2. 2-1-2 original drawing I1 of a single preserved egg;
3. FIG. 2-1-3 grayscale image I2;
4. the edge contour information binary image BW1 of the original image of fig. 2-1-4;
5. 2-1-5 binary image BW 2;
6. fig. 2-1-6 binary image BW3
7. FIG. 2-1-7 grayscale image I3;
8. fig. 2-1-8 crack image I4.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, are merely for convenience of description of the present invention, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
The above-described embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements of the technical solutions of the present invention can be made by those skilled in the art without departing from the spirit of the present invention, and the technical solutions of the present invention are within the scope of the present invention defined by the claims.

Claims (7)

1. A preserved egg crack online detection method based on machine vision is characterized by comprising the following steps:
acquisition of preserved egg image
Continuously acquiring real-time image information of different angles of the preserved eggs to be detected, wherein the real-time images form full-surface image information;
automatic cutting of preserved egg image
A. Obtaining a shot real-time image containing preserved eggs, and identifying the image by utilizing a cascade classifier based on Haar characteristics;
B. cutting the preserved egg real-time image according to the obtained result to obtain an original image I1 containing a single preserved egg;
thirdly, preprocessing the preserved egg image
A. Extracting a G component of the original image I1 to obtain a gray image I2, and performing edge detection through an edge detection operator to obtain an edge information binary image BW1 of the original image I1;
B. fixedly filling a full black ellipse in the center of the binary image BW1 to cover a larger area in the center of the edge of the preserved egg to obtain a binary image BW 2;
C. removing a small-area connected domain in BW2, performing ellipse fitting to obtain a preserved egg-shaped binary image BW3, and performing dot multiplication on the binary image BW3 and a gray image I2 to obtain a background-removed image I3;
D. carrying out gray level enhancement on the image I3, and then carrying out high-pass filtering operation to obtain a gray level image I4;
judging whether the preserved egg has cracks
A. Calculating and extracting three characteristic parameters of average gray value, smoothness and uniformity from the obtained gray image I4;
B. inputting the average gray value, smoothness and uniformity characteristic parameters of the gray image I4 into an SVM (support vector machine) discrimination model for calculation discrimination;
C. if one or more images are judged as a crack, the detected preserved egg is judged as a cracked egg.
2. The machine-vision-based preserved egg crack online detection method as claimed in claim 1, wherein a large number of preserved egg image samples and non-preserved egg image samples are collected, harr-like features of the image samples are extracted, a classifier is trained by using an Adaboost algorithm, preserved eggs and non-preserved eggs are distinguished, the classifiers are cascaded together by using screening type cascading, training is performed layer by layer, all cascading layers are trained until the false drop rate is not higher than 5%, and the classifier is stored to obtain the cascade classifier based on Haar features.
3. The machine vision-based preserved egg crack online detection method as claimed in claim 1, wherein the collected normal egg image samples and cracked egg image samples form a training set according to a ratio of 1:1, average gray value, smoothness and uniformity characteristic parameters of the samples are respectively extracted and input into an SVM (support vector machine) for two-classification training, an optimal parameter is found out, and the SVM discrimination model is obtained by storing a support vector machine model.
4. A detection device for implementing the online preserved egg crack detection method based on machine vision as claimed in claim 1, characterized in that: the detection device comprises a conveyor belt (1), a camera bellows (3), a light source (4), an industrial camera (5), an electromagnetic valve (6), a controller (7) and a computer (8), wherein the camera bellows (3) is arranged above the conveyor belt (1), the light source (4) is placed in the middle of the top of the camera bellows (3), a camera hole is formed right above the camera bellows for placing the industrial camera (5), the industrial camera (5) is connected with the computer (8) through a data transmission line, the controller (7) is respectively connected with the electromagnetic valve (6) and the computer (8) through signal lines, and the electromagnetic valve (6) is installed on one side of an egg outlet of the conveyor belt (1);
the egg tray is arranged on the conveyor belt (1) and is black or other colors different from the color of the preserved egg shell.
5. The detection device of the on-line preserved egg crack detection method based on machine vision as claimed in claim 4, wherein: the dark box (3) is a cubic hollow stainless steel box body.
6. The detection device of the on-line preserved egg crack detection method based on machine vision as claimed in claim 4, wherein: the light source (4) is an annular light source.
7. The detection device of the on-line preserved egg crack detection method based on machine vision as claimed in claim 4, wherein: the computer (8) is internally provided with image processing software.
CN202010117474.XA 2020-02-25 2020-02-25 Preserved egg crack online detection method and detection device based on machine vision Active CN111257339B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010117474.XA CN111257339B (en) 2020-02-25 2020-02-25 Preserved egg crack online detection method and detection device based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010117474.XA CN111257339B (en) 2020-02-25 2020-02-25 Preserved egg crack online detection method and detection device based on machine vision

Publications (2)

Publication Number Publication Date
CN111257339A CN111257339A (en) 2020-06-09
CN111257339B true CN111257339B (en) 2021-07-23

Family

ID=70949425

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010117474.XA Active CN111257339B (en) 2020-02-25 2020-02-25 Preserved egg crack online detection method and detection device based on machine vision

Country Status (1)

Country Link
CN (1) CN111257339B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113686876A (en) * 2021-08-24 2021-11-23 华南农业大学 Poultry egg crack detection method and device

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11287763A (en) * 1998-04-01 1999-10-19 Kyowa Kikai Kk Automatic inspection method of egg, transfer-controlling device of egg suited for it, and automatic inspection device of egg
JP2001211776A (en) * 2000-01-31 2001-08-07 Hokkaido Method for inspecting internal defect of hen's egg
JP2007127467A (en) * 2005-11-02 2007-05-24 Joichiro Tsuboi Automatic egg inspection device by image processing
JP2008020223A (en) * 2006-07-11 2008-01-31 Joichiro Tsuboi Image processor in automatic egg inspection method by image processing
WO2009033041A1 (en) * 2007-09-07 2009-03-12 The United States Of America, As Represented By The Secretary Of Agriculture Egg micro-crack detection systems
JP2012013586A (en) * 2010-07-02 2012-01-19 Joichiro Tsuboi Automatic egg inspection mechanism by image processing
CN104749190A (en) * 2015-04-02 2015-07-01 华中农业大学 Online visual inspection device and online visual inspection method for cracks on surface of poultry eggs
CN106370668A (en) * 2016-08-22 2017-02-01 华中农业大学 Online visual inspection apparatus and method of internal quality of salted egg
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
JP2018189432A (en) * 2017-04-28 2018-11-29 株式会社ナベル Inspection device of egg
CN110006899A (en) * 2019-04-12 2019-07-12 华中农业大学 The lossless vision detection and classification method of lime-preserved egg inside quality

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101915767B (en) * 2010-07-13 2011-10-19 南京农业大学 Method for systematically recognizing egg cracks
CN102147866B (en) * 2011-04-20 2012-11-28 上海交通大学 Target identification method based on training Adaboost and support vector machine
CN102445456B (en) * 2011-10-09 2013-07-03 河海大学常州校区 Device and method for nondestructively detecting egg quality based on DSP (Dynamic Signal Processing) machine vision
GB2518890B (en) * 2013-10-07 2015-09-23 Yair Or Adar System and method for determining viability of eggs
CN103699907B (en) * 2014-01-04 2017-02-15 复旦大学 Pesticide spraying detection method based on machine learning
CN104764744B (en) * 2015-04-21 2017-03-22 华中农业大学 Visual inspection device and method for inspecting freshness of poultry eggs
CN106778800A (en) * 2016-11-14 2017-05-31 天津津航技术物理研究所 A kind of AdaBoost cascade classifiers method for quick
CN106872465B (en) * 2016-12-27 2020-03-03 中国农业大学 Poultry fertilized egg detection and screening device based on machine vision

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11287763A (en) * 1998-04-01 1999-10-19 Kyowa Kikai Kk Automatic inspection method of egg, transfer-controlling device of egg suited for it, and automatic inspection device of egg
JP2001211776A (en) * 2000-01-31 2001-08-07 Hokkaido Method for inspecting internal defect of hen's egg
JP2007127467A (en) * 2005-11-02 2007-05-24 Joichiro Tsuboi Automatic egg inspection device by image processing
JP2008020223A (en) * 2006-07-11 2008-01-31 Joichiro Tsuboi Image processor in automatic egg inspection method by image processing
WO2009033041A1 (en) * 2007-09-07 2009-03-12 The United States Of America, As Represented By The Secretary Of Agriculture Egg micro-crack detection systems
JP2012013586A (en) * 2010-07-02 2012-01-19 Joichiro Tsuboi Automatic egg inspection mechanism by image processing
CN104749190A (en) * 2015-04-02 2015-07-01 华中农业大学 Online visual inspection device and online visual inspection method for cracks on surface of poultry eggs
CN106370668A (en) * 2016-08-22 2017-02-01 华中农业大学 Online visual inspection apparatus and method of internal quality of salted egg
JP2018189432A (en) * 2017-04-28 2018-11-29 株式会社ナベル Inspection device of egg
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
CN110006899A (en) * 2019-04-12 2019-07-12 华中农业大学 The lossless vision detection and classification method of lime-preserved egg inside quality

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Improved Modified Pressure Imaging and Software for Egg Micro-Crack Detection and Egg Quality Grading;S. C. Yoon 等;《Applied Engineering in Agriculture》;20121231;第28卷(第2期);第283-293页 *

Also Published As

Publication number Publication date
CN111257339A (en) 2020-06-09

Similar Documents

Publication Publication Date Title
CN106238342B (en) Panoramic vision potato sorts and defect detecting device and its sorting detection method
CN105388162B (en) Raw material silicon chip surface scratch detection method based on machine vision
CN106409711A (en) Solar silicon wafer defect detecting system and method
CN109724984B (en) Defect detection and identification device and method based on deep learning algorithm
CN105046700B (en) Fruit surface defect detection method and system based on gamma correction and color classification
CN110314854B (en) Workpiece detecting and sorting device and method based on visual robot
CN107328787A (en) A kind of metal plate and belt surface defects detection system based on depth convolutional neural networks
CN101907453B (en) Online measurement method and device of dimensions of massive agricultural products based on machine vision
CN102179374B (en) Automatic detecting and sorting device for poultry egg quality and method thereof
CN107486415A (en) Thin bamboo strip defect on-line detecting system and detection method based on machine vision
CN109772733B (en) Defect bamboo block detecting and sorting device and method based on vision
CN206139527U (en) Panoramic vision potato is selected separately and defect detecting device
CN111257339B (en) Preserved egg crack online detection method and detection device based on machine vision
CN202037127U (en) Automatic egg quality detection and separation equipment
CN109115775A (en) A kind of betel nut level detection method based on machine vision
CN108287010A (en) A kind of crab multi objective grading plant and method
Chao et al. Design of a dual-camera system for poultry carcasses inspection
CN111239142A (en) Paste appearance defect detection device and method
CN210071686U (en) Fruit grading plant based on orthogonal binocular machine vision
CN108318494B (en) The red online vision detection and classification devices and methods therefor for proposing fruit powder
CN110763700A (en) Method and equipment for detecting defects of semiconductor component
CN112676195B (en) Color sorting device and method for solid wood floor based on linear array CMOS camera
CN113077450A (en) Cherry grading detection method and system based on deep convolutional neural network
CN208059993U (en) A kind of crab multi objective grading plant
CN110554052A (en) artificial board surface defect detection method and system

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