CN111136027B - Salted duck egg quality sorting device and method based on convolutional neural network - Google Patents
Salted duck egg quality sorting device and method based on convolutional neural network Download PDFInfo
- Publication number
- CN111136027B CN111136027B CN202010037406.2A CN202010037406A CN111136027B CN 111136027 B CN111136027 B CN 111136027B CN 202010037406 A CN202010037406 A CN 202010037406A CN 111136027 B CN111136027 B CN 111136027B
- Authority
- CN
- China
- Prior art keywords
- salted duck
- conveying mechanism
- duck eggs
- neural network
- convolutional neural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 241000272525 Anas platyrhynchos Species 0.000 title claims abstract description 240
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 20
- 235000013601 eggs Nutrition 0.000 claims abstract description 249
- 238000001514 detection method Methods 0.000 claims abstract description 72
- 230000007246 mechanism Effects 0.000 claims description 187
- 239000007789 gas Substances 0.000 claims description 46
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 claims description 36
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 claims description 36
- 229910000037 hydrogen sulfide Inorganic materials 0.000 claims description 36
- 238000012549 training Methods 0.000 claims description 14
- 230000001360 synchronised effect Effects 0.000 claims description 13
- 238000011176 pooling Methods 0.000 claims description 12
- 210000003278 egg shell Anatomy 0.000 claims description 8
- 230000001502 supplementing effect Effects 0.000 claims description 8
- 102000002322 Egg Proteins Human genes 0.000 claims description 6
- 108010000912 Egg Proteins Proteins 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 6
- 238000007477 logistic regression Methods 0.000 claims description 6
- 101150021123 msrA gene Proteins 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000007664 blowing Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 2
- 210000001503 joint Anatomy 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 abstract description 3
- 238000003062 neural network model Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 210000000078 claw Anatomy 0.000 description 4
- 235000016709 nutrition Nutrition 0.000 description 3
- 230000035764 nutrition Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 244000144977 poultry Species 0.000 description 2
- TVEXGJYMHHTVKP-UHFFFAOYSA-N 6-oxabicyclo[3.2.1]oct-3-en-7-one Chemical compound C1C2C(=O)OC1C=CC2 TVEXGJYMHHTVKP-UHFFFAOYSA-N 0.000 description 1
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005554 pickling Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 235000021404 traditional food Nutrition 0.000 description 1
- 229940088594 vitamin Drugs 0.000 description 1
- 229930003231 vitamin Natural products 0.000 description 1
- 235000013343 vitamin Nutrition 0.000 description 1
- 239000011782 vitamin Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K43/00—Testing, sorting or cleaning eggs ; Conveying devices ; Pick-up devices
- A01K43/04—Grading eggs
- A01K43/10—Grading and stamping
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- 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
- 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
- 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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- 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
- G01N33/0004—Gaseous mixtures, e.g. polluted air
- G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
- G01N33/0027—General constructional details of gas analysers, e.g. portable test equipment concerning the detector
- G01N33/0036—General constructional details of gas analysers, e.g. portable test equipment concerning the detector specially adapted to detect a particular component
- G01N33/0044—Sulphides, e.g. H2S
-
- 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
- G01N33/08—Eggs, e.g. by candling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/0081—Sorting of food items
-
- 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
- G01N2021/8883—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 involving the calculation of gauges, generating models
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Food Science & Technology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Environmental Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medicinal Chemistry (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Combustion & Propulsion (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Neurology (AREA)
- Signal Processing (AREA)
- Sorting Of Articles (AREA)
Abstract
The utility model discloses a salted duck egg quality sorting device and method based on a convolutional neural network, wherein the salted duck egg quality sorting device comprises a frame, a black box arranged on the frame, a detection device arranged in the black box, a conveying device for conveying salted duck eggs into the black box for detection and a control system; according to the salted duck egg quality sorting device, the smelly salted duck eggs are preferentially removed by detecting the gas components in the gas emitted by the salted duck eggs, the remaining salted duck eggs are detected by using the convolution neural network model which is trained in advance and is used for detecting the quality of the salted duck eggs, inferior salted duck eggs and high-quality salted duck eggs are sorted, a traditional manual detection mode is replaced, labor is saved, and production efficiency is improved.
Description
Technical Field
The utility model relates to salted duck egg detection equipment, in particular to a salted duck egg quality sorting device and method based on a convolutional neural network.
Background
Salted duck eggs are also called salted duck eggs, and are a traditional food in China. The salted duck egg is prepared from fresh duck egg as main raw material by pickling, and has rich nutrition, and is rich in fat, protein, various microelements and vitamins required by human body, and is easy to be absorbed by human body. The appearance of the high-quality salted duck egg is round and smooth, the eggshell is complete and clean, no crack exists, and the shell is cyan; the shell of the inferior salted duck egg is dark, more white or black spots exist on the surface, the eggshell is thin and fragile and is easy to break, the deteriorated salted duck egg can even generate a pungent odor, the malodor mainly comes from chemical gases such as ammonia gas, hydrogen sulfide gas and the like, and as a plurality of tiny air holes exist on the surface of the eggshell, the salted duck egg can emit odor even if the shell is complete.
Poultry eggs such as eggs, duck eggs and the like and egg products are important ways for people to ensure sufficient nutrition, classification and detection technologies for the poultry eggs are also layered endlessly, but most of the technology is researched for fresh eggs, the egg products such as salted duck eggs and the like which are processed to a certain degree are mostly detected on nutrition or harmful ingredients, and the quality detection and classification of the salted duck eggs are still mainly carried out by manual selection and classification, so that the method is time-consuming and labor-consuming, low in efficiency and easy to make mistakes. Therefore, some devices and methods for detecting and analyzing the quality of salted duck eggs appear on the market, for example, the patent of the utility model with the application publication number of CN108051449A discloses an online visual detection method for the surface cracks of the salted duck eggs based on morphological edge detection, and the online detection and classification of the cracks of the salted duck eggs can be realized by using machine vision for detection, so that the requirements on the application environment are low, the equipment cost is low, and the online detection method has better application and popularization prospects compared with the use of acoustic detection; taking photos of salted duck eggs at multiple overturning angles by using a single industrial camera, wherein the detection range is full; and the crack is extracted by using morphological edge detection, so that the crack extraction method is more visual and accurate.
However, the online visual detection method for the surface cracks of the salted duck eggs has the following defects:
although the online visual detection method for the surface cracks of the salted duck eggs eliminates the salted duck eggs which are likely to be deteriorated by detecting the surface cracks of the salted duck eggs, the situation that the shells of the inferior salted duck eggs are not broken but the shells of the inferior salted duck eggs are deteriorated to different degrees still exists in the market, so that the online visual detection method for the surface cracks of the salted duck eggs is difficult to detect.
Disclosure of Invention
The utility model aims to overcome the defects of the prior art and provides a salted duck egg quality sorting device based on a convolutional neural network, wherein the salted duck egg quality sorting device can more accurately detect the quality of salted duck eggs and has higher detection precision.
Another object of the utility model is to provide a salted duck egg quality sorting method based on a convolutional neural network.
The technical scheme for solving the technical problems is as follows:
the salted duck egg quality sorting device based on the convolutional neural network comprises a frame, a black box arranged on the frame, a detection device arranged in the black box, a conveying device for conveying salted duck eggs into the black box for detection and a control system,
the double-sided salted duck egg feeding device is characterized in that a salted duck egg inlet and a salted duck egg outlet are respectively arranged on two sides of the black box, wherein the salted duck egg inlet is provided with an inlet baffle plate and a first driving motor used for driving the inlet baffle plate to rotate so as to enable salted duck eggs to enter the black box one by one, the first driving motor is arranged on the black box, and a main shaft of the first driving motor is connected with the inlet baffle plate;
the conveying device comprises a first conveying mechanism, a second conveying mechanism and a third conveying mechanism, wherein the second conveying mechanism penetrates through the black box, the head end of the second conveying mechanism is connected with the tail end of the first conveying mechanism, and the tail end of the second conveying mechanism is connected with the head end of the third conveying mechanism; the third conveying mechanism is used for conveying the detected salted duck eggs to different collecting mechanisms;
the detection device comprises a first detection module arranged in the black box and a second detection module used for detecting the surface of the salted duck egg, wherein,
the first detection module comprises an ammonia gas sensor, a hydrogen sulfide gas sensor and a fan which are arranged in the black box, wherein the ammonia gas sensor and the hydrogen sulfide gas sensor are arranged on the inner wall of the black box and are positioned at one side of the second conveying mechanism and used for detecting whether ammonia gas and hydrogen sulfide gas are contained in gas emitted by salted duck eggs or not; the fan is arranged on the inner wall of the black box, is arranged opposite to the ammonia gas sensor and the hydrogen sulfide gas sensor, and is used for blowing gas emitted by salted duck eggs into the detection range of the ammonia gas sensor and the hydrogen sulfide gas sensor;
the second detection module comprises an image collection device and is used for collecting images of salted duck eggs detected in the black box, transmitting the images to the control system and analyzing and processing the images by the control system.
Preferably, the image collecting device comprises an industrial camera, and the industrial camera is arranged on the top of the inner wall of the black box and is positioned above the second conveying mechanism.
Preferably, the image collecting device further comprises a light supplementing lamp, wherein the light supplementing lamp is arranged at two sides of the industrial camera and used for supplementing light.
Preferably, an infrared sensor is arranged between the ammonia gas sensor and the hydrogen sulfide gas sensor and is used for detecting whether salted duck eggs are being detected.
Preferably, an inner baffle and a second driving motor for driving the inner baffle to rotate are further arranged in the black box, wherein the inner baffle is positioned above the second conveying mechanism; the second driving motor is arranged on the inner wall of the black box, and a main shaft of the second driving motor is connected with the inner baffle plate.
Preferably, the conveying speed of the first conveying mechanism is smaller than that of the second conveying mechanism.
Preferably, the third conveying mechanisms are multiple groups, the head end of each group of third conveying mechanism is communicated with the tail end of the second conveying mechanism, and the tail end of each group of third conveying mechanism is connected with each collecting mechanism; the end of the second conveying mechanism is provided with a sorting baffle plate, and the sorting baffle plate is driven by a third driving motor and used for conveying salted duck eggs into the corresponding third conveying mechanism.
Preferably, the first conveying mechanism, the second conveying mechanism and the third conveying mechanism are all synchronous belt transmission mechanisms.
A salted duck egg quality sorting method based on a convolutional neural network comprises the following steps:
(1) Firstly, a first conveying mechanism drives the salted duck eggs to move, the salted duck eggs are conveyed into a second conveying mechanism, and then the salted duck eggs are conveyed into the detection range of a detection device by the second conveying mechanism; then, the first driving motor drives the inlet baffle plate to move so as to block the salted duck egg inlet in the black box;
(2) The control system controls the fan to work, the odor of the salted duck eggs is blown to the ammonia gas sensor and the hydrogen sulfide gas sensor, and the ammonia gas sensor and the hydrogen sulfide gas sensor transmit detection information to the control system; if the detected content of ammonia gas and hydrogen sulfide gas emitted by the salted duck eggs exceeds the standard value, the salted duck eggs are unqualified; the second conveying mechanism conveys the salted duck eggs to the third conveying mechanism and conveys the salted duck eggs to the collecting mechanism for collecting unqualified salted duck eggs through the third conveying mechanism;
(3) If the content of the ammonia gas and the hydrogen sulfide gas emitted by the detected salted duck eggs does not exceed the standard value, the control system controls the image collecting device to work, photographs the salted duck eggs are taken, and the photograph information is sent to the control system; the control system builds a convolutional neural network model by processing the light images, wherein the building of the convolutional neural network model comprises the following steps:
(3-1) collecting sample images and establishing a sample library, wherein the collected sample images comprise color photos of salted duck eggs with different degrees of merits photographed at different angles; the obtained photographs of the salted duck eggs are subjected to category labeling, which comprises the following steps: the appearance of the egg is round and smooth, the eggshell is complete and clean, no crack exists, and the salted duck egg with a cyan shell is marked as a positive type; marking salted duck eggs with dark shells and more white or black spots on the surfaces or cracks on the surfaces as reverse types; if the input pictures contain pictures which do not contain salted duck eggs, marking the pictures as irrelevant types; then, 70% of the marked image is stored as a training sample set, and 30% is stored as a test sample set;
(3-2) normalizing the input sample images, normalizing the input sample images in the training sample set and the test sample set to 227 x 227 for subsequent input to the convolutional neural network;
(3-3) building a convolutional neural network model; the built convolutional neural network model is an AlexNet model, and the network layer of the convolutional neural network model comprises 5 convolutional layers, 3 maximum pooling layers, 3 full-connection layers and 1 output layer; wherein the first convolution layer adopts a convolution kernel with the size of 11×11, the step length is 4, and then a largest pooling layer with the size of 3×3 is adopted, and the step length is 2; the second convolution layer adopts a convolution kernel with the size of 5 multiplied by 5, the image filling operation is adopted to keep the image size unchanged, and then a largest pooling layer with the size of 3 multiplied by 3 is adopted, and the step length is 2; then, the third convolution layer, the fourth convolution layer and the fifth convolution layer are three tightly connected identical convolution layers with the size of 3×3, and the image filling operation is adopted to keep the image size unchanged; next to a maximum pooling layer of size 3 x 3, the step size is 2; then a fully connected layer with 9216 dimension output is followed by two identical fully connected layers with 4096 dimension output, and then the output layer is followed by the fully connected layers; the output layer adopts a Softmax function as an excitation function, and the rest network layers adopt a Relu function as an excitation function;
(3-4) initializing a convolutional neural network model, namely initializing by utilizing an Msra algorithm, wherein when only the input number is considered, the Msra initialization is a Gaussian distribution with the mean value of 0 and the variance of 2/n;
(3-5) training a convolutional neural network model;
(3-6) classifying the salted duck eggs through a trained convolutional neural network model; classifying normally shot pictures containing salted duck eggs into a normal type or a reverse type; classifying pictures of the non-salted duck eggs which are shot by mistake into irrelevant types;
(4) And the control system controls the third conveying mechanism to convey the salted duck eggs after detection to the corresponding collecting mechanism according to the classification result of the convolutional neural network model.
Preferably, in step (3-5), the step of training the convolutional neural network model is:
(3-51), inputting a characteristic variable;
(3-52) carrying out logic calculation on each item of data in the characteristic variables, and adding a normalization term in the calculation;
(3-53) calculating the output of each neuron of each layer, and randomly discarding the output of a part of neurons in the first two layers of all-connected layers by adopting a Dropout method;
(3-54) calculating a logistic regression cost function;
(3-55) calculating a proper weight matrix and a proper bias vector value by using a gradient descent method, so as to minimize a cost function of logistic regression;
(3-56), repeating the steps (3-53) - (3-55) until the prediction accuracy meets the requirement;
(3-57), result analysis and output.
Compared with the prior art, the utility model has the following beneficial effects:
1. according to the utility model, the odorized salted duck eggs are preferentially removed by detecting the gas components in the gas emitted by the salted duck eggs, the residual salted duck eggs are detected by using the convolution neural network model which is trained in advance and is used for detecting the quality of the salted duck eggs, and inferior salted duck eggs and high-quality salted duck eggs are classified, so that the traditional manual detection mode is replaced, the labor force is saved, and the production efficiency is improved.
2. According to the utility model, the salted duck eggs which are seriously deteriorated are preferentially removed by detecting the gas components emitted by the salted duck eggs, the residual salted duck eggs are detected by using the convolutional neural network, the surface spots of the salted duck eggs with complete shells can still be classified according to the detection, and finally, the high-quality salted duck eggs and the low-quality salted duck eggs can be classified with higher accuracy, so that the detection precision is improved.
3. The utility model can be applied to the product quality detection link before the salted duck eggs are produced and packaged in a factory, replaces the traditional manual detection classification, improves the production efficiency and effectively controls the factory quality of the salted duck eggs.
Drawings
Fig. 1 is a schematic diagram of a first embodiment of a salted duck egg quality sorting device based on a convolutional neural network.
Fig. 2 is a schematic diagram of the structure of the black box, the detecting device and the second conveying mechanism.
Fig. 3 is a schematic flow chart of a salted duck egg quality sorting method based on a convolutional neural network.
Fig. 4 is a schematic flow chart of constructing the convolutional neural network model in fig. 3.
Fig. 5 is a schematic flow chart of the training convolutional neural network model in fig. 4.
Fig. 6 is a schematic diagram of a network structure of a convolutional neural network model.
Fig. 7 is a schematic diagram of the first and second conveying mechanisms in a second embodiment of a salted duck egg quality sorting device based on a convolutional neural network according to the present utility model.
Fig. 8 is a schematic diagram of a third embodiment of a salted duck egg quality sorting device based on a convolutional neural network.
Detailed Description
The present utility model will be described in further detail with reference to examples and drawings, but embodiments of the present utility model are not limited thereto.
Example 1
Referring to fig. 1-2, the salted duck egg quality sorting device based on the convolutional neural network comprises a frame, a black box 7 arranged on the frame, a detection device arranged in the black box 7, a conveying device 11 for conveying salted duck eggs 8 into the black box 7 for detection and a control system.
Referring to fig. 1-2, two sides of the black box 7 are respectively provided with a salted duck egg inlet and a salted duck egg outlet, wherein the salted duck egg inlet is provided with an inlet baffle plate 9 and a first driving motor for driving the inlet baffle plate 9 to rotate so as to enable salted duck eggs 8 to enter the black box 7 one by one, the first driving motor is installed on the black box 7, and a main shaft is connected with the inlet baffle plate 9.
Referring to fig. 1-2, the conveying device 11 includes a first conveying mechanism 11-1, a second conveying mechanism 11-2 and a third conveying mechanism 11-3, wherein the second conveying mechanism 11-2 penetrates through the black box 7, and the head end of the second conveying mechanism 11-2 is connected with the tail end of the first conveying mechanism 11-1, and the tail end is connected with the head end of the third conveying mechanism 11-3; the third conveying mechanism 11-3 is used for conveying the salted duck eggs 8 after detection to the different collecting mechanisms 11-4.
Referring to fig. 1-2, the detecting device comprises a first detecting module arranged in a black box 7 and a second detecting module for detecting the surface of a salted duck egg 8, wherein the first detecting module comprises an ammonia gas sensor 3, a hydrogen sulfide gas sensor 5 and a fan 13 which are arranged in the black box 7, wherein the ammonia gas sensor 3 and the hydrogen sulfide gas sensor 5 are arranged on the inner wall of the black box 7 and are positioned at the side edge of the second conveying mechanism 11-2, and the detecting device is used for detecting whether ammonia gas and hydrogen sulfide gas contained in gas emitted by the salted duck egg 8 are contained or not; the fan is arranged on the inner wall of the black box 7 and is arranged opposite to the ammonia gas sensor 3 and the hydrogen sulfide gas sensor 5, and is used for blowing gas emitted by the salted duck eggs 8 into the detection range of the ammonia gas sensor 3 and the hydrogen sulfide gas sensor 5; an infrared sensor 4 is arranged between the ammonia gas sensor 3 and the hydrogen sulfide gas sensor 5 and is used for detecting whether salted duck eggs 8 are detected;
the second detection module comprises an image collection device, a control system and a first detection module, wherein the image collection device is used for collecting images of salted duck eggs 8 detected in a black box 7 and transmitting the images to the control system, and the control system analyzes and processes the images, the image collection device comprises an industrial camera 1 and a light supplementing lamp 2, and the industrial camera 1 is arranged on the top of the inner wall of the black box 7 through a camera bracket 6 and is positioned above the second conveying mechanism 11-2; the light supplementing lamps 2 are installed at two sides of the industrial camera 1 and are used for supplementing light.
Referring to fig. 1-2, an inner baffle 10 and a second driving motor for driving the inner baffle 10 to rotate are further arranged inside the black box 7, wherein the inner baffle 10 is positioned above the second conveying mechanism 11-2; the second driving motor is arranged on the inner wall of the black box 7 and is connected with the inner baffle 10. The second driving motor drives the inner baffle plate 10 to rotate, thereby playing a role in blocking the movement of the salted duck eggs 8. When the salted duck eggs 8 are detected, the second driving motor drives the inner baffle 10 to rotate, so that the inner baffle 10 is driven to block the salted duck eggs 8, the salted duck eggs are always located in the detection range of the detection device, after detection is completed, the second driving motor drives the inner baffle 10 to rotate, and release is achieved, and detection of the salted duck eggs 8 is facilitated.
Referring to fig. 1-2, the salted duck egg quality sorting device based on the convolutional neural network further comprises sorting devices installed on a rack, wherein the sorting devices are in two groups, the two groups of sorting devices are sequentially arranged along the conveying direction of the third conveying mechanism 11-3, each group of sorting devices comprises a conveying claw 16, a driving cylinder 17 for driving the conveying claw 16 to move perpendicular to the conveying direction of the third conveying mechanism 11-3, and a fourth conveying mechanism 18 for conveying salted duck eggs 8 in the third conveying mechanism 11-3 to the corresponding collecting mechanism 11-4, and the conveying claw 16 is connected with a telescopic rod of the driving cylinder 17; the conveying direction of the fourth conveying mechanism 18 is perpendicular to the conveying direction of the third conveying mechanism 11-3, one end of the fourth conveying mechanism 18 is abutted with the third conveying mechanism 11-3, and the other end is abutted with the collecting mechanism 11-4. After the second conveying mechanism 11-2 conveys the salted duck eggs 8 to the third conveying mechanism 11-3, the third conveying mechanism 11-3 conveys the salted duck eggs 8 to corresponding sorting devices according to different qualities, for example, two sorting devices in the embodiment, wherein one sorting device is used for conveying the salted duck eggs 8 into the unqualified collecting mechanism 11-4; the other sorting device feeds salted duck eggs 8 into a qualified collecting mechanism 11-4; the driving cylinder 17 of the corresponding sorting device drives the carrying claw 16 to move, so that the salted duck eggs 8 are driven to move in the direction perpendicular to the conveying direction of the third conveying mechanism 11-3, the salted duck eggs 8 are conveyed to the corresponding fourth conveying mechanism 18, and the salted duck eggs 8 are conveyed to the corresponding collecting mechanism 11-4 by the fourth conveying mechanism 18, so that sorting work of the salted duck eggs 8 is completed.
In addition to the above embodiment, the sorting device may further adopt a manner of sorting and carrying by a manipulator, to carry salted duck eggs 8 with different qualities to different collecting mechanisms 11-4, wherein the manner of sorting and carrying by the manipulator may be implemented with reference to a commercially available sorting device, for example, an "egg sorting device" disclosed in an utility model patent application publication No. CN109349164 a.
The first conveying mechanism 11-1, the second conveying mechanism 11-2, the third conveying mechanism 11-3 and the fourth conveying mechanism 18 are all synchronous belt transmission mechanisms, and a synchronous belt wheel is driven by a motor to rotate so as to drive the synchronous belt to move, so that the salted duck eggs 8 are conveyed, wherein a limiting block 19 is arranged on the synchronous belt, the limiting block 19 can be a poking tooth on the synchronous belt and is used for preventing the salted duck eggs 8 from generating relative movement with the synchronous belt in the conveying process, the limiting block 19 can be arranged on the front side and the rear side of the salted duck eggs 8, and the cross section of the limiting block 19 is semicircular or circular, so that the salted duck eggs 8 can be conveyed conveniently, and the relative movement between the salted duck eggs 8 and the synchronous belt can be limited conveniently; the first conveying mechanism 11-1, the second conveying mechanism 11-2, the third conveying mechanism 11-3 and the fourth conveying mechanism 18 can be provided with flanges on the left side and the right side of the limiting block 19, so as to prevent the salted duck eggs 8 from rolling down from the synchronous belt.
In addition, the cross section of the limiting block 19 is semicircular or circular, which has the advantages that: when the second conveying mechanism 11-2 conveys the salted duck eggs 8 to the detection device for detection, the second driving motor drives the inner baffle plate 10 to rotate, so that the movement of the salted duck eggs 8 is blocked along with the movement of the synchronous belt of the second conveying mechanism 11-2, and relative movement can be generated between the salted duck eggs 8 and the second conveying mechanism 11-2, but as the section of the limiting block 19 on the synchronous belt of the second conveying mechanism 11-2 is semicircular or circular, when the salted duck eggs 8 and the limiting block 19 move relatively, the salted duck eggs 8 roll along the outer outline of the limiting block 19, so that the salted duck eggs 8 can be always limited at the detection range of the detection device, and meanwhile, no damage can be caused to the salted duck eggs 8.
Referring to fig. 1-2, the salted duck egg quality sorting device based on the convolutional neural network provided by the utility model has the following working principle:
when the salted duck egg detection device works, the first conveying mechanism 11-1 drives the salted duck egg 8 to move, the salted duck egg 8 is conveyed into the second conveying mechanism 11-2, and then the salted duck egg 8 is conveyed into the detection range of the detection device by the second conveying mechanism 11-2; then, the first driving motor drives the inlet baffle plate 9 to move so as to block the inlet of the salted duck eggs 8 in the black box 7; when the infrared sensor 4 detects the salted duck eggs 8, the control system controls the fan 13 to work, the odor of the salted duck eggs 8 is blown to the ammonia gas sensor 3 and the hydrogen sulfide gas sensor 5, and the ammonia gas sensor 3 and the hydrogen sulfide gas sensor 5 transmit detection information to the control system; if the detected content of ammonia gas and hydrogen sulfide gas emitted by the salted duck egg 8 exceeds the standard value, the salted duck egg 8 is unqualified; the second conveying mechanism 11-2 conveys the salted duck eggs 8 to the third conveying mechanism 11-3 and conveys the salted duck eggs to the collecting mechanism 11-4 for collecting unqualified salted duck eggs through the third conveying mechanism 11-3; if the detected content of ammonia gas and hydrogen sulfide gas emitted by the salted duck eggs 8 does not exceed the standard value, the control system controls the image collecting device to work, photographs the salted duck eggs 8 are taken, and the photograph information is sent to the control system; processing the pictures through a control system, constructing a convolutional neural network model, and analyzing the quality of the salted duck eggs 8 through the convolutional neural network model; and the control system controls the third conveying mechanism 11-3 to convey the salted duck eggs 8 after detection to the corresponding collecting mechanism 11-4 according to the analysis result of the convolutional neural network model, so that the automation and the unmanned of the quality sorting work of the salted duck eggs 8 are realized. The data acquired by the method not only comprise the smell of the salted duck eggs 8, cracks of the eggshells of the salted duck eggs 8, but also the colors, spots and the like of the eggshells of the salted duck eggs 8, so that the quality analysis of the salted duck eggs 8 without cracks can be realized, and the detection precision is higher.
Referring to fig. 1-6, the salted duck egg quality sorting method based on the convolutional neural network comprises the following steps:
(1) Firstly, the first conveying mechanism 11-1 drives the salted duck eggs 8 to move, the salted duck eggs 8 are conveyed into the second conveying mechanism 11-2, and then the salted duck eggs 8 are conveyed into the detection range of the detection device by the second conveying mechanism 11-2; the first driving motor drives the inlet baffle plate 9 to move so as to block the inlet of the salted duck eggs 8 in the black box 7;
(2) The control system controls the fan 13 to work, the odor of the salted duck eggs 8 is blown to the positions of the ammonia gas sensor 3 and the hydrogen sulfide gas sensor 5, and the ammonia gas sensor 3 and the hydrogen sulfide gas sensor 5 transmit detection information to the control system; if the detected content of ammonia gas and hydrogen sulfide gas emitted by the salted duck egg 8 exceeds the standard value, the salted duck egg 8 is unqualified; the second conveying mechanism 11-2 conveys the salted duck eggs 8 into the third conveying mechanism 11-3, and conveys the salted duck eggs into the collecting mechanism 11-4 for collecting unqualified salted duck eggs 8 through the third conveying mechanism 11-3;
(3) If the detected content of ammonia gas and hydrogen sulfide gas emitted by the salted duck eggs 8 does not exceed the standard value, the control system controls the image collecting device to work, photographs the salted duck eggs 8 are taken, and the photograph information is sent to the control system; the control system builds a convolutional neural network model by processing the light images, wherein the building of the convolutional neural network model comprises the following steps:
(3-1) sample IMAGE acquisition and sample library establishment, wherein the acquired sample IMAGEs comprise color photos of salted duck eggs 8 with different degrees of merits photographed at different angles (namely RGB-IMAGE in the figure 6 of the specification); the obtained photographs of the salted duck eggs 8 are labeled in category, and specifically comprise: the appearance of the egg is round and smooth, the eggshell is complete and clean, no crack exists, and the salted duck egg 8 with a cyan shell is marked as a positive type; marking salted duck eggs 8 with dark shells and more white or black spots on the surfaces or cracks on the surfaces as reverse types; if the input pictures contain pictures which do not contain salted duck eggs 8, marking the pictures as irrelevant types; saving 70% of the marked images as a training sample set and saving 30% as a test sample set;
(3-2) normalizing the input samples; the input samples in the training sample set and the test sample set are normalized to 227×227 (pixels) for subsequent input into the convolutional neural network, so that the training efficiency of the convolutional neural network is improved;
(3-3) building a convolutional neural network model; the built convolutional neural network model is an AlexNet model, and comprises 5 convolutional layers (CONV), 3 maximum pooling layers (POOL), 3 full connection layers (FC) and 1 output layer; wherein the first convolution layer uses a convolution kernel of 11×11, with a step size of 4, followed by a largest pooling layer of 3×3 (pixels), with a step size of 2 (pixels); the second convolution layer adopts a convolution kernel with the size of 5 multiplied by 5, and the image filling operation is adopted to keep the image size unchanged because the convolution operation is carried out once, the image size can be compressed, namely, a circle of blank pixels are filled outside the original image before the convolution (the convolution result is not influenced), so that the image size after the convolution can be kept unchanged; next to a maximum pooling layer of size 3 x 3, the step size is 2; then, the third convolution layer, the fourth convolution layer and the fifth convolution layer are three tightly connected identical convolution layers with the size of 3×3, and the image filling operation is adopted to keep the image size unchanged; next to a maximum pooling layer of size 3 x 3, the step size is 2; then a fully connected layer with 9216 dimension output is followed by two identical fully connected layers with 4096 dimension output, and then the output layer is followed by the two identical fully connected layers; the output layer adopts a Softmax function as an excitation function, and the rest network layers adopt a Relu function as an excitation function;
(3-4) initializing a convolutional neural network model; initializing by using an Msra method, wherein when only the input number is considered, the Msra initialization is Gaussian distribution with the mean value of 0 and the variance of 2/n;
(3-5) training a convolutional neural network model;
(3-6) classifying the salted duck eggs 8 through a trained convolutional neural network model; classifying the input salted duck egg 8 photos by a convolutional neural network model, namely classifying the normally shot pictures containing the salted duck eggs 8 into positive type or negative type; classifying pictures of the non-salted duck eggs 8 which are shot by mistake into irrelevant types;
(4) And the control system controls the third conveying mechanism 11-3 to convey the salted duck eggs 8 after detection to the corresponding collecting mechanism 11-4 according to the classification result of the convolutional neural network model.
Referring to fig. 1 to 6, in step (3-5), the step of training the convolutional neural network model is:
(3-51), inputting a characteristic variable;
(3-52) carrying out logic calculation on each item of data in the characteristic variables, and adding a normalization term in the calculation;
(3-53) calculating the output of each neuron of each layer, and randomly discarding the output of a part of neurons in the first two layers of all-connected layers by adopting a Dropout method;
(3-54) calculating a logistic regression cost function;
(3-55) calculating a proper weight matrix and a proper bias vector value by using a gradient descent method, so as to minimize a cost function of logistic regression;
(3-56), repeating the steps (3-53) - (3-55) until the prediction accuracy meets the requirement;
(3-57), analyzing the result and outputting the result.
Example 2
Referring to fig. 7, this embodiment is different from embodiment 1 in that: the conveying speed of the first conveying mechanism 11-1 is smaller than that of the second conveying mechanism 11-2, namely V2 > V1. Thus, when the salted duck egg 8 is transferred from the first conveying mechanism 11-1 to the second conveying mechanism 11-2, the conveying speed of the second conveying mechanism 11-2 is larger than that of the first conveying mechanism 11-1, so that the salted duck egg 8 is equivalent to an acceleration, a horizontal forward acting force is generated, the salted duck egg 8 and the following salted duck egg 8 are pulled apart by a distance, for example, when the speed of V2 is twice as high as that of V1, the distance between the salted duck eggs 8 entering the second conveying mechanism 11-2 is twice as high as that of the first conveying mechanism 11-1, therefore, only the parameters of V1 and V2 are required to be reasonably adjusted according to the detection time, the inlet baffle 9 can be ensured to smoothly close the salted duck egg inlet without damaging the salted duck egg 8; simultaneously can make first driving motor can drive import baffle 9 and rotate to stop the salted duck egg 8 at the back smoothly, make salted duck egg 8 can detect one by one, and can avoid damaging salted duck egg 8.
In addition to the above-described structure, the rest of the structure can be implemented with reference to embodiment 1.
Example 3
Referring to fig. 8, the difference between this embodiment and embodiment 1 is that the third conveying mechanisms 11-3 are two groups, wherein an included angle between one group of third conveying mechanisms 11-3 and the second conveying mechanism 11-2 is 135 degrees, an included angle between the other group of third conveying mechanisms 11-3 and the second conveying mechanism 11-2 is 225 degrees, and the two groups of third conveying mechanisms 11-3 are respectively butted with the second conveying mechanisms 11-2, wherein the head end of each group of third conveying mechanisms 11-3 is communicated with the tail end of the second conveying mechanism 11-2, and the tail end is connected with each collecting mechanism 11-4; the tail end of the second conveying mechanism 11-2 is provided with a sorting baffle plate 14, and the sorting baffle plate 14 is driven by a third driving motor and is used for conveying salted duck eggs 8 into different third conveying mechanisms 11-3; when the third driving motor drives the sorting baffle plate 14 to rotate to an included angle of 135 degrees with the second conveying mechanism 11-2, the salted duck eggs 8 coming out of the second conveying mechanism 11-2 are contacted with the sorting baffle plate 14 and are driven by the second conveying mechanism 11-3 to move along the inclined direction of the sorting baffle plate 14 to a third conveying mechanism 11-3 which forms an included angle of 135 degrees with the second conveying mechanism 11-2, and the salted duck eggs are conveyed into the corresponding collecting mechanism 11-4 by the third conveying mechanism 11-3; similarly, when the third driving motor drives the sorting baffle 14 to rotate to an included angle of 225 degrees with the second conveying mechanism 11-2, the salted duck eggs 8 enter the third conveying mechanism 11-3 which forms an included angle of 225 degrees with the second conveying mechanism 11-2 under the guidance of the sorting baffle 14. Thus, the salted duck eggs 8 with different qualities can be sorted.
In this embodiment, the two sides of the synchronous belts of the first conveying mechanism 11-1, the second conveying mechanism 11-2 and the third conveying mechanism 11-3 are provided with flanges, for example, a flange 12 positioned at two sides of the first conveying mechanism 11-1 and a flange 15 positioned at two sides of the third conveying mechanism 11-3; this prevents the salted duck eggs 8 from falling off the timing belt.
In addition to the above-described structure, the rest of the structure can be implemented with reference to embodiment 1.
The foregoing is illustrative of the present utility model and is not to be construed as limiting thereof, but rather as various changes, modifications, substitutions, combinations, and simplifications which may be made therein without departing from the spirit and principles of the utility model are intended to be included within the scope of the utility model.
Claims (8)
1. A salted duck egg quality sorting device based on a convolutional neural network is characterized by comprising a frame, a black box arranged on the frame, a detection device arranged in the black box, a conveying device for conveying salted duck eggs into the black box for detection and a control system, wherein,
the double-sided salted duck egg feeding device is characterized in that a salted duck egg inlet and a salted duck egg outlet are respectively arranged on two sides of the black box, wherein the salted duck egg inlet is provided with an inlet baffle plate and a first driving motor used for driving the inlet baffle plate to rotate so as to enable salted duck eggs to enter the black box one by one, the first driving motor is arranged on the black box, and a main shaft of the first driving motor is connected with the inlet baffle plate;
the conveying device comprises a first conveying mechanism, a second conveying mechanism and a third conveying mechanism, wherein the second conveying mechanism penetrates through the black box, the head end of the second conveying mechanism is connected with the tail end of the first conveying mechanism, and the tail end of the second conveying mechanism is connected with the head end of the third conveying mechanism; the third conveying mechanism is used for conveying the detected salted duck eggs to different collecting mechanisms; the conveying speed of the first conveying mechanism is smaller than that of the second conveying mechanism; the third conveying mechanisms are two groups, wherein the included angle between one group of third conveying mechanisms and the second conveying mechanism is 135 degrees, the included angle between the other group of third conveying mechanisms and the second conveying mechanism is 225 degrees, the two groups of third conveying mechanisms are respectively in butt joint with the second conveying mechanism, when the third driving motor drives the sorting baffle to rotate to the included angle between the third driving motor and the second conveying mechanism is 135 degrees, salted duck eggs coming out of the second conveying mechanism are in contact with the sorting baffle, and are driven by the second conveying mechanism to move into the third conveying mechanism which forms an included angle of 135 degrees with the second conveying mechanism along the inclined direction of the sorting baffle, and are conveyed into the corresponding collecting mechanism by the third conveying mechanism; similarly, when the third driving motor drives the sorting baffle to rotate to an included angle of 225 degrees with the second conveying mechanism, the salted duck eggs enter the third conveying mechanism which forms an included angle of 225 degrees with the second conveying mechanism under the guidance of the sorting baffle;
the detection device comprises a first detection module and a second detection module, wherein the first detection module is arranged in a black box and is used for detecting the surface of a salted duck egg, the first detection module comprises an ammonia gas sensor, a hydrogen sulfide gas sensor and a fan, the ammonia gas sensor and the hydrogen sulfide gas sensor are arranged in the black box, the ammonia gas sensor and the hydrogen sulfide gas sensor are arranged on the inner wall of the black box and are positioned on one side of the second conveying mechanism, and the first detection module is used for detecting whether ammonia gas and hydrogen sulfide gas are contained in gas emitted by the salted duck egg; the fan is arranged on the inner wall of the black box, is arranged opposite to the ammonia gas sensor and the hydrogen sulfide gas sensor, and is used for blowing gas emitted by salted duck eggs into the detection range of the ammonia gas sensor and the hydrogen sulfide gas sensor; the second detection module comprises an image collection device, is used for collecting images of salted duck eggs detected in the black box, and transmits the images to the control system, and the control system analyzes and processes the images;
an inner baffle and a second driving motor for driving the inner baffle to rotate are further arranged in the black box, wherein the inner baffle is positioned above the second conveying mechanism; the second driving motor is arranged on the inner wall of the black box, and a main shaft of the second driving motor is connected with the inner baffle plate.
2. The salted duck egg quality sorting device based on a convolutional neural network according to claim 1, wherein the image collecting device comprises an industrial camera which is arranged on top of the inner wall of the black box and above the second conveying mechanism.
3. The salted duck egg quality sorting device based on a convolutional neural network according to claim 2, wherein the image collecting device further comprises light supplementing lamps which are installed at both sides of the industrial camera for supplementing light.
4. The device for sorting salted duck egg quality based on a convolutional neural network according to claim 1, wherein an infrared sensor is arranged between the ammonia gas sensor and the hydrogen sulfide gas sensor for detecting whether salted duck eggs are being detected.
5. The salted duck egg quality sorting device based on the convolutional neural network according to claim 1, wherein the third conveying mechanisms are multiple groups, the head end of each group of the third conveying mechanism is communicated with the tail end of the second conveying mechanism, and the tail end of each group of the third conveying mechanism is connected with each collecting mechanism; the end of the second conveying mechanism is provided with a sorting baffle plate, and the sorting baffle plate is driven by a third driving motor and used for conveying salted duck eggs into the corresponding third conveying mechanism.
6. The salted duck egg quality sorting device based on a convolutional neural network according to claim 1, wherein the first conveying mechanism, the second conveying mechanism and the third conveying mechanism are all synchronous belt transmission mechanisms.
7. A salted duck egg quality sorting method for the convolutional neural network-based salted duck egg quality sorting device as claimed in any one of claims 1-6, characterized by comprising the steps of:
(1) Firstly, a first conveying mechanism drives the salted duck eggs to move, the salted duck eggs are conveyed into a second conveying mechanism, and then the salted duck eggs are conveyed into the detection range of a detection device by the second conveying mechanism; then, the first driving motor drives the inlet baffle plate to move so as to block the salted duck egg inlet in the black box;
(2) The control system controls the fan to work, the odor of the salted duck eggs is blown to the ammonia gas sensor and the hydrogen sulfide gas sensor, and the ammonia gas sensor and the hydrogen sulfide gas sensor transmit detection information to the control system; if the detected content of ammonia gas and hydrogen sulfide gas emitted by the salted duck eggs exceeds the standard value, the salted duck eggs are unqualified; the second conveying mechanism conveys the salted duck eggs to the third conveying mechanism and conveys the salted duck eggs to the collecting mechanism for collecting unqualified salted duck eggs through the third conveying mechanism;
(3) If the content of the ammonia gas and the hydrogen sulfide gas emitted by the detected salted duck eggs does not exceed the standard value, the control system controls the image collecting device to work, photographs the salted duck eggs are taken, and the photograph information is sent to the control system; the control system builds a convolutional neural network model by processing the light images, wherein the building of the convolutional neural network model comprises the following steps:
(3-1) collecting sample images and establishing a sample library, wherein the collected sample images comprise color photos of salted duck eggs with different degrees of merits photographed at different angles; the obtained photographs of the salted duck eggs are subjected to category labeling, which comprises the following steps: the appearance of the egg is round and smooth, the eggshell is complete and clean, no crack exists, and the salted duck egg with a cyan shell is marked as a positive type; marking salted duck eggs with dark shells and more white or black spots on the surfaces or cracks on the surfaces as reverse types; if the input pictures contain pictures which do not contain salted duck eggs, marking the pictures as irrelevant types; then, 70% of the marked image is stored as a training sample set, and 30% is stored as a test sample set;
(3-2) normalizing the input sample images, normalizing the input sample images in the training sample set and the test sample set to 227 x 227 for subsequent input to the convolutional neural network;
(3-3) building a convolutional neural network model; the built convolutional neural network model is an AlexNet model, and the network layer of the convolutional neural network model comprises 5 convolutional layers, 3 maximum pooling layers, 3 full-connection layers and 1 output layer; wherein the first convolution layer adopts a convolution kernel with the size of 11×11, the step length is 4, and then a largest pooling layer with the size of 3×3 is adopted, and the step length is 2; the second convolution layer adopts a convolution kernel with the size of 5 multiplied by 5, the image filling operation is adopted to keep the image size unchanged, and then a largest pooling layer with the size of 3 multiplied by 3 is adopted, and the step length is 2; then, the third convolution layer, the fourth convolution layer and the fifth convolution layer are three tightly connected identical convolution layers with the size of 3×3, and the image filling operation is adopted to keep the image size unchanged; next to a maximum pooling layer of size 3 x 3, the step size is 2; then a fully connected layer with 9216 dimension output is followed by two identical fully connected layers with 4096 dimension output, and then the output layer is followed by the fully connected layers; the output layer adopts a Softmax function as an excitation function, and the rest network layers adopt a Relu function as an excitation function;
(3-4) initializing a convolutional neural network model, namely initializing by utilizing an Msra algorithm, wherein when only the input number is considered, the Msra initialization is a Gaussian distribution with the mean value of 0 and the variance of 2/n;
(3-5) training a convolutional neural network model;
(3-6) classifying the salted duck eggs through a trained convolutional neural network model; classifying normally shot pictures containing salted duck eggs into a normal type or a reverse type; classifying pictures of the non-salted duck eggs which are shot by mistake into irrelevant types;
(4) And the control system controls the third conveying mechanism to convey the salted duck eggs after detection to the corresponding collecting mechanism according to the classification result of the convolutional neural network model.
8. The method of claim 7, wherein in step (3-5), the step of training a convolutional neural network model is:
(3-51), inputting a characteristic variable;
(3-52) carrying out logic calculation on each item of data in the characteristic variables, and adding a normalization term in the calculation;
(3-53) calculating the output of each neuron of each layer, and randomly discarding the output of a part of neurons in the first two layers of all-connected layers by adopting a Dropout method;
(3-54) calculating a logistic regression cost function;
(3-55) calculating a proper weight matrix and a proper bias vector value by using a gradient descent method, so as to minimize a cost function of logistic regression;
(3-56), repeating the steps (3-53) - (3-55) until the prediction accuracy meets the requirement;
(3-57), result analysis and output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010037406.2A CN111136027B (en) | 2020-01-14 | 2020-01-14 | Salted duck egg quality sorting device and method based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010037406.2A CN111136027B (en) | 2020-01-14 | 2020-01-14 | Salted duck egg quality sorting device and method based on convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111136027A CN111136027A (en) | 2020-05-12 |
| CN111136027B true CN111136027B (en) | 2024-04-12 |
Family
ID=70524905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010037406.2A Active CN111136027B (en) | 2020-01-14 | 2020-01-14 | Salted duck egg quality sorting device and method based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111136027B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111790639B (en) * | 2020-05-22 | 2021-12-10 | 北京正大蛋业有限公司 | Poultry egg transportation is with assembly line turnover case letter sorting system |
| CN112136722A (en) * | 2020-08-28 | 2020-12-29 | 江苏理工学院 | Egg sorting system and egg sorting method |
| CN112317338A (en) * | 2020-10-15 | 2021-02-05 | 兰州大学 | Piston ring detection system |
| CN113945560A (en) * | 2021-10-15 | 2022-01-18 | 高邮市双欣蛋品有限公司 | Salted duck egg processing is with automatic light inspection device |
| CN114342838B (en) * | 2022-01-08 | 2022-12-09 | 河北农业大学 | Egg dark spot detection and automatic grading system based on deep learning or image recognition |
| CN114544772B (en) * | 2022-04-26 | 2022-08-05 | 华南农业大学 | Device and method for detecting duck egg cracks based on convolutional neural network and voice frequency spectrum |
| CN114532253B (en) * | 2022-04-26 | 2022-07-22 | 华南农业大学 | Automatic intelligent detection device for hatching egg activity |
| CN117546800B (en) * | 2023-11-17 | 2024-07-12 | 江苏省家禽科学研究所 | Internet of things intelligent detection and distinguishing device and method for black eggs and common eggs |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101419213A (en) * | 2008-12-08 | 2009-04-29 | 浙江大学 | Bird egg crack detection device and method by utilizing volatile matter |
| CN101419212A (en) * | 2008-12-08 | 2009-04-29 | 浙江大学 | Bird egg freshness detection device and method by utilizing volatile matter |
| CN102179374A (en) * | 2010-12-23 | 2011-09-14 | 华中农业大学 | Automatic detecting and sorting device for poultry egg quality and method thereof |
| CN106778902A (en) * | 2017-01-03 | 2017-05-31 | 河北工业大学 | Milk cow individual discrimination method based on depth convolutional neural networks |
| 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 |
| CN108446729A (en) * | 2018-03-13 | 2018-08-24 | 天津工业大学 | Egg embryo classification method based on convolutional neural networks |
| CN108663367A (en) * | 2018-03-30 | 2018-10-16 | 中国农业大学 | A kind of egg quality lossless detection method based on egg unit weight |
| CN108700528A (en) * | 2016-02-17 | 2018-10-23 | 股份公司南备尔 | The surface examining device of egg |
| CN109937912A (en) * | 2019-04-08 | 2019-06-28 | 武汉科技大学 | A kind of egg categorizing system and method based on machine vision |
| 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 |
| CN110455806A (en) * | 2018-05-07 | 2019-11-15 | 南京农业大学 | A kind of egg dynamic image acquisition equipment |
| CN211756981U (en) * | 2020-01-14 | 2020-10-27 | 广东技术师范大学 | Salted duck egg quality sorting device based on convolutional neural network |
-
2020
- 2020-01-14 CN CN202010037406.2A patent/CN111136027B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101419213A (en) * | 2008-12-08 | 2009-04-29 | 浙江大学 | Bird egg crack detection device and method by utilizing volatile matter |
| CN101419212A (en) * | 2008-12-08 | 2009-04-29 | 浙江大学 | Bird egg freshness detection device and method by utilizing volatile matter |
| CN102179374A (en) * | 2010-12-23 | 2011-09-14 | 华中农业大学 | Automatic detecting and sorting device for poultry egg quality and method thereof |
| CN108700528A (en) * | 2016-02-17 | 2018-10-23 | 股份公司南备尔 | The surface examining device of egg |
| CN106778902A (en) * | 2017-01-03 | 2017-05-31 | 河北工业大学 | Milk cow individual discrimination method based on depth convolutional neural networks |
| 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 |
| CN108446729A (en) * | 2018-03-13 | 2018-08-24 | 天津工业大学 | Egg embryo classification method based on convolutional neural networks |
| CN108663367A (en) * | 2018-03-30 | 2018-10-16 | 中国农业大学 | A kind of egg quality lossless detection method based on egg unit weight |
| CN110455806A (en) * | 2018-05-07 | 2019-11-15 | 南京农业大学 | A kind of egg dynamic image acquisition equipment |
| CN109937912A (en) * | 2019-04-08 | 2019-06-28 | 武汉科技大学 | A kind of egg categorizing system and method based on machine vision |
| 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 |
| CN211756981U (en) * | 2020-01-14 | 2020-10-27 | 广东技术师范大学 | Salted duck egg quality sorting device based on convolutional neural network |
Non-Patent Citations (1)
| Title |
|---|
| 雷伏元.《规则形体物品的包装计量》.天津科学技术出版社,1986,(第1版),第96页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111136027A (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111136027B (en) | Salted duck egg quality sorting device and method based on convolutional neural network | |
| CN106238342B (en) | Panoramic vision potato sorts and defect detecting device and its sorting detection method | |
| CN102217559B (en) | On-line automatic detection and sorting equipment and method for incubated egg quality | |
| JP7186304B2 (en) | Defect inspection device | |
| CN112452801A (en) | High-efficiency online detection device for defects of glass bottles and working method thereof | |
| Ozdemir et al. | A quality control application on a smart factory prototype using deep learning methods | |
| CN102539443B (en) | Bottle body defect automatic detection method based on machine vision | |
| CN102179374B (en) | Automatic detecting and sorting device for poultry egg quality and method thereof | |
| CN106290382A (en) | Bubble-cap tablet package defective vision detection device and method | |
| CN111862028B (en) | Wood defect detecting and sorting device and method based on depth camera and depth learning | |
| CN206139527U (en) | Panoramic vision potato is selected separately and defect detecting device | |
| CN110694921B (en) | Vegetable sorting system and control method thereof | |
| CN104614375B (en) | Nondestructive testing system for multi-layer food wrappage | |
| CN106370667A (en) | Visual detection apparatus and method for quality of corn kernel | |
| TWI700129B (en) | Moving object classification system and method using self-learning technology | |
| CN113145492A (en) | Visual grading method and grading production line for pear appearance quality | |
| CN202133655U (en) | Online automatic detecting sorting equipment for quality of incubated eggs | |
| CN204346935U (en) | The location of food multi-packaging thing nondestructive detection system and dust guard | |
| CN112950602B (en) | Candy defect detection device and classification method based on depth camera and machine learning | |
| CN103234974A (en) | Lithium battery non-destructive detection method | |
| CN211756981U (en) | Salted duck egg quality sorting device based on convolutional neural network | |
| CN113077450A (en) | Cherry grading detection method and system based on deep convolutional neural network | |
| CN117546800B (en) | Internet of things intelligent detection and distinguishing device and method for black eggs and common eggs | |
| CN204448621U (en) | The location of food multi-packaging thing nondestructive detection system and device for eliminating | |
| CN114677597B (en) | Gear defect visual inspection method and system based on improved YOLOv5 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 |