• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.667-674
• /
• 2007

Facial expressions provide significant clues about one's emotional state; however, it always has been a great challenge for machine to recognize facial expressions effectively and reliably. In this paper, we report a method of feature-based adaptive motion energy analysis for recognizing facial expression. Our method optimizes the information gain heuristics of ID3 tree and introduces new approaches on (1) facial feature representation, (2) facial feature extraction, and (3) facial feature classification. We use minimal reasonable facial features, suggested by the information gain heuristics of ID3 tree, to represent the geometric face model. For the feature extraction, our method proceeds as follows. Features are first detected and then carefully "selected." Feature "selection" is finding the features with high variability for differentiating features with high variability from the ones with low variability, to effectively estimate the feature's motion pattern. For each facial feature, motion analysis is performed adaptively. That is, each facial feature's motion pattern (from the neutral face to the expressed face) is estimated based on its variability. After the feature extraction is done, the facial expression is classified using the ID3 tree (which is built from the 1728 possible facial expressions) and the test images from the JAFFE database. The proposed method excels and overcomes the problems aroused by previous methods. First of all, it is simple but effective. Our method effectively and reliably estimates the expressive facial features by differentiating features with high variability from the ones with low variability. Second, it is fast by avoiding complicated or time-consuming computations. Rather, it exploits few selected expressive features' motion energy values (acquired from intensity-based threshold). Lastly, our method gives reliable recognition rates with overall recognition rate of 77%. The effectiveness of the proposed method will be demonstrated from the experimental results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1495-1504
• /
• 2012

This paper proposes an algorithm to classify and analyze facial features such as eyebrow, eye, mouth and chin based on the geometric features of the face. As a preprocessing process to classify and analyze the facial features, the algorithm extracts the facial features such as eyebrow, eye, nose, mouth and chin. From the extracted facial features, it detects the shape and form information and the ratio of distance between the features and formulated them to evaluation functions to classify 12 eyebrows types, 3 eyes types, 9 mouth types and 4 chine types. Using these facial features, it analyzes a face. The face analysis algorithm contains the information about pixel distribution and gradient of each feature. In other words, the algorithm analyzes a face by comparing such information about the features.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.945-957
• /
• 2019

In this study, we propose a coarse to fine image registration method for eliminating geometric error between images over agricultural areas acquired using Unmanned Aerial Vehicle (UAV). First, images of agricultural area were acquired using UAV, and then orthophotos were generated. In order to reduce the probability of extracting outliers that cause errors during image registration, the region of interest is selected by using the metadata of the generated orthophotos to minimize the search area. The coarse image registration was performed based on the extracted tie-points using the Speeded-Up Robust Features (SURF) method to eliminate geometric error between orthophotos. Subsequently, the fine image registration was performed using tie-points extracted through the Mutual Information (MI) method, which can extract the tie-points effectively even if there is no outstanding spatial properties or structure in the image. To verify the effectiveness and superiority of the proposed method, a comparison analysis using 8 orthophotos was performed with the results of image registration using the SURF method and the MI method individually. As a result, we confirmed that the proposed method can effectively eliminated the geometric errors between the orthophotos.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.4 no.2
• /
• pp.139-161
• /
• 2002

This study investigates the characteristics of Nordic sweaters works from a historical perspective. Specifically, this study deals with the following research topics: 1) development of Nordic sweaters, 2) the characteristics of Nordic sweaters industry according to the change of times, 3) the comparison of local knitting patterns, 4) the symbolic meaning of the designs in the Nordic sweaters and patterns. The results of the study are summarized as follows. 1. Knitted work developed mostly in Northern Europe, a cold area, and the barren, mountainous coastal areas where people frequently used woolen materials for clothes. It was also developed in Scandinavian regions which lead the fashion in modern days. Scandinavian knitting techniques have been diffused into the east coast of England and Northern Europe by Vikings. 2. Scandinavian countries are distinguished from other countries by their conservative but creative cultural tradition. Their knitting patterns are characterized by small geometric figures such as dots, triangles, squares, rhombuses, and crosses used often with stars and roses. Scandinavian knitting is also salient for its vertical stripes and simple motifs repeating at short intervals. 1) Norway ; Simple and geometric Norwegian patterns are classified into three groups of motifs: (a) the motifs of cross, diamond, X, and swastika (equation omitted). (b) the motifs of human figures, animals and birds, (c) floral motifs (especially eight-petal roses). Their use of color is also simple, and is limited to more than two colors. (2) Sweden ; Swedish patterns are colorful and geometric. They are characterized by features such as brocade, complex embroidery, and contrast of red and black colors. They also show Guernsey patterns. Initials and production years were knitted in sweaters which have different patterns in their trunks and sleeves. 3) Denmark ; The Danish pattern is the purl stitch knitted against the stockinette stitch. The technique is used to copy woven damask motifs. The patterns are seen most clearly when they are knit with smooth yarn. The Faeroe sweaters are the representative work of Danish knitting. Faeroe knitting, incorporates stranded pattern and is knit in the round, either with circular needles. 4) Finland ; Finnish patterns are similar to Norwegian patterns. Finnish knitted work show very colorful, variety and free-flowing geometric patterns. 5) Iceland ; Icelandic knitting shows original ribbon pattern. Lope sweater is the representative work. 3. The traditional knitting patterns not only carried symbolic meanings but also served as means of communication. First of all, patterns had incantatory meanings. Patterns were symbolic of one's social standing, too. The colors, motifs and their arrangements were very important features symbolizing one's social position or family line. People often communicated by certain pieces of knitted work or patterns. In short, the knitted work in the Nordic sweaters served the function of admiring the beauty of nature and symbolizing various meanings. The unique designs and colors of the knitted work reflected the characteristics of the culture those works belonged to. This study also turns our attention to the issue of how the traditional colors and designs of the knitted work can contribute to the development of modern designs, and by doing so, if makes us realize the importance of knitted works in modern society.

• Journal of Korean Society of Transportation
• /
• v.21 no.3
• /
• pp.59-69
• /
• 2003

Signalized intersections are widely used in urban street network. However, it was reported that a roundabout is better than a signalized intersection in terms of delay when the approaching traffic volume for each bound is low. The objective of this study is to develop entry capacity models of roundabout and establish the warrant for signalized intersection based on the delay. The entry capacity of a roundabout is determined by the circulating traffic volume and the geometric design of the roundabout such as the diameter of central island, entry lane widths, and the circulating roadway width. The traffic and geometric characteristics of four roundabouts were collected and analyzed. The study reveals that; i)among the geometric features, the diameter of central island and the circulating roadway width influence the entry capacity, and ii)even though it is difficult to compare the models of each country due to different geometric features considered in the models, the models developed in this study show higher capacity than the models from Israel or Germany. These seem to be attributed to the facts that; i)the outside diameters of the roundabouts selected in this study are larger than in the other studies, and ii)the acceptable gap in Korea is smaller than that in the other countries. In order to compare the performances of round- about and signalized intersection, the performance of roundabouts was evaluated with the SIDRA. The simulation was conducted only for the roundabouts composed of single lane. According to the result of the analysis, it may be concluded that when the approaching traffic volume for each bound is lower than 600pcph, a roundabout is better than a signalized intersection in terms of its operational performance.

• Journal of the Korean School Mathematics Society
• /
• v.26 no.2
• /
• pp.111-135
• /
• 2023

This study conducted a student-centered inquiry lesson on the similarity of figures using AlgeoMath, with student learning aspects analyzed from a communication perspective. This approach aimed to inform pedagogical implications related to teaching geometric similarity. Through utilizing AlgeoMath, students were able to visually confirm that their chosen figures were similar, experiencing key mathematical concepts such as the ratio of similarity to the area of similar figures, and congruency and similarity conditions of triangles. In the lessons applying this concept, we categorized the features of similarity learning displayed by students, as seen in the communication aspects of their exploratory activities, into 'Understanding similarity ratios', 'Grasping conditions of similarity in triangles', and 'Comparing concepts of congruency and similarity'. Through exploratory activities based on AlgeoMath, students discussed the meaning and mathematical relationships of key concepts related to similarity, such as the ratio of similarity to the area of figures, and the meaning and conditions of congruence and similarity in triangles. By improving misconceptions about the similarity of figures, they were able to develop deeper mathematical understanding. This study revealed that in teaching and learning the geometric similarity using AlgeoMath, obtaining meaningful pedagogical outcome was not solely due to the features of the AlgeoMath environment, but also largely depended on the teacher's guidance and intervention that stimulated students' thinking.

• Journal of Korean Society for Geospatial Information Science
• /
• v.24 no.1
• /
• pp.89-98
• /
• 2016

In this paper, we proposed an automated areal feature matching method based on geometric similarity without user intervention and is applied into areal features of many-to-many relation, for confusion of spatial data-sets of different scale and updating cycle. Firstly, areal feature(node) that a value of inclusion function is more than 0.4 was connected as an edge in adjacency matrix and candidate corresponding areal features included many-to-many relation was identified by multiplication of adjacency matrix. For geometrical matching, these multiple candidates corresponding areal features were transformed into an aggregated polygon as a convex hull generated by a curve-fitting algorithm. Secondly, we defined matching criteria to measure geometrical quality, and these criteria were changed into normalized values, similarity, by similarity function. Next, shape similarity is defined as a weighted linear combination of these similarities and weights which are calculated by Criteria Importance Through Intercriteria Correlation(CRITIC) method. Finally, in training data, we identified Equal Error Rate(EER) which is trade-off value in a plot of precision versus recall for all threshold values(PR curve) as a threshold and decided if these candidate pairs are corresponding pairs or not. To the result of applying the proposed method in a digital topographic map and a base map of address system(KAIS), we confirmed that some many-to-many areal features were mis-detected in visual evaluation and precision, recall and F-Measure was highly 0.951, 0.906, 0.928, respectively in statistical evaluation. These means that accuracy of the automated matching between different spatial data-sets by the proposed method is highly. However, we should do a research on an inclusion function and a detail matching criterion to exactly quantify many-to-many areal features in future.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2005.06a
• /
• pp.1733-1736
• /
• 2005

Many studies have been carried out to produce 3D features in the size range between $10{\mu}m\~10,000{\mu}m$, called Meso-scale. If these miniaturized systems have high relative accuracy and good volumetric utilization, it is possible to manufacture more complex and accurate shapes with various materials as well as there are advantages of reducing energy, space and resources. Due to imperfect components and misalignment in assembly, it is necessary to assess the accuracy of the miniaturized system itself to obtain high relative accuracy. Laser interferometers are widely used to measure geometric errors called as quasi-static errors. For miniaturized system, however, it is difficult to install the required accessories such as optics and the measuring range is limited because of the size of the system and also this method is very expensive. Moreover, it is impossible to measure each error component simultaneously. A new system to measure simultaneously multiple geometric errors is proposed using capacitance sensors. Each error was measured using capacitance sensors and a measurement algorithm was mathematically derived. The experiments show that the proposed measurement system can be used effectively to assess the accuracy of miniaturized system at a low cost.

• The Journal of Art Theory & Practice
• /
• no.9
• /
• pp.151-170
• /
• 2010

As an art group, De Stijl (1917-1931) led a total art movement encompassing painting, sculpture, design, and architecture. Among these, architecture, as a model of the total art pursued by the group, was encapsulated by the term 'plastic architecture.' The term reflects architecture's shared features with plastic art, especially its pictorial characteristics. Firstly, De Stijl architecture shares geometric form with painting. Assembled in simple, clear and rational structures, the geometric forms signified universal forms, and extended the pictorial experimentation that Mondrian exercised through Neo-Plasticism to architecture. Constructed with colour fields made of concrete wall, De Stijl architecture is geometric abstract painting embodied in space. Together with such pictorial characteristics, large plate glass windows, narrow window frames, and cantilever structure minimize the building's visual weight. De Stijl architecture, which appears suspended in the air, is an architectural version of the abstract paintings of the era that revealed unknown spaces beyond perspective. De Stijl architecture is also an 'open' architecture, where the units placed as if radiating from the center form relations with each other flexibly and organically. The observer in such a space is encouraged to experience space within time, as his/her physical and visual mobility and extension are maximized. De Stijl architecture is an example of how the time-space continuum, represented within picture frame through Cubism, Futurism, and abstract art, can be realized in space. By transforming the ideal space of painting into real space in this way, 'plastic architecture' turned out to be an architectural manifestation of the utopianism of the era, aimed at building a society in 'perfect harmony.' However, such rationalism and universalism are not free from the violence of totalization that deletes various differences. This is evident in the history that followed as the geometric form of architecture and urban planning proliferated across the globe, engulfing the diverse natural landscapes and local cultures.

• Wind and Structures
• /
• v.20 no.2
• /
• pp.249-274
• /
• 2015

Long-span cable-stayed bridges exhibit some features which are more critical than typical long span bridges such as geometric and aerodynamic nonlinearities, higher probability of the presence of multiple vehicles on the bridge, and more significant influence of wind loads acting on the ultra high pylon and super long cables. A three-dimensional nonlinear fully-coupled analytical model is developed in this study to improve the dynamic performance prediction of long cable-stayed bridges under combined traffic and wind loads. The modified spectral representation method is introduced to simulate the fluctuating wind field of all the components of the whole bridge simultaneously with high accuracy and efficiency. Then, the aerostatic and aerodynamic wind forces acting on the whole bridge including the bridge deck, pylon, cables and even piers are all derived. The cellular automation method is applied to simulate the stochastic traffic flow which can reflect the real traffic properties on the long span bridge such as lane changing, acceleration, or deceleration. The dynamic interaction between vehicles and the bridge depends on both the geometrical and mechanical relationships between the wheels of vehicles and the contact points on the bridge deck. Nonlinear properties such as geometric nonlinearity and aerodynamic nonlinearity are fully considered. The equations of motion of the coupled wind-traffic-bridge system are derived and solved with a nonlinear separate iteration method which can considerably improve the calculation efficiency. A long cable-stayed bridge, Sutong Bridge across the Yangze River in China, is selected as a numerical example to demonstrate the dynamic interaction of the coupled system. The influences of the whole bridge wind field as well as the geometric and aerodynamic nonlinearities on the responses of the wind-traffic-bridge system are discussed.