• International Journal of Contents
• /
• v.15 no.4
• /
• pp.8-15
• /
• 2019

This paper presents a solution of the 'Quick, Draw! Doodle Recognition Challenge' hosted by Google. Doodles are drawings comprised of concrete representational meaning or abstract lines creatively expressed by individuals. In this challenge, a doodle is presented as a sequence of sketches. From the view of at the sketch level, to learn the pattern of strokes representing a doodle, we propose a sequential model stacked with multiple convolution layers and Long Short-Term Memory (LSTM) cells following the attention mechanism [15]. From the view at the image level, we use multiple models pre-trained on ImageNet to recognize the doodle. Finally, an ensemble and a post-processing method using the minimum cost flow algorithm are introduced to combine multiple models in achieving better results. In this challenge, our solutions garnered 11th place among 1,316 teams. Our performance was 0.95037 MAP@3, only 0.4% lower than the winner. It demonstrates that our method is very competitive. The source code for this competition is published at: https://github.com/ngxbac/Kaggle-QuickDraw.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.5
• /
• pp.29-38
• /
• 2023

Doodles, often possess irregular shapes and patterns, making it challenging for artificial intelligence to mechanically recognize and predict patterns in random doodles. Unlike humans who can effortlessly recognize and predict doodles even when circles are imperfect or lines are not perfectly straight, artificial intelligence requires learning from given training data to recognize and predict doodles. In this paper, we leverage a diverse dataset of doodle images from individuals of various nationalities, cultures, left-handedness, and right-handedness. After training two neural networks, we determine which network offers higher accuracy and is more suitable for doodle image prediction. The motivation behind predicting doodle images using artificial intelligence lies in providing a unique perspective on human expression and intent through the utilization of neural networks. For instance, by using the various images generated by artificial intelligence based on human-drawn doodles, we expect to foster diversity in artistic expression and expand the creative domain.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.29-31
• /
• 2020

본 논문에서는 코로나19 사태로 인한 팬데믹(pandemic) 현상으로 인해 또래와 단절된 아동들의 정서발달을 위해 인공지능 낙서 로봇인 Doodle Robot을 제안한다. Doodle Robot은 또래 형제가 없는 아동에게 함께 그림을 그릴 수 있는 그림친구로서 아동의 정서적 발달에 기여한다. YOLO 알고리즘을 사용하여 객체검출기능을 구현하였고 낙서 Data는 Quick! Draw Dataset에서 추출하였다.

• The Journal of the Korea Contents Association
• /
• v.13 no.5
• /
• pp.146-158
• /
• 2013

The purpose of this study is to analyze the story-retelling structure of tablet PC-based applications that designed to help infants to create stories. Owing to the popularization and the usability of smart devices, infants have become from content consumers to creators who reconstruct stories in creative ways, based on the stories they heard. In those participatory process, infants experience enjoying stories independently and expanding the meaning of texts. Story-retelling is an adequate methodology that cultivates creativity, expressiveness, and literacy ability to infant. Consequently, this study investigates three types of story-retelling in , , and , and searches structure elements and methods of story-retelling in integrated approach. In conclusion, the story-retelling applications that provide 'creative gap' have educational value, because they allow infants to demonstrate imagination by filling in the gap and to realize the rule of stories.

• Trans-
• /
• v.13
• /
• pp.117-140
• /
• 2022

Recently, artificial intelligence technology is being used throughout the industry. Currently, Currently, AI art generators are used in the NFT industry, and works using them have been exhibited and sold. AI art generators in the art field include Gated Photos, Google Deep Dream, Sketch-RNN, and Auto Draw. AI art generators in the music field are Beat Blender, Google Doodle Bach, AIVA, Duet, and Neural Synth. The characteristics of AI art generators are as follows. First, AI art generator in the art field are being used to create new works based on existing work data. Second, it is possible to quickly and quickly derive creative results to provide ideas to creators, or to implement various creative materials. In the future, AI art generators are expected to have a great influence on content planning and production such as visual art, music composition, literature, and movie.

• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.355-361
• /
• 2019

The purpose of this study is to analyze how brands are perceived to be most positive when they are presented to users in brand experience design, and to help them communicate more effectively. Originally, brands changed their logos periodically with the aim of communicating anniversaries. These days, not only this information but also emotional communication with users. As a research method, two major portal sites were selected for use in Korea, and a preference survey and in-depth interview were conducted based on the case of the event logos. From the results of the study, we were able to obtain results that the event logos act as a more positive factor when they provide users with various emotional motivations. In the future, we anticipate that users will be given higher value if they have a design approach that will elicit more diverse emotions from the brand experience.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.2
• /
• pp.125-132
• /
• 2010

Since the ancient times, animals that can imitate the voices of human beings have been considered extremely special. There are very few such animals, and the parrot is an example of them. For a long time, there had been no reported case of a rooster being able to mimic the voice of a human being, but talking roosters were recently found in Korea and the Kyrgyz Republic, generating much talk. In this study, the vocal characteristics of such roosters were examined, and their pronunciation-related statistics and actual sound sources were analyzed. The analysis results showed that even though the roostets cannot converse with people, they can imitate the human voice, uttering the words "An-dwae," and "A-ni-ya" in Korean, which mean "No" in English, when someone tries to catch their wings. A similar situation 'occurred in the Kyrgyzstan. The results of the listening survey on these sounds made by the roosters showed that most people recognized the words uttered by the roosters and that nobody thought that the words sounded like "cock-a-doodle-doo." It can be said that such roosters can make the sounds of the human voice because of their innate vocal organ and characteristics, which are significantly different from those of the general roosters. Their vocal organ and characteristics cause the sounds that they make to change in their vocal cords due to their high tension when humans try to catch them.