• Spatial Information Research
• /
• 제10권2호
• /
• pp.331-343
• /
• 2002

최근 위성 영상정보를 이용하는 활용 연구의 중요성이 강조되면서 다중 분해능을 갖는 위성 영상정보의 통합적인 적용에 대한 관심이 증가하고 있다. 본 연구에서는 광역적인 분석에서 다중 분해능 위성 영상정보의 광역적 통합 분석에 대한 적용 가능성을 살펴보기 위하여 경기도 남양주시에 대한 Landsat 7 ETM+ 다중 분광 영상정보와 KOMPSAT EOC 영상정보에 대한 화소 값(DN) 분석 및 다중 분해능 영상 분류를 수행한 뒤에, 분류 결과를 같은 지역에 대하여 구축된 토지이용현황 주제도와 대비 분석하고자 하였다. 다중 분해능 영상 분류로 나타난 주요 결과로는 단일 분해능 영상정보 분류결과에 비하여 도로 정보와 같은 선형적인 요소의 추출이 용이한 것으로 나타났다. 한편 연구 지역내 주요 도로에 대한 영향권 설정 분석 또는 거리 질의 방법을 이용하여 수행된 영상 분류 결과와 토지이용현황 주제정보의 대비 분석 결과는 두 가지 정보가 유사한 패턴을 보이므로, 다중 분해능 영상정보의 분류 결과는 도시 환경분석문제에도 효과적으로 이용될 수 있을 것으로 생각된다.

• 한국조경학회지
• /
• 제26권2호
• /
• pp.240-250
• /
• 1998

This study is to have attempted to analyze the characteristics of the change in forest landscape pattern of Seoul for 18 years by grasping it through satellite image data on the forest area in Seoul where a rapid change according urbanization and industrialization is going on. On the basis of Landsat MSS data- satellite image data, this writer analyzed the change in the number and size of patch and the mean edge length of each forest land, and the index of patch shape by each year from a landscape -ecological point of view. The results are as follows; First, in the pattern change of the forest patch of Seoul, the highest patch fragmentation area is the forest of the Yangchon-gu district where is decreasing it forest area by 654ha, 511ha, 495ha, 402ha each year from its total size of 742ha in 1979. Second, the change tendency shows that the average forest size decreased at 552.58ha in 1983, 435.03ha in 1988, 396.23ha in 1992, and 379.96ha in 1996. And analysis showed that even in the number of patches, the forest fragmentation phenomenon was presenting by the increase of development disturbance. Third, the mean edge by year was longest at 23,385m in 1979, but it is decreasing continuously. This shows the regular and artificial uniformity of forest landscape by disturbance-effect increase of the built-up development and shows low portion against edge effect by the time-series change like 1979>1983>198>1992>1996. Finally, in the analysis of a shape index indicated by ratio of size and edge, total averages were 2.56, 2.33, 2.17, 2.14, 2.14 each year, so that it is considered that the disturbance and ecological health status against forest landscape can be grasped according to being examined as 1979>1983>1988>1992, 1996 by the time-series change of the landscape.

• 대한임베디드공학회논문지
• /
• 제19권1호
• /
• pp.47-55
• /
• 2024

We spend a lot of time in indoor space, and the space has a huge impact on our lives. Interior design plays a significant role to make an indoor space attractive and functional. However, it should consider a lot of complex elements such as color, pattern, and material etc. With the increasing demand for interior design, there is a growing need for technologies that analyze these design elements accurately and efficiently. To address this need, this study suggests a deep learning-based design analysis system. The proposed system consists of a semantic segmentation model that classifies spatial components and an image classification model that classifies attributes such as color, pattern, and material from the segmented components. Semantic segmentation model was trained using a dataset of 30000 personal indoor interior images collected for research, and during inference, the model separate the input image pixel into 34 categories. And experiments were conducted with various backbones in order to obtain the optimal performance of the deep learning model for the collected interior dataset. Finally, the model achieved good performance of 89.05% and 0.5768 in terms of accuracy and mean intersection over union (mIoU). In classification part convolutional neural network (CNN) model which has recorded high performance in other image recognition tasks was used. To improve the performance of the classification model we suggests an approach that how to handle data that has data imbalance and vulnerable to light intensity. Using our methods, we achieve satisfactory results in classifying interior design component attributes. In this paper, we propose indoor space design analysis system that automatically analyzes and classifies the attributes of indoor images using a deep learning-based model. This analysis system, used as a core module in the A.I interior recommendation service, can help users pursuing self-interior design to complete their designs more easily and efficiently.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권3호
• /
• pp.205-208
• /
• 2013

일반적으로 이진패턴 변환은 조명 변화에 강인한 특성을 가지므로, 얼굴인식 및 표정인식 분야에 널리 사용되고 있다. 이에, 본 논문에서는 기존의 LDP(Local Directional Pattern)의 텍스처 성분을 개선한 MLDP(Modified LDP) 변환 영상에 2D-PCA(Two-Dimensional Principal Component Analysis) 알고리즘을 결합한 조명변화에 강인한 얼굴인식 방법에 대하여 제안한다. 기존의 LBP(Local Binary Pattern)나 LDP와 같은 이진패턴 변환들이 히스토그램 특징 추출을 위해 주로 사용되는 것과는 다르게, 본 논문에서 제안하는 방법은 MLDP 영상을 2D-PCA 특징추출을 위해 직접 사용한다는 특성을 갖는다. 제안 방법의 성능평가는 PCA(Principal Component Analysis), 2D-PCA 및 가버변환 영상과 LBP를 결합한 알고리즘을 사용하여, 다양한 조명변화 환경에서 구축된 Yale B 및 CMU-PIE 데이터베이스를 이용하여 수행되었다. 실험 결과, MLDP 영상과 2D-PCA를 사용한 제안 방법이 가장 우수한 인식 성능을 보임을 확인하였다.

• Journal of Multimedia Information System
• /
• 제7권2호
• /
• pp.97-106
• /
• 2020

The subjective experience would degrade the current artificial artistic aesthetic analysis. Since Qiong kiln ceramics have a long history and occupy a very important position in ceramic arts, we employed computer-aided technologies to quickly automatically accurately and quantitatively process a large number of Qiong kiln ceramic images and generate the detailed statistical data. Because the color features are simple and significant visual characteristics, the color features of Qiong kiln ceramics are analyzed for the quantitative aesthetics. The Qiong kiln ceramic images are segmented with GrabCut algorithm. Three moments (1st-order, 2nd-order, and 3rd-order) are calculated in two typical color spaces, namely RGB and HSV. The discrimination powers of the color features are analyzed according to various dynasties (Tang Dynasty, Five Dynasties, Song Dynasty) and various utensils (Pot, kettle, bowl), which are helpful to the selection of the discriminant color features among various dynasties and utensils. This paper is helpful to promoting the quantitative aesthetic research of Qiong kiln ceramics and is also conducive to the research on the aesthetics of other ceramics.

• Journal of Information Processing Systems
• /
• 제13권2호
• /
• pp.385-399
• /
• 2017

Nowadays, with the development of signal processing technique, the protection to the integrity and authenticity of images has become a topic of great concern. A blind image authentication technology with high tamper detection accuracy for different common attacks is urgently needed. In this paper, an improved fragile watermarking method based on local binary pattern (LBP) is presented for blind tamper location in images. In this method, a binary watermark is generated by LBP operator which is often utilized in face identification and texture analysis. In order to guarantee the safety of the proposed algorithm, Arnold transform and logistic map are used to scramble the authentication watermark. Then, the least significant bits (LSBs) of original pixels are substituted by the encrypted watermark. Since the authentication data is constructed from the image itself, no original image is needed in tamper detection. The LBP map of watermarked image is compared to the extracted authentication data to determine whether it is tampered or not. In comparison with other state-of-the-art schemes, various experiments prove that the proposed algorithm achieves better performance in forgery detection and location for baleful attacks.

• 한국정보시스템학회지:정보시스템연구
• /
• 제27권3호
• /
• pp.123-140
• /
• 2018

Purpose The purpose of this study is to explore the optimal trading frequency which is useful for stock price prediction by using deep learning for charting image data. We also want to identify the appropriate time for accurate forecasting of stock price when performing pattern analysis. Design/methodology/approach In order to find the optimal trading frequency patterns and forecast timings, this study is performed as follows. First, stock price data is collected using OpenAPI provided by Daishin Securities, and candle chart images are created by data frequency and forecasting time. Second, the patterns are generated by the charting images and the learning is performed using the CNN. Finally, we find the optimal trading frequency patterns and forecasting timings. Findings According to the experiment results, this study confirmed that when the 10 minute frequency data is judged to be a decline pattern at previous 1 tick, the accuracy of predicting the market frequency pattern at which the market decreasing is 76%, which is determined by the optimal frequency pattern. In addition, we confirmed that forecasting of the sales frequency pattern at previous 1 tick shows higher accuracy than previous 2 tick and 3 tick.

• 한국관광식음료학회지:관광식음료경영연구
• /
• 제12권1호
• /
• pp.79-110
• /
• 2001

Tourist Destination is based on tourism attractions. Components of Tourism attraction are included tourism resources, entertainment facilities, transportation, accommodation, infrastructure, assistance facilities & service, hospitality, information facilities & service, and retailing & service. Tourism resources of them is the key to determine destination development pattern, because tourism attraction that attract tourists is based on tourism resources. Therefore, there are need to study what is tourism attraction of destination at the view of tourists and what is destination development pattern based on it to develop tourism attraction that is able appeal tourists. The purpose of this study is to examine what effect of tourism attraction affects destination development pattern. This study defined Haeundae, Kwanganri, Songjung, Taejongdae in Pusan, Korea as research areas. Research data were collected from 300 respondents by a simple random sampling method. A final 284 usable questionaries were used for empirical analysis after data purification process. Reliability and validity of the scale on the tourism attraction, destination image, and facility needs have been evaluated using Cronbach $\alpha$, item-total correlations. This study analyzed the factors of the tourism attraction and destination images. The result obtained that tourism attraction is divided relaxation attraction, local activity attraction, culture . nature attraction and touring circuit attraction, and destination image is divided culture . urban attractiveness, touring attractiveness, local . stay attractiveness, convenience of travel and relativeness for destination investigated. ANOVA and regression (stepwise) were used to test hypotheses. Based on the results of hypotheses testing, major findings of the empirical research are as follow : 1. The tourism attraction and destination image are significantly different, but facility needs are not significantly by destinations (e. g. Haeundae, Kwanganri, Songjung, Taejongdae) . 2. Destination development pattern is a(fact by the tourism attraction in partial. In case of Haeundea, relaxation attraction take effect partially spa, history and marine/spa tourism. 3. The destination development pattern is influenced by the destination image in partial. In case of Kwanganri, the natural . activity attractiveness and urban tourism images have been found as influential factors that affect marine tourism. 4. The destination images are influenced the physical attributes in literature review, but the destination image are taken effect partially the tourism attraction in this study. 5. Destination development pattern are influenced by the tourism attraction and the destination image partially. This research has provided a variety of practical suggestions. Especially, it was suggested that the destination have appeal to tourists by strengthening attraction and improving weakness. Also, we need to specialize destination in same destination development pattern.

• 전기학회논문지
• /
• 제64권7호
• /
• pp.1104-1113
• /
• 2015

In this paper, we propose Two-Dimensional Robust Face Recognition System Realized with the Aid of Facial Symmetry with Illumination Variation. Preprocessing process is carried out to obtain mirror image which means new image rearranged by using difference between light and shade of right and left face based on a vertical axis of original face image. After image preprocessing, high dimensional image data is transformed to low-dimensional feature data through 2-directional and 2-dimensional Principal Component Analysis (2D)2PCA, which is one of dimensional reduction techniques. Polynomial-based Radial Basis Function Neural Network pattern classifier is used for face recognition. While FCM clustering is applied in the hidden layer, connection weights are defined as a linear polynomial function. In addition, the coefficients of linear function are learned through Weighted Least Square Estimation(WLSE). The Structural as well as parametric factors of the proposed classifier are optimized by using Particle Swarm Optimization(PSO). In the experiment, Yale B data is employed in order to confirm the advantage of the proposed methodology designed in the diverse illumination variation

• 대한한의학회지
• /
• 제42권1호
• /
• pp.1-11
• /
• 2021

Objectives: This pilot study aimed to evaluate the agreement between traditional face-to-face Korean medicine (KM) pattern identification and non-face-to-face KM pattern identification using the data from related questionnaires, tongue image, and pulse features in patients with cancer. Methods: From January to June 2020, 16 participants with a cancer diagnosis were recruited at the one Korean medicine hospital. Three experienced Korean medicine doctors independently diagnosed the participants whether they belong to the cold pattern or not, heat pattern or not, deficiency pattern or not, and excess pattern or not. Another researcher collected KM pattern related data using questionnaires including Cold-Heat Pattern Identification (CHPI), tongue image analysis system, and pulse analyzer. Collected KM pattern related data without participants' identifier was provided for the three Korean medicine doctors in random order, and non-face-to-face KM pattern identification was carried out. The kappa value between face-to-face and non-face-to-face pattern identification was calculated. Results: From the face-to-face pattern identification, there were 13/3 cold/non-cold pattern, 4/12 heat/non-heat pattern, 14/2 deficiency/non-deficiency pattern, and 0/16 excess/non-excess pattern participants. In cold/non-cold pattern, kappa value was 0.455 (sensitivity: 0.85, specificity: 0.67, accuracy: 0.81). In heat/non-heat pattern, the kappa value was 0.429 (sensitivity: 0.75, specificity: 0.72, accuracy: 0.75). The kappa value of deficiency/non-deficiency and excess/non-excess pattern was not calculated because of the few participants of non-deficiency, and excess pattern. Conclusions: The agreement between traditional face-to-face pattern identification and non-face-to-face pattern identification seems to be moderate. The non-face-to-face pattern identification using questionnaires, tongue, and pulse features may feasible for the large clinical study.