KR20230062754A - Automatic ginseng classification solution based on AI - Google Patents
Automatic ginseng classification solution based on AI Download PDFInfo
- Publication number
- KR20230062754A KR20230062754A KR1020210147530A KR20210147530A KR20230062754A KR 20230062754 A KR20230062754 A KR 20230062754A KR 1020210147530 A KR1020210147530 A KR 1020210147530A KR 20210147530 A KR20210147530 A KR 20210147530A KR 20230062754 A KR20230062754 A KR 20230062754A
- Authority
- KR
- South Korea
- Prior art keywords
- classification
- ginseng
- automatic
- artificial intelligence
- acquisition
- Prior art date
Links
- 241000208340 Araliaceae Species 0.000 title claims abstract description 17
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 title claims abstract description 17
- 235000003140 Panax quinquefolius Nutrition 0.000 title claims abstract description 17
- 235000008434 ginseng Nutrition 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 15
- 238000012216 screening Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
본 고안은 인공지능에 관한 것으로 인삼 품질 분류를 위해 제공 기술분야The present invention relates to artificial intelligence and provides technology for ginseng quality classification
최근 농가에서 재배 부터 수확까지 농작물 재배를 자동화 하는 스마트팜 기술이 보급되고 있다. 기존 농가에서 수작업 하고 있는 품질 선별도 자동 반영이 되고 있어 이러한 자동화 기술 중 인공지능이 활용 되고 있다. 보다 정밀하고 능률적인 면에서 인공지능 자동화가 필요로 한다.Recently, smart farm technology that automates crop cultivation from cultivation to harvest is spreading. Quality selection, which is done manually in existing farms, is also automatically reflected, and artificial intelligence is being used among these automation technologies. Artificial intelligence automation is needed in a more precise and efficient way.
기존 사람이 직접 만지고, 눈으로 확인하여 분류 작업을 하다 보니 정밀도가 떨어지고, 상품 손상이 발생함. 인력 공급이 수월하지 않아 작업이 지체됨. 품질 및 출하 시기로 불균형으로 농가에 피해가 발생 되어 인공지능 자동화 기술을 적용하여 균일성과 정밀도가 떨어지는 문제점을 해결하고 직접 손으로 만지지 않아 제품을 줄려 완성도 높고 효율적인 인삼의 품질 자동 분류하려고 한다.Existing people directly touch and check with their own eyes to sort, resulting in poor precision and product damage. Work is delayed due to lack of manpower supply. Imbalance in quality and shipping time caused damage to farmhouses, so artificial intelligence automation technology was applied to solve the problem of low uniformity and precision, and to reduce products without touching them with hands, to automatically classify high-quality and efficient ginseng.
인공지능 인삼 분류 방법은 도1과 같이 크게 4단계의 구성으로 진행된다.The artificial intelligence ginseng classification method proceeds in a four-step configuration as shown in FIG.
자동 취득 후 자동 분석을 통해 인삼 품질의 이상 유무를 결정하여 최종 분류를 시행하는 일련의 프로세서를 갖는다. 이를 통해서 기존의 농작물 분류작업을 보다 효율적이고, 완성도 있게 관리가 가능하고, 시간적 문제를 개선할 수 있으며, 이후 능동적으로 품질 선별 개선방식을 스스로 개선해 나갈 수 있게 하는 것을 특징으로 한다.It has a series of processors that perform final classification by determining whether or not there is an abnormality in ginseng quality through automatic analysis after automatic acquisition. Through this, it is possible to manage the existing crop classification work more efficiently and with completeness, and to improve the time problem, and then to actively improve the quality selection and improvement method on its own.
도1은 인공지능 인삼 품질 선별의 전체적인 프로세스로 자동화 선별의 일련의 과정을 구성한 표이다.Figure 1 is a table consisting of a series of automated screening processes as an overall process of artificial intelligence ginseng quality screening.
인공지능 인삼 분류 방법은 도1과 같이 크게 4단계의 구성으로 진행된다.The artificial intelligence ginseng classification method proceeds in a four-step configuration as shown in FIG.
자동 취득 후 자동 분석을 통해 인삼 품질의 이상 유무를 결정하여 최종 분류를 시행하는 일련의 프로세서를 갖는다. 이를 통해서 기존의 농작물 분류작업을 보다 효율적이고, 완성도 있게 관리가 가능하고, 시간적 문제를 개선할 수 있으며, 이후 능동적으로 품질 선별 개선방식을 스스로 개선해 나갈 수 있게 하는 것을 특징으로 한다.It has a series of processors that perform final classification by determining whether or not there is an abnormality in ginseng quality through automatic analysis after automatic acquisition. Through this, it is possible to manage the existing crop classification work more efficiently and with completeness, and to improve the time problem, and then to actively improve the quality selection and improvement method on its own.
도1의 취득 항목은 취득장치, 취득장치와의 통신방법, 취득 데이터의 포맷등의 세부항목으로 구성 될 수 있으며, The acquisition items in FIG. 1 may consist of detailed items such as the acquisition device, the communication method with the acquisition device, and the format of the acquired data.
도1의 분석 항목은 취득데이터 유형 분석, 취득데이터의 상태 분석 등의 세부항목으로 구성 될 수 있으며,The analysis items of FIG. 1 may consist of detailed items such as analysis of the type of acquired data and analysis of the status of acquired data.
도1의 결정 항목은 기준 값 기반 결정 방식과 학습데이터에 기반한 결정 방식으로 나뉘며 이를 병합한 기준 값과 학습데이터 기반의 통합 방식으로 세부항목으로 구성 될 수 있으며,The decision items in FIG. 1 are divided into a reference value-based decision method and a learning data-based decision method, and can be composed of detailed items by merging the reference value and learning data-based integrated method.
도1의 분류 항목은 수동, 자동, 반자동 분류 등의 세부항목으로 구성 될 수 있다.The classification items of FIG. 1 may be composed of detailed items such as manual, automatic, and semi-automatic classification.
도1 취득 항목의 세부항목 취득장치는 카메라, 물체감지 센서 등(비파괴 센서) 등으로 구성 될수 있으며,The detailed item acquisition device of the acquisition item in FIG. 1 may be composed of a camera, an object detection sensor, etc. (non-destructive sensor),
도1 취득 항목의 세부항목 취득장치와의 통신방법은 무선통신, 유선통신, 전용 프로토콜 등으로 구성 될 수 있으며,The communication method with the detailed item acquisition device of the acquisition item in Fig. 1 can be composed of wireless communication, wired communication, dedicated protocol, etc.
도1 취득 항목의 세부항목 취득 데이터의 포맷은 이미지, 동영상, 위치 정보, 기타 센서 값 등으로 구성 될 수 있다.The format of acquisition data of detailed items of Fig. 1 acquisition items may be composed of images, videos, location information, and other sensor values.
도1 분석 항목의 세부항목 취득데이터 유형 분석은 인삼의 유형을 분석하여 결정 기준 값 제시 하며,The analysis of the type of acquisition data of the detailed items of the analysis item in Figure 1 analyzes the type of ginseng and presents the decision standard value,
도1 분석 항목의 세부항목 취득데이터의 상태 분석은 인삼의 상태를 분석하여 결정 기준 값 제시 한다.The state analysis of the detailed item acquisition data of Fig. 1 analyzes the state of ginseng and presents the decision standard value.
도1 결정 항목의 세부항목 기준 값 기반 결정 방식은 제공된 기준 값 기준의 결정 방식으로 크기, 무게 등의 물리적 데이터 기준으로 센서 또는 일반적인 이미지 프로세싱 알고리즘으로 결정하는 방식이며 The detailed reference value-based decision method of the decision item in Fig. 1 is a method based on the provided reference value, which is determined by a sensor or a general image processing algorithm based on physical data such as size and weight.
도1 결정 항목의 세부항목 학습데이터에 기반한 결정 방식은 상품의 생김새 등을 학습하여 미적, 형태, 상태 등을 결정하는 시각지능 학습 방식의 학습기반 인공지능 결정 방식을 말한다.The decision method based on the detailed item learning data of the decision item in Fig. 1 refers to the learning-based artificial intelligence decision method of the visual intelligence learning method that determines the aesthetic, form, state, etc. by learning the appearance of the product.
도1 결정 항목의 세부항목 통합 방식은 센서, 알고리즘, 인공지능 융합 된 결정 방식을 말한다.The method of integrating the details of the decision items in Fig. 1 refers to the method of convergence of sensors, algorithms, and artificial intelligence.
도1 분류 항목의 세부항목 수동 분류는 분류작업자가 분류 상품을 이동 할 수 있게 특정 분류 함 등에 적재 하여 이후 후속 작업이 가능하게 임시 분류하는 방식을 말하며Manual classification of the detailed items of the classification item in Fig. 1 refers to a method of temporarily classifying the classified goods so that the classification worker can move the classified goods by loading them in a specific sorting box so that subsequent work is possible.
도1 분류 항목의 세부항목 자동 분류는 분류된 상품을 패키지(포장)라인 까지 자동 연결 되는 원스톱 분류 방식으로 분류 데이터를 자동 전달 하는 방식을 말하며The automatic classification of the details of the classification item in Fig. 1 refers to a method of automatically delivering classification data in a one-stop classification method that automatically connects the classified goods to the package (packaging) line.
도1 분류 항목의 세부항목 반자동 분류는 분류작업자나 분류 센서가 인식하여 분류 할 수 있게 하는 바코드 텍스트가 인쇄 되는 마킹 방식 등에 이후 자동 인식이 가능하 표식을 제공하는 분류 방식을 말한다.Semi-automatic classification of detailed items of the classification item in FIG. 1 refers to a classification method that provides a mark that can be automatically recognized later, such as a marking method in which a barcode text is printed so that a classification operator or a classification sensor can recognize and classify.
인삼의 분류에는 여러가지 요소가 문제가 되는데 특히 잔뿌리의 유무와 같은 시각적 판단 기준이 모호함으로 사람이 기준값을 도출해 내기 어렵다. 도1의 프로세스에 의해 기준치가 없는 분류 기준점을 인공지능은 보다 정리하게 도출해 낼 수 있으며 보다 효율적인 상품 제공이 가능해 진다.Various factors are problematic in the classification of ginseng. In particular, it is difficult for a person to derive a standard value because the visual criteria such as the presence or absence of fine roots are ambiguous. Through the process of FIG. 1, artificial intelligence can derive a classification reference point without a reference value in a more organized manner, and more efficient product provision is possible.
Claims (1)
Artificial intelligence ginseng quality screening method with 4 processes of acquisition, analysis, determination, and classification
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020210147530A KR20230062754A (en) | 2021-10-31 | 2021-10-31 | Automatic ginseng classification solution based on AI |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020210147530A KR20230062754A (en) | 2021-10-31 | 2021-10-31 | Automatic ginseng classification solution based on AI |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20230062754A true KR20230062754A (en) | 2023-05-09 |
Family
ID=86409000
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020210147530A KR20230062754A (en) | 2021-10-31 | 2021-10-31 | Automatic ginseng classification solution based on AI |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR20230062754A (en) |
-
2021
- 2021-10-31 KR KR1020210147530A patent/KR20230062754A/en unknown
Similar Documents
Publication | Publication Date | Title |
---|---|---|
RU2672389C1 (en) | System of follow-up inspection of orders | |
WO2021087490A1 (en) | Profiling pallets and goods in a warehouse environment | |
US20170066597A1 (en) | Information processing device, information processing system, distribution system, information processing method, and program storage medium | |
CN102275656B (en) | On-line visual pack absence detection device and detection method for cigarette pack cartoning machine | |
CN107832780B (en) | Artificial intelligence-based wood board sorting low-confidence sample processing method and system | |
CN107486415A (en) | Thin bamboo strip defect on-line detecting system and detection method based on machine vision | |
Rokunuzzaman et al. | Development of a low cost machine vision system for sorting of tomatoes. | |
WO2019114380A1 (en) | Wood board identification method, machine learning method and device for wood board identification, and electronic device | |
CN106672345B (en) | A kind of method and system of industrial robot automatic sorting | |
JP2021021729A (en) | Moving article classification system and method | |
US20220284699A1 (en) | System and method of object detection using ai deep learning models | |
CN113877836B (en) | Intelligent identification sorting system based on visual detection system | |
CN207238542U (en) | A kind of thin bamboo strip defect on-line detecting system based on machine vision | |
US20190385337A1 (en) | Article positioning method and system | |
CN110136044B (en) | Article sorting method, system and equipment and intelligent terminal | |
KR20170015338A (en) | Method for creating grade discrimination standard in granular object appearance grade discrimination device | |
CN112150439A (en) | Automatic sorting equipment and sorting method for injection molding parts | |
CN111805541A (en) | Deep learning-based traditional Chinese medicine decoction piece cleaning and selecting device and cleaning and selecting method | |
JP2016080583A (en) | Agricultural product determination device | |
EP3594682A1 (en) | Leather inspection equipment | |
KR20230062754A (en) | Automatic ginseng classification solution based on AI | |
CN206854125U (en) | A kind of sorting equipment for being used to improve logistics sort efficiency | |
CN209550027U (en) | Disposable paper urine pants intelligent sorting system based on computer vision | |
Cunha et al. | Computer vision and robotic manipulation for automated feeding of cork drillers | |
CN110745441A (en) | Logistics product classification and identification method based on image target detection |