• Journal of the Korean Society of Clothing and Textiles
• /
• v.41 no.5
• /
• pp.825-839
• /
• 2017

Generative Art (also called as the art of the algorithm) creates unexpected results, moving autonomously according to rules or algorithms. The evolution of digital media in art, which tries to seek novelty, increases the possibility of new artistic fields; subsequently, this study establishes the basis for new design approaches by analyzing visual cases of Generative Art that have emerged since the 20th century and characteristics expressed on fashion. For the methodology, the study analyzes fashion designs that have emerged since 2000, based on theoretical research that includes literature and research papers relating to Generative Art. According to the study, expression characteristics shown in fashion, based on visual properties of Generative Art, are as follows. First, abstract randomness is expressed with unexpected coincidental forms using movements of a creator and properties of materials as variables in accordance to rules or algorithms. Second, endlessly repeated pattern imitation expresses an emergent shape by endless repetition created by a modular system using rules or 3D printing using a computer algorithm. Third, the systematic variability expresses constantly changing images with a combination of system and digital media by a wearing method. It is expected that design by algorithm becomes a significant method in producing other creative ideas and expressions in modern fashion.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.1-13
• /
• 2021

In this research, we study the problem of font image skeletonization using an end-to-end deep adversarial network, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies have been concerned with skeletonization, but a few have utilized deep learning. Further, no study has considered generative models based on deep neural networks for font character skeletonization, which are more delicate than natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of font characters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization, in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generator is proved superior to all well-known mathematical skeletonization methods in terms of character structure, including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominance of our method against the state-of-the-art supervised image-to-image translation method in font character skeletonization task.

• Current Optics and Photonics
• /
• v.7 no.6
• /
• pp.655-664
• /
• 2023

Ghost imaging (GI) technology is developing rapidly, but there are inevitably some limitations such as the influence of atmospheric turbulence. In this paper, we study a ghost imaging system in atmospheric turbulence and use a gamma-gamma (GG) model to simulate the medium to strong range of turbulence distribution. With a compressed sensing (CS) algorithm and generative adversarial network (GAN), the image can be restored well. We analyze the performance of correlation imaging, the influence of atmospheric turbulence and the restoration algorithm's effects. The restored image's peak signal-to-noise ratio (PSNR) and structural similarity index map (SSIM) increased to 21.9 dB and 0.67 dB, respectively. This proves that deep learning (DL) methods can restore a distorted image well, and it has specific significance for computational imaging in noisy and fuzzy environments.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.667-679
• /
• 2023

The advent of image generative AI has made it possible for people who are not experts in art and design to create finished artworks through text input. With the increasing availability of generated images and their impact on the art industry, there is a need for research on how users perceive the process of co-creating with AI. In this study, we conducted an experimental study to investigate the expected and experienced processes of image generative AI creation among general users and to find out which processes affect users' sense of creative agency. The results showed that there was a gap between the expected and experienced creative process, and users tended to perceive a low sense of creative agency. We recommend eight ways that AI can act as an enabler to support users' creative intentions so that they can experience a higher sense of creative agency. This study can contribute to the future development of image-generating AI by considering user-centered creative experiences.

• Journal of Korea Game Society
• /
• v.16 no.5
• /
• pp.131-148
• /
• 2016

The cultural status of the game is always compared with the various area of art, and this discussion is continuing from appearance of the game to the present. During the same period, the cultural influence of the game is gradually increased, but public awareness was significantly undervalued the artistic value of the game. So, the change in this evaluation is needed in order to constantly maintain a cultural influence and to provide a positive influence on our society. Therefore, it is required that the research to prove their aesthetic value in the viewpoint of the game. This paper explores the new aesthetic potential of the game through a discussion of various similarities and the relationship between games and art. We look at the views on the game from the artistic point of view through game art and art game. And it find out the aesthetic subject and value of game. Finally, the approach through features of the information aesthetics and the generative aesthetics helps your understanding of the game aesthetics.

• Journal of information and communication convergence engineering
• /
• v.17 no.1
• /
• pp.14-20
• /
• 2019

Currently, microarray gene expression data take advantage of the sufficient classification of cancers, which addresses the problems relating to cancer causes and treatment regimens. However, the sample size of gene expression data is often restricted, because the price of microarray technology on studies in humans is high. We propose enhancing the gene expression classification of support vector machines with generative adversarial networks (GAN-SVMs). A GAN that generates new data from original training datasets was implemented. The GAN was used in conjunction with nonlinear SVMs that efficiently classify gene expression data. Numerical test results on 20 low-sample-size and very high-dimensional microarray gene expression datasets from the Kent Ridge Biomedical and Array Expression repositories indicate that the model is more accurate than state-of-the-art classifying models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2115-2127
• /
• 2021

Although significant progress has been made in synthesizing visually realistic face images by Generative Adversarial Networks (GANs), there still lacks effective approaches to provide fine-grained control over the generation process for semantic facial attribute editing. In this work, we propose a novel cross channel self-attention based generative adversarial network (CCA-GAN), which weights the importance of multiple channels of features and archives pixel-level feature alignment and conversion, to reduce the impact on irrelevant attributes while editing the target attributes. Evaluation results show that CCA-GAN outperforms state-of-the-art models on the CelebA dataset, reducing Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) by 15~28% and 25~100%, respectively. Furthermore, visualization of generated samples confirms the effect of disentanglement of the proposed model.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.23-30
• /
• 2022

Glaucoma is a chronic neuropathy that affects the optic nerve which can lead to blindness. The detection and prediction of glaucoma become possible using deep neural networks. However, the detection performance relies on the availability of a large number of data. Therefore, we propose different frameworks, including a hybrid of a generative adversarial network and a convolutional neural network to automate and increase the performance of glaucoma detection. The proposed frameworks are evaluated using five public glaucoma datasets. The framework which uses a Deconvolutional Generative Adversarial Network (DCGAN) and a DenseNet pre-trained model achieves 99.6%, 99.08%, 99.4%, 98.69%, and 92.95% of classification accuracy on RIMONE, Drishti-GS, ACRIMA, ORIGA-light, and HRF datasets respectively. Based on the experimental results and evaluation, the proposed framework closely competes with the state-of-the-art methods using the five public glaucoma datasets without requiring any manually preprocessing step.

• ETRI Journal
• /
• v.44 no.6
• /
• pp.1004-1019
• /
• 2022

For autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: feature extraction network (FEN) and path generation network (PGN). The FEN extracts meaningful features from an egocentric image, whereas the PGN generates multiple paths from the features, given a driving intention and speed. To ensure that the paths generated are plausible and consistent with the intention, we introduce an attentive discriminator and train it with the PGN under a generative adversarial network framework. Furthermore, we devise an interaction model between the positions in the paths and the intentions hidden in the positions and design a novel PGN architecture that reflects the interaction model for improving the accuracy and diversity of the generated paths. Finally, we introduce ETRIDriving, a dataset for autonomous driving, in which the recorded sensor data are labeled with discrete high-level driving actions, and demonstrate the state-of-the-art performance of the proposed model on ETRIDriving in terms of accuracy and diversity.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.1107-1112
• /
• 2009

To design and build a deformed building, new approaches and technologies are required, in which a design approach with parametric and generative technology is used for design and for building it, computer based fabrication technology. Even if parametric design technology is not a state of the art thing, the technology is still used widely, in order to effect the efficiency and furthermore it will continue to be innovated upon continuously. To cope with the limitation of it, the generative design system is developed. Deformed building design requires new methodology to overcome the limitations of conventional ways, which have difficulties to create enough design alternatives to explore satisfied design solutions order to deformed design have geometrical complexity and dramatically increased amount of data. Hence the generative design system can be a cutting edge methodology to solve it. However we should consider how to build the design in the real world. For this, the computer based fabrication technology which is used in mechanical industry is required to introduce to architecture and construction domain for efficiency. In this research, the methodology is modeled and tested with Bezier surface based shell structure.