• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.644-646
• /
• 2019

테크놀로지의 발달로 영상 이미지는 영상 예술 뿐 만 아니라 다매체에서 디지털이미지로 전달되고 있다. 기존의 영상 이미지는 화면 프레임을 단순히 시간적 움직임을 재현하는 것이나 제한된 화면 효과를 통해 표현되었다. 그러나 테크놀로지의 진보로 인하여 디지털 미디어는 기존 영상 기법을 확장시켜 다양한 표현을 빠르고 쉽고 편리하게 구현이 가능하게 되었다. 이와 같은 기술적 진화는 결과적으로 영상 이미지가 생성하는 이미지와 이미지 사이에 생기는 이질적 간격을 복잡하고 자극적으로 끝임 없이 전달 받게 되는 상황에 놓이게 되었다. 우리에게 디지털 이미지가 생성하는 이미지의 시간성이 움직임을 어떻게 해석할 수 있는지 들뢰즈의 관점에서 살펴보고, 인식적 요소가 실질적으로 어떻게 표현될 수 있는지 실증적인 사례<아디다스 광고 영상>을 중심으로 분석해 보고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.125-128
• /
• 2019

이미지를 보호하기 위한 보안 수단으로는 크게 워터마킹, 스테가노그래피 기법 등이 있다. 그 중 워터마킹 기법은 배경 이미지 위에 사용자가 워터마크로 사용하기 위해 원하는 텍스트나 이미지를 새겨 다른 사람이 사용했을 때, 새겨둔 워터마크를 통해 저작권 등을 증명할 수 있는 용도로 사용하여 이미지를 보호하는 기법이며, 워터마크의 속성에 따라 텍스트 워터마킹, 이미지 워터마킹으로 나뉜다. 본 논문에서는 워터마킹 기법을 이용한 이미지 생성 시, 워터마크 대상 텍스트나 이미지의 크기 및 배치 등을 알맞게 설정하는 방법을 제시하였다. 워터마크 대상의 크기를 배경 이미지에 알맞게 자동으로 조절해 주거나 사용자가 임의로 지정하도록 하여 더욱 자유롭고 효과적인 워터마킹 기법을 구현하였다.

• The Journal of the Korea Contents Association
• /
• v.15 no.9
• /
• pp.11-20
• /
• 2015

Digital watermarking provides electronic means for proving the copyrights of distributed digital media copies. Research on digital watermarking for images is recently directed toward that for color images extensively used in real life, based on the substantial results in digital watermarking for gray-scale images. Color images have multiple channels, each of which corresponds to a gray-scale image. While there are some watermarking techniques for color images that just apply those for gray-scale images to one channel of the color images, the correlation characteristics between the channels are not considered in them. This paper proposes a zero-watermarking technique that makes keys via combining an image dependent watermark, created through comparing two channels of the color image and copyright watermark scrambled. Due to zero-watermarking, it does not change anything of cover(host) images. Watermark images are robust against some common attacks such as sharpening, blurring, JPEG lossy compression, scaling, and cropping.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.4
• /
• pp.355-360
• /
• 2018

We propose a method to connect partial image in whole image to partial image in whole image of other internet site. For this study, we have developed four partial image generation methods and retrieval methods. A method of 'image segmentation' that cuts out only partial images that want to provide information from the whole image, a method of 'creating an image block' that finds outermost points of a cut-out partial image, a method of 'Stamp transformation of outer points', which connects outer points and registers them as the most similar image stamp, and a retrieval method that connects image stamps with other image stamps are developed. We suggested a image search UI that can use image stamps in various ways.

• Journal of KIISE:Software and Applications
• /
• v.31 no.10
• /
• pp.1386-1399
• /
• 2004

This paper presents correlation-based automatic image captioning. Given a training set of annotated images, we want to discover correlations between visual features and textual features, so that we can automatically generate descriptive textual features for a new unseen image. We develop models with multiple design alternatives such as 1) adaptively clustering visual features, 2) weighting visual features and textual features, and 3) reducing dimensionality for noise sup-Pression. We experiment thoroughly on 10 data sets of various content styles from the Corel image database, about 680MB. The major contributions of this work are: (a) we show that careful weighting visual and textual features, as well as clustering visual features adaptively leads to consistent performance improvements, and (b) our proposed methods achieve a relative improvement of up to 45% on annotation accuracy over the state-of-the-art, EM approach.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.31-38
• /
• 2024

In this paper, we propose an ASAP(AI-driven Service for Advertisement Production) application that provides a generative AI-based automatic advertising image production service. This application utilizes GPT-3.5 Turbo Instruct to generate suitable background mood and promotional copy based on user-entered keywords. It utilizes OpenAI's DALL·E 3 model and Stability AI's SDXL model to generate background images and text images based on these inputs. Furthermore, OCR technology is employed to improve the accuracy of text images, and all generated outputs are synthesized to create the final advertisement. Additionally, using the PILLOW and OpenCV libraries, text boxes are implemented to insert details such as phone numbers and business hours at the edges of promotional materials. This application offers small business owners who face difficulties in advertising production a simple and cost-effective solution.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.214-216
• /
• 2003

이 논문은 그래픽스 API인 OpenGL에서 제공하는 기존의 빌보드 기법을 좀 더 사실적으로 표현하기 위한 방법에 대해서 고찰한다. 빌보드 기법은 다각형에 텍스처 이미지를 매핑하여 이 다각형이 항상 시점을 바라보도록 표시하여 어느 정도의 사실성을 유지하는 3차원 영상을 빠르게 생성한다. 그러나, 기존의 빌보드 기법은 물체의 위치에 관계없이 항상 동일한 이미지를 사용하여 사실성이 떨어지는 단점이 있다. 이 논문에서는 기존의 빌보드 기법과 관측 방향에 따라 다른 이미지를 생성하는 뷰 모핑 기법을 조합하여 관측 방향에 따라 물체가 변화하여 보다 사실적인 3차원 영상을 생성하는 빌보드 기법을 제안한다.

• Journal of Internet Computing and Services
• /
• v.18 no.5
• /
• pp.79-85
• /
• 2017

This paper proposes the use of mobile ad-hoc cloud for reducing the process time of panoramic image generation in mobile smart devices. In order to effectively assign tasks relevant to panoramic image generation to the mobile ad-hoc cloud, a method for image acquisition and sorting and an algorithm for task distribution and offloading decision making are proposed. The proposed methods are applied to Android OS based smart devices, and their effects on panoramic image generation are analyzed.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.381-390
• /
• 2022

Many attempts have been made to apply image recognition based on machine learning which has recently advanced dramatically to malware detection. They convert executable files to images and train deep learning networks like CNN to recognize or categorize dangerous executable files, which shows promising results. In this study, we are looking for an effective image generation method that may be used to identify malware using machine learning. To that end, we experiment and assess the effectiveness of various image generation methods in relation to malware detection. Then, we suggest a linear image creation method which represents control flow more clearly and our experiment shows our method can result in better precision in malware detection.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.772-774
• /
• 2008

A navigation system for virtual environments using low-quality HMD(head mounted display)must quantize images when the system presents true-color image with restricted number of colors. Such navigation system quantizes an image by using fixed palette. If the system represents an image by using a variable palette which is made considering a region around the viewpoint then user can perceive a virtual environments more vividly because human visual system is sensitive to the colors variation in the region around the viewpoint. In this paper we propose a color quantization algorithm that quantize a region around the viewpoint more finely than other regions at each variation of viewpoint for virtual environments navigation system and compose virtual environments navigation system using proposed algorithm. The system quantizes an image at each variation of viewpoint and shows a quantized image to user through HMD. We tested user preferences for our proposed system and the results show that users preferred our system.