• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.105-111
• /
• 2023

Currently, most of content restoration using artificial intelligence learning is 2D learning. However, 3D form of artificial intelligence learning is in an incomplete state due to the disadvantage of requiring a lot of computation and learning speed from the existing 2 axes (X, Y) to 3 axes (X, Y, Z). The purpose of this paper is to secure a data-set for artificial intelligence learning by analyzing and 3D modeling the stone pagodas of ourinari by era based on the two-dimensional information (image) of cultural assets. In addition, we analyzed the differences and characteristics of towers in each era in Korea, and proposed a feature modeling method suitable for artificial intelligence learning. Restoration of cultural properties relies on a variety of materials, expert techniques and historical archives. By recording and managing the information necessary for the restoration of cultural properties through this study, it is expected that it will be used as an important documentary heritage for restoring and maintaining Korean traditional pagodas in the future.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.122-131
• /
• 2011

A widely used single image-based 3D face reconstruction method, 3D morphable shape model, reconstructs an accurate 3D facial shape when 2D facial feature points are correctly extracted from an input face image. However, in the case that a user's cooperation is not available such as a real-time 3D face reconstruction system, this method can be vulnerable to the errors of automatic facial feature point extraction. In order to solve this problem, we automatically classify extracted facial feature points into two groups, erroneous and correct ones, and then reconstruct a 3D facial shape by using only the correctly extracted facial feature points. The experimental results showed that the 3D reconstruction performance of the proposed method was remarkably improved compared to that of the previous method which does not consider the errors of automatic facial feature point extraction.

• Journal of the Korea Convergence Society
• /
• v.11 no.11
• /
• pp.165-173
• /
• 2020

ABS and PLA are applied for restoring missing part of damaged ceramics, but are not similar to the material of ceramics, so this study conducted a research on the properties and applicability of ceramic resin. This study conducted actual restoration of ABS and ceramic resin as well as cast restoration method with experiment of properties. Results show that manufacturing of restored part showed higher precision than existing materials, which enables printing of tiny shapes showing excellent surface texture and gloss than L30 and ABS resin. As a result of measuring properties, the material showed excellent durability than existing materials with no contraction and deformation and compressive strength, but value of specific gravity and hardness can lower processability after manufacturing. Long-term monitoring, evaluation of reliability of ceramic resin applied in this study, additional researches on the restorability of the original shape when printing too thin or long restored part are needed.

• Journal of the Korea Computer Graphics Society
• /
• v.21 no.5
• /
• pp.37-44
• /
• 2015

This paper presents a novel 3D model representation, called hybrid model representation, to overcome existing 3D volume-based indoor scene reconstruction mechanism. In indoor 3D scene reconstruction, volume-based model representation can reconstruct detailed 3D model for the narrow scene. However it cannot reconstruct large-scale indoor scene due to its memory consumption. This paper presents a memory efficient plane-hash model representation to enlarge the scalability of the indoor scene reconstruction. Also, the proposed method uses plane-hash model representation to reconstruct large, structural planar objects, and at the same time it uses volume-based model representation to recover small detailed region. Proposed method can be implemented in GPU to accelerate the computation and reconstruct the indoor scene in real-time.

• Conservation Science in Museum
• /
• v.16
• /
• pp.122-137
• /
• 2015

White porcelain pitcher with an openwork dragon and cloud design across its surface in the collection of the National Museum of Korea (Deoksu 5531) was acquired in 1915. The restoration has been so far completed only for the mouth of the pitcher. This study discusses a new method based on 3D scanning and printing for the restoration of missing parts in the openwork dragon and cloud design. A strength test was performed on six output materials that have been already commercialized for comparison with the strength of materials used for traditional restoration such as epoxy putty (Quick Wood^®) and epoxy (Araldite AY103+HY956^®). This process confirmed that the digital technology-aided making of a restoration model requires less time and efforts than handmade work, all the while producing a more precise model. More importantly, this method being a non-contact method, it reduces risks associated with handmade work. Another advantage of this method is that digital pre-restoration images can be saved and used for future references. Notwithstanding, future research is needed on how to effectively apply digital technology for restoration of ancient objects and how to evaluate and use 3D output as well as on the method of shaping, joining and coloring the 3D output.

• Journal of Conservation Science
• /
• v.31 no.2
• /
• pp.131-145
• /
• 2015

Cultural assets restoration is being considered highly as a practical way to extend the lifespan of damaged cultural assets and re-highlight their value. However, restoration process has been mostly dependent on the manual work involving the experience and skill of a person performing restoration, thereby requiring much time and effort. In recent, it became possible to apply a method allowing restoration to be performed more accurately and easily according to the material characteristics and shape of cultural assets. Namely, it is to use a method of printing out the 3D shape data computed in computer as real object by using 3D printer for the restoration that has been performed manually. The missing part of a cultural asset is computed into computer data first and is printed out by using 3D printer to undergo a simple shaping process. The result of 3D printer application showed that repetitive output and shape and figure revision of digital data were possible, and it was possible to improve the degree of completedness of restoration through test output using various types of restoration materials using various materials. For the purpose of verifying the possibility of applying 3D printer to restore missing part of earthenware, two pieces of modern reproductions, namely, the Seven Treasure Incense Burner and Earthenware with Wagon Wheel Decoration, were artificially damaged. The restoration result showed that compared to manual work, it showed better effectiveness in curtailing work time and reproducing accurate shape. On the other hand, secondary manual work was slightly needed for detailed binding and to vividly express surface texture.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.525-527
• /
• 2023

본 논문은 2차원적인 문화재 이미지를 모델링 하여, 대한민국의 시대 별 탑의 차이점과 특징을 분석하고 인공지능을 이용한 3D 복원과 구현을 위한 연구이다. 오늘날 현대 사회에서 디지털 매체 및 정보화 시대에서 여러 산업 분야에 적용이 되고 있다. 기존 2D 이미지를 벗어나 문화재의 모습을 다양한 각도에서 쉽게 관찰해 볼 수 있도록 하여, 3D 형태의 복원이 적합하여 연구를 진행하였다. 최근 인공지능 및 기술의 발달로 문화재 정보를 바탕으로 한 3차원 기술을 사용하여 다양한 데이터들과 프로그램을 이용한 모델링이 가능하다. 현재 문화재 복원은 다양한 자료와 전문가의 기술 및 역사적인 기록물 자료에 의존해 복구한다. 이러한 기법의 문화재 복원은 기록에 남길 수 있는 정보 수집의 효율적인 방법이 될 수 있다. 본 연구는 우리나라의 시대별 탑의 특징을 보여주며, 복원이 실제적이고도 구체적인 다각도의 방향에서 더 정밀하고 정확하게 도출하는데 기여할 것으로 기대된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.10
• /
• pp.2280-2286
• /
• 2012

In this paper, we propose a novel nonlinear 3D image correlator using a fast computational integral imaging reconstruction (CIIR) method. In order to implement the fast CIIR method, the magnification process was eliminated. In the proposed correlator, elemental images of the reference and target objects are picked up by lenslet arrays. Using these elemental images, reference and target plane images are reconstructed on the output plane by means of the proposed fast CIIR method. Then, through nonlinear cross-correlations between the reconstructed reference and the target plane images, the pattern recognition can be performed from the correlation outputs. Nonlinear correlation operation can improve the recognition of 3D objects. To show the feasibility of the proposed method, some preliminary experiments are carried out and the results are presented by comparing the conventional method.

• Journal of KIISE:Software and Applications
• /
• v.31 no.11
• /
• pp.1543-1550
• /
• 2004

Modeling from images is a cost-effective means of obtaining 3D geometric models. These models can be effectively constructed from classical Structure from Motion algorithm. However, it's too difficult to reconstruct whole scenes using SFM method since general sites contain a very complex shapes and brilliant colours. To overcome this difficulty, the current paper proposes a new reconstruction method based on a moving Planar mirror. We devise the mirror posture instead of scene itself as a cue for reconstructing the geometry That implies that the geometric cues are inserted into the scene by compulsion. With this method, we can obtain the geometric details regardless of the scene complexity. For this purpose, we first capture image sequences through the moving mirror containing the interested scene, and then calibrate the camera through the mirror's posture. Since the calibration results are still inaccurate due to the detection error, the camera pose is revised using frame-correspondence of the comer points that are easily obtained using the initial camera posture. Finally, 3D information is computed from a set of calibrated image sequences. We validate our approach with a set of experiments on some complex objects.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.486-492
• /
• 2006

본 논문에서는 비디오에서의 특징점 추적을 통해 얻은 2D 좌표를 이용한 3D 구조를 추정하는 방법과 네 점 이상의 공통점을 이용한 융합 방법을 제안한다. 영상의 각 프레임에서 공통되는 특징점을 이용하여 형상을 추정한다. 영상의 각 프레임에 대한 특징점의 추적은 Lucas-Kanade 방법을 사용하였다. 3D 좌표 추정 방법으로 개선된 직교분해기법을 사용하였다. 개선된 직교분해기법에서는 3D 좌표를 복원함과 동시에 카메라의 위치와 방향을 계산할 수 있다. 복원된 부분 데이터들은 전체를 이루는 일부분이므로, 융합을 통해 완성된 모습을 만들 수 있다. 복원된 부분 데이터들의 서로 다른 좌표계를 기준 좌표계로 변환함으로써 융합할 수 있다. 융합은 카메라의 모션에 해당하는 카메라의 위치와 방향에 의존된다. 융합 과정은 모두 선형으로 평균 0.5초 이하의 수행 속도를 보이며 융합의 오차는 평균 0.1cm 이하의 오차를 보였다.