영상의 1차 모멘트와 기저영상을 이용한 효율적인 얼굴인식

조용현,Cho Yong-Hyun 한국정보처리학회 2006 정보처리학회논문지B Vol.13 No.1

본 논문에서는 영상의 1차 모멘트와 기저영상을 이용한 효율적인 얼굴인식 방법을 제안하였다. 여기서 1차 모멘트는 입력되는 얼굴영상의 중심 좌표를 계산하여 중심 이동하는 전처리로 인식에 불필요한 배경을 배제시킴으로써 인식성능을 개선하기 위함이다. 또한 기저영상은 얼굴의 특징으로 주요성분분석과 고정점 알고리즘의 독립성분분석을 각각 이용하여 추출하였다. 이는 2차와 고차의 통계성을 각각 고려한 중복신호의 제거로 인식성능을 개선하기 위함이다. 제안된 2가지 방법을 각각 64*64 픽셀의 48개(12명*4장) 얼굴영상에 적용하여 city-block, Euclidean, 그리고 negative angle의 3가지 거리 척도를 분류척도로 이용하여 실험하였다. 실험결과, 중심이동의 제안된 방법은 전처리과정을 거치지 않는 기존방법보다 우수한 인식성능이 있음을 확인하였다. 또한 제안된 중심이동의 독립성분분석이 중심이동의 주요성분분석보다 더욱 우수한 인식성능이 있음도 확인하였다. 특히 city-block이 Euclidean이나 negative angle의 거리척도보다 상대적으로 정확하게 유사성을 측정함을 알 수 있었다. This paper presents an efficient face recognition method using both first moment of image and basis images. First moment which is a method for finding centroid of image, is applied to exclude the needless backgrounds in the face recognitions by shifting to the centroid of face image. Basis images which are the face features, are respectively extracted by principal component analysis(PCA) and fixed-point independent component analysis(FP-ICA). This is to improve the recognition performance by excluding the redundancy considering to second- and higher-order statistics of face image. The proposed methods has been applied to the problem for recognizing the 48 face images(12 persons*4 scenes) of 64*64 pixels. The 3 distances such as city-block, Euclidean, negative angle are used as measures when match the probe images to the nearest gallery images. The experimental results show that the proposed methods has a superior recognition performances(speed, rate) than conventional PCA and FP-ICA without preprocessing, the proposed FP-ICA has also better performance than the proposed PCA. The city-block has been relatively achieved more an accurate similarity than Euclidean or negative angle.

소규모 대지의 조경 개선방안에 관한 연구 - 서울시를 사례로 -

조용현,Cho, Yong-Hyeon 한국조경학회 2009 한국조경학회지 Vol.37 No.5

Under the Korea Building Act, anyone planning to build a building or buildings on a site over $200m^2$ must plant plants over a specific area. In large scale development this rule is adhered to well, but such is not the case in small scale development. Therefore, special attention must be given to small scale development. Thus, the purpose of this research is to analyze the current situation and practice of planting at small scale development sites in Seoul, and then suggest policies for improving them. In this study using the data covering Seongbuk-Gu and Gangnam-Gu, which was surveyed in 2002, the current situation and practice of planting at small scale development sites was analyzed. After a questionnaire survey was conducted with government officers and building owners, the same analysis was made. Then the policies for improvement were extracted. The results are as follows: 1. In superordinate planning stage, because the minimum standards are too low, those must be strengthened. Any district plan does not control planting in private building lots. This requests active application of planting in private building lots as a design control measure in district planning. 2. In the building design stage, there are no guidelines. The obligation of building set-back between adjacent buildings by the Korean Building Act produces mass shaded and inferior planting beds. The act also is blocking landscape architects' participation in small scale development. And wall installations deteriorate the streetscape and growth of plants with shading. Therefore guidelines must be made. 3. In each stage of the building permit, the permit for building completion, and maintenance the Korean Building Act is blocking landscape architects' participation in small scale development, so the planting plan is completely handled by nonprofessional persons. Therefore, the act should be amended in order to make way for landscape architects' participation in each stage of the small scale development process.

경관 시뮬레이션을 통한 가로 녹시율 증진방안 및 목표수준 설정 - 서울시를 사례로 -

조용현,Cho Yong-Hyeon 한국조경학회 2006 한국조경학회지 Vol.34 No.2

The purpose of this research is to suggest the planting methods and the reasonable target levels of IGS for promoting green streetscape in Seoul. Using the three dimensional computer simulations, various greening methods were applied to evaluate effectiveness of promoting green streetscape. The results of this study suggest that promoting tree planting on car lane is more effective than on pedestrian side walks. In wide streets, the height of tree has positive effects on promoting green streetscape. In both car lane and pedestrian side walks, the greening effects of tree planting both in zig-zag pattern and in parallel pattern were similarly most high. The width of strip in side strip planting has positive effect on promoting green streetscape. Promoting stratified planting is very effective. Promoting greening wall on pedestrian side walks is more effective than on car lane. Combined the results of IGS survey with the public officials and complex simulations, suggest that the optimal levels of IGS is ranging from 12.0% in alleys to 54.0% in car lanes among arterial roads.

우리나라 보호지역 관리 실태와 개선방안

조용현,이용광,Cho, Yong-Hyeon,Lee, Yong-Kwahng 한국조경학회 2010 한국조경학회지 Vol.38 No.1

This research intends to suggest the ways to improve protected area management in Korea. To this end, the current protected areas appointed in the nation and their management has been examined, and the problems of management have been identified by means of a field research of protected areas and a survey. In addition, a scheme for an integrated management system has been suggested for management improvement, and a management plan guide, as well as after-evaluation guide, has been suggested. The outcome of the research is as follows. First, the protected area management plan is needed since the protected area in our nation is not managed in a proper way after being appointed as such. Second, when making a management plan, a management organization should make a management plan that can attract voluntary participation from stake-holders by means of efficient communications with them. Third, to maintain the management plan in a consistent and systematic way, related policy, law, and institutions should be (re)formulated. Fourth, an organization responsible only for management of protected areas should be established in consideration of management inefficiency due to the overlapped appointment of managing the protected area. Fifth, the management plan guide and after-evaluation guide can be used for effective protected area management. The results of this study are expected to be helpful for creating a management improvement scheme to address the problems related to the protected areas in our nation. But, it is required to review the guides for the management plan and after-evaluation, and consistent and systemic support from the government in such areas as legislation and policy are also in great need.

생태공원

조용현,Cho Yong-Hyeon 한국관개배수위원회 2000 한국관개배수논문집 Vol.7 No.2

조합형 고정점 알고리즘에 의한 신경망 기반 독립성분분석

조용현,Cho, Yong-Hyun 한국정보처리학회 2002 정보처리학회논문지B Vol.9 No.5

본 연구에서는 신경망 기반 독립성분분석의 분리성능을 개선하기 위해 할선법과 모멘트의 조합형 고정점 알고리즘을 제안하였다. 할선법은 독립성분 상호간의 정보를 최소화하는 목적함수의 근을 근사적으로 구함으로써 계산과정을 단순화하여 좀 더 개선된 분리성능을 얻기 위함이고, 모멘트는 계산과정에서 발생하는 발진을 억제하여 보다 빠른 분리속도를 얻기 위함이다. 이렇게 하면 할선법이 가지는 근사성에 따른 우수성과 과거의 속성을 반영하여 발진을 억제하는 모멘트의 우수성을 동시에 살릴 수 있다. 제안된 알고리즘을 $256\times{256}$ 픽셀의 8개 지문과 $512\times{512}$ 픽셀의 10개 영상으로부터 임의의 혼합행렬에 따라 생성된 복합지문과 복합영상을 각각 대상으로 시뮬레이션 한 결과, 뉴우턴법에 기초한 기존의 알고리즘과 할선법만에 기초한 알고리즘보다 각각 우수한 분리률과 빠른 분리속도가 있음을 확인하였다. 또한 할선법의 이용은 뉴우턴법을 이용한 고정점 알고리즘보다 초기값에도 덜 의존하며, 문제의 규모가 커짐에 따른 비현실적인 분리시간도 해결할 수 있음을 확인하였다. This paper proposes an efficient hybrid fixed-point (FP) algorithm for improving performances of the independent component analysis (ICA) based on neural networks. The proposed algorithm is the FP algorithm based on secant method and momentum for ICA. Secant method is applied to improve the separation performance by simplifying the computation process for estimating the root of objective function, which is to minimize the mutual informations of the independent components. The momentum is applied for high-speed convergence by restraining the oscillation if the process of converging to the optimal solution. It can simultaneously achieve a superior properties of the secant method and the momentum. The proposed algorithm has been applied to the composite fingerprints and the images generated by random mixing matrix in the 8 fingerprints of $256\times{256}$-pixel and the 10 images of $512\times{512}$-pixel, respectively. The simulation results show that the proposed algorithm has better performances of the separation speed and rate than those using the FP algorithm based on Newton and secant method. Especially, the secant FP algorithm can be solved the separating performances depending on initial points settings and the nonrealistic learning time for separating the large size images by using the Newton FP algorithm.

녹지량 지표로서 녹시율 개념을 도입한 서울시 가로 환경 특성 분석

조용현,정용문,김광동,Cho Yong-Hyeon,Cheong Yong-Moon,Kim Kwang-Dong 한국조경학회 2006 한국조경학회지 Vol.34 No.1

The purposes of this study are to develop the concept and the measurement method of IGS(Index of Greenness in Streetscape) and to analyze the present condition of street environments through field surveys of IGS in Seoul. IGS is a new index which directly expresses human's perceptions of plants in a street and defined as the area ratio of which leaves of plants occupy in an eye-level view of a person standing on the center line of a street. In practice, IGS can be calculated from a photograph taken from a center point of a street at about 1.5 meter height from the ground with single lens reflex camera equiped with 50mm standard lens. The photograph must have a special composition in a way that the center point of the photograph is positioning at the visual vanishing point of street center line. Then the IGS can be calculated by computing the percentage of the area covered with the plant leaves in the photograph. Types of streets in Seoul were classified according to road functions into 4 types. We performed field surveys and calculated IGSs from 300 sample sites in Seoul. Followings summarize some of study results. The average IGSs for arterial roads, highways, alleys and back streets are 16.91%, 16.33%, 13.97% and 7.50% respectively. The difference of average IGS values between Ginkgo biloba and Platanus occidentalis was relatively large. From observation IGSs from April 4th, 2003 to October 2nd, 2003, it was evident that the range and timing of each plant species' IGS change is not the same. According to questionnaire to public officials taking charge of street greening, the current evaluated IGS is 24.4%, and it is expected to be 40.7% in the future.

주요성분분석에 의한 일반회귀 신경망의 성능개선

조용현,Cho, Yong-Hyun 한국정보처리학회 2000 정보처리논문지 Vol.7 No.11

This paper proposes an efficient method for improving the performance of a general regression neural network by using the feature to the independent variables as the center for partern-layer neurons. The adaptive principal component analysis is applied for extracting, efficiently the fcarures by reducing the dimension of given independent variables. In can acluevc a supertor property of the principal component analysis that converts input data into set of statistically independent features and the general regression neuralnetwork, espedtively. The proposed general regression neural network has been applied to regress the Solow's economy(2-independent variable set) and the wie elephone(1-independent vanable set). The simulation results show that the proposed meural networks have better performances of the regressionfor the lest data, in comparison with those using the means or the weighted means of independent variables. Also,it is affected less by the number of neurons and the scope of the smoothing factor. 본 논문에서는 독립변수들의 특징을 추출하여 패턴층 뉴런의 중앙값을 이용함으로써 일반회귀 신경망의 성능을 개선하는 방법을 제안하였다. 제안된 방법에서는 적응적 학습 알고리즘의 주요성분분석 기법을 이용하여 회귀분석에 이용되는 데이터의 각 독립변수들의 집합으로 변환시키는 특징을 살려 일반회귀 신경망의 성능을 더 개선하기 위함이다. 제안된 기법의 일반회귀 신경망을 2개의 독립변수 집합을 가진 Solow의 경제문제와 4개의 독립변수 집합을 가진 국내 유선전화문제에 각각 적용하여 시뮬레이션한 결과, 중심값을 각 독립변수들의 평균이나 가중평균을 이용하는 일반회귀 신경망에 의한 결과와 비교할 때 더욱 우수한 회귀성능이 있음을 확인할 수 있었다. 그리고 신경망의 뉴런 수나 평활요소의 설정 면에서도 우수한 특성이 있음을 확인할 수 있었다.

효율적인 학습규칙의 신경망 기반 독립성분분석을 이용한 영상신호의 분리 및 특징추출

조용현,Cho, Yong-Hyun 한국지능시스템학회 2003 한국지능시스템학회논문지 Vol.12 No.2

본 연구에서는 효율적인 학습규칙의 신경망 기반 독립성분분석기법을 이용한 영상신호의 분리와 특징추출을 제안하였다. 제안된 학습규칙은 할선법과 모멘트를 이용한 조합형 고정점 학습알고리즘이다. 여기서 할선법은 독립성분 상호간의 정보를 최소화하기 위한 목적함수의 최적화 과정에서 요구되는 1차 미분에 따른 계산을 간략화하기 위함이고, 모멘트는 최적화 과정에서 발생하는 발진을 억제하여 보다 빠른 학습을 위함이다. 제안된 기법을 $512\times512$의 픽셀을 가지는 10개의 영상을 대상으로 임의의 혼합행렬에 따라 발생되는 혼합영상의 분리에 적용한 결과, 뉴우턴법에 기초한 기존의 알고리즘과 할선법만에 기초한 알고리즘보다 각각 우수한 분리률과 빠른 분리속도가 있음을 확인하였다. 또한 $256\times256$ 픽셀의 10개 지문상과 $480\times225$ 픽셀의 지폐영상에서 선택된 각각 10,000개의 3가지 영상패치들을 대상으로 적용한 결과, 제안된 기법은 뉴우턴법이나 할선법의 알고리즘보다도 빠른 특징추출 속도가 있음을 확인하였다. 한편 추출된 $16\times16$ 펙셀의 160개 독립성분 기저벡터 각각은 영상 각각에 포함된 공간적인 주파수 특성과 방향성을 가지는 경계 특성이 잘 드러나는 국부적인 특징들임을 확인하였다. This paper proposes a separation and feature extraction of image signals using the independent component analysis(ICA) based on neural networks of efficient learning rule. The proposed learning rule is a hybrid fixed-point(FP) algorithm based on secant method and momentum. Secant method is applied to improve the performance by simplifying the 1st-order derivative computation for optimizing the objective function, which is to minimize the mutual informations of the independent components. The momentum is applied for high-speed convergence by restraining the oscillation in the process of converging to the optimal solution. The proposed algorithm has been applied to the composite images generated by random mixing matrix from the 10 images of $512\times512$-pixel. The simulation results show that the proposed algorithm has better performances of the separation speed and rate than those using the FP algorithm based on Newton and secant method. The proposed algorithm has been also applied to extract the features using a 3 set of 10,000 image patches from the 10 fingerprints of $256\times256$-pixel and the front and the rear paper money of $480\times225$-pixel, respectively, The simulation results show that the proposed algorithm has also better extraction speed than those using the another methods. Especially, the 160 basis vectors(features) of $16\times16$-pixel show the local features which have the characteristics of spatial frequency and oriented edges in the images.

대기경험이 주제공원 이용자의 만족도에 미치는 영향

조용현,김란희,Cho Yong-Hyun,Kim Nan-Hee 한국조경학회 2005 한국조경학회지 Vol.33 No.3

Despite there have been m?my studies about the relationships between congestions and satisfaction in outdoor recreation field, the results indicated only weak impacts of congestions on the satisfaction. This study thus aims to investigate the influence of waiting situation on the whole valuation and satisfaction of guests at theme parks using new variables such as 'goal attainment' and then to suggest implications for waiting management. This study shows meaningful theoretical implications. First, congestion influences the satisfaction more strongly when it prevents guests from achieving their plan. Second, management of waiting time is important and the can be controlled well. When guests have something interested during the waiting time, they were satisfied with the quality of waiting time and overall experience in the theme park.