• Journal of the Korean Institute of Telematics and Electronics
• /
• v.15 no.6
• /
• pp.8-22
• /
• 1978

Recently developed Computed Topography (CT) reconstruction algorithms are reviewed in a more generalized sense and a few reconstruction examples are given for illustration. The construction of an image function from the physically measured projections of some object is Discussed with reference to the least squares optimum filters, originally derived to enhance the signal-to-noise ratio in communications theory. The computerifed image processing associated with topography is generalized so as to include 3 distinct parts: the construction of an image from the projection, the restoration of a blurred, noisy image, degraded by a known space-invariant impulse response, and the further enhancement of the image, e.g. by edge sharpening. In conjunction with given versions of the popular convolution algorithm, n6t 19 be confused with filtering by a 2-diminsional convolution, we consider the conditions under which a concurrent construction, restoration, and enhancement are possible. Extensive bibliographical limits are given in the references.

• Journal of Conservation Science
• /
• v.27 no.2
• /
• pp.181-190
• /
• 2011

A precision measurement and digital image restoration of the 5th century's gilt bronze cap of Baekje dynasty, excavated from the ancient tomb of Andong, Goheung in 2006, was undertaken. The objective of the scanning is to preserve precise feature of the artefact in the form of digital data by embodying it in 3 dimensional space. Acquirement of the data has been undertaken in the following process : 3D scanning to obtain 3D shape and color information(original data photographing)-3D modelling(joining original data and restoring non-photographed or damaged area)-CG image production. Production of restoration CG image was based on joined shape of original data and each part's measurement on CAD. Non-photographed part and area of loss was restored referring actual measurement and research result of excavated cap from the 5th to 8th century. 3D image restoration is one of artefact restoration methods which restores artefact without risk. It is also undertaken with historical research. As result, this method can enhance aesthetic and academic value of the artefact by successful restoration.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.3
• /
• pp.112-119
• /
• 2005

In this paper, a model of neural circuit was proposed, which abstracts the depth information in two images gotten from right and left retinas. The proposed neural circuit corresponds to binocular stereo vision based on psychologic and physiological knowledge, and we examine a restoration method of three-dimensional surface. In case of drawing a disparity based on characteristics of images, we can not abstract the depth information correctly if resemblant characteristics are repeated on the boundary region of an object. A binocular disparity is decided in a model of neural circuit by abstraction, synthesis, and correction of a disparity. And we propose a method which restores three-dimensional shape by correcting a depth information, and also restores a three-dimensional surface by mapping a left input image on the restored three-dimensional shape. And we confirmed that the computation time for disparity abstraction can be greatly reduced through the simulation.

• Current Optics and Photonics
• /
• v.7 no.3
• /
• pp.237-247
• /
• 2023

In middle- and long-distance imaging systems, due to the atmospheric turbulence caused by temperature, wind speed, humidity, and so on, light waves propagating in the air are distorted, resulting in image-quality degradation such as geometric deformation and fuzziness. In remote sensing, astronomical observation, and traffic monitoring, image information loss due to degradation causes huge losses, so effective restoration of degraded images is very important. To restore images degraded by atmospheric turbulence, an image-restoration method based on improved compound multibranch feature fusion (CMFNetPro) was proposed. Based on the CMFNet network, an efficient channel-attention mechanism was used to replace the channel-attention mechanism to improve image quality and network efficiency. In the experiment, two-dimensional random distortion vector fields were used to construct two turbulent datasets with different degrees of distortion, based on the Google Landmarks Dataset v2 dataset. The experimental results showed that compared to the CMFNet, DeblurGAN-v2, and MIMO-UNet models, the proposed CMFNetPro network achieves better performance in both quality and training cost of turbulent-image restoration. In the mixed training, CMFNetPro was 1.2391 dB (weak turbulence), 0.8602 dB (strong turbulence) respectively higher in terms of peak signal-to-noise ratio and 0.0015 (weak turbulence), 0.0136 (strong turbulence) respectively higher in terms of structure similarity compared to CMFNet. CMFNetPro was 14.4 hours faster compared to the CMFNet. This provides a feasible scheme for turbulent-image restoration based on deep learning.

• Proceedings of the KIEE Conference
• /
• 1979.08a
• /
• pp.158-159
• /
• 1979

Based on minimum-mean-sqare error criterion, a noise filtering algorithm for the reconstruction of an image function from noisy projection data is suggested. The filter is constructed with a few projection data. This algorithm requires less computational time compared with other noise filtering algorithm.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.723-731
• /
• 2017

The restoration of archaeological data was carried out using photographs and drawings left as past records. It can be divided into ruins and artifacts. The restoration of the ruins was performed by modeling the individual parts and parts left by the photographs, aligning them and synthesizing them, and reconstructing them three-dimensionally as one object. Restoration of artifacts was performed on both photographs and drawings. After the modeling work is prioritized through the photographs, there is a method of restoring the original image by modifying the texture image of the damaged part of the modeled artifact, or restoring the original image by modeling and synthesizing the deleted part in the artifact. The restoration of the artifacts through the drawings was carried out by three - dimensional modeling and reconstruction through real mapping of images. The reconstructed archaeological data can be used in various directions. In particular, it is possible to verify and compare the results of the numerical analysis and interpretation of the past 2D data, and to provide a more accurate analysis plan in the future.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.11a
• /
• pp.153-159
• /
• 2004

Recently remote sensing technology is applied for digital and photographical data acquisition by use of satellites sensors. And It used for images restoration of vanished spatial information at the same sites according to changed of time and spaces. In this study, it applied for the 3-dimensional images generation and fly simulation to possibility for various application. As a results of its applied, it gained the results not only improvement of present methods but also real various application possibilities for 3 dimensional Image restoration.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.4
• /
• pp.135-142
• /
• 2013

This study aims to seek adequate and optimized method of applying high quality three-dimensional spatial data created via high-resolution digital aerial photograph image and aerial LiDAR data onto three-dimensional planning of environmentally friendly, ecological restoration of rivers in accordance with irrigation and flood control objectives of urban rivers. Through three-dimensional modeling of before and after the restoration, the research also offers basic information regarding restorations of rivers. Also the transition from the conventional two-dimensional planning into three-dimensional planning environment using smart spatial information acquire accuracy of river analysis, analyze possible civil complaints and suggest solutions to potential problems.

• Journal of Conservation Science
• /
• v.25 no.2
• /
• pp.115-130
• /
• 2009

This study was focused on digital restoration and structural stability evaluation applying 3D scanning system of five-storied Magoksa temple stone pagoda in Gongju. For these, the digital restoration of the pagoda was completed using laser scan data which is measured 16 directions and data processing program of 7 stages. As a result of digital restoration, the overall height and width of stone properties showed a little difference in directions and the width of roof stones appeared very high difference of each floor. The width of pagoda body become smaller to the fifth floor, but gradual decrease rate showed irregular characteristics. Also, as result of 3D image analysis for structural stability evaluation, the displacement occurred toward northwest in second body stone to upper final stone except for central axis of the first body stone which inclines toward southwest. Such 3D image analysis is required quantification of survey method and should be applied to various field such as quantitative damage maps in order to utilize a conservation of stone cultural heritages, continuously.

• Imaging Science in Dentistry
• /
• v.50 no.4
• /
• pp.331-337
• /
• 2020

Purpose: As cone-beam computed tomography (CBCT) has become the most widely used 3-dimensional (3D) imaging modality in the dental field, storage space and costs for large-capacity data have become an important issue. Therefore, if 3D data can be stored at a clinically acceptable compression rate, the burden in terms of storage space and cost can be reduced and data can be managed more efficiently. In this study, a deep learning network for super-resolution was tested to restore compressed virtual CBCT images. Materials and Methods: Virtual CBCT image data were created with a publicly available online dataset (CQ500) of multidetector computed tomography images using CBCT reconstruction software (TIGRE). A very deep super-resolution (VDSR) network was trained to restore high-resolution virtual CBCT images from the low-resolution virtual CBCT images. Results: The images reconstructed by VDSR showed better image quality than bicubic interpolation in restored images at various scale ratios. The highest scale ratio with clinically acceptable reconstruction accuracy using VDSR was 2.1. Conclusion: VDSR showed promising restoration accuracy in this study. In the future, it will be necessary to experiment with new deep learning algorithms and large-scale data for clinical application of this technology.