• 한국컴퓨터산업학회논문지
• /
• 제2권3호
• /
• pp.265-274
• /
• 2001

본 논문에서는 얼굴의 특징 영역에 근거하여 얼굴을 검색할 수 있는 내용기반의 얼굴 검색 시스템을 제안한다. 질의를 위해 이름이나 주민등록번호와 같은 키워드를 사용하는 대신에, 제안한 시스템은 시각적 질의로서 얼굴 영상을 사용한다. 이를 위해, 얼굴 구성 요소를 포함하는 특징 영역을 HSl 칼라 모델이 제공하는 칼라 정보와 Wavelet 변환이 제공하는 에지 정보를 이용하여 추출한 후, 신경망을 통하여 분류ㆍ검색한다. 제안한 검색 시스템은 Oracle DBMS를 사용하여 클라이언트/서버 환경으로 구축되었다. 150개의 다양한 얼굴 영상으로 실험한 결과, 약 88.3%의 검색율을 보였다.

• Animal cells and systems
• /
• 제13권1호
• /
• pp.83-89
• /
• 2009

Investigations were made on population biology of Pampus echinogaster (Basilewsky, 1855) in the coastal areas of Korea, Yellow Sea, between August 2005 and July 2006. Population structure was not significantly different between male and females. Monthly variation of gonadosomatic index (GSI) of both sexes defined spawning period extending from March through July. A similar pattern was also observed in change at maturity stages. For males and females GSI was positively correlated with hepatosomatic index (HSI). Fecundity, ranging from 41,250 to 103,610 eggs, was related to body size, indicating that body size is the useful determinant of fecundity. The sexual maturity ($L_{50}$) was estimated as 14.98 cm TL for males and 19.32 cm TL for females. Parameters of growth estimated by the modified von Bertalanffy growth function model showed that the values of $L_{\infty}$ and K for combined data were 39.12 cm TL and 0.65 $yr^{-1}$. The growth performance index of this study (2.75) was higher than that of the previous study (2.45). This difference could be attributed to sampling method. The recruitment patterns indicated one normally distributed group. Percentage of the recruitment was 51.04% in the spawning season and the highest in August (19.78%).

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.276-282
• /
• 2015

This paper proposes a SMD (surface mounting device) classification method for the PCB assembly inspection machines. The package types of SMD components should be classified to create the job program of the inspection machine. In order to reduce the creation time of job program, we developed the automatic classification algorithm for the SMD packages. We identified the chip-type packages by color and edge distribution of the images. The input images are transformed into the HSI color model, and the binarized histroms are extracted for H and S spaces. Also the edges are extracted from the binarized image, and quantized histograms are obtained for horizontal and vertical direction. The neural network is then applied to classify the package types from the histogram inputs. The experimental results are presented to verify the usefulness of the proposed method.

• 한국물환경학회지
• /
• 제33권3호
• /
• pp.311-325
• /
• 2017

Habitat suitability index (HSI) of 17 benthic macroinvertebrate taxa, which were lotic insects of generic category except Potamanthidae in mayfly, was developed for three physical habitat factors (current velocity, water depth and substrate) based on an ecological monitoring in a Korean stream (Gapyeong). Weibull model was used as a probability density function to analyze the distribution of individual abundance related with physical factors, which showed it was so available. Number of species and total individual abundance increased along with the increase of current velocity and the mean diameter of substrate, and decreased along with the increase of water depth. Most taxa showed a clear preference for a fast current velocity, shallow water depth and coarse substrate except Ephemera, Potamanthidae (mayfly), and Plectrocnemia (caddisfly) which were rheophobic, potamophilic and lithophobious. Based on the canonical correspondence analysis, the relative importance of each factor was determined as follows: current velocity > substrate > water depth.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2016년도 학술발표회
• /
• pp.24-28
• /
• 2016

댐의 발전방류는 댐 하류의 하천에 비정상성이 큰 흐름을 발생시킨다. 이와 같은 흐름은 하류 하천의 수심 및 유속 조건을 급격하게 변화시키게 되어 어류 물리서식처에 큰 영향을 끼치게 된다. 또한 갑작스런 유량의 상승은 어류를 하류로 강제로 이동시키며, 빠른 수위의 하강은 어류를 하안에 고립되게 하여 죽음을 초래하게 된다. 발전방류가 어류 물리서식처에 미치는 영향을 평가한 기존의 연구는 대부분 흐름계산을 위하여 준정류 모형을 사용하였다. 하지만 준정류 모형은 발전방류와 같은 비정상성이 큰 흐름에 대하여 적절히 모의하지 못하는 한계가 있다. 본 연구의 목적은 2차원 부정류 모의가 가능한 River2D 모형을 이용하여 댐 하류 하천에서의 발전방류가 어류 물리서식처에 미치는 영향을 분석하는 것이다. 연구 대상지역은 괴산댐 하류 지점인 수전교부터 대수보까지 2.3 km 구간이다. 서식처모형은 피라미에 대한 HSI 모형을 사용하였다. 복합서식처 적합도 지수, 하상전단응력을 모의하였으며 소와 여울의 지형조건에서 발전방류가 위의 인자들에 미치는 영향에 대하여 분석하였다. 또한 발전방류량이 발생하였을 때 기저유량의 조건에 따라 어류 물리서식처에 미치는 영향에 대하여 분석하였다.

• International Journal of Computer Science & Network Security
• /
• 제21권1호
• /
• pp.40-48
• /
• 2021

Content-Based Image Retrieval (CBIR) system plays a vital role to retrieve the relevant images as per the user perception from the huge database is a challenging task. Images are represented is to employ a combination of low-level features as per their visual content to form a feature vector. To reduce the search time of a large database while retrieving images, a novel image retrieval technique based on feature dimensionality reduction is being proposed with the exploit of metaheuristic optimization techniques based on Genetic Algorithm (GA), Extended Binary Cuckoo Search (EBCS) and Whale Optimization Algorithm (WOA). Each image in the database is indexed using a feature vector comprising of fuzzified based color histogram descriptor for color and Median binary pattern were derived in the color space from HSI for texture feature variants respectively. Finally, results are being compared in terms of Precision, Recall, F-measure, Accuracy, and error rate with benchmark classification algorithms (Linear discriminant analysis, CatBoost, Extra Trees, Random Forest, Naive Bayes, light gradient boosting, Extreme gradient boosting, k-NN, and Ridge) to validate the efficiency of the proposed approach. Finally, a ranking of the techniques using TOPSIS has been considered choosing the best feature selection technique based on different model parameters.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2017년도 춘계공동학술대회
• /
• pp.44-44
• /
• 2017

The objective of this study was to evaluate firmness, and sweetness index (SI) of tomatoes (Lycopersicum esculentum) by using hyperspectral imaging (HSI) in the range of 1000-1400 nm. The mean spectra of the 95 matured tomato samples were extracted from the hyperspectral images, and the reference firmness and sweetness index of the same sample were measured and calibrated with their corresponding spectral data by partial least squares (PLS) regression with different preprocessing method. The results showed that the regression model developed by PLS regression based on Savitzky-Golay (S-G) second-derivative preprocessed spectra resulted in better performance for firmness, and SI of tomatoes compared to models developed by other preprocessing methods, with correlation coefficients (rpred) of 0.82, and 0.74 with standard error of prediction (SEP) of 0.86 N, and 0.63 respectively. Then, the feature wavelengths were identified using model-based variable selection method, i.e., variable important in projection (VIP), resulting from the PLS regression analyses and finally chemical images were derived by applying the respective regression coefficient on the spectral image in a pixel-wise manner. The resulting chemical images provided detailed information on firmness, and sweetness index (SI) of tomatoes. Therefore, these research demonstrated that HIS technique has a potential for rapid and non-destructive evaluation of the firmness and sweetness index of tomatoes.

• 환경영향평가
• /
• 제22권3호
• /
• pp.277-290
• /
• 2013

This study was carried out to propose the new procedure to apply Habitat Evaluation Procedure(HEP) of target species using delphi technique, which is suitable to develop endangered species with few researches and ecological knowledges. To identify habitat quality of specific species in development project site, we can develop habitat model and create habitat suitability maps. In this study, we select the Common Kestrel(Falco tinnunculus) as target species in four areas(Paju, Siheung, Ansan, Hwaseong) which is located near the Seoul metropolitan area. The Delphi technique was selected to get the reliable information on the species and habitats requirements. Through the delphi approach, seven habitat components were determined as suitable variables for the Common Kestrel: density($n/km^2$) of small mammals, area($km^2$) of bare-grounds, pasturelands and riparian, and open area(%), spatial distribution and area of croplands, landscape diversity, breeding sites(tall trees, cliffs, high-rise buildings), and the length of shelf. Habitat variables used in this model were classified into two categories: % of suitable land-cover type(open areas, croplands, pasturelands, wetlands, and baregrounds) and the quality of feeding sites(within 250m from edges of woodlands). Habitat quality of the Common Kestrel was assessed against occurred sites derived from the nationwide survey. Predicted habitat suitability map were closely related to the observed sites of the endangered avian species in the study areas. With the habitat suitability map of the Common Kestrel, we assess the environmental impacts with habitat loss after development project in environmental impact assessment.

• 한국정보전자통신기술학회논문지
• /
• 제2권3호
• /
• pp.79-86
• /
• 2009

본 논문은 피부색 요소의 유클리디안거리를 계산 얼굴영역을 추출하고 얼굴의 특징요소를 추출하는 방법을 제안하였다. 제안한 알고리즘은 조명보정과 얼굴 검출 과정으로구성되었다. 조명보정 과정에서는 조명변화에 대한 보정기능을 수행한다. 얼굴 검출 과정은 20개의 피부색 표본영상에서 색상과 채도를 특징벡터로 사용, 입력영상과의 유클리디안 거리를 구하여 피부색 영역을 추출하였다. 추출된 얼굴 후보영역에서 CMY칼라 모델 C공간에서 눈을 검출 하였고, YIQ 칼라 모델 Q공간에서 입을 검출하였다. 추출된 얼굴 후보영역에서 일반적인 얼굴에 대한 지식을 기반으로 얼굴 영역을 검출하였다. 입력받은 40개의 정면 칼라 영상으로 실험한 결과 100%의 얼굴 검출율을 보였다.

• 한국수자원학회논문집
• /
• 제52권spc2호
• /
• pp.823-833
• /
• 2019

This study presents the impact of natural flow patterns on downstream fish habitat and economic outcomes in the Dal Stream, Korea. The study reach is 3.35 km long, located downstream form the Goesan Dam. To assess such impact, this study performed physical habitat simulations. The River2D model was used for the computation of the flow and the HSI model for the habitat simulation. Two physical habitat variables, flow depth and velocity, were used. The Zacco platypus, Zacco temminckii, Coreoleuciscus splendidus, and Opsariichthys bidens were selected as the target species in the study area. Using the building block approach (BBA), the scenarios for the hydropeaking mitigation were presented. Scenario 1 and scenario 2 were proposed by using the magnitude - duration concept and averaged the hydrologic data over the each month, respectively. Simulation results indicated that the scenarios effects significantly increased by about 18.6% for the weighted usable area (WUA). In addition, hydroelectric power benefits with both scenarios were investigated. It was revealed that the change of storing and releasing water decreased by about 27% for hydroelectric power benefits. In order to increase economic benefits, the scenario was modified with the discharges corresponding to the hydropeaking condition except the flood season. As a result, the hydroelectric power benefits were almost the same, however the aquatic habitat for the target species increased by about 5%. The change of dam re-operations through natural flow patterns provides an opportunity to minimize environmental and economic benefits in order to balance water management.