• Journal of the Korea Computer Graphics Society
• /
• v.12 no.1
• /
• pp.17-20
• /
• 2006

본 논문에서는 실사 렌더링에서 디테일한 조명 효과를 위해 쓰이는 범프 매핑 기술을 이용하여 기하적으로 복잡한 지오메트리를 표현하되, 이미지 스페이스상의 실루엣 검출 기법과 카툰 쉐이딩을 적용하여 만화적인 스타일을 연출하였다. 이 연구를 통해 기존의 카툰 렌더링된 3D 씬에 범프매핑으로 표현된 오브젝트가 자연스럽게 어울릴 수 있고, 빌보드 이미지에도 카툰 렌더링을 적용하여 빛에 대한 변화 효과를 보여줄 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.575-576
• /
• 2023

본 논문에서는 텍스처 합성할 때 방향을 고려하여 합성의 품질의 개선시킬 수 있는 방법을 제안한다. 또한 고정된 회전 각도가 아닌, 다양한 각도를 자동으로 샘플링하여 효율적으로 예제 이미지를 생성할 수 있도록 하였고, 이를 통해 합성 경계간의 차이를 자연스럽게 완화시킬 수 있는 결과를 실험을 통해 보여준다.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.205-214
• /
• 2006

Texts in images have significant and detailed information about the scenes, and if we can automatically detect and recognize those texts in real-time, it can be used in various applications. In this paper, we propose a new text detection method that can find texts from the various camera-captured images and propose a text segmentation method from the detected text regions. The detection method proposes color variance as a detection feature in RGB color space, and the segmentation method suggests an improved K-means color clustering in RGB color space. We have tested the proposed methods using various kinds of document style and natural scene images captured by digital cameras and mobile-phone camera, and we also tested the method with a portion of ICDAR[1] contest images.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.727-730
• /
• 2021

이미지와 비디오 합성 기술에 대한 수요가 늘어남에 따라, 인간의 손에만 의존하여 이미지나 비디오를 합성하는데에는 시간과 자원이 한정적이며, 전문적인 지식을 요한다. 이러한 문제를 해결하기 위해 최근에는 스타일 변환 네트워크를 통해 이미지를 변환하고, 믹싱하여 생성하는 알고리즘이 등장하고 있다. 이에 본 논문에서는 GAN을 이용한 스타일 변환 네트워크를 통한 자연스러운 스타일 믹싱에 대해 연구했다. 먼저 애니메이션 토이 스토리의 등장인물에 대한 데이터를 구축하고, 모델을 학습하고 두 개의 모델을 블렌딩하는 일련의 과정을 거쳐 모델을 준비한다. 그 다음에 블렌딩된 모델을 통해 타겟 이미지에 대하여 스타일 믹싱을 진행하며, 이 때 이미지 해상도와 projection 반복 값으로 스타일 변환 정도를 조절한다. 최종적으로 스타일 믹싱한 결과 이미지들을 바탕으로 하여 스타일 변형, 스타일 합성이 된 인물에 대한 동영상을 생성한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.6
• /
• pp.700-705
• /
• 2020

Generative adversarial networks are methods of generating images by opposing two neural networks. When generating the image, randomly generated noise is rearranged to generate the image. The image generated by this method is not generated well depending on the noise, and it is difficult to generate a proper image when the number of pixels of the image is small In addition, the speed and size of data accumulation in data classification increases, and there are many difficulties in labeling them. In this paper, to solve this problem, we propose a technique to generate noise based on random noise using real data. Since the proposed system generates an image based on the existing image, it is confirmed that it is possible to generate a more natural image, and if it is used for learning, it shows a higher hit rate than the existing method using the hostile neural network respectively.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.33 no.4
• /
• pp.278-283
• /
• 2017

Purpose: The aim of this study was to evaluate the interdental distances of anterior, premolar, and molar teeth at the cementoenamel junction (CEJ) and 2 mm below the CEJ in healthy natural dentition with cone-beam computerized tomography (cone-beam CT) in order to provide valuable data for ideal implant positioning relative to mesiodistal bone dimensions. Materials and Methods: Two hundred patients who visited Dental Hospital, Wonkwang University, who had natural dentition with healthy interdental papillae, and who underwent cone-beam CT were selected. The cone-beam CT images were converted to digital imaging and communication in medicine (DICOM) files and reconstructed in three-dimensional images. To standardize the cone-beam CT images, head reorientation was performed. All of the measurements were determined on the reconstructed panoramic images by three professionally trained dentists. Results: At the CEJ, the mean maxillary interdental distances were 1.84 mm (anterior teeth), 2.07 mm (premolar), and 2.08 mm (molar), and the mean mandibular interproximal distances were 1.55 mm (anterior teeth), 2.20 mm (premolar), and 2.36 mm (molar). At 2mm below the CEJ, the mean maxillary interdental distances were 2.19 mm (anterior teeth), 2.51 mm (premolar), and 2.60 mm (molar), and the mean mandibular interproximal distances were 1.86 mm (anterior teeth), 2.53 mm (premolar), and 3.01 mm (molar). Conclusion: The interdental distances in the natural dentition were larger at the posterior teeth than at the anterior teeth and also at 2 mm below the CEJ level compared with at the CEJ level. The distances between mandibular incisors were the narrowest and the distances between mandibular molars were the widest in the entire dentition.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.75-81
• /
• 2013

We presents a novel (2, 2) secret sharing (SS) scheme for all grayscale images. Generally, a secret image is distribute more than two shadow images, which are dealt out among participants. In order to find out secret image, participants print shadow images to transparent papers. Then, a secret image will appear as stacking transparent papers. The secret sharing scheme in this paper distribute secret image into natural grayscale images using multiplexer and data hiding scheme. After then, two participant have two shadow images respectively. The merit of the proposed scheme is that shadow images have small loss in aspect of the quality with steganographic features. Therefore, the proposed secret sharing scheme in this paper is not easily detected by attackers. The experiment result verified that the proposed scheme, obviously outperforms previous SS schemes.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.65-70
• /
• 2013

Recently, the field of computer vision has been actively researched through digital image which can be easily generated as the development and expansion of digital camera technology. Especially, research that extracts and utilizes the feature in image has been actively carried out. The image stitching is a method that creates the high resolution image using features extract and match. Image stitching can be widely used in military and medical purposes as well as in variety fields of real life. In this paper, we have proposed efficient image stitching method using fast feature descriptor extraction and matching based on SURF algorithm. It can be accurately, and quickly found matching point by reduction of dimension of feature descriptor. The feature descriptor is generated by classifying of unnecessary minutiae in extracted features. To reduce the computational time and efficient match feature, we have reduced dimension of the descriptor and expanded orientation window. In our results, the processing time of feature matching and image stitching are faster than previous algorithms, and also that method can make natural-looking stitched image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.5
• /
• pp.959-966
• /
• 2017

Currently, the market of digital contents such as e-books, cartoons and webtoons is growing up, but the copyrights infringement are serious issue due to their distribution through illegal ways. However, the technologies for copyright protection are not developed enough. Therefore, in this paper, we propose the NSS-based publication classification method for copyright protection. Using histogram calculated by NSS, we propose classification method for digital contents using SVM. The proposed algorithm will be useful for copyright protection because it lets us distinguish illegal distributed digital contents more easily.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.385-392
• /
• 2018

Iksan is one of medium city in Jellabukdo, South Korea. It has a favorable natural environment for the specialization potential of natural industries and development projects. In addition, it has various historical and cultural resources including Mireuksajji, and KTX Honam line which has been opened for a representative feature as transport city. However, it faces week connection with neighboring cities and large scale of development in neighboring areas, especially in Jeonju and Gunsan. In this paper, we try to classify the urban image assets of Iksan as 'Iksan Station' and 'ktx' on keywords and analyze the possibility of being a center of transportation and logistics through big data analysis extracted from SNS and website. In comparison with Gwangju Songjeong, KTX Honam line station, which has been developed with similar regional characteristics, it is aimed to establish the basis of improvement and establishment of urban image of Iksan city in the future.