CN109191461A - A kind of Countryside Egg recognition methods and identification device based on machine vision technique - Google Patents
A kind of Countryside Egg recognition methods and identification device based on machine vision technique Download PDFInfo
- Publication number
- CN109191461A CN109191461A CN201811231267.6A CN201811231267A CN109191461A CN 109191461 A CN109191461 A CN 109191461A CN 201811231267 A CN201811231267 A CN 201811231267A CN 109191461 A CN109191461 A CN 109191461A
- Authority
- CN
- China
- Prior art keywords
- egg
- measured
- countryside
- impurity level
- information entropy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
Abstract
The Countryside Egg recognition methods and identification device that the present invention provides a kind of based on machine vision technique, it takes pictures first to egg to be measured, and the egg shape index, gray value information entropy, eggshell surface impurity level of egg to be measured are calculated according to photo, then the egg shape index of egg to be measured, gray value information entropy, eggshell surface impurity level are gradually compared with benchmark index range, reference information entropy, benchmark impurity level respectively, to identify judge whether it is Countryside Egg to egg to be measured.The egg shape index, gray value information entropy, eggshell surface impurity level of egg to be measured are obtained by machine vision technique, it is compared with a reference value again, it can rapidly identify Countryside Egg, greatly reduce manual identified cost, due to being compared using the multiple characteristics of egg to be measured, the purpose that can more effectively realize identification, makes to identify more acurrate.
Description
Technical field
The present invention relates to the technical field of agricultural product production more particularly to a kind of Countryside Egg knowledges based on machine vision technique
Other method and identification device.
Background technique
China is egg production and big export country and the lavish consumer of egg.As the most common food on people's dining table
One of product, egg play important role with its quality-high and inexpensive characteristic in people's daily life.Compared to stable breeding chicken
Produced egg, the Countryside Egg of chicken output have a relatively better quality, its is pollution-free with nationality for Countryside Egg, is rich in vitamin, mouth
The feature felt and be deeply loved by the public.Just occur some the phenomenon that pretending to be Countryside Egg to sell with stable breeding egg in the market, and
The mode that Countryside Egg is judged by artificial experience is usual identification method, when egg number is more, the mode of manual identified
Will there is a problem of low efficiency, at high cost.
However, automatic identification technology is gradually applied to agricultural production row with the development of computer and image processing techniques
In industry field.In the prior art, egg automatic identification equipment mainly identifies Countryside Egg according to the dimensional parameters of egg to be measured,
Although this mode can effectively solve manual identified Countryside Egg and bring low efficiency, problem at high cost, still, above-mentioned knowledge
Other mode is only applicable to the biggish Countryside Egg of size difference and stable breeding egg, when the size difference between two kinds of eggs is smaller, just
It is possible that the case where judging in vain, so that stable breeding egg and Countryside Egg can be obscured because of misrecognition, once the batch
Egg come into the market, the equity of agricultural production quotient and consumer will be damaged.
Therefore, a kind of Countryside Egg recognition methods that can overcome the above problem how is found, it has also become those skilled in the art
Important subject.
Summary of the invention
The technical problem to be solved in the present invention is that in view of the deficiencies of the prior art, providing a kind of based on machine vision skill
The Countryside Egg recognition methods of art and identification device, it is inaccurate because there is identification to solve existing Countryside Egg identification method, and
Connect the problem of causing the equity of agricultural production quotient and consumer to be damaged.
To achieve the above object, the present invention provides technical solution below:
A kind of Countryside Egg recognition methods based on machine vision technique, comprising:
Shoot the photo of egg to be measured;
Egg shape index, the gray value information entropy, eggshell of the egg to be measured are calculated according to the photo of the egg to be measured
Surface impurity amount;
The egg shape index of the egg to be measured is compared with benchmark index range;
If the egg shape index of the egg to be measured belongs within the scope of the benchmark index, by the gray scale of the egg to be measured
Value information entropy is compared with reference information entropy, if the gray value information entropy of the egg to be measured is greater than reference information entropy, judgement
The egg to be measured is Countryside Egg;
If the gray value information entropy of the egg to be measured is less than or equal to the reference information entropy, by the egg to be measured
Eggshell surface impurity level is compared with benchmark impurity level, if the eggshell surface impurity level of the egg to be measured is greater than the benchmark
Impurity level judges the egg to be measured for Countryside Egg;If the eggshell surface impurity level of the egg to be measured is less than or equal to described
Benchmark impurity level judges the egg to be measured for stable breeding egg.
Optionally, the photo according to the egg to be measured calculates egg shape index, the gray value of the egg to be measured
Comentropy, eggshell surface impurity level, specifically:
The photo of the egg to be measured is subjected to gray processing processing;
The egg shape index of the egg to be measured, gray value letter are calculated according to the photo of the egg to be measured after gray processing
Cease entropy, eggshell surface impurity level.
Optionally, the benchmark index range, the method for determination of reference information entropy, benchmark impurity level, specifically:
Shoot the photo of Countryside Egg and stable breeding egg;
The photo of the Countryside Egg and stable breeding egg is subjected to gray processing processing;
According to the photo of the Countryside Egg after gray processing, egg shape index, the gray value information of the Countryside Egg are calculated
Entropy, eggshell surface impurity level;
According to the photo of the stable breeding egg after gray processing, the egg shape index for leading to the stable breeding egg, gray scale are calculated
Value information entropy, eggshell surface impurity level;
According to the egg shape index of the egg shape index of the Countryside Egg and the stable breeding egg, calculated by machine learning algorithm
The benchmark index range out;
According to the gray value information entropy of the gray value information entropy of the Countryside Egg and the stable breeding egg, pass through machine learning
Algorithm calculates the reference information entropy;
According to the eggshell surface impurity level of the eggshell surface impurity level of the Countryside Egg and the stable breeding egg, pass through machine
Learning algorithm calculates the benchmark impurity level.
Optionally, the egg shape index is obtained especially by following manner:
According to the diameter and height of the photo acquisition egg after gray processing;
According to the diameter and height, the ratio between diameter and height is calculated, using the ratio as the egg type
Index.
Optionally, the gray value information entropy is obtained especially by following manner:
According to the gray value in several regions of photo acquisition egg surface after gray processing;
The gray value information entropy is calculated according to the gray value in several regions.
Optionally, the eggshell surface impurity level is obtained especially by following manner:
According to the gray scale difference value in the photo after gray processing between eggshell and impurity, the eggshell surface impurity is calculated
Amount.
The present invention also accordingly discloses a kind of Countryside Egg identification device based on machine vision technique, comprising:
Photographing module, for shooting the photo of egg to be measured;
First computing module, for calculated according to the photo of the egg to be measured the egg to be measured egg shape index,
Gray value information entropy, eggshell surface impurity level;
First comparison module, for the egg shape index of the egg to be measured to be compared with benchmark index range;
Second comparison module, if within the scope of the egg shape index for the egg to be measured belongs to the benchmark index, it will
The gray value information entropy of the egg to be measured is compared with reference information entropy, if the gray value information entropy of the egg to be measured is big
In reference information entropy, judge the egg to be measured for Countryside Egg;
Third comparison module, if the gray value information entropy for the egg to be measured is less than or equal to the reference information
The eggshell surface impurity level of the egg to be measured is compared by entropy with benchmark impurity level, if the eggshell table of the egg to be measured
Face impurity level is greater than the benchmark impurity level, judges the egg to be measured for Countryside Egg;If the eggshell surface of the egg to be measured
Impurity level is less than or equal to the benchmark impurity level, judges the egg to be measured for stable breeding egg.
Optionally, further includes:
Image processing module, for the photo of the egg to be measured to be carried out gray processing processing;
Second computing module, for calculating the egg to be measured according to the photo of the egg to be measured after gray processing
Egg shape index, gray value information entropy, eggshell surface impurity level.
Optionally, further includes:
Third computing module calculates the egg of the Countryside Egg for the photo according to the Countryside Egg after gray processing
Shape index, gray value information entropy, eggshell surface impurity level;According to the photo of the stable breeding egg after gray processing, calculate logical
Egg shape index, gray value information entropy, the eggshell surface impurity level of the stable breeding egg;
Study module, for passing through machine according to the egg shape index of the Countryside Egg and the egg shape index of the stable breeding egg
Device learning algorithm calculates the benchmark index range;According to the gray value information entropy of the Countryside Egg and the stable breeding egg
Gray value information entropy calculates the reference information entropy by machine learning algorithm;Eggshell surface according to the Countryside Egg is miscellaneous
The eggshell surface impurity level of quality and the stable breeding egg calculates the benchmark impurity level by machine learning algorithm.
Compared with prior art, the invention has the following advantages:
The Countryside Egg recognition methods and identification device that the present invention provides a kind of based on machine vision technique, first to be measured
Egg is taken pictures, and the egg shape index, gray value information entropy, eggshell surface impurity level of egg to be measured are calculated according to photo,
Then by the egg shape index of egg to be measured, gray value information entropy, eggshell surface impurity level respectively gradually with benchmark index range, base
Calibration information entropy, benchmark impurity level are compared, to identify judge whether it is Countryside Egg to egg to be measured.Pass through machine
Device vision technique obtains the egg shape index of egg to be measured, gray value information entropy, eggshell surface impurity level, then by itself and a reference value into
Row compares, and can rapidly identify Countryside Egg, greatly reduce manual identified cost, due to being carried out using the multiple characteristics of egg to be measured
Compare, can more effectively realize the purpose of identification, make to identify more acurrate.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of flow chart of the Countryside Egg recognition methods based on machine vision technique provided in this embodiment;
Fig. 2 is the flow chart of another Countryside Egg recognition methods based on machine vision technique provided in this embodiment;
Fig. 3 is the flow chart of another Countryside Egg recognition methods based on machine vision technique provided in this embodiment;
Fig. 4 is a kind of structural schematic diagram of the Countryside Egg identification device based on machine vision technique provided in this embodiment.
Specific embodiment
To enable the purpose of the present invention, feature, advantage more obvious and understandable, implement below in conjunction with the present invention
Attached drawing in example, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that reality disclosed below
Applying example is only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field is common
Technical staff's all other embodiment obtained without making creative work belongs to the model that the present invention protects
It encloses.
In the description of the present invention, it is to be understood that, when a component is considered as " connection " another component, it can
To be directly to another component or may be simultaneously present the component being centrally located.When a component is considered as " setting
Set " another component, it, which can be, is set up directly on another component or may be simultaneously present the component being centrally located.
In addition, the indicating positions such as term " length " " short " "inner" "outside" or positional relationship for the orientation that is shown based on attached drawing or
Person's positional relationship is merely for convenience of the description present invention, rather than the device or original part of indication or suggestion meaning must have this
Specific orientation is operated with specific orientation construction, should not be understood as limitation of the invention with this.
To further illustrate the technical scheme of the present invention below with reference to the accompanying drawings and specific embodiments.
As shown in Figure 1, present embodiments providing a kind of Countryside Egg recognition methods based on machine vision technique, comprising:
Step S101, the photo of egg to be measured is shot;
Step S102, the egg shape index of the egg to be measured is calculated according to the photo of the egg to be measured, gray value is believed
Cease entropy, eggshell surface impurity level;
Step S103, the egg shape index of the egg to be measured is compared with benchmark index range, is judged described to be measured
Whether the egg shape index of egg belongs within the scope of the benchmark index;
If the egg shape index of the egg to be measured belongs within the scope of the benchmark index, S104 is thened follow the steps;
Step S104, the gray value information entropy of the egg to be measured is compared with reference information entropy, judgement it is described to
Whether the gray value information entropy for surveying egg is greater than reference information entropy;
If the gray value information entropy of the egg to be measured is greater than reference information entropy, S105 is thened follow the steps;
Step S105, judge the egg to be measured for Countryside Egg;
If the gray value information entropy of the egg to be measured is less than or equal to reference information entropy, S106 is thened follow the steps;
Step S106, the eggshell surface impurity level of the egg to be measured is compared with benchmark impurity level, described in judgement
Whether the eggshell surface impurity level of egg to be measured is greater than the benchmark impurity level;
If the eggshell surface impurity level of the egg to be measured is greater than the benchmark impurity level, S105 is thened follow the steps, is judged
The egg to be measured is Countryside Egg;
If the eggshell surface impurity level of the egg to be measured is less than or equal to the benchmark impurity level, then follow the steps
S107;
Step S107, judge the egg to be measured for stable breeding egg.
It should be noted that egg shape index be the diameter and altitude conversion according to egg and come, that reflects eggs
Features of shape.Since stable breeding chicken nutrition intake amount is relatively fixed, and the production cycle is shorter, and oviposition period is more regular, so, circle
The poultry produced egg of egg, diameter and height are relatively fixed, opposite, and Countryside Egg is raw due to the unfixed influence of nutrition intake
The factors such as the period is longer, and oviposition period is irregular are produced, leading to the ratio between Countryside Egg diameter and height will not be a fixation
Value, so utilizing this features of shape of egg shape index, so that it may carry out preliminary screening to egg;
In order to make the eggshell surface of stable breeding egg seem uniform color beauty, band is also usually added in stable breeding egg feed
There is the additive of pigment, just because of the food that chicken and stable breeding chicken are taken in is different, Countryside Egg has with stable breeding egg output factor
Biggish difference, leading to the gray value information entropy of the two, there is also difference, and the reflection of gray value information entropy is that egg surface is more
The uncertainty degree of a area grayscale value, gray value information entropy is bigger, the uncertainty degree of egg surface multiple regions gray value
It is bigger, it more can certainly be Countryside Egg;Based on this thought, by the gray value information entropy of egg to be measured and reference information entropy into
Row comparison, that is, can reach further identifying purpose;
In addition, there is also differences for chicken and the environment of laying eggs of stable breeding chicken, and since the environment of laying eggs of stable breeding chicken is more clean and tidy, institute
It is equivalent to Countryside Egg meeting much less with the impurity level on the surface of stable breeding egg, therefore carries out last screening with such characteristic,
It more effectively can to egg identify.
As it can be seen that a kind of Countryside Egg recognition methods based on machine vision technique provided by the invention, first to egg to be measured
It takes pictures, and calculates the egg shape index, gray value information entropy, eggshell surface impurity level of egg to be measured according to photo, then
The egg shape index of egg to be measured, gray value information entropy, eggshell surface impurity level are gradually believed with benchmark index range, benchmark respectively
Breath entropy, benchmark impurity level are compared, to identify judge whether it is Countryside Egg to egg to be measured.It is regarded by machine
Feel technology obtains the features such as egg shape index of egg to be measured, then it is compared with a reference value, can rapidly identify Countryside Egg,
Manual identified cost is greatly reduced, due to being compared using the multiple characteristics of egg to be measured, can more effectively realize identification
Purpose makes to identify more acurrate.
As shown in Fig. 2, in actual operation, a kind of Countryside Egg knowledge based on machine vision technique provided in this embodiment
In other method, the photo according to the egg to be measured calculate the egg shape index of the egg to be measured, gray value information entropy,
Eggshell surface impurity level, specifically:
S201, the photo of the egg to be measured is subjected to gray processing processing;
It is understood that can reduce the color intervention factor of machine recognition after being handled by gray processing, provide subsequent knowledge
Other accuracy;
S202, egg shape index, the ash that the egg to be measured is calculated according to the photo of the egg to be measured after gray processing
Angle value comentropy, eggshell surface impurity level;
Specifically, after step S103, if the egg shape index of the egg to be measured be not belonging to the benchmark index range it
It is interior, S105 is thened follow the steps, that is, can determine whether that the egg to be measured is Countryside Egg;
It is understood that the features of shape using egg to be measured quickly identifies egg, and then improve identification
Efficiency.
In actual operation, it is passed through under type such as and obtains the picture of egg or Countryside Egg or stable breeding egg to be measured: will be more
A Countryside Egg is put into Package Testing box, and Package Testing box can arrange 10 × 10 egg holes, and the diameter in hole may be provided at the left side 3cm
The right side, width about 2.5cm, and Package Testing box are larger so that machine distinguishes egg and test bag mounted box with egg color difference;By egg
It ajusts and shoots egg picture with camera after marshalling, the camera pixel that machine vision technique uses can be 2592 × 1944
More than, the height of camera and egg is consistent when shooting every time.
Further, in a kind of Countryside Egg recognition methods based on machine vision technique provided in this embodiment, the base
The method of determination of quasi- index range, reference information entropy, benchmark impurity level, specifically:
Shoot the photo of multiple Countryside Eggs and stable breeding egg;
The photo of the Countryside Egg and stable breeding egg is subjected to gray processing processing;
According to the photo of the Countryside Egg after gray processing, egg shape index, the gray value information of the Countryside Egg are calculated
Entropy, eggshell surface impurity level;
According to the photo of the stable breeding egg after gray processing, the egg shape index for leading to the stable breeding egg, gray scale are calculated
Value information entropy, eggshell surface impurity level;
According to the egg shape index of the egg shape index of the Countryside Egg and the stable breeding egg, calculated by machine learning algorithm
The benchmark index range out;
According to the gray value information entropy of the gray value information entropy of the Countryside Egg and the stable breeding egg, pass through machine learning
Algorithm calculates the reference information entropy;
According to the eggshell surface impurity level of the eggshell surface impurity level of the Countryside Egg and the stable breeding egg, pass through machine
Learning algorithm calculates the benchmark impurity level.
Specifically, according to the egg shape index of the Countryside Egg of above-mentioned acquisition and stable breeding egg, gray value information entropy, eggshell surface
Correlation machine learning algorithm is arranged in impurity level, in conjunction with the egg shape index of the egg shape index range computation statistics stable breeding egg of Countryside Egg
Range is used as benchmark index range after being modified automatically to the egg shape index range by the algorithm of machine deep learning;
Similar, the threshold value for distinguishing stable breeding egg and Countryside Egg gray value information entropy is calculated by the algorithm of deep learning as benchmark letter
Cease entropy;Similar, the threshold value work for distinguishing stable breeding egg and Countryside Egg eggshell impurity level is calculated by the algorithm of machine deep learning
For benchmark impurity level;
It is understood that obtaining the egg shape index of Countryside Egg and stable breeding egg using the picture of gray processing, gray value is believed
Entropy, eggshell surface impurity level are ceased, calculates benchmark index range, benchmark with machine learning algorithm further according to these egg characteristics
Comentropy, benchmark impurity level can further ensure the accuracy of identification, mitigate the workload of manual identified.
As shown in figure 3, further, this method is applicable to large batch of egg identification, when the chicken to be measured of a batch
After egg has identified completely, further includes:
After judging the egg to be measured for Countryside Egg, S301 is executed;
S301, the Countryside Egg in egg to be measured is marked;
S302, the label according to Countryside Egg, calculate the ratio of Countryside Egg in egg to be measured.
It is understood that can be identified to large batch of egg to be measured using aforesaid way, and will wherein Countryside Egg
Classification marker is carried out with stable breeding egg, calculates the ratio of Countryside Egg, effectively mitigates the workload manually counted, improves work effect
Rate.
In this present embodiment, further, the egg shape index is obtained especially by following manner:
According to the diameter and height of the photo acquisition egg after gray processing;
According to the diameter and height, the ratio between diameter and height is calculated, using the ratio as the egg type
Index.
Specifically, with the egg each ajusted on program Automatic-searching picture most four, upper and lower, left and right point and exporting four
The coordinate of a point.By picture gray processing, binary conversion treatment is then carried out, at this time the area of all whites in each egg picture centre
Domain is the region where egg, and the value of egg region coordinate points is 1 after binaryzation, black portions coordinate points outside egg
Value be 0.Rectangular coordinate system is established as origin using the point in the picture most upper left corner on picture after treatment, one available [m,
N] 0-1 matrix, detection egg contour edge leftmost when, design value of the program from the first coordinate points column in upper left
Start from top to down plus, continue if value is not greater than 0 by same sequence plus the coordinate value of next column, when value is greater than 0 with regard to defeated
Coordinate (the D of the point outs1,Hs1), this point is the coordinate of egg contour edge Far Left point, and identical, egg contour edge is most
Right point and most upper and lower point can obtain its coordinate (Ds2,Hs2),(Dl1,Hl1),(Dl2,Hl2), it is straight that each egg can be calculated by coordinate
The length of diameter and height, utilizes formula:Calculate separately its diameter and height
Spend D, H;
According to the diameter and height, the ratio between diameter and height is calculated using formula R=D/H, by the ratio
Value R is as the egg shape index.
Further, the gray value information entropy is obtained especially by following manner:
According to the gray value in several regions of photo acquisition egg surface after gray processing;
The gray value information entropy is calculated according to the gray value in several regions.
Specifically, extract the gray value of each stable breeding egg and Countryside Egg, to obtained gray value by same step-length into
Row grouping, gray value each in this way are assigned in each group, calculate the probability P (x of each group of gray value appearancei), utilize public affairs
FormulaCalculate its gray value information entropy.
Further, the eggshell surface impurity level is obtained especially by following manner:
According to the gray scale difference value in the photo after gray processing between eggshell and impurity, the eggshell surface impurity is calculated
Amount.
Specifically, program is arranged according to gray scale difference value and calculates gray threshold K for eggshell with major part by after egg gray processing
Impurity separates, and the gray value that will be greater than the threshold value is stored in the one-dimensional matrix of [1, m], then each egg can use 1 × m table
Show its impurity level.
In conjunction with the mode of Machine Vision Recognition Technology, egg or Countryside Egg or stable breeding egg to be measured can be rapidly and accurately obtained
Egg shape index, gray value information entropy, eggshell surface impurity level, provide effective data for subsequent identification step and support,
Ground connection improves identification accuracy.
Correspondingly, the present invention also provides a kind of Countryside Egg identification device based on machine vision technique, as shown in figure 4,
Include:
Photographing module 11, for shooting the photo of egg to be measured;
First computing module 21, the egg type for calculating the egg to be measured according to the photo of the egg to be measured refer to
Number, gray value information entropy, eggshell surface impurity level;
First comparison module 31, for the egg shape index of the egg to be measured to be compared with benchmark index range;
Second comparison module 32, if within the scope of the egg shape index for the egg to be measured belongs to the benchmark index,
The gray value information entropy of the egg to be measured is compared with reference information entropy, if the gray value information entropy of the egg to be measured
Greater than reference information entropy, judge the egg to be measured for Countryside Egg;
Third comparison module 33, if the gray value information entropy for the egg to be measured is less than or equal to the reference information
The eggshell surface impurity level of the egg to be measured is compared by entropy with benchmark impurity level, if the eggshell table of the egg to be measured
Face impurity level is greater than the benchmark impurity level, judges the egg to be measured for Countryside Egg;If the eggshell surface of the egg to be measured
Impurity level is less than or equal to the benchmark impurity level, judges the egg to be measured for stable breeding egg.
In this present embodiment, Countryside Egg identification device provided by the invention, further includes:
Image processing module 12, for the photo of the egg to be measured to be carried out gray processing processing;
Second computing module 22, for calculating the egg to be measured according to the photo of the egg to be measured after gray processing
Egg shape index, gray value information entropy, eggshell surface impurity level.
In this present embodiment, Countryside Egg identification device provided by the invention, further includes:
Third computing module 23 calculates the Countryside Egg for the photo according to the Countryside Egg after gray processing
Egg shape index, gray value information entropy, eggshell surface impurity level;According to the photo of the stable breeding egg after gray processing, calculate
Lead to the egg shape index, gray value information entropy, eggshell surface impurity level of the stable breeding egg;
Study module 40, for passing through according to the egg shape index of the Countryside Egg and the egg shape index of the stable breeding egg
Machine learning algorithm calculates the benchmark index range;According to the gray value information entropy of the Countryside Egg and the stable breeding egg
Gray value information entropy, the reference information entropy is calculated by machine learning algorithm;According to the eggshell surface of the Countryside Egg
The eggshell surface impurity level of impurity level and the stable breeding egg calculates the benchmark impurity level by machine learning algorithm.
It is understood that the specific workflow of above-mentioned modules can be identified with reference to Countryside Egg provided by the invention
Method is no longer repeated herein.A kind of Countryside Egg identification device based on machine vision technique provided by the invention, it is right first
Egg to be measured is taken pictures, and the egg shape index, gray value information entropy, eggshell surface impurity of egg to be measured are calculated according to photo
Amount, then by the egg shape index of egg to be measured, gray value information entropy, eggshell surface impurity level respectively gradually with benchmark index model
Enclose, reference information entropy, benchmark impurity level are compared, to identify judge whether it is Countryside Egg to egg to be measured.It is logical
The features such as machine vision technique obtains the egg shape index of egg to be measured is crossed, then it is compared with a reference value, can rapidly be known
Other Countryside Egg, greatly reduces manual identified cost, can be more effectively real due to being compared using the multiple characteristics of egg to be measured
The purpose now identified makes to identify more acurrate.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although referring to before
Stating embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features;And these
It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (9)
1. a kind of Countryside Egg recognition methods based on machine vision technique characterized by comprising
Shoot the photo of egg to be measured;
Egg shape index, the gray value information entropy, eggshell surface of the egg to be measured are calculated according to the photo of the egg to be measured
Impurity level;
The egg shape index of the egg to be measured is compared with benchmark index range;
If the egg shape index of the egg to be measured belongs within the scope of the benchmark index, the gray value of the egg to be measured is believed
Breath entropy is compared with reference information entropy, if the gray value information entropy of the egg to be measured greater than reference information entropy, described in judgement
Egg to be measured is Countryside Egg;
If the gray value information entropy of the egg to be measured is less than or equal to the reference information entropy, by the eggshell of the egg to be measured
Surface impurity amount is compared with benchmark impurity level, if the eggshell surface impurity level of the egg to be measured is greater than the benchmark impurity
Amount, judges the egg to be measured for Countryside Egg;If the eggshell surface impurity level of the egg to be measured is less than or equal to the benchmark
Impurity level judges the egg to be measured for stable breeding egg.
2. Countryside Egg recognition methods according to claim 1, which is characterized in that the photo according to the egg to be measured
The egg shape index, gray value information entropy, eggshell surface impurity level of the egg to be measured are calculated, specifically:
The photo of the egg to be measured is subjected to gray processing processing;
Egg shape index, the gray value information of the egg to be measured are calculated according to the photo of the egg to be measured after gray processing
Entropy, eggshell surface impurity level.
3. Countryside Egg recognition methods according to claim 1, which is characterized in that the benchmark index range, reference information
The method of determination of entropy, benchmark impurity level, specifically:
Shoot the photo of Countryside Egg and stable breeding egg;
The photo of the Countryside Egg and stable breeding egg is subjected to gray processing processing;
According to the photo of the Countryside Egg after gray processing, egg shape index, the gray value information entropy, egg of the Countryside Egg are calculated
Shell surface impurity amount;
According to the photo of the stable breeding egg after gray processing, the egg shape index for leading to the stable breeding egg, gray value letter are calculated
Cease entropy, eggshell surface impurity level;
According to the egg shape index of the egg shape index of the Countryside Egg and the stable breeding egg, institute is calculated by machine learning algorithm
State benchmark index range;
According to the gray value information entropy of the gray value information entropy of the Countryside Egg and the stable breeding egg, pass through machine learning algorithm
Calculate the reference information entropy;
According to the eggshell surface impurity level of the eggshell surface impurity level of the Countryside Egg and the stable breeding egg, pass through machine learning
Algorithm calculates the benchmark impurity level.
4. Countryside Egg recognition methods according to claim 2 or 3, which is characterized in that the egg shape index especially by with
Under type obtains:
According to the diameter and height of the photo acquisition egg after gray processing;
According to the diameter and height, the ratio between diameter and height is calculated, using the ratio as the egg shape index.
5. Countryside Egg recognition methods according to claim 2 or 3, which is characterized in that the gray value information entropy specifically leads to
Cross following manner acquisition:
According to the gray value in several regions of photo acquisition egg surface after gray processing;
The gray value information entropy is calculated according to the gray value in several regions.
6. Countryside Egg recognition methods according to claim 2 or 3, which is characterized in that the eggshell surface impurity level is specific
It obtains in the following manner:
According to the gray scale difference value in the photo after gray processing between eggshell and impurity, the eggshell surface impurity level is calculated.
7. a kind of Countryside Egg identification device based on machine vision technique characterized by comprising
Photographing module, for shooting the photo of egg to be measured;
First computing module, for calculating egg shape index, the gray scale of the egg to be measured according to the photo of the egg to be measured
Value information entropy, eggshell surface impurity level;
First comparison module, for the egg shape index of the egg to be measured to be compared with benchmark index range;
Second comparison module, if within the scope of the egg shape index for the egg to be measured belongs to the benchmark index, it will be described
The gray value information entropy of egg to be measured is compared with reference information entropy, if the gray value information entropy of the egg to be measured is greater than base
Calibration information entropy judges the egg to be measured for Countryside Egg;
Third comparison module will if the gray value information entropy for the egg to be measured is less than or equal to the reference information entropy
The eggshell surface impurity level of the egg to be measured is compared with benchmark impurity level, if the eggshell surface impurity of the egg to be measured
Amount is greater than the benchmark impurity level, judges the egg to be measured for Countryside Egg;If the eggshell surface impurity level of the egg to be measured
Less than or equal to the benchmark impurity level, judge the egg to be measured for stable breeding egg.
8. Countryside Egg identification device according to claim 7, which is characterized in that further include:
Image processing module, for the photo of the egg to be measured to be carried out gray processing processing;
Second computing module, for calculating the egg type of the egg to be measured according to the photo of the egg to be measured after gray processing
Index, gray value information entropy, eggshell surface impurity level.
9. Countryside Egg recognition methods according to claim 8, which is characterized in that further include:
Third computing module, for the photo according to the Countryside Egg after gray processing, the egg type for calculating the Countryside Egg refers to
Number, gray value information entropy, eggshell surface impurity level;According to the photo of the stable breeding egg after gray processing, calculate logical described
Egg shape index, gray value information entropy, the eggshell surface impurity level of stable breeding egg;
Study module, for passing through engineering according to the egg shape index of the Countryside Egg and the egg shape index of the stable breeding egg
It practises algorithm and calculates the benchmark index range;According to the gray scale of the gray value information entropy of the Countryside Egg and the stable breeding egg
Value information entropy calculates the reference information entropy by machine learning algorithm;According to the eggshell surface impurity level of the Countryside Egg
With the eggshell surface impurity level of the stable breeding egg, the benchmark impurity level is calculated by machine learning algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811231267.6A CN109191461A (en) | 2018-10-22 | 2018-10-22 | A kind of Countryside Egg recognition methods and identification device based on machine vision technique |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811231267.6A CN109191461A (en) | 2018-10-22 | 2018-10-22 | A kind of Countryside Egg recognition methods and identification device based on machine vision technique |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109191461A true CN109191461A (en) | 2019-01-11 |
Family
ID=64942497
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811231267.6A Pending CN109191461A (en) | 2018-10-22 | 2018-10-22 | A kind of Countryside Egg recognition methods and identification device based on machine vision technique |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109191461A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109916901A (en) * | 2019-02-26 | 2019-06-21 | 中国农业科学院农产品加工研究所 | The method for quick identification of calm and peaceful black-bone chicken egg and hybridization black-bone chicken egg |
CN110929755A (en) * | 2019-10-21 | 2020-03-27 | 北京海益同展信息科技有限公司 | Poultry egg detection method, device and system, electronic equipment and storage medium |
CN113793328A (en) * | 2021-09-23 | 2021-12-14 | 中国农业大学 | Light-weight egg shape recognition method based on SE-ResNet structure |
CN114897784A (en) * | 2022-04-13 | 2022-08-12 | 广东工业大学 | Monocular egg size assembly line measuring method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1804620A (en) * | 2005-12-30 | 2006-07-19 | 南京农业大学 | Method and apparatus for detecting surface quality of egg |
CN106954563A (en) * | 2017-04-24 | 2017-07-18 | 广东工业大学 | A kind of recognition methods of native birds, beasts and eggs and its identifying device |
CN108647675A (en) * | 2018-05-10 | 2018-10-12 | 众安信息技术服务有限公司 | A kind of egg type discrimination method and device |
-
2018
- 2018-10-22 CN CN201811231267.6A patent/CN109191461A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1804620A (en) * | 2005-12-30 | 2006-07-19 | 南京农业大学 | Method and apparatus for detecting surface quality of egg |
CN106954563A (en) * | 2017-04-24 | 2017-07-18 | 广东工业大学 | A kind of recognition methods of native birds, beasts and eggs and its identifying device |
CN108647675A (en) * | 2018-05-10 | 2018-10-12 | 众安信息技术服务有限公司 | A kind of egg type discrimination method and device |
Non-Patent Citations (1)
Title |
---|
陆拾,江灼华,张瑛编: "《假冒伪劣视频识别》", 31 December 1992 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109916901A (en) * | 2019-02-26 | 2019-06-21 | 中国农业科学院农产品加工研究所 | The method for quick identification of calm and peaceful black-bone chicken egg and hybridization black-bone chicken egg |
CN109916901B (en) * | 2019-02-26 | 2021-07-20 | 中国农业科学院农产品加工研究所 | Rapid identification method for Taihe black-bone chicken eggs and hybrid black-bone chicken eggs |
CN110929755A (en) * | 2019-10-21 | 2020-03-27 | 北京海益同展信息科技有限公司 | Poultry egg detection method, device and system, electronic equipment and storage medium |
CN113793328A (en) * | 2021-09-23 | 2021-12-14 | 中国农业大学 | Light-weight egg shape recognition method based on SE-ResNet structure |
CN114897784A (en) * | 2022-04-13 | 2022-08-12 | 广东工业大学 | Monocular egg size assembly line measuring method |
CN114897784B (en) * | 2022-04-13 | 2023-02-21 | 广东工业大学 | Monocular egg size assembly line measuring method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109191461A (en) | A kind of Countryside Egg recognition methods and identification device based on machine vision technique | |
Ward et al. | Deep leaf segmentation using synthetic data | |
Aquino et al. | vitisBerry: An Android-smartphone application to early evaluate the number of grapevine berries by means of image analysis | |
CN107657639A (en) | A kind of method and apparatus of quickly positioning target | |
CN107844797A (en) | A kind of method of the milking sow posture automatic identification based on depth image | |
CN107871316B (en) | Automatic X-ray film hand bone interest area extraction method based on deep neural network | |
CN108491788A (en) | A kind of intelligent extract method and device for financial statement cell | |
TW200307810A (en) | Method and apparatus for determining the sex of a fertilized egg | |
CN105205437B (en) | Side face detection method and device based on contouring head verifying | |
CN105651776A (en) | Device and method for automatically grading beef carcass meat yield based on computer vision | |
CN105825168B (en) | A kind of Rhinopithecus roxellana face detection and method for tracing based on S-TLD | |
CN102704215A (en) | Automatic cutting method of embroidery cloth based on combination of DST file parsing and machine vision | |
CN103852034B (en) | A kind of method for measuring perendicular | |
CN109636779A (en) | Identify the method, apparatus and storage medium of poultry volume ruler | |
CN108133471A (en) | Agriculture Mobile Robot guidance path extracting method and device based on artificial bee colony algorithm under the conditions of a kind of natural lighting | |
CN112288793B (en) | Method and device for detecting backfat of livestock individuals, electronic equipment and storage medium | |
CN110503638A (en) | Spiral colloid amount online test method | |
CN103729621B (en) | Plant leaf image automatic recognition method based on leaf skeleton model | |
CN108629762A (en) | A kind of stone age evaluation and test model reduces the image pre-processing method and system of interference characteristic | |
CN111145205B (en) | Pig body temperature detection method based on infrared image under multiple pig scenes | |
CN113222889B (en) | Industrial aquaculture counting method and device for aquaculture under high-resolution image | |
CN110348344A (en) | A method of the special facial expression recognition based on two and three dimensions fusion | |
CN111369497B (en) | Walking type tree fruit continuous counting method and device | |
CN117456358A (en) | Method for detecting plant diseases and insect pests based on YOLOv5 neural network | |
CN116740758A (en) | Bird image recognition method and system for preventing misjudgment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |
|
RJ01 | Rejection of invention patent application after publication |