• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.1
• /
• pp.139-147
• /
• 2019

In this paper we propose a method to distinguish damaged electronic records and an electronic record recovery method according to damage type. The proposed classification engine and recovery engine classify damaged electronic records based on the form and structure of electronic records and increase the probability of recovery according to the damaged form. Through this process, we propose a method to minimize the electronic records that are destroyed and verify them through experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.550-552
• /
• 2014

In this paper, we propose an interleaver reconstruction method for punctured channel coded signals. We calculate the ratio of the number of '1' bits to the number of '0' bits in the matrix which is generated by a Gaussian elimination process. Then, we can reconstruct an interleaver by checking the minimum values of the ratio that have a smaller ratio than a certain threshold. We validate the proposed method through computer simulations.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.41-48
• /
• 2022

This paper presents the unified Bayesian Tikhonov regularization method as a solution to total variation regularization. The integrated method presents a formula for obtaining the regularization parameter by transforming the total variation term into a weighted Tikhonov regularization term. It repeats until the reconstructed image converges to obtain a regularization parameter and a new weighting factor based on it. The experimental results show the effectiveness of the proposed method for the image restoration problem.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.327-330
• /
• 2021

본 논문은 RGB 영상 데이터셋의 일부만을 지도학습하여(Sparsely-supervised learning) Annotation 되지 않은 영상에 대해 손-객체의 3D 포즈를 복원하기 위한 방법을 제안한다. 기존의 연구에서는 손-객체의 포즈에 해당하는 6DoF 만을 학습 데이터로 활용한다. 이와 달리, 본 논문에서는 정확도 향상을 위해 복원된 결과를 동일한 입력 영상 내에서 비교 가능하도록 3D 모델로 복원한 결과를 입력 영상의 마스크로 만들어 학습에 반영하였다. 구체적으로 추정된 포즈로 만들어낸 마스크를 입력 영상에 적용한 결과와 Ground-truth 포즈를 적용한 영상을 학습 시에 손실 함수에 반영하였다. 비교 실험을 통해 제안된 방법이 해당 방법을 적용하지 않은 경우 보다 3D 매쉬 오차가 적었음을 확인할 수 있었다.

• The KIPS Transactions:PartD
• /
• v.15D no.4
• /
• pp.581-588
• /
• 2008

Old films or photographs usually have damages from physical or chemical effects, and the damage and digitalization make stain, scratch, scribbling, noise, and digital drop out in frames. Damages include global damage and local damage, and it is well known that local damage restoration is a main factor for improving image quality. Previous researches have focused on impairment localization (esp. for line scratch impairments) and restoration techniques for line scratch, dirt, blob, and intentional scratch. Inpainting is a key technique using partial derivatives to restore damages in images. It does not show good quality for the complex images because it is based on finite order for partial derivatives, and it takes much time complexity. In this paper, we present a modified inpainting scheme, where we use Sobel edge operator's and angle to compute isophotes, and compare our scheme with Bertalmio's scheme. We experiment our scheme with two old Korean films, and Simulation results show that our scheme requires smaller time complexity than Bertalmio's scheme with comparable reconstructed image quality.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.8
• /
• pp.1803-1813
• /
• 1997

The goal of image restoration is to remove the degradations in a way that the resrored image will best approximate the original image. This can be done by the iterative regularized image restoration method. In any iterative image restoration algorithm, using a "better" termination rule results in both "better" quality of ther restored image and "less" computation, and hence, "faster" and "simp;er" practical system. Therefore, finding a better termmination rule for an iterative image restoration algorithm has been an interesting and improtant question for many researchers in the iterative image restoration. In these reasons, the new termination rule using the estimated distance between the original image and the restored image is proposed inthis paper. Noise suppression parameter(NSP) and the rule for estimating NSP with the noise variance are also proposed. The experimental results shows that the proposed termination rule is superior to the conventional methods.

• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.183-188
• /
• 2010

A factorization-based 3D reconstruction system is realized to recover 3D scene from an image sequence. The image sequence is captured from uncalibrated perspective camera from several views. Many matched feature points over all images are obtained by feature tracking method. Then, these data are supplied to the 3D reconstruction module to obtain the projective reconstruction. Projective reconstruction is converted to Euclidean reconstruction by enforcing several metric constraints. After many triangular meshes are obtained, realistic reconstruction of 3D models are finished by texture mapping. The developed system is implemented in C++, and Qt library is used to implement the system user interface. OpenGL graphics library is used to realize the texture mapping routine and the model visualization program. Experimental results using synthetic and real image data are included to demonstrate the effectiveness of the developed system.

• Korean Journal of Heritage: History & Science
• /
• v.48 no.4
• /
• pp.138-153
• /
• 2015

A Jincheon Seokjangri B23 furnace was reconstructed and iron smelting experiment was performed to investigate an ancient Baekjae iron production process. The work mainly described in this paper is the $1^{st}$ and $2^{nd}$ experiments among the several experiments carried out at Jungwon National Research Institute of Cultural Heritage. Iron ore(magnetite) and oak charcoal were used as a source and a foot bellow was used for air supply. Common results of the experiments are masses of iron, slag and charcoal formed in the furnace. Most iron lumps were formed nearby the tuyere rather than the area of tapping hole. Metallographic and chemical analysis shows that the iron lumps can be used for either forge or cast depending on their carbon content. Low Fe content and glassy texture of the inner slags suggest that the operation environment was quite reducing. Based on the results of the iron smelting experiments, measurements and analysis, various information was obtained regarding physical-chemical and metallurgical processes of the ancient iron smelting process. It is firmly believed that its undisclosed contents can be revealed more in depth with continual reconstitution experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.10C
• /
• pp.621-628
• /
• 2011

The skin color has been used as important cues in the systems for detecting or recognizmg the face. However, the color difference in images under different illuminants makes it difficult to find out the skin in these systems. For solving the problem, this paper proposes a method of recovering skin colors based on well-known color constancy approaches, such as Retinex, Gray World, White Patch, and Simplified Horn. To acquire experimental images under the colored scene illumination, the effects of colored illuminants were added to source images. Next, result images, having the corrected skin color by the constancy methods, were derived from the source images. The experiment results showed that most of the skin colors in our experiments were recovered into some steady range in the color space, and that Gray World had higher performance than the other methods compared.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.457-461
• /
• 2010

Even though face recognition researches have been developed for a long ago, there is no practical face recognition system in real life. It is caused by several real situations where non-facial components such as glasses, scarf, and hair occlude facial components while facial images in a face database are well designed. This occlusion decreases recognition performance. Previous approaches in recent years have tried to solve non-facial components but have not resulted in enough performance. In this paper, we propose a method to handle this problem based on support vector data description, which trains the hyperball in feature space to find the minimum distance estimating the approximated face. In order to evaluate its performance and validate the effectiveness of the proposed method, we make several experiments and the results show that the proposed method has a considerable effectiveness.