KR20240092767A - System for determining defects in silkworm cocoons using near-infrared transmission spectrum - Google Patents
System for determining defects in silkworm cocoons using near-infrared transmission spectrum Download PDFInfo
- Publication number
- KR20240092767A KR20240092767A KR1020220175462A KR20220175462A KR20240092767A KR 20240092767 A KR20240092767 A KR 20240092767A KR 1020220175462 A KR1020220175462 A KR 1020220175462A KR 20220175462 A KR20220175462 A KR 20220175462A KR 20240092767 A KR20240092767 A KR 20240092767A
- Authority
- KR
- South Korea
- Prior art keywords
- infrared transmission
- transmission spectrum
- cocoons
- cocoon
- silkworm
- Prior art date
Links
- 241000255789 Bombyx mori Species 0.000 title claims abstract description 49
- 238000004433 infrared transmission spectrum Methods 0.000 title claims abstract description 31
- 230000007547 defect Effects 0.000 title claims abstract description 15
- 230000002950 deficient Effects 0.000 claims abstract description 39
- 230000003595 spectral effect Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000005540 biological transmission Effects 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 238000012546 transfer Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 8
- 230000001066 destructive effect Effects 0.000 description 4
- 230000032258 transport Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 240000004160 Capsicum annuum Species 0.000 description 1
- 235000008534 Capsicum annuum var annuum Nutrition 0.000 description 1
- 240000008067 Cucumis sativus Species 0.000 description 1
- 235000010799 Cucumis sativus var sativus Nutrition 0.000 description 1
- 244000301850 Cupressus sempervirens Species 0.000 description 1
- 244000000626 Daucus carota Species 0.000 description 1
- 235000002767 Daucus carota Nutrition 0.000 description 1
- 244000017020 Ipomoea batatas Species 0.000 description 1
- 235000002678 Ipomoea batatas Nutrition 0.000 description 1
- 235000008331 Pinus X rigitaeda Nutrition 0.000 description 1
- 241000018646 Pinus brutia Species 0.000 description 1
- 235000011613 Pinus brutia Nutrition 0.000 description 1
- 241000382353 Pupa Species 0.000 description 1
- 244000061458 Solanum melongena Species 0.000 description 1
- 235000002597 Solanum melongena Nutrition 0.000 description 1
- 244000061456 Solanum tuberosum Species 0.000 description 1
- 235000002595 Solanum tuberosum Nutrition 0.000 description 1
- 239000001511 capsicum annuum Substances 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000012864 cross contamination Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 229910052736 halogen Inorganic materials 0.000 description 1
- 150000002367 halogens Chemical class 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 239000010902 straw Substances 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
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
- G01N21/8806—Specially adapted optical and illumination features
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
-
- 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
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- 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
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8845—Multiple wavelengths of illumination or detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/10—Scanning
- G01N2201/104—Mechano-optical scan, i.e. object and beam moving
- G01N2201/1042—X, Y scan, i.e. object moving in X, beam in Y
Landscapes
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
본 발명의 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템에 관한 것으로, 이는 누에고치에 대한 근적외선 투과 스펙트럼을 획득하는 분광 검출부; 및 상기 근적외선 투과 스펙트럼으로부터 가장 높은 투과 강도를 보이는 스펙트럼 대역을 검출한 후, 기 설정된 불량 기준과 비교하여 누에고치 불량 여부를 판별하는 신호 처리부를 포함할 수 있다.The present invention relates to a system for determining defective silkworm cocoons using a near-infrared transmission spectrum, which includes a spectroscopic detection unit that acquires a near-infrared transmission spectrum for a silkworm cocoon; and a signal processing unit that detects a spectral band showing the highest transmission intensity from the near-infrared transmission spectrum and then determines whether the silkworm cocoon is defective by comparing it with a preset defect standard.
Description
본 발명은 누에고치에 대한 근적외선 투과 스펙트럼을 촬영 및 분석하여, 누에고치의 불량 여부를 비파괴적으로 보다 간단하고 정확하게 판별할 수 있도록 하는 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템에 관한 것이다.The present invention relates to a system for determining silkworm cocoon defects using the near-infrared transmission spectrum, which allows non-destructive, simpler and more accurate determination of whether a cocoon is defective by photographing and analyzing the near-infrared transmission spectrum of the silkworm cocoon.
누에고치를 거래하기 위해서는 누에고치 기계검사규칙에 따라 불량 누에고치인 이상견 제거 후 견면 채취된 누에고치들에 대해 검사를 신청해야 한다.In order to trade silkworm cocoons, you must apply for an inspection of the cocoons collected after removing defective silkworms, which are defective cocoons, in accordance with the silkworm cocoon mechanical inspection rules.
자동수견 견면채취기는 고치를 수집하는 단계부터 견면 채취, 섶 청소까지 3가지 작업을 동시에 수행하는 기계로서 농가에서 인력으로 수행하고 있는 작업 방식에 비하여 작업능률이 높고, 소요경비도 절감되는 효과가 있다.The automatic silk harvester is a machine that performs three tasks at the same time, from cocoon collection to silk harvesting and comb cleaning, and has higher work efficiency and reduced costs compared to the work method performed by manpower in farms. .
자동수견 견면채취기를 사용 시에 불량 고치가 있으면 고치 속의 번데기가 터지게 되어 교차 오염되는 문제가 발생하므로 견면채취 전 선별작업이 필요하다.When using an automatic silk collecting machine, if there is a defective cocoon, the pupa inside the cocoon will burst, causing cross-contamination, so screening is necessary before collecting silk.
현재 노동자가 직접 불량 선별을 하고 있으며, 흔들었을 때 소리가 나지 않거나 햇빛에 비추었을 때 검게 나타나는 고치를 불량으로 판단한다.Currently, workers directly select defects, and cocoons that do not make a sound when shaken or appear black when exposed to sunlight are judged to be defective.
한편, 노동력 절감을 위해 인력에 의한 불량 누에고치 선별 작업을 실시간, 비파괴적으로 자동 판별할 수 있는 기술 개발이 요구된다.Meanwhile, in order to save labor, there is a need to develop technology that can automatically and non-destructively identify defective cocoon selection by human resources in real time.
대한민국 등록특허공보 제10-0590595호에 개시되어 있는 입상형 작물의 선별장치는 파프리카, 고구마, 가지, 오이, 당근 및 감자와 같이 입상형으로 형성된 과일, 채소 또는 기타 식용작물을 선별하기 위한 선별장치를 제공할 뿐, 누에고치 불량 판별 동작을 수행하는 선별 장치에 대해서는 전혀 개시하지 못하는 한계가 있다. The granular crop sorting device disclosed in Korean Patent Publication No. 10-0590595 is a sorting device for selecting granular fruits, vegetables, or other edible crops such as paprika, sweet potato, eggplant, cucumber, carrot, and potato. However, there is a limitation in that it cannot disclose at all the sorting device that performs the operation of determining defective silkworm cocoons.
상기한 문제점을 해결하고자 하는 차원에서, 본 발명에서는 누에고치에 대한 근적외선 투과 스펙트럼을 촬영 및 분석하여, 누에고치의 불량 여부를 비파괴적으로 보다 간단하고 정확하게 판별할 수 있도록 하는 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템을 제공하고자 한다. In order to solve the above problems, the present invention photographs and analyzes the near-infrared transmission spectrum of the silkworm cocoon, and uses the near-infrared transmission spectrum to more simply and accurately determine whether the cocoon is defective in a non-destructive manner. We would like to provide a system for determining defective cocoons.
상기와 같은 목적을 달성하기 위한 본 발명의 일 실시예에 따르면, 누에고치에 대한 근적외선 투과 스펙트럼을 획득하는 분광 검출부; 및 상기 근적외선 투과 스펙트럼으로부터 가장 높은 투과 강도를 보이는 스펙트럼 대역을 검출한 후, 기 설정된 불량 기준과 비교하여 누에고치 불량 여부를 판별하는 신호 처리부를 포함하는 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템을 제공한다. According to an embodiment of the present invention for achieving the above object, there is provided a spectroscopic detection unit that acquires a near-infrared transmission spectrum for a silkworm cocoon; and a signal processing unit that detects the spectral band showing the highest transmission intensity from the near-infrared transmission spectrum and then determines whether the silkworm cocoon is defective by comparing it with a preset defect standard. do.
상기 신호 처리부는 가장 높은 투과 강도를 보이는 스펙트럼 대역이 "1050~1020nm"에 속하면 정상 누에고치로 판단하고, 그렇지 않으면 불량 누에고치를 판단하는 것을 특징으로 한다. The signal processing unit determines that the cocoon is normal if the spectral band showing the highest transmission intensity falls within “1050-1020 nm,” and if not, it determines that it is a defective cocoon.
상기 신호 처리부는 범위 정규화 또는 최대 정규화 방식에 따라 근적외선 투과 스펙트럼에 포함된 각종 노이즈를 제거하는 데이터 전처리 기능을 더 포함하는 것을 특징으로 한다. The signal processing unit further includes a data preprocessing function to remove various noises included in the near-infrared transmission spectrum according to a range normalization or maximum normalization method.
상기 누에고치 불량 판별 시스템은 누에고치를 일정 속도로 이송시키는 이송부; 및 다수의 누에고치를 수납하며, 상기 다수의 누에고치 중 어느 하나를 순차적으로 선택하여 상기 이송부에 공급하는 누에고치 공급부를 더 포함하는 것을 특징으로 한다. The system for determining defective silkworm cocoons includes a transport unit that transports the silkworm cocoons at a constant speed; and a cocoon supply unit that stores a plurality of silkworm cocoons and sequentially selects one of the plurality of cocoons and supplies it to the transfer unit.
또한 상기 누에고치 불량 판별 시스템은 상기 신호 처리부의 불량 판별 결과에 따라 정상 누에고치와 불량 누에고치를 분리 수거하는 선별부를 더 포함할 수도 있다. In addition, the system for determining defective silkworm cocoons may further include a sorting unit that separates and collects normal cocoons and defective cocoons according to the defect determination result of the signal processing unit.
본 발명에 따른 누에고치에 대한 근적외선 투과 스펙트럼을 촬영 및 분석하여, 누에고치의 불량 여부를 비파괴적으로 보다 간단하고 정확하게 판별할 수 잇도록 한다. By photographing and analyzing the near-infrared transmission spectrum of the silkworm cocoon according to the present invention, it is possible to more simply and accurately determine whether the silkworm cocoon is defective in a non-destructive manner.
또한 본 발명은 이송부를 통해 누에고치를 이송을 시키면서 상기의 불량 판별동작을 수행할수 있도록 함으로써, 보다 많은 누에고치를 보다 신속 정확하게 판별할 수도 있도록 한다. In addition, the present invention allows the above-mentioned defect determination operation to be performed while transporting the silkworm cocoons through the transfer unit, thereby enabling more rapid and accurate identification of more silkworm cocoons.
도 1은 본 발명의 일 실시예에 따른 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템을 도시한 도면이다.
도 2는 본 발명의 일 실시예에 따른 신호 처리부의 상세 구성을 도시한 도면이다.
도 3은 본 발명의 일 실시예에 따른 신호 처리부의 누에고치 상태 판별 근거를 설명하기 위한 도면이다.
도 4는 본 발명의 일 실시예에 따른 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 방법을 설명하기 위한 도면이다. Figure 1 is a diagram illustrating a system for determining defective silkworm cocoons using a near-infrared transmission spectrum according to an embodiment of the present invention.
Figure 2 is a diagram showing the detailed configuration of a signal processing unit according to an embodiment of the present invention.
Figure 3 is a diagram for explaining the basis for determining the cocoon state of the signal processing unit according to an embodiment of the present invention.
Figure 4 is a diagram illustrating a method for determining defective silkworm cocoons using a near-infrared transmission spectrum according to an embodiment of the present invention.
이하, 도면을 참조하여 본 발명의 실시예의 구성 및 작용을 상세히 설명한다. 본 발명에 따른 획득 영상을 이용한 불량 누에고치 판별장치를 설명한다.Hereinafter, the configuration and operation of an embodiment of the present invention will be described in detail with reference to the drawings. A device for determining defective silkworm cocoons using acquired images according to the present invention will be described.
본 발명 상에서 섶은 '누에가 올라가 고치를 짓도록 마련해 놓은 짚이나 잎나무'를 말하는 것으로서, 잠족이라고도 한다. 잎나무로는 주로 싸리나무·솔가지·참나무 등을 사용하며, 누에가 들어가 고치를 짓는 칸의 간격이 알맞고 수도 많으며 습기를 어느 정도 흡수하고 손쉽게 만들되 오래 쓸 수 있으며 넣고 빼기가 편리해야 한다.In the present invention, ‘seop’ refers to ‘straw or leaf trees prepared for silkworms to climb and build cocoons’, and is also called jamjok. Leaf wood, such as cypress, pine branches, and oak, is mainly used. The space between the compartments where the silkworms enter and build the cocoon must be plentiful, absorb some moisture, be easy to make, be usable for a long time, and be easy to put in and take out.
도 1은 본 발명의 일 실시예에 따른 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템을 도시한 도면이다. Figure 1 is a diagram illustrating a system for determining defective silkworm cocoons using a near-infrared transmission spectrum according to an embodiment of the present invention.
도 1을 참조하면, 본 발명의 장치는 이송부(110), 누에고치 공급부(120), 분광 검출부(130), 신호 처리부(140) 및 선별부(150) 등을 포함한다. Referring to Figure 1, the device of the present invention includes a transfer unit 110, a cocoon supply unit 120, a spectral detection unit 130, a signal processing unit 140, and a selection unit 150.
이송부(110)는 컨베이어 밸트 등으로 구현되어, 누에고치 공급부(120)에 의해 공급된 누에고치를 선별부(150) 쪽으로 일정 속도로 이송하도록 한다. The transfer unit 110 is implemented as a conveyor belt, etc., and transports the silkworm cocoons supplied by the cocoon supply unit 120 toward the sorting unit 150 at a constant speed.
누에고치 공급부(120)는 다수의 누에고치를 수납하며, 다수의 누에고치 중 어느 하나를 순차적으로 선택하여 이송부(110)에 공급하도록 한다. The silkworm cocoon supply unit 120 stores a plurality of silkworm cocoons, and sequentially selects one of the plurality of cocoons to supply it to the transfer unit 110.
분광 검출부(130)는 이송부(110)를 통해 이송되고 있는 누에고치에 100W 할로겐 광을 조사한 후, 이에 상응하는 근적외선 투과 스펙트럼을 획득하도록 한다. The spectral detection unit 130 irradiates 100W halogen light to the silkworm cocoon being transported through the transfer unit 110 and then acquires a near-infrared transmission spectrum corresponding thereto.
신호 처리부(140)는 근적외선 투과 스펙트럼으로부터 가장 높은 투과 강도를 보이는 스펙트럼 대역을 검출하고, 이를 기 설정된 불량 기준과 비교하여 누에고치 불량 여부를 판별한다. 즉, 가장 높은 투과 강도를 보이는 스펙트럼 대역이 "1050~1020nm"에 속하면 정상 누에고치로 판단하고, 그렇지 않으면 불량 누에고치를 판단하도록 한다.The signal processing unit 140 detects the spectral band showing the highest transmission intensity from the near-infrared transmission spectrum and determines whether the silkworm cocoon is defective by comparing it with a preset defect standard. In other words, if the spectral band showing the highest transmission intensity falls within "1050~1020nm", it is judged to be a normal cocoon; otherwise, it is judged to be a defective cocoon.
선별부(150)는 신호 처리부(140)의 누에고치 불량 판별 결과에 따라 에어 분사 여부가 결정되는 에어 분사기 등을 구비하고, 이를 통해 이송부(110)를 통해 이송 중인 누에고치를 정상과 불량으로 분리하여 수거하도록 한다. The selection unit 150 is equipped with an air injector that determines whether or not to spray air according to the result of determining whether the cocoon is defective by the signal processing unit 140, and through this, the cocoons being transported through the transfer unit 110 are separated into normal and defective ones. and collect it.
도 2는 본 발명의 일 실시예에 따른 신호 처리부의 상세 구성을 도시한 도면이다. Figure 2 is a diagram showing the detailed configuration of a signal processing unit according to an embodiment of the present invention.
도 2를 참조하면, 본 발명의 신호 처리부(140)는 데이터 전처리부(141), 스펙트럼 분석부(130(142), 및 불량 판별부(143) 등을 포함한다. Referring to FIG. 2, the signal processing unit 140 of the present invention includes a data preprocessing unit 141, a spectrum analysis unit 130 (142), and a defect determination unit 143.
데이터 전처리부(141)는 근적외선 투과 스펙트럼에 포함된 각종 노이즈를 제거하기 위한 데이터 전처리 작업을 수행한다. The data preprocessing unit 141 performs data preprocessing to remove various noises included in the near-infrared transmission spectrum.
이때, 데이터 전처리 작업은 기준선 오프셋(baseline offset), 1/2차 미분( 1st/2nd derivatives), 평균/최대/범위 정규화(Mean/Max/Range Normalization), MSC(Multiplicative Scattering Correction), SNV(Standard Normal Variate), 평활화(Smoothing) 등의 방법으로 수행될 수 있으나, 범위 정규화 또는 최대 정규화 방식을 이용하는 것이 가장 바람직할 것이다. At this time, data preprocessing tasks include baseline offset, 1st/2nd derivatives, Mean/Max/Range Normalization, MSC (Multiplicative Scattering Correction), and SNV (Standard It can be performed using methods such as Normal Variate and Smoothing, but it would be most desirable to use range normalization or maximum normalization methods.
스펙트럼 분석부(130(142)는 누에고치를 촬영한 근적외선 투과 스펙트럼의 투과 강도를 전 영역에 거쳐 스캐닝함으로써, 가장 높은 투과 강도를 보이는 스펙트럼 대역을 추출한다. The spectrum analysis unit 130 (142) extracts the spectral band showing the highest transmission intensity by scanning the transmission intensity of the near-infrared transmission spectrum taken from the silkworm cocoon across the entire region.
불량 판별부(143)는 투과 강도 분석부(130(142)에 의해 추출된 가장 높은 투과 강도를 보이는 스펙트럼 대역이 1080nm 부근이면, 현재 검사한 누에고치는 정상 상태의 누에고치라고 판단하고, 그렇지 않으면 불량 상태의 누에고치라고 판단한다. The defect determination unit 143 determines that the currently inspected silkworm cocoon is a normal cocoon if the spectral band showing the highest transmission intensity extracted by the transmission intensity analysis unit 130 (142) is around 1080 nm, and otherwise, it is judged to be defective. It is judged to be a cocoon of the state.
도 3은 본 발명의 일 실시예에 따른 신호 처리부의 누에고치 상태 판별 근거를 설명하기 위한 도면이다. Figure 3 is a diagram for explaining the basis for determining the cocoon state of the signal processing unit according to an embodiment of the present invention.
본 발명의 누에고치 상태 판별 근거를 확보하기 위해, 367개의 정상 누에고치와 152개의 불량 누에고치에 대한 근적외선 투과 스펙트럼을 획득 및 분석한 결과, 367개의 정상 누에고치 중 366개는 1080nm 부근에서 가장 높은 투과 강도를 나타내었음을 확인하였으며, 불량 고치 중 152개 중 26개를 제외한 나머지는 1080nm 부근에서 가장 높은 투과 강도를 나타내지 않음을 확인하였다. In order to secure a basis for determining the condition of the silkworm cocoons of the present invention, the near-infrared transmission spectra of 367 normal cocoons and 152 defective cocoons were acquired and analyzed. As a result, 366 of the 367 normal cocoons had the highest value around 1080nm. It was confirmed that the transmission intensity was shown, and it was confirmed that all but 26 of the 152 defective cocoons did not show the highest transmission intensity around 1080nm.
그리고 누에고치 519에 대한 주성분(PCA) 분석을 수행한 결과, PC1 90.42%, PC2 8.42%의 설명력을 보이며, 불량 누에고치는 PC2의 0을 기준으로 우하향에 위치하는 그룹으로 형성됨을 확인하였다. And as a result of performing principal component (PCA) analysis on 519 silkworm cocoons, it was confirmed that PC1 had an explanatory power of 90.42% and PC2 8.42%, and that defective cocoons were formed as a group located downward to the right based on PC2's 0.
이에 본 발명에서는 상기의 스펙트럼 특성과 주성분 분석 결과에 기반하여 모든 스펙트럼 대역을 분석하는 대신에 가장 높은 투과 강도를 보이는 스펙트럼 대역만을 확인하여, 누에고치의 불량 여부를 손쉽게 결정할 수 있도록 한다. Accordingly, in the present invention, instead of analyzing all spectral bands based on the above spectral characteristics and principal component analysis results, only the spectral band showing the highest transmission intensity is confirmed, making it possible to easily determine whether or not the silkworm cocoon is defective.
도 4는 본 발명의 일 실시예에 따른 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 방법을 설명하기 위한 도면이다. Figure 4 is a diagram illustrating a method for determining defective silkworm cocoons using a near-infrared transmission spectrum according to an embodiment of the present invention.
먼저, 누에고치 상태 판별이 요청되면, 누에고치 공급부(120)는 누에고치가 일정 간격을 두고 분광 검출부(130) 쪽으로 하나씩 이송되도록 한다(S1). First, when a determination of the cocoon status is requested, the cocoon supply unit 120 causes the cocoons to be transferred one by one toward the spectroscopic detection unit 130 at regular intervals (S1).
이에 누에고치가 분광 검출부(130)의 검출 영역으로 이송되면, 분광 검출부(130)는 누에고치에 광을 조사하여 누에고치의 근적외선 투과 스펙트럼을 획득하도록 한다(S2). Accordingly, when the silkworm cocoon is transferred to the detection area of the spectral detection unit 130, the spectral detection unit 130 radiates light to the cocoon to obtain the near-infrared transmission spectrum of the cocoon (S2).
그러면 신호 처리부(140)는 근적외선 투과 스펙트럼을 분석하여 가장 높은 투과 강도를 보이는 스펙트럼 대역을 검출하고, 가장 높은 투과 강도를 보이는 스펙트럼 대역이 "1050~1020nm"에 속하는 지 확인하도록 한다(S3). Then, the signal processing unit 140 analyzes the near-infrared transmission spectrum to detect the spectral band showing the highest transmission intensity, and checks whether the spectral band showing the highest transmission intensity falls within “1050-1020 nm” (S3).
만약, 가장 높은 투과 강도를 보이는 스펙트럼 대역이 "1050~1020nm"에 속하면(S4), 현재 검사한 누에고치를 정상 누에고치로 판정하여 정상 누에고치 수집함으로 이송시키고(S5), 그렇지 않으면(S4), 불량 누에고치로 판정하여 불량 누에고치 수집함쪽으로 이송시키도록 한다(S6). If the spectral band showing the highest transmission intensity falls within “1050~1020 nm” (S4), the currently examined cocoon is judged to be a normal cocoon and transferred to the normal cocoon collection box (S5), otherwise (S4) ), it is determined to be a defective cocoon and is transported to the defective cocoon collection box (S6).
이와 같이, 본 발명은 다수의 누에고치를 이송시키면서 비파과적 방법으로 불량 여부를 즉각 판정할 수 있도록 해준다. In this way, the present invention allows for immediate determination of defects in a non-destructive manner while transporting a large number of silkworm cocoons.
이상 실시예를 통해 본 발명을 설명하였으나, 본 발명은 이에 제한되는 것은 아니다. 상기 실시예는 본 발명의 취지 및 범위를 벗어나지 않고 수정되거나 변경될 수 있으며, 본 기술분야의 통상의 기술자는 이러한 수정과 변경도 본 발명에 속하는 것임을 알 수 있을 것이다.Although the present invention has been described through the above examples, the present invention is not limited thereto. The above embodiments may be modified or changed without departing from the spirit and scope of the present invention, and those skilled in the art will recognize that such modifications and changes also fall within the present invention.
Claims (5)
상기 근적외선 투과 스펙트럼으로부터 가장 높은 투과 강도를 보이는 스펙트럼 대역을 검출한 후, 기 설정된 불량 기준과 비교하여 누에고치 불량 여부를 판별하는 신호 처리부를 포함하는 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템. A spectral detection unit that acquires a near-infrared transmission spectrum for the silkworm cocoon; and
A system for determining silkworm cocoon defects using a near-infrared transmission spectrum, including a signal processing unit that detects the spectral band showing the highest transmission intensity from the near-infrared transmission spectrum and then determines whether the silkworm cocoon is defective by comparing it with a preset defect standard.
가장 높은 투과 강도를 보이는 스펙트럼 대역이 "1050~1020nm"에 속하면 정상 누에고치로 판단하고, 그렇지 않으면 불량 누에고치를 판단하는 것을 특징으로 하는 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템. The method of claim 1, wherein the signal processing unit
A silkworm cocoon defect determination system using a near-infrared transmission spectrum, characterized in that it is judged to be a normal silkworm cocoon if the spectral band showing the highest transmission intensity falls within "1050~1020nm", and if not, it is judged to be a defective cocoon.
범위 정규화 또는 최대 정규화 방식에 따라 근적외선 투과 스펙트럼에 포함된 각종 노이즈를 제거하는 데이터 전처리 기능을 더 포함하는 것을 특징으로 하는 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템. The method of claim 1, wherein the signal processing unit
A system for determining defective silkworm cocoons using a near-infrared transmission spectrum, further comprising a data preprocessing function that removes various noises included in the near-infrared transmission spectrum according to a range normalization or maximum normalization method.
누에고치를 일정 속도로 이송시키는 이송부; 및
다수의 누에고치를 수납하며, 상기 다수의 누에고치 중 어느 하나를 순차적으로 선택하여 상기 이송부에 공급하는 누에고치 공급부를 더 포함하는 것을 특징으로 하는 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템. According to paragraph 1,
A transfer unit that transfers the silkworm cocoon at a constant speed; and
A system for determining defective silkworm cocoons using a near-infrared transmission spectrum, comprising a cocoon supply unit that stores a plurality of cocoons and sequentially selects one of the plurality of cocoons and supplies it to the transfer unit.
상기 신호 처리부의 불량 판별 결과에 따라 정상 누에고치와 불량 누에고치를 분리 수거하는 선별부를 더 포함하는 것을 특징으로 하는 근적외선 투과 스펙트럼을 이용한 누에고치 불량 판별 시스템. According to paragraph 1,
A system for determining defective silkworm cocoons using a near-infrared transmission spectrum, further comprising a sorting unit that separates and collects normal cocoons and defective cocoons according to the defect determination result of the signal processing unit.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020220175462A KR20240092767A (en) | 2022-12-15 | 2022-12-15 | System for determining defects in silkworm cocoons using near-infrared transmission spectrum |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020220175462A KR20240092767A (en) | 2022-12-15 | 2022-12-15 | System for determining defects in silkworm cocoons using near-infrared transmission spectrum |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20240092767A true KR20240092767A (en) | 2024-06-24 |
Family
ID=91711588
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020220175462A KR20240092767A (en) | 2022-12-15 | 2022-12-15 | System for determining defects in silkworm cocoons using near-infrared transmission spectrum |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR20240092767A (en) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100590595B1 (en) | 2004-11-12 | 2006-06-19 | 대한민국(관리부서:농촌진흥청) | Apparatus of taking an image of bulk crops, apparatus of dividing bulk crops and apparatus of sorting bulk crops |
-
2022
- 2022-12-15 KR KR1020220175462A patent/KR20240092767A/en unknown
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100590595B1 (en) | 2004-11-12 | 2006-06-19 | 대한민국(관리부서:농촌진흥청) | Apparatus of taking an image of bulk crops, apparatus of dividing bulk crops and apparatus of sorting bulk crops |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zayas et al. | Detection of insects in bulkwheat samples with machine vision | |
US7218775B2 (en) | Method and apparatus for identifying and quantifying characteristics of seeds and other small objects | |
Mahendran et al. | Application of computer vision technique on sorting and grading of fruits and vegetables | |
Lu | Detection of bruises on apples using near–infrared hyperspectral imaging | |
JP6590907B2 (en) | Fruit sorting system, fruit sorting device, and fruit sorting method | |
JP4704804B2 (en) | Wood section exploration method, apparatus and program | |
CN106442561B (en) | Online image acquisition system and method for detecting citrus peel defects | |
Zareiforoush et al. | Potential applications of computer vision in quality inspection of rice: a review | |
Park et al. | Multispectral imaging system for fecal and ingesta detection on poultry carcasses | |
EP2140749A1 (en) | Classification of seeds | |
Li et al. | Development of algorithms for detecting citrus canker based on hyperspectral reflectance imaging | |
Ding et al. | Quality and safety inspection of food and agricultural products by LabVIEW IMAQ vision | |
JP2007071620A (en) | Method and device for determining sex of silkworm pupa | |
KR20240092767A (en) | System for determining defects in silkworm cocoons using near-infrared transmission spectrum | |
Chao et al. | Fast line-scan imaging system for broiler carcass inspection | |
Huang et al. | Early detection of bruises on apples using near-infrared hyperspectral image | |
US11636588B2 (en) | Apparatus and system for assessing paddy rice grains | |
Guyer et al. | Tissue reflectance and machine vision for automated sweet cherry sorting | |
US20050017186A1 (en) | Method and means for detecting internal larval infestation in granular material | |
CN117074353B (en) | Nondestructive detection method and system for litchi fruit Di-moths | |
Huang et al. | Development of a multi-spectral imaging system for the detection of bruises on apples | |
US11605178B2 (en) | White cap detection device | |
Huang et al. | Identification of maize kernel embryo based on hyperspectral imaging technology and PCA | |
JP6997495B1 (en) | Pistachio sorting device | |
Li et al. | Hyperspectral reflectance imaging for detecting citrus canker based on dual-band ratio image classification method |