• Journal of Biosystems Engineering
• /
• 제19권4호
• /
• pp.380-396
• /
• 1994

A personal computer based color machine vision system with video camera and fluorescent lighting system was used to generate images of stationary tobacco leaves. Image processing algorithms were developed to extract both the geometric and the color features of tobacco leaves. Geometric features include area, perimeter, centroid, roundness and complex ratio. Color calibration scheme was developed to convert measured pixel values to the standard color unit using both statistics and artificial neural network algorithm. Improved back propagation algorithm showed less sum of square errors than multiple linear regression. Color features provide not only quality evaluation quantities but the accurate color measurement. Those quality features would be useful in grading tobacco automatically. This system would also be useful in measuring visual features of other agricultural products.

• 축산식품과학과 산업
• /
• 제6권1호
• /
• pp.34-45
• /
• 2017

• 농업과학연구
• /
• 제22권2호
• /
• pp.231-243
• /
• 1995

This paper aims to study regional difference in strawberry farming technology and its causal factors based on the survey of controlled strawberry farmers in three major strawberry cultivating regions, which are Nonsan county of Chungnam Province, Damyang County of Junnam Province and Guchang County of Kyungnam Province. There are differences in variety adoption, packaging and grading method which cause the farming income gap among these regions. Farmers of Guchang County, who adopt new variety Yeobong and packing system, raised highest gross receipts but ranked next to Damyang in terms of net income because of high packing cost. Farmers of Nonsan County earned lowest income because of poor quality and low price in spite of adopting packing cost saving method. Therefore, results of this study shows that successful farming technology depend on whether or not farmers adopt market oriented technology. It is suggested that direction of strawberry farming technology should focus on adopting new varieties which can contribute to increasing farmers' paid price and developing technology of reducing cost such as labor saving and packing machine.

• Journal of the Korean Wood Science and Technology
• /
• 제36권5호
• /
• pp.33-41
• /
• 2008

This study was aimed to develop the knot quantification method to predict bending strength, using x-ray scanner. The bending strength prediction model was proposed in this paper. The model was based on Knot Depth Ratio (KDR) and closely-spaced knot was taken into account. The previous paper reported that KDR is the ratio of the knot and transit zone to the lumber thickness. Even though KDR involves transit zone, it was verified that the ratio of the moment of inertia for knot to gross cross section ($I_k/I_g$) based on KDR was a good predictor for bending strength of lumber. To take closely-spaced knot into account, a projection method was also proposed. This projection method improved the predictive accuracy significantly. It showed coefficient of determinant of 0.65 and root mean square error (RMSE) of 9.17.

• 한국멀티미디어학회논문지
• /
• 제7권4호
• /
• pp.451-458
• /
• 2004

육안에 의한 피혁의 등급 판정 과정은 장시간 시 피로에 의한 일관성 결여로 인해 판정 결과에 대한 신뢰성을 주지 못한다. 따라서 피혁의 품질을 결정하기 위한 객관적인 지표와 이를 기준으로 등급 판정 과정의 자동화가 필요하다. 본 논문에서 적용된 피혁 자동 선별 시스템은 피혁에 대한 정보를 취 득하는 과정과 이들로부터 등급을 판정하는 과정으로 구성된다. 피혁의 품질은 조밀도와 결함의 종류 및 분포도와 같은 피혁의 특성에 의해 결정된다. 본 논문에서는 디지털 카메라에 의해 획득된 흑백 영상으로부터 피혁의 조밀도 및 결함을 추출하여 피혁의 등급을 판정하는 알고리즘을 제안한다. 조밀도는 퓨리에 스펙트럼이 존재하는 영역의 넓이 및 가로, 세로 비율로서 계산된다. 그리고 결함은 전처리 과정을 거친 영상으로부터 검색 윈도우를 사용하여 윈도우에 해당하는 픽셀들의 히스토그램 분포의 특징에 의해서 검출된다. 피혁 전체에 대한 특성들은 피혁의 등급을 판정하는 지표로 사용되며 다른 분야에서의 인간의 시각 검사를 대체 할 수 있으리라 판단된다.

• Journal of Biosystems Engineering
• /
• 제37권3호
• /
• pp.177-183
• /
• 2012

Purpose: In near infrared spectroscopy, interactance configuration of a light source and a spectrometer probe can provide more information regarding fruit internal attributes, compared to reflectance and transmittance configuration. However, there is no through study on the parameters of interactance measurement setup. The objective of this study was to investigate the effect of the parameters on the estimation of soluble solids content (SSC) and firmness of muskmelons. Methods: Melon samples were taken from greenhouses at three different harvesting seasons. The prediction models were developed at three distances of 2, 5, and 8 cm between the light source and the spectrometer probe, three measurement points of 2, 3, and 6 evenly distributed on each sample, and different number of fruit samples for calibration models. The performance of the models was compared. Results: In the test at the three distances, the best results were found at a 5 cm distance. The coefficient of determination ($R_{cv}{^2}$) values of the cross-validation were 0.717 (standard error of prediction, SEP=$1.16^{\circ}Brix$) and 0.504 (SEP=4.31 N) for the estimation of SSC and firmness, respectively. The minimum measurement point required to fully represent the spectral characteristics of each fruit sample was 3. The highest $R_{cv}{^2}$ values were 0.736 (SEP=$0.87^{\circ}Brix$) and 0.644 (SEP=4.16 N) for the estimation of SSC and firmness, respectively. The performance of the models began to be saturated when 60 fruit samples were used for developing calibration models. The highest $R_{cv}{^2}$ of 0.713 (SEP=$0.88^{\circ}Brix$) and 0.750 (SEP=3.30 N) for the estimation of SSC and firmness, respectively, were achieved. Conclusions: The performance of the prediction models was quite different according to the condition of interactance measurement setup. In designing a fruit grading machine with interactance configuration, the parameters for interactance measurement setup should be chosen carefully.

• 한국컴퓨터정보학회논문지
• /
• 제20권3호
• /
• pp.47-56
• /
• 2015

흥미 있는 웹페이지의 자동화된 탐색은 다양한 응용 분야에 활용될 수 있다. 웹페이지에 대한 사용자의 흥미는 판단하는 것은 사용자의 행동을 관찰함으로 자동화가 가능하다. 흥미 있는 웹페이지를 구분하는 작업은 판별 문제에 속하며, 우리는 실증을 위해 화이트 박스의 학습 방법(로짓회귀분석, 지지기반학습)을 선택한다. 실험 결과는 다음을 나타내었다. (1) 고정효과 로짓회귀분석, polynomial 과 radial 커널을 이용한 고정효과 지지기반학습은 선형 커널보다 높은 성능을 보였다. (2) 개인화가 모델 성능을 향상시킴에 있어 주요한 이슈이다. (3) 사용자에게 웹페이지에 대항 흥미를 물을 때, 구간은 단순히 예/아니 도 충분할 수 있다. (4) 웹페이지에 머문 기간이 매초 증가할 때마다 성공확률은 1.004배 증가하며, 하지만 스크롤바 클릭 수 (p=0.56) 와 마우스 클릭 수 (p=0.36) 지표는 흥미와 통계적으로 유의한 관계를 가지지 않았다.

• 임산에너지
• /
• 제25권2호
• /
• pp.49-54
• /
• 2006

국산 침엽수재의 구조재 활용에 필요한 등급구분을 위해 소나무, 잣나무와 낙엽송 $2{\times}6"$ 부재에 대해 초음파를 이용한 비파괴 방법을 적용하였다. 정적 탄성계수와 초음파 시험에 의한 동적 탄성계수의 상관관계를 나타내는 k-factor는 소나무의 경우 1.0602, 잣나무 1.0013, 낙엽송 1.2320로 나타났다. k-factor를 적용할 경우 비파괴방법에 의한 동적 탄성계수 측정에 의해 침엽수 구조부재 등급구분이 가능할 것으로 판단되었다. 기계응력 등급구분에서 소나무는 E9 이상의 등급이 전체의 76%인 반면 잣나무는 E7 이상의 등급이 전체의 85%, 낙엽송은 E11 이상의 등급이 68% 분포하였다. 정적 탄성계수와 휨파괴계수(MOR)의 상관관계도 비교적 높게 나타나 이를 동적 탄성계수로부터 추정한 k-factor와 연계할 경우 초음파 비파괴 등급구분 방법에 의해 국산 침엽수재의 휨강도 성능평가가 가능할 것으로 판단되었다.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2004년도 학술.기술논문발표회
• /
• pp.71-74
• /
• 2004

Recently, with the wide shortage of natural sand resources, it has been increasingly used the crushed sand. rushed sand is made by the process of crushing the rocks artificially, which has different particle properties compared with that of natural sand. Because such different panicle properties of crushed sand results in an undesirable effects of concrete. improvement technology for crushed sand particle properties like grain shape and fine particle needed during the manufacturing process. In this paper, improvement technology of grain shape and fine particle is reported. According to test results, adequate investment for manufacturing facilities like impact crusher and abrasion test machine is required to meet the advanced grain shape and grading of crushed sand. Based on the investigation of test result, mixing of natural land and crushed sand with given proportion can achieve the improvement of grain shape. For improving excessive fine panicle contents. current manufacturing system also can enhance the existing technology for fine particle without additional investment. It can be concluded that adequate investment and research can improve the quality of crushed sand.

• 드라이브 ㆍ 컨트롤
• /
• 제12권2호
• /
• pp.27-33
• /
• 2015

Excavators are versatile earthmoving equipment that are used in civil engineering, hydraulic engineering, grading and landscaping, pipeline construction and mining. Effective operator training is essential to ensure safe and efficient operating of the machine. The virtual reality excavator based on simulation using conventional large size monitors is limited by the inability to provide a realistic real world training experience. We proposed a flexible observation method with a head tracking system to improve user feeling and sensation when operating a virtual reality excavator. First, an excavation simulator is designed by combining an excavator SimMechanics model and the virtual world. Second, a head mounted display (HMD) device is presented to replace the cumbersome large screens. Moreover, an Inertial Measurement Unit (IMU) sensor is mounted to the HMD for tracking the movement of the operator's head. These signals consequently change the virtual viewpoint of the virtual reality excavator. Simulation results were used to analyze the performance of the proposed system.