CN106442525A - Online detecting method for wizened defects of insides of walnuts - Google Patents
Online detecting method for wizened defects of insides of walnuts Download PDFInfo
- Publication number
- CN106442525A CN106442525A CN201610753560.3A CN201610753560A CN106442525A CN 106442525 A CN106442525 A CN 106442525A CN 201610753560 A CN201610753560 A CN 201610753560A CN 106442525 A CN106442525 A CN 106442525A
- Authority
- CN
- China
- Prior art keywords
- walnut
- weight
- image
- relative error
- shrivelled
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an online detecting method for wizened defects of insides of walnuts. The online detecting method comprises the following steps: acquiring an image of a walnut under a dynamic condition by using an industrial CCD camera, carrying out binarization processing on the image to obtain a projection area of the walnut, and meanwhile acquiring weight information of the walnut under the dynamic condition by using a weighing sensor and a digital acceleration sensor; carrying out regression analysis on the projection area and the weight of the walnut to obtain a walnut weight prediction model, and calculating by using the walnut weight prediction model to obtain predicted weight of the walnut, and calculating relative error between the predicted weight of the walnut and the real weight of the walnut, judging whether the detected walnut is a wizened walnut or not by using the relative error as a judgment threshold value, and breaking the hull to verify judgment accuracy; carrying out regression analysis on different judgment threshold values and judgment accuracies corresponding to the judgment threshold values; and finally, searching a fitting function between the judgment threshold values and the judgment accuracies by using a golden section method, finding out the optimal judgment threshold value, if the relative error of the weight of the detected walnut is greater than the threshold value, determining that the walnut is the wizened walnut, and if the relative error of the weight of the detected walnut is smaller than or equal to the threshold value, determining that the walnut is an abnormal walnut. Nondestructive detection of wizened walnuts can be realized by the projection area of the images of the walnuts and the weight information of the walnuts only, and the method is simple. Compared with the prior art, the online detecting method has the advantages that detecting cost is greatly reduced, detecting speed and accuracy are improved, and the online detecting method is suitable for factory large-scale production, and can be used for online detection of wizened defects of the insides of various nuts such as the walnuts.
Description
Technical field
The present invention relates to nut inside quality detection method, particularly relate to a kind of online for the shrivelled defect in walnut inside
Detection method.
Background technology
The shrivelled defect of walnut is a kind of quality problems that on market, complete walnut is common, and it has had a strong impact on commodity walnut
Quality and selling price.Under natural conditions, walnut is mainly the reason that produce shrivelled defect:Walnut growing environment condition limits, as
Soil nutrient is low and lack of moisture;Pest and disease damage etc. in walnut growth course.So, the shrivelled defect of walnut is inevitably universal
It is present on market in the complete walnut commodity sold.Meanwhile, the shrivelled defect of walnut is different from other defect, and it belongs to interior component
Geological Problems, shrivelled walnut is difficult to differentiate between in appearance with normal walnut.Under the conditions of naturally observing, both outward appearances are basically identical, and
By after its broken shell it appeared that there are serious quality problems inside shrivelled walnut.Based on above reason, the present invention proposes power
The shrivelled walnut online test method that sensing merges with visual information, merely with digital image information and the weight information thereof of walnut
Just the online Fast nondestructive evaluation of shrivelled walnut can be realized.
At present, the research for walnut Inner Defect Testing is less, the defect inspection that great majority are both under static conditions
Survey research, the domestic relevant report that yet there are no about walnut internal flaw on-line checking.Yellow star is grand etc. utilizes grenz ray to obtain core
Ghost, damaged and normal walnut are differentiated by peach image, and test accuracy rate is higher, but the method exists radiation to operating personnel
Danger, and food safety risk is unknown;Jensen etc. utilize near-infrared spectrum technique to carry out the acetaldehyde of walnut kernel partially
Least square regression is analyzed, r2=0.72;The application tera-hertz spectra technology for detection hickory nut insect pest of the desk studies such as Li Bin
Feasibility, research has found that higher moisture and the strong absorption to moisture isopolarity molecule for the tera-hertz spectra of live body insect
Characteristic, by finding with hickory nut section contrast, live body insect pest presents obviously spectral absorption characteristics, equal with normal walnut
There are differences.Although near-infrared spectrum technique and terahertz light spectral technology are to moisture-sensitive, walnut internal moisture, work can be detected
Body insect etc., but shrivelled few with ghost iso-metamorphism thin skin walnut internal moisture, therefore utilize near-infrared spectrum technique and terahertz light
Shrivelled and ghost iso-metamorphism thin skin walnut cannot effectively be detected by spectral technology.And above technical equipment is relatively costly,
Information data amount is big, and poor real is difficult to meet the requirement of online production mostly.
Content of the invention
It is an object of the invention to provide a kind of with low cost, the degree of accuracy is higher, quick nondestructive shrivelled for walnut inside
The online test method of defect.
It is an object of the invention to be achieved through the following technical solutions:
The step of the method is as follows:Obtain the image under walnut dynamic condition and weight information, binaryzation is carried out to image
After segmentation and Morphological scale-space go background to obtain walnut projected area, the projected area and weight of walnut is carried out regression analysis and obtain
To optimum walnut quality prediction model, gone out the quality of walnut by this model prediction, and calculate itself and walnut real quality
Whether relative error, utilizes golden section optimizing algorithm to find out optimal discrimination threshold afterwards, be shrivelled in this, as differentiation walnut
The discrimination threshold of walnut, it is judged that whether institute's test sample is shrivelled walnut.
1) the walnut dynamic image described in:With black synchronization conveyer belt as background, utilize camera external trigger acquisition mode
Weight information synchronous acquisition with walnut;
2) collection of the walnut weight information described in:Utilize digital acceleromete by cantilever type weighing sensor
Collection walnut weight signal under dynamic condition carries out digital filtering, thus obtains more accurate walnut weight information.
3) the walnut image binaryzation segmentation described in and Morphological scale-space go background:Extract the R component of walnut RGB image,
Carry out background segment with 50/255 for segmentation threshold, utilize medium filtering and continuous opening operation to remove noise afterwards, obtain the back of the body
The walnut image of scape.
4) described walnut projected area:Gather the image of coin under the same conditions, obtain through identical processing method
It goes the image of background to calculate the standard area of single pixel, adds up pixel shared by walnut in the walnut image go background
Point number, is calculated the projected area of walnut.
5) described walnut quality relative error:With gained walnut projected area as independent variable, with record under dynamic condition
Walnut weight is that dependent variable carries out regression analysis and be there is linear relationship between the two, and as the prediction of walnut weight
Model calculates predicted value, and the absolute value of walnut weight predicted value and the difference of test value has just obtained walnut divided by test value
Weight relative error.
6) described golden section optimizing algorithm seeks optimal threshold:With the weight relative error of institute's test sample as independent variable,
With each relative error for differentiation accuracy rate during threshold value as dependent variable, carry out regression analysis and obtain and there is Pulse letter between the two
Number relation, this function is unimodal function, utilizes the maximum that Fibonacci method is calculated in independent variable interval, now corresponding
The value of independent variable be optimal threshold.
7) described shrivelled walnut method of discrimination:And calculate through Digital Image Processing with the walnut image under the conditions of online
To walnut projected area, predict walnut weight with projected area, and obtain with walnut test weight computing that walnut weight is relative to be missed
Difference, compares with gained optimal threshold, if relative error is more than threshold value, differentiates and which is shrivelled walnut, otherwise is then normal walnut.
Compared with prior art, the present invention is according to the material characteristic of walnut itself, melts with visual information based on power sensing
The method closed achieves the on-line checking of the shrivelled defect of walnut, with low cost, quickly effectively, is suitable for industrialized production.This
Bright accurate and effective, economical and practical, strong adaptability, is a kind of method that can well realize walnut shrivelled defect on-line checking.
What the present invention had has the advantages that:
The present invention just can realize the online nothing of shrivelled walnut merely with the digital image information of walnut and walnut weight information
Damaging detection, method is simple, compared to existing technology, greatly reduces testing cost, improves detection speed and accuracy rate, suitable
Produce together in plant layout metaplasia.The present invention can be used for the on-line checking of the shrivelled defect in inside of all kinds of nuts such as walnut.
Brief description
Fig. 1 is the internal shrivelled defect online detection method flowchart of walnut of the present invention.
Fig. 2 is assembly of the invention structural representation.
Fig. 3 for through image procossing obtain go background after walnut image and shared pixel number.
Fig. 4 is the fit correlation curve between walnut projected area and walnut weight.
Fig. 5 is the matched curve relation between the differentiation accuracy rate under each threshold value and discrimination threshold.
In diagram:1 is industrial CCD camera;2 is synchronization conveyer belt;3 is direct current generator;4 is digital acceleration sensing
Device;5 is pad;6 is base;7 is LOAD CELLS;8 is support;9 is walnut sample;10 is light source.
Detailed description of the invention
Embodiment:Fig. 1 show the internal shrivelled defect online detection method flowchart of walnut.First, by walnut sample
Originally it is positioned on described synchronization conveyer belt 2, industrial CCD camera 1 is obtained image clearly, and binary conversion treatment is carried out to it obtain
To its projected area, it is dynamic that the mode simultaneously utilizing LOAD CELLS 5 to combine with digital acceleromete 6 obtains walnut
Under the conditions of weight information;The projected area to walnut and weight is utilized to carry out the walnut weight prediction that regression analysis obtains afterwards
Model calculates the pre-measured weight of walnut, and calculates the relative error between itself and walnut real quality, with relative error
Judge whether detected walnut is shrivelled walnut by discrimination threshold, and broken shell checking differentiates accuracy rate;Afterwards difference is differentiated
Threshold value and its corresponding differentiation accuracy rate carry out regression analysis;Finally utilize Fibonacci method search discrimination threshold and differentiate accurately
Fitting function between rate finds out optimal discrimination threshold, if the weight relative error of detected walnut is more than this threshold value, differentiates
It for shrivelled walnut, if the weight relative error of detected walnut is less than or equal to this threshold value, is determined as normal walnut.
Claims (2)
1. the online test method for the internal shrivelled defect of walnut, it is characterised in that:The step of the method is as follows:Obtain
Image under walnut dynamic condition and weight information, carry out binarization segmentation to image and Morphological scale-space goes background to obtain walnut
After projected area, the walnut quality prediction model that regression analysis obtains optimum is carried out to the projected area and weight of walnut, passes through
This model prediction goes out the quality of walnut, and calculates the relative error of itself and walnut real quality, utilizes golden section optimizing afterwards
Algorithm finds out optimal discrimination threshold, in this, as the discrimination threshold differentiating that whether walnut is shrivelled walnut, it is judged that institute's test sample
It whether is shrivelled walnut.
2. a kind of online test method for the shrivelled defect in walnut inside according to claim 1, it is characterised in that:
1) image under walnut dynamic condition described in:With black synchronization conveyer belt as background, utilize camera external trigger collection
Mode and the weight information synchronous acquisition of walnut;
2) collection of the weight information under walnut dynamic condition described in:Digital acceleromete is utilized to claim beam type
Collection walnut weight signal under weight sensor dynamic condition carries out digital filtering, thus obtains more accurate walnut weight letter
Breath.
3) binarization segmentation of the walnut image described in and Morphological scale-space go background:Extract the R component of walnut RGB image, with
50/255 carries out background segment for segmentation threshold, utilizes medium filtering and continuous opening operation to remove noise afterwards, obtains background
Walnut image.
4) described walnut projected area:Gather the image of coin under the same conditions, obtain it through identical processing method
The image of background calculates the standard area of single pixel, adds up pixel shared by walnut in the walnut image go background
Number, is calculated the projected area of walnut.
5) relative error of described walnut quality:With gained walnut projected area as independent variable, with the core recording under dynamic condition
Peach weight is that dependent variable carries out regression analysis and be there is linear relationship between the two, and predicts mould as walnut weight
Type calculates predicted value, and the absolute value of walnut weight predicted value and the difference of test value has just obtained walnut weight divided by test value
Amount relative error.
6) described golden section optimizing algorithm finds out optimal discrimination threshold:Become with the weight relative error of institute's test sample for oneself
Amount, with each relative error for differentiation accuracy rate during threshold value as dependent variable, carries out regression analysis and obtains and there is Pulse between the two
Functional relation, this function is unimodal function, utilize Fibonacci method be calculated independent variable interval in maximum, now right
The value of the independent variable answered is optimal threshold.
7) shrivelled walnut utilizes the method for discrimination of optimal threshold:With the walnut image under the conditions of online through Digital Image Processing simultaneously
It is calculated walnut projected area, predict walnut weight with projected area, and obtain walnut weight with walnut test weight computing
Relative error, compares with gained optimal threshold, if relative error is more than threshold value, differentiates and which is shrivelled walnut, otherwise be then normal
Walnut.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610753560.3A CN106442525B (en) | 2016-08-30 | 2016-08-30 | Online detection method for walnut internal shriveling defect |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610753560.3A CN106442525B (en) | 2016-08-30 | 2016-08-30 | Online detection method for walnut internal shriveling defect |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106442525A true CN106442525A (en) | 2017-02-22 |
CN106442525B CN106442525B (en) | 2021-09-14 |
Family
ID=58090683
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610753560.3A Active CN106442525B (en) | 2016-08-30 | 2016-08-30 | Online detection method for walnut internal shriveling defect |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106442525B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108311402A (en) * | 2018-02-06 | 2018-07-24 | 石河子大学 | Shrivelled walnut multi-channel detection and sorting unit |
CN109102034A (en) * | 2018-09-04 | 2018-12-28 | 刘勇峰 | Text plays the accurate matching method and computer storage medium of walnut |
CN109297963A (en) * | 2018-10-12 | 2019-02-01 | 湖南农业大学 | Soil image acquisition equipment, soil water-containing amount detection systems and detection method |
CN109622407A (en) * | 2018-11-30 | 2019-04-16 | 中北大学 | Walnut non-destructive detecting device and method based on image recognition |
CN110030927A (en) * | 2019-03-27 | 2019-07-19 | 中北大学 | Walnut detection device |
CN112819746A (en) * | 2019-10-31 | 2021-05-18 | 合肥美亚光电技术股份有限公司 | Nut kernel worm-eating defect detection method and device |
CN112819745A (en) * | 2019-10-31 | 2021-05-18 | 合肥美亚光电技术股份有限公司 | Nut kernel center worm-eating defect detection method and device |
CN113655020A (en) * | 2021-08-12 | 2021-11-16 | 河南工业大学 | Method for detecting empty-shell walnuts |
CN115193704A (en) * | 2022-07-06 | 2022-10-18 | 北京林业大学 | Appearance defect walnut detects and sorting facilities |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202591136U (en) * | 2012-05-15 | 2012-12-12 | 塔里木大学 | Automatic walnut sorting machine based on relative specific weight |
CN104438133A (en) * | 2014-12-17 | 2015-03-25 | 杭州郝姆斯食品有限公司 | Walnut sorting machine and walnut sorting method |
-
2016
- 2016-08-30 CN CN201610753560.3A patent/CN106442525B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN202591136U (en) * | 2012-05-15 | 2012-12-12 | 塔里木大学 | Automatic walnut sorting machine based on relative specific weight |
CN104438133A (en) * | 2014-12-17 | 2015-03-25 | 杭州郝姆斯食品有限公司 | Walnut sorting machine and walnut sorting method |
Non-Patent Citations (2)
Title |
---|
王科权等: "核桃分选机的研究现状", 《农机化研究》 * |
薛忠等: "基于机器视觉的澳洲坚果分级研究", 《农机化研究》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108311402B (en) * | 2018-02-06 | 2023-10-24 | 石河子大学 | Multi-channel detecting and sorting device for shrunken walnuts |
CN108311402A (en) * | 2018-02-06 | 2018-07-24 | 石河子大学 | Shrivelled walnut multi-channel detection and sorting unit |
CN109102034B (en) * | 2018-09-04 | 2021-12-21 | 刘勇峰 | Precise pairing method of Chinese and playing walnuts and computer storage medium |
CN109102034A (en) * | 2018-09-04 | 2018-12-28 | 刘勇峰 | Text plays the accurate matching method and computer storage medium of walnut |
CN109297963A (en) * | 2018-10-12 | 2019-02-01 | 湖南农业大学 | Soil image acquisition equipment, soil water-containing amount detection systems and detection method |
CN109622407A (en) * | 2018-11-30 | 2019-04-16 | 中北大学 | Walnut non-destructive detecting device and method based on image recognition |
CN110030927A (en) * | 2019-03-27 | 2019-07-19 | 中北大学 | Walnut detection device |
CN112819745A (en) * | 2019-10-31 | 2021-05-18 | 合肥美亚光电技术股份有限公司 | Nut kernel center worm-eating defect detection method and device |
CN112819745B (en) * | 2019-10-31 | 2023-02-28 | 合肥美亚光电技术股份有限公司 | Nut kernel center worm-eating defect detection method and device |
CN112819746A (en) * | 2019-10-31 | 2021-05-18 | 合肥美亚光电技术股份有限公司 | Nut kernel worm-eating defect detection method and device |
CN112819746B (en) * | 2019-10-31 | 2024-04-23 | 合肥美亚光电技术股份有限公司 | Nut kernel worm erosion defect detection method and device |
CN113655020A (en) * | 2021-08-12 | 2021-11-16 | 河南工业大学 | Method for detecting empty-shell walnuts |
CN113655020B (en) * | 2021-08-12 | 2024-05-24 | 河南工业大学 | Method for detecting empty walnut |
CN115193704A (en) * | 2022-07-06 | 2022-10-18 | 北京林业大学 | Appearance defect walnut detects and sorting facilities |
CN115193704B (en) * | 2022-07-06 | 2023-07-14 | 北京林业大学 | Appearance defect walnut detects and sorting facilities |
Also Published As
Publication number | Publication date |
---|---|
CN106442525B (en) | 2021-09-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106442525A (en) | Online detecting method for wizened defects of insides of walnuts | |
CN101144780B (en) | Pork freshness intelligent detection device | |
CN101832941B (en) | Fruit quality evaluation device based on multispectral image | |
Sun et al. | On-line detection of eggshell crack based on acoustic resonance analysis | |
CN109886298A (en) | A kind of detection method for quality of welding line based on convolutional neural networks | |
Pan et al. | Eggshell crack detection based on computer vision and acoustic response by means of back-propagation artificial neural network | |
CN1995987A (en) | Non-destructive detection method and device for agricultural and animal products based on hyperspectral image technology | |
CN102928435A (en) | Aircraft skin damage identification method and device based on image and ultrasound information fusion | |
CN101949686A (en) | Online nondestructive testing (NDT) method and device for comprehensive internal/external qualities of fruits | |
CN101059424A (en) | Multiple spectrum meat freshness artificial intelligence measurement method and system | |
CN103439342A (en) | Infrared nondestructive testing method based on thermal image time sequence characteristics | |
Sharma et al. | Grain quality detection by using image processing for public distribution | |
Wang et al. | A multimodal machine vision system for quality inspection of onions | |
CN201392319Y (en) | Meat online lossless detecting device based on the combination of images and spectrum information | |
CN105092579A (en) | Mango quality non-destructive testing device | |
Gnanavel et al. | Quality detection of fresh fruits and vegetables to improve horticulture and agro-industries | |
CN104297206A (en) | Quick liquid milk brand identifying method | |
CN203658250U (en) | Online honeydew melon internal quality detection device capable of combining diffuse transmission spectrum and image information | |
CN105956591B (en) | A kind of online hot parts infrared image spectrum sampling Detection method | |
CN108152231A (en) | Jujube fruit Inner Defect Testing method and device based on Vis/NIR | |
CN111753877A (en) | Product quality detection method based on deep neural network transfer learning | |
CN104833724A (en) | Poultry eggshell crack detection method and device | |
CN204613160U (en) | A kind of bird egg crack detection device | |
CN114354508A (en) | Wisdom agricultural plant support system | |
CN109622407B (en) | Image recognition-based walnut nondestructive testing equipment and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |