• The Research Journal of the Costume Culture
• /
• 제15권6호
• /
• pp.982-995
• /
• 2007

The purpose of this study was to investigate the differences of the visual image evaluation according to coloration of men's dress shirts and neckties, and perceiver's gender. Subjects were 336 males and females living in Seoul. Five dimensions of visual evaluation were derived by factor analysis: elegance/intelligence, sociability, potency/attractiveness, individuality, and manliness. White shirts were evaluated highly in elegance/intelligence, and blue shirts were shown the manliest. Women evaluated the blue shirts manlier than men did. Dark blue neckties were evaluated highly in elegance/intelligence and sociability, and red ties were perceived to be very distinctive. Black shirts and white shirts with silvery gray ties were perceived to be the most elegant and intelligent. Blue shirts with dark blue ties was evaluated highly in sociability and potency/attractiveness, and black shirts with yellow ties were evaluated the highest in individuality. The evaluations of elegance/intelligence, potency/attractiveness, and manliness had significant interaction effects between the color of shirts and neckties. White shirts and blue shirts with dark blue ties were perceived to be more elegant and intelligent, potent, attractive and manlier than with red ties.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• pp.305-326
• /
• 2019

Discriminative correlation filter (DCF) based tracking algorithms have recently shown impressive performance on benchmark datasets. However, amount of recent researches are vulnerable to heavy occlusions, irregular deformations and so on. In this paper, we intend to solve these problems and handle the contradiction between accuracy and real-time in the framework of tracking-by-detection. Firstly, we propose an innovative strategy to combine the template and color-based models instead of a simple linear superposition and rely on the strengths of both to promote the accuracy. Secondly, to enhance the discriminative power of the learned template model, the spatial regularization is introduced in the learning stage to penalize the objective boundary information corresponding to features in the background. Thirdly, we utilize a discriminative multi-scale estimate method to solve the problem of scale variations. Finally, we research strategies to limit the computational complexity of our tracker. Abundant experiments demonstrate that our tracker performs superiorly against several advanced algorithms on both the OTB2013 and OTB2015 datasets while maintaining the high frame rates.

• KIEAE Journal
• /
• 제3권2호
• /
• pp.25-32
• /
• 2003

This study deals with the investigation of recognition structure on architectural environment and reconstruction of it by artificial intelligence. To test the possibility of the reconstruction, recognition structure on architectural environment is analysed and each steps of the structure are matched with computational methods. Edge Detection and Neural Network were selected as matching methods to each steps of recognition process. Visual perception system established by selected methods is trained and tested, and the result of the system is compared with that of experiment of human. Assuming that the artificial system resembles the process of human recognition on architectural environment, does the system give similar response of human? The result shows that it is possible to establish artificial visual perception system giving similar response with that of human when it models after the recognition structure and process of human.

• KIEAE Journal
• /
• 제3권2호
• /
• pp.59-66
• /
• 2003

To be the design method supporting aesthetic ability of human, CAAD system should essentially recognize architectural form in the same way of human. In this study, visual perception process of human was analyzed to search proper computational method performing similar step of perception of it. Through the analysis of visual perception, vision was separated to low-level vision and high-level vision. Edge detection and neural network were selected to model after low-level vision and high-level vision. The 24 images of building, tree and landscape were processed by edge detection and trained by neural network. And 24 new images were used to test trained network. The test shows that trained network gives right perception result toward each images with low error rate. This study is on the meaning of artificial intelligence in design process rather than on the design automation strategy through artificial intelligence.

• Journal of information and communication convergence engineering
• /
• 제21권2호
• /
• pp.152-158
• /
• 2023

In recent years, as computer-generated imagery has been applied to more industries, realistic facial animation is one of the important research topics. The current solution for realistic facial animation is to create realistic rendered 3D characters, but the 3D characters created by traditional methods are always different from the actual characters and require high cost in terms of staff and time. Deepfake technology can achieve the effect of realistic faces and replicate facial animation. The facial details and animations are automatically done by the computer after the AI model is trained, and the AI model can be reused, thus reducing the human and time costs of realistic face animation. In addition, this study summarizes the way human face information is captured and proposes a new workflow for video to image conversion and demonstrates that the new work scheme can obtain higher quality images and exchange effects by evaluating the quality of No Reference Image Quality Assessment.

• Journal of Gifted/Talented Education
• /
• 제7권1호
• /
• pp.51-76
• /
• 1997

The purpose of this study was to investigate the effects of Structure of Intellect( SOI) program for children. To achieve this purpose, 81 second grade children were sampled in a elementary school located In Seoul-city and randomly assigned to the experimental group and control group The SO1 training program were treated to the experimental group for 10 weeks, and the 'Thinking Abilities Test developed by Korea Creativity Research Institute were administered to them for pre-test and post-test. The collected data were analyzed by t-test for comparing the group means of experimental group and control group 'I'he results of this study were as follows : Firstly ere were statistically significant differences between experimental group and control group on the post-test scores of arithmetic[t(79)=2.73p,< .01] and visual memory[t(79)-3.68,p <.001]. The mean scores of experimental group(M=8.63) u ere higher than that of control group(Mz7.34) on arithmetic, and the mean scores to experimental group(M=16.68) were higher than that of control group(M=15 32) on visual memory Secondly there were no statistically significant differences between experimental group and control group on the post-test scores of logistic thinking abilities[t(79)=0.22, p>.05] and abstract thinking abilities[t(79)-0.22, p>.051. Thirdly, the post-test scores of visual memory and logical thinking abilities were more increased in the low intelligence group than the high intelligence group. This result showed that the SO1 program were more effective for the low intelligence group. Fourthly, the post-test scores of visual memory and logical thinking abilities were more increased in the low achievement group than the high achievement group. This result showed that the SO1 program were more effective for the low achievement group.

• Korean Association of Arts Management
• /
• 제59호
• /
• pp.5-31
• /
• 2021

The purpose of this study is to analyze social perceptions and discourses about creating arts in the era of artificial intelligence with making an implication of responding to the emergence of artificial intelligence. We conceptually understand the principles and limitations of creating visual arts using artificial intelligence whilst this paper addresses ai art in the social context by borrowing the theoretical lens from the sociology of arts. This article considers 472 newspapers about artificial intelligence art as the main data, which are interpreted through semantic network analysis. The analysis of this research shows that it is a controversial issue regarding who/which creates the artworks between humans and computers. However, judging from the dominant influence of a group of words representing the recognition of intellectual property rights, we have detected that social awareness is formed around the perspective of considering artificial intelligence creates visual arts rather than artists. In addition, based on the close relationship between the cluster and the cluster reflecting institutional support, we confirm that the discourse about artificial intelligence art is limited to technological development and legal system maintenance. Thus, this study suggests the need for defining artificial intelligence as the medium of art and constructing policy discourses on artificial intelligence art as an artistic genre.

• Journal of Korea Multimedia Society
• /
• 제24권7호
• /
• pp.880-889
• /
• 2021

In everyday life, recognizing people's emotions from their frames is essential and is a popular research domain in the area of computer vision. Visual emotion has a severe class imbalance in which most of the data are distributed in specific categories. The existing methods do not consider class imbalance and used accuracy as the performance metric, which is not suitable for evaluating the performance of the imbalanced dataset. Therefore, we proposed a method for recognizing visual emotion using balanced data augmentation to address the class imbalance. The proposed method generates a balanced dataset by adopting the random over-sampling and image transformation methods. Also, the proposed method uses the Focal loss as a loss function, which can mitigate the class imbalance by down weighting the well-classified samples. EfficientNet, which is the state-of-the-art method for image classification is used to recognize visual emotion. We compare the performance of the proposed method with that of conventional methods by using a public dataset. The experimental results show that the proposed method increases the F1 score by 40% compared with the method without data augmentation, mitigating class imbalance without loss of classification accuracy.

• The Journal of the Convergence on Culture Technology
• /
• 제9권1호
• /
• pp.53-59
• /
• 2023

We aim to investigate whether the activities in the 2015 revised elementary English textbooks are reflected in terms of Multiple Intelligences. Specifically, we analyze three types of activities including project, game, and cultural activities in three types of the 5^th grade English textbooks. Additionally, we compare the differences in the Multiple Intelligences according to three different publishers. The data includes three different sorts of fifth-grade English textbook activities. We found that verbal-linguistic intelligence, interpersonal intelligence, and visual-spatial intelligence are heavily involved in project activities. Verbal-linguistic intelligence, interpersonal intelligence, visual-spatial intelligence, and kinesthetic intelligence are all utilized in game activities. Lastly, cultural activities demonstrate verbal-linguistic and visual-spatial intelligence. In consideration of the diversity of students, we suggest that English textbooks need to consider diverse and well balanced approach to incorporating Multiple Intelligences in order to make the textbooks to meet the needs of the diversity of learners.

• Educational Technology International
• /
• 제10권1호
• /
• pp.25-40
• /
• 2009

The purpose of this study was to explore procedures and modalities on collaborative visualization processing of text information for developing e-Learning contents. In order to investigate, two research questions were explored: 1) what are procedures on collaborative visualization processing of text information, 2) what kinds of patterns and modalities can be found in each procedure of collaborative visualization of text information. This research method was employed a qualitative research approaches by means of grounded theory. As a result of this research, collaborative visualization processing of text information were emerged six steps: identifying text, analyzing text, exploring visual clues, creating visuals, discussing visuals, elaborating visuals, and creating visuals. Collaborative visualization processing of text information came out the characteristic of systemic and systematic system like spiral sequencing. Also, another result of this study, modalities in collaborative visualization processing of text information was divided two dimensions: individual processing by internal representation, social processing by external representation. This case study suggested that collaborative visualization strategy has full possibility of providing ideal methods for sharing cognitive system or thinking system as using human visual intelligence.