• 한국실내디자인학회:학술대회논문집
• /
• 한국실내디자인학회 2005년도 춘계학술발표대회 논문집
• /
• pp.116-121
• /
• 2005

This research against the method of applying a traditional design elements to modern interior space is classified and analyzed by direct expression method, a transfigure expression method, a metaphor expression method and a symbol expression method. The direct expression method means the modernizing the traditional design elements by expressing traditional material and structural formative style as they are, and the transfigure expression method is the design method of re-organizing the elements by simplifying and transfiguring the traditional design elements. Metaphor expression method includes the method of expressing visually the formative concept which does not known concretely, and the symbol expression method exchanges the rising concepts into concrete elements and expresses by new design.

• 한국실내디자인학회논문집
• /
• 제14권6호
• /
• pp.66-74
• /
• 2005

The purpose of this study analyzes an expression method and a characteristic of transparency of a surface in commercial space, and it is to show an index of a surface design. We did image evaluation by SD method for the commercial space which directed transparency to a surface as the method. We used a factor analysis and cluster analysis to get the image characteristic and type of the expression methods. As a result, we got six following expression methods and design indexes. (1) Transparency expression of a surface by a multiple layer. (2) Transparency expression of a surface by unification with a structure. (3) Transparency expression of a surface by transparency of materials. (4) Transparency expression of a surface by a combination of various materials. (5) Transparency expression of a surface by unification of the image media. (6) Transparency expression of a surface by transparency transformation of materials. We think that it will be able to make use of these results as a design index for the surface design of a commercial space in the future.

• 복식
• /
• 제56권8호
• /
• pp.148-159
• /
• 2006

The objective of this study is to consider the uniform as visual communication, and analyze the expression of symbol shown on the uniform design by the pattern by applying the visual symbol in the communication and operation of the meaning. Also, it is to construct the systematic modeling method of the expression of design symbol by the pattern of uniform in th e various fields. This study is to analyze the symbolic expression method of the uniform design by the pattern by suggesting the symbolic expression method as a frame through the visual symbolic approach of the uniform design and the analysis of semantic symbol according to that. As a result, there arose simplification and emphasis and a method of symbolic expression with the national flag, a conceptual factor characteristically in the sports uniform design. The characteristics of symbolic expression of uniform design were mainly used in the symbolic expression with the customary code and symbol. Also, the uniform in the enterprises were widely used in the expression of uniform with the suggestion and code by the color. As for the characteristics of symbolic expression shown on the event uniform design, the method of symbolic expression by the pattern of uniform was grasped differently asa result of symbolic expression through the image. The method of symbolic expression suggested on this study could be used on a basis of uniform design in the future. Accordingly, this study has a meaning of suggesting the methodology of uniform design that would be a parameter.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 추계학술대회
• /
• pp.197-200
• /
• 2014

본 논문은 얼굴의 표정 인식을 이용한 위험상황 인지 알고리즘을 제안한다. 제안방법은 인간의 다양한 감정 표정 중 위험상황을 인지하기 위한 표정인 놀람과 공포의 표정을 인식한다. 제안방법은 먼저 얼굴 영역을 추출하고 검출된 얼굴 영역으로부터 눈 영역과 입술 영역을 추출한다. 각 영역에 Uniform LBP 방법을 적용하여 표정을 판별하고 위험 상황을 인식한다. 제안방법은 Cohn-Kanade 데이터베이스 영상을 대상으로 성능을 평가하였다. 그 결과 표정 인식에 좋은 결과를 보였으며 이를 이용하여 위험상황을 잘 판별하였다.

• 제어로봇시스템학회논문지
• /
• 제20권5호
• /
• pp.520-525
• /
• 2014

Generally, feature area detection methods are widely used for face expression recognition by detecting the feature areas of human eyes, eyebrows and mouth. In this paper, we proposed a face expression recognition method using the histograms of the face, eyes and mouth for many applications including robot technology. The experimental results show that the proposed method has a new type of face expression recognition capability compared to conventional methods.

• International Journal of Internet, Broadcasting and Communication
• /
• 제7권2호
• /
• pp.51-55
• /
• 2015

This paper proposes an algorithm for risk situation recognition using facial expression. The proposed method recognitions the surprise and fear expression among human's various emotional expression for recognizing dangerous situation. The proposed method firstly extracts the facial region using Harr-like technique from input, detects eye region and lip region from the extracted face. And then, the method applies Uniform LBP to each region, detects facial expression, and recognizes dangerous situation. The proposed method is evaluated for MUCT database image and web cam input. The proposed method produces good results of facial expression and discriminates dangerous situation well and the average recognition rate is 91.05%.

• 한국실내디자인학회논문집
• /
• 제22권2호
• /
• pp.186-193
• /
• 2013

In the commercial space, the modern consumers want to consume not only product but also culture. Thus, the modern commercial space tries to induce the customer's concern and purchase to the differentiated design. The introduction of this 'the natural element' delivers the pleasure and stability to the consumer buying process and availability is enlarged. Therefore, the purpose of study is gain that expression and characteristic method of the natural element in the commercial space. The detailed study method are as follows. First, the study looks into the natural element expression tendency in the modern space. Second, the expression type of the natural element was classified as 'Reappearance', 'Transformation', and 'Fuse' based on the preceding research. And according to the content of the expression type, subdivided method of 'Inclusion' and 'Replication' of 'Reappearance' and method of 'Imitation' and 'Association' of 'Transformation' and method of 'Juxtaposition' and 'Combine' of 'Fuse'. Third, the result of analyze the characteristic of expression of the natural element of the besides the commercial space case 20 place is as follows. First, 'Inclusion' of 'Reappearance' introduced the external scenery or planned garden as the inside through the opening. 'Replication' is used for decorative purposes or functional purposes as the natural element. 'Imitation' of 'Transformation' imitated the form, pattern, and color of the natural element and was mainly expressed in the wall and objet. The method of 'Association' expressed the concept of the natural element for the whole of the space and a portion of the wall and objet repetitively. As for 'Juxtaposition', mixture of 'Reappearance' had a good visual effect, because it can be obtained the external-internal nature. As for 'Combine', mixture of 'Replication' and 'Imitation' was the most common method. Thus, the study results are expected to be utilized as base date in designing the commercial with development of the natural element application method.

• 한국콘텐츠학회논문지
• /
• 제16권10호
• /
• pp.598-607
• /
• 2016

본 연구의 목적은 기존의 발상법의 문제점을 파악하여 우리나라 사람들에게 적합한 발상법의 필요성 제시하고 이에 맞는 그래픽 발상법을 도출하는 것이다. 많은 그래픽 디자이너들이 활용하고 있는 발상법(연상 자극법이나 발상전환법, 정보조합법)은 발상과정에서 초기 키워드를 제시하는데 효과적이지만 컨셉까지 도출해내는 과정에서 어려움이 있다. 컨셉으로 발전시키기 위해서는 핵심 키워드 도출도 중요하지만 키워드의 연결 분리, 결합 등의 과정이 중요한 역할을 차지하며 대부분의 발상법이 과정에 대한 구체적 방법을 제시하고 못하고 있다. 또한 대부분의 아이디어 발상법이 영어권에서 개발되어 전파되었기 때문에 단어위주의 사고를 하는 영어권 문화에는 적합하지만 서술 위주로 사고하는 우리나라 사람에게는 언어 사고의 차이점을 고려하지 못하고 있어 단계 별 발상에 한계를 지니고 있다. 본 연구는 기존에 발상법에 의하여 도출된 키워드를 보다 쉽게 연결, 분리, 결합 등을 위한 과정을 만들기 위해 4가지 가설을 제시하고 논증하는 방식으로 본 발상법의 가치를 증명하고 이러한 가설에 입각하여 발상법설계 제시함으로써 우리나라 사람들의 정서에 적합한 발상법을 도출하였다. 본 발상법은 서술 표현에 강한 우리나라 사람들에게 적합하도록 수사법을 활용하였다.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.556-570
• /
• 2021

The existing video expression recognition methods mainly focus on the spatial feature extraction of video expression images, but tend to ignore the dynamic features of video sequences. To solve this problem, a multi-mode convolution neural network method is proposed to effectively improve the performance of facial expression recognition in video. Firstly, OpenFace 2.0 is used to detect face images in video, and two deep convolution neural networks are used to extract spatiotemporal expression features. Furthermore, spatial convolution neural network is used to extract the spatial information features of each static expression image, and the dynamic information feature is extracted from the optical flow information of multiple expression images based on temporal convolution neural network. Then, the spatiotemporal features learned by the two deep convolution neural networks are fused by multiplication. Finally, the fused features are input into support vector machine to realize the facial expression classification. Experimental results show that the recognition accuracy of the proposed method can reach 64.57% and 60.89%, respectively on RML and Baum-ls datasets. It is better than that of other contrast methods.

• 한국콘텐츠학회논문지
• /
• 제8권2호
• /
• pp.18-26
• /
• 2008

본 논문은 사용자로 하여금 표정공간으로부터 일련의 표정들을 선택하게 함으로써 3차원 아바타의 표정을 제어할 수 있는 표정공간의 단계적 가시화 기법을 기술한다. 본 기법에 의한 시스템은 무표정 상태를 포함하여 11개의 서로 다른 모션들로 구성된 2400여개의 표정 프레임으로 2차원 표정공간을 구성하였으며, 3차원 아바타의 표정 제어는 사용자가 표정공간을 항해함으로서 수행되어진다. 그러나 표정공간에서는 과격한 표정 변화에서부터 세밀한 표정 변화까지 다양한 표정 제어를 수행할 수 있어야하기 때문에 단계적 가시화 기법이 필요하다. 표정공간을 단계적으로 가시화하기 위해서는 퍼지 클러스터링을 이용한다. 초기 단계에서는 11개의 클러스터 센터를 가지도록 클러스터링하고, 단계가 증가될 때 마다 클러스터 센터의 수를 두 배씩 증가시켜 표정들을 클러스터링한다. 이때 클러스터 센터와 표정공간에 분포된 표정들의 위치는 서로 다른 경우가 많기 때문에, 클러스터 센터에서 가장 가까운 표정상태를 찾아 클러스터 센터로 간주한다. 본 논문은 본 시스템이 어떤 효과가 있는지를 알기 위해 사용자들로 하여금 본 시스템을 사용하여 3차원 아바타의 단계적 표정 제어를 수행하게 하였으며, 그 결과를 평가한다.