KR101750858B1 - System and method for detecting defect - Google Patents
System and method for detecting defect Download PDFInfo
- Publication number
- KR101750858B1 KR101750858B1 KR1020150155721A KR20150155721A KR101750858B1 KR 101750858 B1 KR101750858 B1 KR 101750858B1 KR 1020150155721 A KR1020150155721 A KR 1020150155721A KR 20150155721 A KR20150155721 A KR 20150155721A KR 101750858 B1 KR101750858 B1 KR 101750858B1
- Authority
- KR
- South Korea
- Prior art keywords
- defect
- fruit
- external
- image
- type
- Prior art date
Links
- 230000007547 defect Effects 0.000 title claims abstract description 228
- 238000000034 method Methods 0.000 title claims description 19
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 97
- 238000001514 detection method Methods 0.000 claims abstract description 51
- 238000005096 rolling process Methods 0.000 claims abstract description 32
- 238000012546 transfer Methods 0.000 claims abstract description 16
- 238000005259 measurement Methods 0.000 claims abstract description 11
- 238000002604 ultrasonography Methods 0.000 claims abstract description 8
- 238000003384 imaging method Methods 0.000 claims abstract 2
- 238000010219 correlation analysis Methods 0.000 claims description 15
- 230000002950 deficient Effects 0.000 claims description 14
- 238000001228 spectrum Methods 0.000 claims description 14
- 238000000540 analysis of variance Methods 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 9
- 239000006185 dispersion Substances 0.000 claims description 7
- 238000012285 ultrasound imaging Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 5
- 238000004497 NIR spectroscopy Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 241000220225 Malus Species 0.000 description 16
- 235000021016 apples Nutrition 0.000 description 11
- 208000034656 Contusions Diseases 0.000 description 7
- 208000034526 bruise Diseases 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 206010039509 Scab Diseases 0.000 description 4
- 238000004040 coloring Methods 0.000 description 4
- 238000005336 cracking Methods 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 206010052428 Wound Diseases 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012864 cross contamination Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002845 discoloration Methods 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
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
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G13/00—Roller-ways
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/52—Devices for transferring articles or materials between conveyors i.e. discharging or feeding devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/74—Feeding, transfer, or discharging devices of particular kinds or types
-
- 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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- 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
- G01N33/025—Fruits or vegetables
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2201/00—Indexing codes relating to handling devices, e.g. conveyors, characterised by the type of product or load being conveyed or handled
- B65G2201/02—Articles
- B65G2201/0202—Agricultural and processed food products
- B65G2201/0211—Fruits and vegetables
Abstract
The present invention relates to a defect detection method for a fruit defect detection system, and a defect detection system according to one aspect of the present invention is a defect detection system for a fruit, comprising: a roller type transfer device for transferring and feeding inserted fruit; An external defect detection part for detecting an external defect of the fruit through the measurement of the entire surface, a transfer part for transferring the fruit transferred while being rotated by the rolling device to the selection cup, and the internal defect and quality of the fruit placed in the selection cup And an internal quality measuring unit for measuring the quality. The external defect detector detects an external defect using an ultrasound image, a non-image, and a differential image for the optimum wavelength for each defect type. Thus, by applying a rolling device and ultrasonic imaging technology to scan the entire surface of the fruit, it is possible to improve the reliability of defect detection on fruits and agricultural productivity.
Description
The present invention relates to a defect detection system and a defect detection method, and more particularly, to a defect detection system and a defect detection method for detecting defects generated inside or outside a fruit such as an apple.
The screening of defects with defects in fruit surface such as apples is discriminated by the operator one by one and the worker is overloaded. Since the defect is detected by subjective judgment of the worker, the reliability and detection There is a problem of poor accuracy. Accordingly, there is a high demand for an automation system capable of detecting defects in fruit such as apples in which defects are generated.
In addition, when defective fruit that is not found by the worker is circulated, cross contamination affects the quality of other normal fruits, and when the product is delivered to the consumer, the complaint about the product may increase, Technology development is needed.
Conventionally, in place of a visual inspection, there is a case where a defect on one side of a fruit is detected by using a machine vision such as a general color camera or a CCD camera. However, in the case of a defect on a side It is required to develop a defect detection technique which can detect the defect.
SUMMARY OF THE INVENTION Accordingly, the present invention has been made keeping in mind the above problems occurring in the prior art, and it is an object of the present invention to provide a method and apparatus for detecting fruit defects by measuring an entire surface through an ultrasound imaging camera while rotating fruit through a rolling device, And a defect detection method capable of improving the defect detection method and the defect detection method.
A defect detection system according to one aspect of the present invention is a defect detection system comprising: a roller-type rolling device for rotating and feeding an inserted fruit; an external device for detecting an external defect of the fruit through measurement of the entire surface of the fruit rotated by the rolling device A transfer unit for transferring the fruit transferred while being rotated by the rolling apparatus to the sorting cup, and an internal quality measuring unit for measuring internal defects and quality of fruits placed in the sorting cup.
The external defect detection unit includes a visible and near-infrared (VNIR) ultrasound imaging camera for photographing a surface of a fruit rotated by the rolling apparatus.
The external defect detector may detect an external defect of a fruit using a reflection spectrum obtained through the measurement of the VNIR ultrasonic spectroscopic image camera and an ultrasonic image in a specific wavelength band.
Wherein the external defect detector selects an optimal wavelength for at least one defect type using reflection spectrum data for a normal portion and a defective portion of the fruit sample extracted for each binding type, An external defect can be detected using at least one of a difference image for a plurality of the single wavelength images and a non-image for a plurality of the single wavelength images.
Wherein the external defect detection unit selects an optimal wavelength for each defect type through at least one of analysis of variance and correlation analysis using reflection spectrum data for a normal part and a defective part of a fruit sample extracted for each defect type as input variables .
The internal quality measuring unit includes a near-infrared spectroscopic sensor.
According to an aspect of the present invention, there is provided a defect detection method comprising the steps of: detecting an external defect of a fruit by measuring the entire surface of the fruit with a VNIR ultrasonic spectroscopic image camera for a fruit being transported while being rotated through a roller type rolling device; Transferring the fruit being transferred while being rotated by the rolling apparatus to the sorting cup after the detection of the defect, and measuring the internal defect and quality of the fruit using the near-infrared spectroscopy sensor for the fruit seated in the sorting cup .
The step of detecting an external defect of the fruit may include the steps of: selecting an optimal wavelength for at least one defect type using reflection spectrum data for a normal part and a defective part of the fruit sample extracted for each defect type; Detecting an external defect using at least one of a single wavelength image for an optimal wavelength, a difference image for a plurality of the single wavelength images, and a non-image for a plurality of the single wavelength images. have.
The selecting of the optimal wavelength for each defect type may include analyzing at least one of variance analysis and correlation analysis using reflection spectrum data for a normal part and a defective part of a fruit sample extracted for each defect type as input variables, The optimum wavelength for each defect type can be selected.
The detecting of the external defect may detect an external defect by converting the single wavelength image into a binarized image reconstructed based on a specific threshold value.
The optimum wavelength for the defect types may be selected to be 710 nm for heat and defect, 715 nm for diseased defect, 561 nm for poor coloring, 720 nm for wound defect, and 940 nm for bony defect.
Wherein the step of detecting the external defect comprises the steps of: selecting the optimum wavelength for each of the two or more defect types through the dispersion analysis and the correlation analysis; and selecting at least one of a difference image and a non-image for the optimal wavelengths Can be converted into a binarized image reconstructed on the basis of a specific threshold value to detect an external defect.
The optimal wavelengths for the defect types are 792 nm and 806 nm for heat and defect, 720 nm and 964 nm for diseased defect, 403 nm and 528 nm for discolored defect, 739 nm and 998 nm for wound defect, and 749 nm and 753 nm for bony defect have.
According to the defect detection system and the defect detection method of the present invention, the entire surface is measured through the VNIR ultra-spectral image camera while rotating the fruit through the rolling apparatus, and a single wavelength image for the optimum wavelength selected for each defect type, The non-image and the differential image of the fruit are used to detect the external defect of the fruit, thereby improving the reliability of the defect detection and the agricultural productivity.
1 is a block diagram illustrating a defect detection system according to an embodiment of the present invention.
2 is a flowchart illustrating an external defect detection method using an external defect detection algorithm according to an embodiment of the present invention.
FIG. 3 is a graph showing the results of analysis of variance for defect types in the VNIR wavelength band for apples. FIG.
FIG. 4 is a graph showing the correlation analysis results of the types of defects in the VNIR wavelength band for apples. FIG.
5 is a diagram showing a binarized image obtained by binarizing a single wavelength image with respect to an optimal wavelength for each defect type.
FIG. 6 is a graph showing the result of analysis of variance according to defect types in the VNIR wavelength band for apples. FIG.
7 is a diagram showing a binary image obtained by binarizing non-images for each defect type.
The present invention is capable of various modifications and various forms, and specific embodiments are illustrated in the drawings and described in detail in the text. It should be understood, however, that the invention is not intended to be limited to the particular forms disclosed, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.
The terms first, second, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprising" or "having ", and the like, are intended to specify the presence of stated features, integers, steps, operations, elements, parts, or combinations thereof, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, parts, or combinations thereof.
Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the meaning in the context of the relevant art and are to be interpreted as ideal or overly formal in meaning unless explicitly defined in the present application Do not.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Reference will now be made in detail to preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings.
1 is a block diagram illustrating a defect detection system according to an embodiment of the present invention.
Referring to FIG. 1, a defect detection system according to an embodiment of the present invention includes a
The
The
The external
The external
The
The internal
In the defect detection method using the defect detection system having the above-described configuration, the fruit surface is measured by the VNIR
Meanwhile, the
2 is a flowchart illustrating an external defect detection method using an external defect detection algorithm according to an embodiment of the present invention.
Referring to FIG. 2, in order to detect external defects of fruit, at least one optimum wavelength for each defect type is selected by using reflection spectrum data for a normal portion and a defective portion of a fruit sample extracted for each defect type (S100) .
Specifically, external defects of fruits such as apples are classified into types such as cracking, scab, cuts, coloring disorder, and bruise. Therefore, a plurality of Extract the fruit samples.
Thereafter, the fruit samples extracted for each defect type are measured through the VNIR ultrasonic
Thereafter, at least one defect (s) is analyzed through at least one of analysis of variance (ANOVA) and correlation analysis (CR) using the reflection spectrum data for the normal part and the defective part of the fruit sample as input variables, Select the optimum wavelength for each type. Here, the ANOVA is a general statistical analysis technique for comparing the average of two or more groups, and the correlation analysis (CR) is a general statistical analysis technique for analyzing the closeness or correlation between variables. It will be omitted.
FIG. 3 is a graph showing the results of analysis of variance for defect types in the VNIR wavelength band for apples. FIG.
Referring to FIG. 3, it is possible to select the wavelength having the largest F-value for each type of defect from the result of the variance analysis for the defect type in the normal region and the defective region of the apple in the VNIR wavelength band.
The optimal wavelength for the type of defect for the apple is 710 nm for cracking defects, 715 nm for scab defects, 561 nm for coloring disorder, and cuts defects 720nm for bruise defect, and 940nm for bruise defect.
FIG. 4 is a graph showing the correlation analysis results of the types of defects in the VNIR wavelength band for apples. FIG.
Referring to FIG. 4, a wavelength with the largest R-value for each defect type can be selected as the optimum wavelength from the result of correlation analysis for the defect type and the normal part of the apple in the VNIR wavelength band. The result of the correlation analysis shown in FIG. 4 is the same as the result of the analysis of variance shown in FIG.
After selecting the optimum wavelength for each defect type by the above-described method, a single wavelength image for the optimal wavelength for each selected defect type is extracted (S200). That is, in a state in which the optimum wavelength for each defect type is stored, the fruit to be actually examined is measured by the
Thereafter, the single-wavelength image is converted into a binary image reconstructed based on a specific threshold value, and external defects are detected through the binary image (S400). The threshold value may be set to a predetermined value obtained through a number of experiments and may be set to the same value or different value for each defect type. In addition, the binarized image is an image obtained by binarizing the single wavelength image to 0 and 1 based on the threshold value. The defect is detected by considering the size, shape, and the like of the defect part through the binarized image.
5 is a diagram showing a binarized image obtained by binarizing a single wavelength image with respect to an optimal wavelength for each defect type.
Referring to FIG. 5, a single wavelength image extracted by applying an optimal wavelength for each defect type is binarized, and as a result, a defect detection rate of 100% for defects such as cracking, color disorder, and cuts , Scab defects were detected in 86.7%, and Bruise defects were detected in 6.7%.
By detecting external defects of fruits through one single wavelength image corresponding to the optimum wavelength for each defect type, defects can be detected quickly and the detection system can be simplified.
Meanwhile, in order to further improve the accuracy of defect detection through a single wavelength image, a method using a difference image and a non-image can be applied.
For this purpose, in the process of selecting the optimal wavelength for each defect type, an optimal wavelength for each of two or more defect types is selected through analysis of variance and correlation, and a non-image and a difference image for the optimum wavelength according to two or more types of defect types (S300).
FIG. 6 is a graph showing the result of analysis of variance according to defect types in the VNIR wavelength band for apples. FIG.
Referring to FIG. 6, the result of the variance analysis for the defect type and the normal part of the apple in the VNIR wavelength band is shown as a contour shape, and as the wavelength of the dispersion coefficient (F) Wavelengths that are expressed in color and less relevant are expressed in blue. Thus, two optimum wavelengths can be selected from the point where the dispersion coefficient (F) is the largest for each defect type.
As shown in Fig. 6, the optimal wavelengths of the two types of defects selected by the analysis of variance against apples were 792 nm and 806 nm in the case of heat and defect, 720 nm and 964 nm in case of diseased defect, 403 nm and 528 nm in case of poor coloring, 739nm and 998nm for defects, and 749nm and 753nm for bony defects.
After selecting two optimal wavelengths for each type of defect by the above method, non-image and difference images of the single wavelength images are calculated using single wavelength images for the optimal wavelength for each of the selected two defect types (S300). Here, the non-image means an image obtained by dividing data values of two ultrasound spectral images corresponding to two optimal wavelengths, and the difference image includes two ultrasound spectra corresponding to the two optimum wavelengths Means an image obtained by subtracting data values of an image from each other.
Thereafter, the non-image or difference image is converted into a binary image reconstructed on the basis of a specific threshold value, and an external defect is detected through the binary image (S400). The threshold value may be set to a predetermined value obtained through a number of experiments and may be set to the same value or different value for each defect type and may be set to the same value or different values for non-image and difference images. Also, the binarized image is an image binarized to 0 and 1 based on the threshold value for the non-image or difference image, and the defect is detected by considering the size and shape of the defect region through the binarized image.
7 is a diagram showing a binary image obtained by binarizing non-images for each defect type.
Referring to FIG. 7, non-images of the two optimal wavelengths selected by using the dispersion analysis are binarized, resulting in defects such as cracking, scab, color disorder, and cuts The defect detection rate is 100% for Bruise defect, and the detection rate is about 73.3% for Bruise defect.
Meanwhile, the method of using the dispersion analysis in selecting the optimum wavelength for each of the two defect types has been described with reference to FIG. 6. Alternatively, the optimal wavelength for two defect types can be selected by the same method using the correlation analysis.
In this way, by selecting two optimal wavelengths for each defect type through analysis of variance and correlation, and detecting external defects of fruit by using non-image or difference image of single wavelength images respectively corresponding to the two optimum wavelengths, The reliability of defect detection can be improved.
While the present invention has been described in connection with what is presently considered to be practical and exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
100: Rolling device 200: External defect detection part
220: VNIR ultrasound image camera 300: Transmission unit
400: internal quality measuring part 420: near infrared ray spectral sensor
Claims (13)
An external defect detector for detecting an external defect of the fruit through measurement of the entire surface of the fruit rotated by the rolling apparatus;
A transfer unit for transferring the fruit transferred while being rotated by the rolling apparatus to the selection cup; And
And an internal quality measuring unit for measuring internal defects and quality of fruits placed in the selection cup,
The rolling apparatus includes two servo motors having different rotational speeds, a plurality of rollers rotated at different rotational speeds by the respective servo motors, and a chain connecting the rollers,
The two rollers rotating at different speeds rotate the fruits so that the external defect detector can scan the entire surface of the fruit,
Wherein the transfer part picks up the fruit transferred by the rolling device through the clamping type transfer device and places it on the selection cup.
And a vosible and near-infrared (VNIR) ultrasound imaging camera for imaging the surface of the fruit being rotated by said rolling device.
Wherein the external defect of the fruit is detected by using the reflection spectrum obtained through the measurement of the VNIR ultrasound imaging camera and the ultrasound image in the specific wavelength band.
Selecting optimal wavelengths for at least one defect type using reflection spectral data of normal portions and defective portions of the fruit samples extracted for each defect type,
An external defect is detected using at least one of a single wavelength image for the optimal wavelength for each defect type, a difference image for a plurality of the single wavelength images, and a non-image for a plurality of the single wavelength images, And the defect detection system.
Wherein the optimum wavelength for each defect type is selected through analysis of at least one of dispersion analysis and correlation analysis using reflection spectrum data for a normal part and a defective part of a fruit sample extracted for each defect type as input variables, system.
And a near-infrared spectroscopic sensor.
Transferring the fruit being transferred while being rotated by the rolling apparatus to the selection cup through the transfer unit after the detection of the external defect; And
And measuring the internal defect and quality of the fruit using the near-infrared spectroscopy sensor for the fruit placed in the selection cup,
The rolling apparatus includes two servo motors having different rotational speeds, a plurality of rollers rotated at different rotational speeds by the respective servo motors, and a chain connecting the rollers,
The two rollers rotating at different speeds rotate the fruits so that the external defect detector can scan the entire surface of the fruit,
Wherein the transfer part picks up the fruit transferred by the rolling device through the grip type transfer device and places it on the selection cup.
Selecting optimal wavelengths for at least one defect type using reflection spectral data of a normal part and a defective part of a fruit sample extracted for each defect type; And
An external defect is detected using at least one of a single wavelength image for the optimal wavelength for each defect type, a difference image for a plurality of the single wavelength images, and a non-image for a plurality of the single wavelength images, The defect detection method comprising the steps of:
Wherein at least one optimal wavelength for each defect type is selected through at least one of analysis of variance and correlation analysis using reflection spectrum data for a normal part and a defective part of a fruit sample extracted for each defect type as input variables, Gt;
And converting the single-wavelength image into a binarized image reconstructed based on a specific threshold value to detect an external defect.
Wherein the defect is selected to be 710 nm for heat and defect, 715 nm for diseased defect, 561 nm for color defect, 720 nm for wound defect, and 940 nm for bony defect.
The optimum wavelength for each of the two or more defect types is selected through the dispersion analysis and the correlation analysis,
Wherein at least one of a difference image and a non-image with respect to the optimal wavelengths of the two or more selected defect types is converted into a reconstructed binary image based on a specific threshold value to detect an external defect.
The defect is detected at 792 nm and 806 nm, the defect at 720 nm and 964 nm, the defect at 403 nm and 528 nm, the defect at 739 nm and 998 nm, and the defect at 749 nm and 753 nm, respectively.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150155721A KR101750858B1 (en) | 2015-11-06 | 2015-11-06 | System and method for detecting defect |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020150155721A KR101750858B1 (en) | 2015-11-06 | 2015-11-06 | System and method for detecting defect |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20170056716A KR20170056716A (en) | 2017-05-24 |
KR101750858B1 true KR101750858B1 (en) | 2017-07-11 |
Family
ID=59051694
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020150155721A KR101750858B1 (en) | 2015-11-06 | 2015-11-06 | System and method for detecting defect |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101750858B1 (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109720374B (en) * | 2018-12-26 | 2021-03-02 | 台晶(重庆)电子有限公司 | Sputtering machine track testing device and method |
KR102205445B1 (en) * | 2019-02-28 | 2021-01-20 | 충남대학교산학협력단 | Method and System for Detecting Foreign Material on Processing Vegetable Using Multispectral Fluorescence Imaging |
KR102367804B1 (en) * | 2020-06-08 | 2022-02-25 | 주식회사 한성엔지니어링 | Apparatus for feeding fruit |
KR102388752B1 (en) * | 2020-10-22 | 2022-04-20 | (주)레이텍 | Hyperspectral inspection device capable of detecting soft foreign substances |
KR102285603B1 (en) * | 2021-01-15 | 2021-08-04 | 주식회사 에이오팜 | Apparatus and method for selecting a fruit |
KR102390740B1 (en) | 2021-07-07 | 2022-04-26 | 주식회사 에이오팜 | Method and device for training model to classify bad agricultural products, and device for classifying defective agricultural products using the same |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100946749B1 (en) | 2008-03-19 | 2010-03-11 | 정양권 | The Methord and the System of the fog detection using the Image recognition and image learning methord |
-
2015
- 2015-11-06 KR KR1020150155721A patent/KR101750858B1/en active IP Right Grant
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100946749B1 (en) | 2008-03-19 | 2010-03-11 | 정양권 | The Methord and the System of the fog detection using the Image recognition and image learning methord |
Also Published As
Publication number | Publication date |
---|---|
KR20170056716A (en) | 2017-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101750858B1 (en) | System and method for detecting defect | |
JP6940215B2 (en) | Learning method of inspection device and identification means of inspection device | |
Keresztes et al. | Real-time pixel based early apple bruise detection using short wave infrared hyperspectral imaging in combination with calibration and glare correction techniques | |
Qiao et al. | Prediction of drip-loss, pH, and color for pork using a hyperspectral imaging technique | |
US9910024B2 (en) | Method, sensor unit and machine for detecting “sugar top” defects in potatoes | |
Ariana et al. | Evaluation of internal defect and surface color of whole pickles using hyperspectral imaging | |
CN1995987B (en) | Non-destructive detection method for agricultural and animal products based on hyperspectral image technology | |
US9014434B2 (en) | Method for scoring and controlling quality of food products in a dynamic production line | |
US7787111B2 (en) | Simultaneous acquisition of fluorescence and reflectance imaging techniques with a single imaging device for multitask inspection | |
JP5206335B2 (en) | Principal component analysis method, principal component analysis apparatus, heterogeneous product detection apparatus, principal component analysis program, and recording medium on which principal component analysis program is recorded | |
KR102003781B1 (en) | Apparatus for detecting defects on the glass substrate using hyper-spectral imaging | |
Eissa et al. | Understanding color image processing by machine vision for biological materials | |
WO2012074372A2 (en) | A system for fruit grading and quality determination | |
JP2006170669A (en) | Quality inspection device of vegetables and fruits | |
KR101706065B1 (en) | Produce defect inspection device and system | |
Aredo et al. | Predicting of the Quality Attributes of Orange Fruit Using Hyperspec-tral Images | |
Noordam et al. | Detection and classification of latent defects and diseases on raw French fries with multispectral imaging | |
JP3614980B2 (en) | Agricultural product appearance inspection method and apparatus | |
JP6403872B2 (en) | Fruit and vegetable inspection equipment | |
US9568438B1 (en) | Single-camera angled conveyance imaging method and apparatus for whole-surface inspection of rotating objects | |
Balabanov et al. | Mechatronic system for fruit and vegetables sorting | |
Peng et al. | Real-time detection of natural bruises in apple surface using machine vision | |
US20190364935A1 (en) | Method for inspecting legume and method for producing legume food product | |
JP6753651B2 (en) | Egg yolk viscosity determination method and egg yolk viscosity determination device | |
Huang et al. | Development of a multi-spectral imaging system for the detection of bruises on apples |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
AMND | Amendment | ||
E601 | Decision to refuse application | ||
AMND | Amendment | ||
X701 | Decision to grant (after re-examination) | ||
GRNT | Written decision to grant |