• Journal of Biosystems Engineering
• /
• 제20권4호
• /
• pp.376-382
• /
• 1995

This study was intended to develop more reliable fruit sorting algorithm regardless of the feeding positions of fruits by using the neural network in which various information could be included as input data. Specific objectives of this study were to select proper input units in the neural network by investigating the features of input image, to analyze the sorting accuracy of the algorithm depending on the feeding positions of Fuji apple and to evaluate the performance of the algorithm for practical usage. the average value in color grading accuracy was 90%. Based on the computing time required for color grading, the maximum sorting capacity was estimated to approximately 10, 800 apples per hours. Finally, it is concluded that the neuro-net based color sorting algorithm developed in this study has feasibility for practical usage.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.231-234
• /
• 2003

This paper describes the structure, operation, image processing, and decision making techniques of a color machine vision system designed for the automatic sorting of soybeans. The system consists of feeder, conveyor belt, line-scan camera, lights. ejector, and a PC Unlike manufactured goods, agricultural products including soybeans have quite uneven features. The criteria for sorting good and bad beans also vary depending on inspectors. We tackle these problem by letting the system learn the inspecting parameters from good samples selected manually by a machine user before running the system for sorting. Real-time processing has another importance In the design. Four parallel DSPs are employed to increase the processing speed. When the designed system was tested with real soybeans and the result was successful.

• Journal of Biosystems Engineering
• /
• 제32권2호
• /
• pp.130-135
• /
• 2007

An on-line real time grading and sorting system for dried oak mushrooms was developed for on-site application. Quality grades of the mushrooms were determined according to an industrial specification. Three dimensional visual quality features were used for the grading. A progressive color computer vision system with white LED illumination was implemented to develop an algorithm to extract external quality patterns of the dried oak mushrooms. Cap (top) and gil (stem) surface images were acquired sequentially and side image was obtained using mirror. Algorithms for extracting size, roundness, pattern and color of the cap, thickness, color of the gil and amount of rolled edge of the dried mushroom were developed. Utilizing those quality factors normal and abnormal ones were classified and normal mushrooms were further classified into 30 different grades. The sorting device was developed using microprocessor controlled electro-pneumatic system with stainless buckets. Grading accuracy was around 97% and processing time was 0.4 s in average.

• Journal of Biosystems Engineering
• /
• 제26권3호
• /
• pp.279-286
• /
• 2001

The purpose of this study were to organize a sorting system, to develop an algorithm of image processing for the shape sorting, and to finally develop a scientific and objective shape sorting system of Korean Red-Ginseng for mechanization of the shape sorting. The results of this study are followed. 1. The shape sorting system of Korean Red-Ginseng consists of a control computer, a color CCD camera(WV-CP4110) for image processing, an image processing board(DT3153), and an image acquisition unit. 2. Many image processing skill, such as sliding, stretching, threshold, binary and D$\sub$t/ were used to analyze the shape sorting factors of Korean Red-ginseng. 3. The sorting accuracy of the shape sorting system for the Korean Red-Ginseng was 74.7%. It is 21.1% lower than that of human inspector. Although the system has low accuracy, using more cameras may improve its sorting accuracy.

• Agricultural and Biosystems Engineering
• /
• 제1권2호
• /
• pp.100-105
• /
• 2000

Quality sorting of cut flowers is very essential to increase the value of products. There are many factors that determine the quality of cut flowers such as length, thickness, and straightness of stem, and color and maturity of bud. Among these factors, the straightness of stem and the maturity of bud are generally considered to be more difficult to evaluate. A prototype grading and sorting machine for cut flowers was developed and tested for a rose variety. The machine consisted of a chain-drive feed mechanism, a pneumatic discharge system, and a grading system utilizing color image processing and neural network. Artificial neural network algorithm was utilized to grade cut roses based on the straightness of stem and maturity of bud. Test results showed 89% agreement with human expert for the straightness of stem and 90% agreement for the maturity of bud. Average processing time for evaluating straightness of the stem and maturity of the bud were 1.01 and 0.44 second, respectively. Application of neural network eliminated difficulties in determining criteria of each grade category while maintaining similar level of classification error.

• 자원리싸이클링
• /
• 제28권2호
• /
• pp.23-30
• /
• 2019

폐자동차 범퍼 파쇄물 재활용을 위하여 색채선별법을 도입하였다. 색채선별법은 기존의 비중, 입도 차이에 의한 선별이 어려운 물질을 색상 차이를 이용한 카메라와 영상 분석기법으로 분리하는 선별법이다. 본 연구에서는 반응표면법 중 BBD (Box-Behnken Design)를 적용하여 실험을 계획하고 최적 조건을 도출하였다. 색채민감도, 피드투입량 및 입자크기의 영향을 분석하였으며, 회귀분석과 통계적인 방법에 기초하여 2차 반응 모델을 획득하였다. $R^2$ 및 p-value는 각각 99.56%, < 0.001로 타당하였으며, 추정된 최적조건은 색채민감도 32%, 피드투입 200 kg/h, 입자크기 33 mm 조건에서 94.1%의 회수율이 나올 것으로 예측하였다. 실제 실험을 통한 회수율은 93.8%로 나타나 해당 모델이 적절함을 확인하였다.

• 한국가시화정보학회지
• /
• 제6권2호
• /
• pp.20-27
• /
• 2008

The color sorting technique utilizing the image processing method is very applicable tool to analyze motion of a free-falling object in many agricultural and industrial research fields. In the present study, we have developed an image processing system and algorithm to sort good quality rice grains effectively from the bad ones. The system employs a high speed rate line-scan CCD camera with 2K-pixels and worked with a high speed DSP and FPGA in-line. It can accumulate acquired line-scan image data and visualize each grain image clearly. As a result, we can easily calculate the number of pixels occupied by grain(=grain size), gray level and its correct position by visualizing grain images rapidly.

• 농업과학연구
• /
• 제37권2호
• /
• pp.303-308
• /
• 2010

Surface color is the most important quality factor for the grade evaluation of cherry tomato. Color is one of the representative indicators for the maturity which is closely related to the internal quality of cherry tomato, such as firmness, sugar content, and acidity. This study was carried out to investigate the relationship between surface color and internal quality of cherry tomatoes harvested from both hydroponic and soil culture at different ripening stages. To calculate the color values of cherry tomatoes an automatic color imaging system was constructed. A specially designed image processing algorithm for the color measurement was developed. The color values of L*, a*, b* were calculated from the initial color values of RGB and then compared with the internal quality. Statistical analyses indicated that the internal quality was more highly correlated with the surface color than size of cherry tomatoes. Color image features were also investigated to detect external damage of cherry tomatoes. The value of (R value - R mean value)/R mean value was the most effective image feature for the detection of damaged areas on the surface of cherry tomatoes. The results of this study demonstrated the feasibility of color sorting process as an alternative of the conventional drum type size sorting system for cherry tomato industry.

• Journal of Biosystems Engineering
• /
• 제17권4호
• /
• pp.382-395
• /
• 1992

The surface color of several varieties of apples were expressed quantitatively in xyz chromaticity coordinates. The spectral reflectance of 'Fuji' apples were measured in 400-820 nm range by using a spectrophotometer. Based on the spectrophotometer data and the result of visual sensory test, linear regression models were developed to select wavelengths effective for sorting apples. The models utilized reflectance at single wavelength, and the difference and ratio of the reflectance at two distinct wavelengths. The model which best fitted the visual sensory test data was one utilizing the ratio of the reflectance at 618 nm and 514nm. The correlation coefficient for this model was 0.967. Several other models were also described.

• 자원리싸이클링
• /
• 제17권6호
• /
• pp.43-49
• /
• 2008

본 연구에서는 라인스캔 카메라를 이용한 색도인식 스크랩 선별시스템을 설계 제작하고 제작한 시스템을 이용하여 철스크랩에 혼합되어 있는 Cu 스크랩을 자동으로 분리하는 연구를 수행하였다. 스크랩 자동선별 시스템은 크게 측정부, 이송부 그리고 이젝터로 구분되며 라인스캔 카메라, 광원 및 frame grabber로 구성된 측정부에서 스크랩 표면의 색도를 이메지 프로쎄싱 알고리즘에 의해 인식함으로써. 임의로 지정한 특정한 표면색상의 스크랩만에 에어노즐을 작동케 하여 선별하도록 되어 있다. 본 연구에서는 선별처리의 고속화에 대응하기 위하여 주파수 가변 광원시스템을 제작하여 선별시스템에 적용하였으며, 최적실험조건으로 스크랩 이송속도 25 m/min.에서 철스크랩중에 포함되어 있는 Cu스크랩을 90%이상 인식하여 약 80%의 선별효율을 얻었다.