• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.85-88
• /
• 2023

미국 콜로라도주 박람회 미술전에서 신인 디지털 아티스트 부문에서 1위를 차지한 게임 디자이너인 제이슨 앨런의 작품 스페이스오페라 극장'이 AI Image generator Midjourney를 활용해서 완성된 작품이라는 것이 알려지면서 창작과 예술 분야에 AI 활용이라는 논쟁이 가속화되고 있다. 창작과 예술을 돕는 탁월한 기능을 가진 툴로 바라보거나 창작과 예술 활동에 아이디어를 제공하고 작품을 구체화하는 과정의 조력자로 환영하는 입장과 예술가의 작품을 허가 없이 훔쳐서 만들어 낸 이미지일 뿐이라는 이상도 이하도 아니며 도덕적으로 허락되어서는 안되다는 입장이 크게 충돌하고 있다. 하루가 다르게 빠르게 발전하고 있는 주요 AI Image generator를 살펴보고 창작과 예술 분야에 AI 활용은 어떤 변화를 가져올지, AI 활용의 긍정적인 측면을 예측하고 연구해 보고자 한다.

• International Journal of Advanced Culture Technology
• /
• v.11 no.3
• /
• pp.225-230
• /
• 2023

With the development of AI technology, there is a growing discussion about Text-to-Image Generative AI. We presented a Generative AI video production method and delineated a methodology for the production of personalized AI-generated videos with the objective of broadening the landscape of the video domain. And we meticulously examined the procedural steps involved in AI-driven video production and directly implemented a video creation approach utilizing the VQGAN-CLIP model. The outcomes produced by the VQGAN-CLIP model exhibited a relatively moderate resolution and frame rate, and predominantly manifested as abstract images. Such characteristics indicated potential applicability in OTT-based video content or the realm of visual arts. It is anticipated that AI-driven video production techniques will see heightened utilization in forthcoming endeavors.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.333-339
• /
• 2023

In three-dimensional(3D) modeling, texturing plays a crucial role as a visual element, imparting detail and realism to models. In contrast to traditional texturing methods, the current trend involves utilizing AI tools such as Leonardo.Ai and Meshy to create textures for 3D models in a more efficient and precise manner. This paper focuses on 3D texturing, conducting a comprehensive comparative study of AI tools, specifically Leonardo.Ai and Meshy. By delving into the performance, functional differences, and respective application scopes of these two tools in the generation of 3D textures, we highlight potential applications and development trends within the realm of 3D texturing. The efficient use of AI tools in texture creation also has the potential to drive innovation and enhancement in the field of 3D modeling. In conclusion, this research aims to provide a comprehensive perspective for researchers, practitioners, and enthusiasts in related fields, fostering further innovation and development in this domain.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.569-572
• /
• 2023

최근 하루가 다르게 발전하고 있는 생성형 AI가 창작과 예술 분야에 어떤 영향을 미칠 수 있는지, 새롭게 등장하고 있는 다양한 분야에서 활용 가능한 획기적인 기능 등을 살펴보고 이를 바탕으로 새로운 창작 방향을 제시할 수 있는 방법들을 살펴보려 한다. 최근, 작곡가와 소설가들은 물론, 디지털 아티스트들까지도 생성형 AI를 활용하여 독특한 음악, 글, 그리고 이미지를 창조하는데 성공했다는 사례들이 속속 드러나고 있고 영상, 게임, 웹툰 등 많은 산업현장에서 직접적인 활용방법에 대한 연구결과가 등장하고 실제 적용 사례도 늘어나고 있다. 이미지 생성기인 미드저니와 스테이블디퓨전 같은 도구들은 혁신적인 방법으로 빠르게 높은 퀄리티의 이미지를 생성하고 다양한 아이디어를 제공 받을 수 있는 도구로 창작과 예술 분야에서 큰 관심을 받고 있다. 이러한 발전은 창작과 예술 분야에서 생성형 AI의 무한한 가능성을 보여주는 한편, 인간의 창의성 침해와 예술가들의 노력 희석에 대한 비판적 시각을 불러일으키기도 한다. 본 연구는 이런 다양한 관점에서 창작·예술 분야의 생성형 AI 활용을 깊이 있게 탐구한다. 그 과정에서 여러 생성형 AI 도구들, 특히 이미지 생성기 미드저니와 스테이블디퓨전의 기능과 활용 방안, 그로 인한 사회적, 윤리적 측면을 분석하며, 창작·예술 분야에서의 생성형 AI 활용의 적절한 방향성과 미래 전망을 제시해 보고자 한다.

• Journal of Service Research and Studies
• /
• v.14 no.1
• /
• pp.13-26
• /
• 2024

Multi-modal generation is the process of generating results based on a variety of information, such as text, images, and audio. With the rapid development of AI technology, there is a growing number of multi-modal based systems that synthesize different types of data to produce results. In this paper, we present an AI system that uses speech and text recognition to describe a person and generate a montage image. While the existing montage generation technology is based on the appearance of Westerners, the montage generation system developed in this paper learns a model based on Korean facial features. Therefore, it is possible to create more accurate and effective Korean montage images based on multi-modal voice and text specific to Korean. Since the developed montage generation app can be utilized as a draft montage, it can dramatically reduce the manual labor of existing montage production personnel. For this purpose, we utilized persona-based virtual person montage data provided by the AI-Hub of the National Information Society Agency. AI-Hub is an AI integration platform aimed at providing a one-stop service by building artificial intelligence learning data necessary for the development of AI technology and services. The image generation system was implemented using VQGAN, a deep learning model used to generate high-resolution images, and the KoDALLE model, a Korean-based image generation model. It can be confirmed that the learned AI model creates a montage image of a face that is very similar to what was described using voice and text. To verify the practicality of the developed montage generation app, 10 testers used it and more than 70% responded that they were satisfied. The montage generator can be used in various fields, such as criminal detection, to describe and image facial features.

• Journal of the Korean Society of Industry Convergence
• /
• v.24 no.6_2
• /
• pp.699-706
• /
• 2021

Existing license plate recognition system is used as an optical character recognition method, but a method of using deep learning has been proposed in recent studies because it has problems with image quality and Korean misrecognition. This requires a lot of data collection, but the collection of license plates is not easy to collect due to the problem of the Personal Information Protection Act, and labeling work to designate the location of individual license plates is required, but it also requires a lot of time. Therefore, in this paper, to solve this problem, five types of license plates were created using a virtual Korean license plate generation program according to the notice of the Ministry of Land, Infrastructure and Transport. And the generated license plate is synthesized in the license plate part of collectable vehicle images to construct 10,147 learning data to be used in deep learning. The learning data classifies license plates, Korean, and numbers into individual classes and learn using YOLOv5. Since the proposed method recognizes letters and numbers individually, if the font does not change, it can be recognized even if the license plate standard changes or the number of characters increases. As a result of the experiment, an accuracy of 96.82% was obtained, and it can be applied not only to the learned license plate but also to new types of license plates such as new license plates and eco-friendly license plates.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.617-619
• /
• 2018

In this paper, We suggest a face image generating GAN model which is improved by an additive discriminator. This discriminator is trained to be specialized in preventing frequent mistake of generator. To verify the model suggested, we used $^*Inception$ score. We used 155,680 images of $^*celebA$ which is frontal face. We earned average 1.742p at Inception score and it is much better score compare to previous model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.252-254
• /
• 2022

The purpose of this study is to show the works of Jeju artists and ways to contribute to the Jeju tourism industry, with the research background in that it has recently continued to accept the works of Jeju contemporary artists and draws active works. As a measure to achieve this research purpose, the Deep Dream Generator software was judged to be an effective method for promoting this study. As a specific research process, we will use the Deep Dream Generator to synthesize each of the works of Jeju artists and works of famous foreign artists provided by Deep Dream Generators with their own photos of Jeju Oreum and display the results, and attempt to reinterpret Jeju Oreum using artificial intelligence. In addition, it is expected to revitalize Jeju's art works and tourism by seeking ways to use the results in Jeju tourism products.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.121-127
• /
• 2023

The purpose of this pilot study is to examine the responses of middle school students to English learning after conducting English writing activities using DALL-E2, an image-generating artificial intelligence tool. To this end, an experimental class was conducted for 3 weeks for 15 middle school English learners, and the results are summarized as follows. First, as a result of a survey on English writing activities using DALL-E2, it was found that confidence, interest, and awareness of writing using artificial intelligence-based tools changed positively. In addition, it was confirmed that there was a statistically significant difference, which meant that learning using artificial intelligence had a positive effect on English writing and overall English learning. Second, as a result of analyzing the English writing activities using DALL-E2, core themes could be extracted into three (cognitive, affective, and psychodynamic characteristics), and the use and implementation of artificial intelligence-based DALL-E2 in English learning showed potential to increase learning interest, challenge, will, and desire in learning and ultimately contribute to enhancing productive skill.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.360-366
• /
• 2022

This paper presents a AI model structure for restoring Korean traditional palace photographs, which remain only black-and-white photographs, to color photographs using Pix2Pix, one of the adversarial generative neural network techniques. Pix2Pix consists of a combination of a synthetic image generator model and a discriminator model that determines whether a synthetic image is real or fake. This paper deals with an artificial intelligence model by adjusting a receptive field of the discriminator, and analyzes the results by considering the characteristics of the ancient palace photograph. The receptive field of Pix2Pix, which is used to restore black-and-white photographs, was commonly used in a fixed size, but a fixed size of receptive field is not suitable for a photograph which consisting with various change in an image. This paper observed the result of changing the size of the existing fixed a receptive field to identify the proper size of the discriminator that could reflect the characteristics of ancient palaces. In this experiment, the receptive field of the discriminator was adjusted based on the prepared ancient palace photos. This paper measure a loss of the model according to the change in a receptive field of the discriminator and check the results of restored photos using a well trained AI model from experiments.