• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.215-218
• /
• 2007

이 논문은 고해상도 Quickbird 영상을 이용하여 세부레벨계획을 위한 토지피복분류를 수행하였으며 고해상도 영상을 이용한 토지피복분류를 위하여 객체기반분류와 ISODATA 기법을 적용하였다. 객체기반분류는 eCognition 소프트웨어를 사용하였으며 ISODATA 기법의 토지피복분류 결과와 비교분석을 수행하였다. 연구 대상지역은 인도의 Sukkalampatti이라 하는 작은 유역을 대상으로 연구를 진행하였다. 고해상도 영상의 사용으로 토지피복분류에 있어서 공간 해상도에 따른 토지피복의 세부레벨분류 정확도를 향상 시킬 수 있는 이점을 확인 할 수 있으며 또한, 객체기반분류와 ISODATA 기법의 분류 결과는 eCognition을 사용한 객체기반 토지피복분류결과가 ISODATA의 픽셀기반의 분류방법보다 높은 정확도를 보였다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.2 no.1
• /
• pp.73-79
• /
• 2009

Analyze semantic of files recorded in the user's computer file system based on C++ program language which pursue modularization program and object-oriented programming language. And this refers to it, it design that clustering semantic of filename with thesaurus for user convenience. WTPM makes User Write Files into Cluster with thesaurus semantic structure and reserved words. WTPM process has designed for Icon file's display Mashup structure and implemented by automation algorithm of classification.

• Journal of Multimedia Information System
• /
• v.1 no.2
• /
• pp.119-126
• /
• 2014

We propose a bicycle detection system riding on people based on modified projected local binary pattern(PLBP) for vision based intelligent vehicles. Projection method has robustness for rotation invariant and reducing dimensionality for original image. The features of Local binary pattern(LBP) are fast to compute and simple to implement for object recognition and texture classification area. Moreover, We use uniform pattern to remove the noise. This paper suggests that modified LBP method and projection vector having different weighting values according to the local shape and area in the image. Also our system maintains the simplicity of evaluation of traditional formulation while being more discriminative. Our experimental results show that a bicycle and motorcycle riding on people detection system based on proposed PLBP features achieve higher detection accuracy rate than traditional features.

• Korean Journal of Computational Design and Engineering
• /
• v.1 no.2
• /
• pp.163-172
• /
• 1996

One of the design methods which emulates the engineering design process, the configuration design methodology, is applied to the design process of paper feeding mechanism which handles paper in a laser beam printer. Components of a paper feeding mechanism should be designed not to incur vibration to paper and to keep paper flat when transferring. Hybrid knowledge representation is used where the design methods and experience is represented as rules, design parts are represented as objects according to the functions within the printer feeding mechanisms Reliability of design can be improved by referencing various design constraints concurrently.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.72-75
• /
• 2008

Image segmentation techniques becoming increasingly important in the field of remote sensing image analysis in areas such as object oriented image classification. This paper presents a new method for image segmentation in High Resolution Remote Sensing Image based on Seeded Region Growing (SRG) and Edge Information. Firstly, multi-spectral edge detection was done using an entropy operator in pan-sharpened QuickBird imagery. Then, the initial seeds were automatically selected from the obtained edge map. After automatic selection of significant seeds, an initial segmentation was achieved by applying SRG. Finally the region merging process, using region adjacency graph (RAG), was carried out to get the final segmentation result. Experimental results demonstrated that the proposed method has good potential for application in the segmentation of high resolution satellite images.

• Proceedings of the KSRS Conference
• /
• 2008.03a
• /
• pp.224-230
• /
• 2008

본 연구는 산림 내 임상을 구획하기 위해 고해상도 IKONOS 위성영상을 객체 지향기반으로 분할 및 분류하였다. 영상분할 시 분광정보와 공간정보를 동시에 이용하여 모양이나 분광정보에 있어서 동질한 영역이라고 정의되는 영상객체를 생성하였다. 분할된 영상을 분류계급(class)으로 분류하기 위하여 NDVI와 경사, 방위, 고도 등 지형인자를 새로운 레이어로 추가시키고, 분류개념을 형성하기 위하여 퍼지 규칙을 사용하였다. 영상의 획득시기가 5월초인 점을 감안하여 NDVI는 0.2, 경사 $^{\circ}5^{\circ}$ 그리고 고도 130m를 기준으로 산림과 비산림지역을 분류할 수 있었고, 지형인자에 영향을 많이 받는 굴참나무와 신갈나무 또한 효율적으로 분류할 수 있었다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.1
• /
• pp.73-81
• /
• 2010

In recent years, there have been diverse researches and utilizations of creating geo-spatial information with high resolution satellite images. However thematic maps made with middle or low resolution satellite images have low location accuracy and precision of thematic information. This study set out to propose a method of making a precision thematic map with high resolution satellite images by examining the conversion from the conventional method based on middle or low resolution satellite images to the automatic method based on high resolution satellite images of GSD 1m or lower, extracting thematic information of middle or large scale of 1/5,000 or lower, and analyzing its accuracy. Seven classification classes were categorized according to the object-oriented classification in order to automatically extract thematic information with high resolution satellite images. And the classification results were compared and analyzed with the old middle scale land cover map and 1/1000 digital map.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.1-9
• /
• 2022

UML class diagrams are used to visualize the static aspects of a software system and are involved from analysis and design to documentation and testing. Software modeling using class diagrams is essential for software development, but it may be not an easy activity for inexperienced modelers. The modeling productivity could be improved with a dataset of class diagrams which are classified by domain categories. To this end, this paper provides a classification method for a dataset of class diagram images. First, real class diagrams are selected from collected images. Then, class names are extracted from the real class diagram images and the class diagram images are classified according to domain categories. The proposed classification model has achieved 100.00%, 95.59%, 97.74%, and 97.77% in precision, recall, F1-score, and accuracy, respectively. The accuracy scores for the domain categorization are distributed between 81.1% and 95.2%. Although the number of class diagram images in the experiment is not large enough, the experimental results indicate that it is worth considering the proposed approach to class diagram image classification.

• Journal of Environmental Impact Assessment
• /
• v.22 no.2
• /
• pp.147-156
• /
• 2013

Myanmar(Burma) has been preserved valuable environmental resources because of its political isolation. But recently, Myanmar has moved a capital city(Naypyidaw) at central forest area and it has been urbanized radically since 2005. In this paper, we built multi-temporal land cover map from Landsat images of 1970s to 2012 with ENVI 4.5 software. For a broad approach, administrative district Yamethin which includes Naypyidaw is classified into 3 classes and with only Naypyidaw region is classified with 4-5 classes to analyse specific changes. And with forest cover extracted by Object Oriented Classification, we evaluated forest fragmentation before and after the development using Patch Analyst(FRAGSTATs 3.3) at Yamethin area. For Yamethin area, there were significant forest cover change, 51% in 1999 to 48% in 2012, and for Naypyidaw area, 67% in 1999 to 57% in 2012 respectively. Also landscape indices resulted from Patch Analyst concluded that the total edge, edge density and mean shaped index of forest patches increased and total core area is decreased. It is attributed from land cover change with urbanization and agricultural land expansion.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2007.06a
• /
• pp.289-292
• /
• 2007

객체기반 영상분류를 위한 영상분할에 있어서 중요한 요소로는 분할축척(Scale), 분광 정보(Color), 공간 정보(Shape) 등이 있으며 공간 정보에 해당하는 공간 변수는 평활도(Smoothness)와 조밀도(Compactness)가 있다. 이들 가중치의 선택이 최종적으로 객체기반 영상분류의 결과를 좌우하게 된다. 본 연구는 객체기반 영상분류의 준비 과정이라 할 수 있는 영상분할에 있어서 다양한 가중치를 적용을 통하여 영상을 분할하였다. 영상분할을 위해 적용한 가중치는 10, 20, 30의 분할축척(Scale)과 분광 정보(Color)와 공간 정보(Shape)간의 가중치 조합, 공간 변수인 평활도(Smoothness)와 조밀도(Compactness)간의 가중치 조합을 사용하였다. 각 가중치 조합을 통하여 분할된 영상의 분석은 Moran's I 와 객체 내부 분산(Intrasegment Variance)을 이용하여 분석하였다. 각 객체간의 상관관계 분석을 위하여 Moran's I를 계산하였으며 분류된 지역의 동질성을 분석하기 위하여 객체 면적을 고려한 객체 내부 분산(Intrasegment Variance)값을 계산하였다. Moran's I 가 낮은 값을 가질수록 객체 간의 공간상관관계가 낮아지므로 이웃 객체간의 이질성은 높아지며 객체 내부 분산(Intrasegment Variance)이 낮은 값을 가질수록 지역간의 동질성은 높아지게 된다. Moran's I 와 객체 내부 분산(Intrasegment Variance)의 조합을 통하여 객체기반 영상분류 시 가장 높은 분류 정확도가 예상되는 밴드별 영상분할 가중치를 얻을 수 있다.