• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.19 no.1
• /
• pp.47-56
• /
• 2015

In this paper, we present an implicit method for reconstructing a 3D solid model from two 2D cross section images. The proposed method is based on the Cahn-Hilliard model for the image inpainting. Image inpainting is the process of reconstructing lost parts of images based on information from neighboring areas. We treat the empty region between the two cross sections as inpainting region and use two cross sections as neighboring information. We initialize the empty region by the linear interpolation. We perform numerical experiments demonstrating that our proposed method can generate a smooth 3D solid model from two cross section data.

• The Journal of the Korea Contents Association
• /
• v.14 no.2
• /
• pp.1-9
• /
• 2014

Image inpainting is the widely used technique to restore a damaged region or to fill a hole in an image. The exemplar-based technique effectively generates new texture by copying colour values of the most correlated patch in the source into the empty region of the current patch. In traditional exemplar-based synthesis, the patch correlation is computed using only the already filled pixels of the current patch. Thus, by ignoring the correlation between the hole regions of the two patches, an undesirable patch which is highly correlated with the current patch in the already filled area but considerably dissimilar in the area to be filled can be selected, which results in bad texture propagation. To avoid such problems, a new exemplar-based inpainting method using patch extrapolation is proposed. The empty part of the current patch is extrapolated beforehand, and then the complete patch is used for finding its exemplar. Experimental results show that the proposed method provides more natural synthesis results than the conventional ones.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.13 no.3
• /
• pp.225-236
• /
• 2009

Image inpainting is the process of reconstructing lost or deteriorated parts of images using information from surrounding areas. We propose a computationally efficient and fast phase-field method which uses automatic switching parameter, adaptive time step, and automatic stopping of calculation. The algorithm is based on an energy functional. We demonstrate the performance of our new method and compare it with a previous method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.881-895
• /
• 2023

Modern image inpainting techniques based on deep learning have achieved remarkable performance, and more and more people are working on repairing more complex and larger missing areas, although this is still challenging, especially for facial image inpainting. For a face image with a huge missing area, there are very few valid pixels available; however, people have an ability to imagine the complete picture in their mind according to their subjective will. It is important to simulate this capability while maintaining the identity features of the face as much as possible. To achieve this goal, we propose a three-stage network model, which we refer to as the identity and structure feature refinement network (ISFRNet). ISFRNet is based on 1) a pre-trained pSp-styleGAN model that generates an extremely realistic face image with rich structural features; 2) a shallow structured network with a small receptive field; and 3) a modified U-net with two encoders and a decoder, which has a large receptive field. We choose structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), L1 Loss and learned perceptual image patch similarity (LPIPS) to evaluate our model. When the missing region is 20%-40%, the above four metric scores of our model are 28.12, 0.942, 0.015 and 0.090, respectively. When the lost area is between 40% and 60%, the metric scores are 23.31, 0.840, 0.053 and 0.177, respectively. Our inpainting network not only guarantees excellent face identity feature recovery but also exhibits state-of-the-art performance compared to other multi-stage refinement models.

• Journal of Korea Game Society
• /
• v.15 no.6
• /
• pp.121-130
• /
• 2015

In this paper, we propose a method to automatically create the contents for spot-the-difference games. A spot-the-difference game is the game that finds the differences such as removal of some objects in the image or changes of shapes and colors from the original image. The original purpose of the exemplar-based image inpainting technique is to remove unnecessary objects. We use the exemplar-based inpainting technique to make the spot-the-difference game contents. From our implementation and experiments, we showed the effectiveness of our automatic generation technique of spot-the-difference contents.

• Journal of the Optical Society of Korea
• /
• v.19 no.3
• /
• pp.248-254
• /
• 2015

In this paper we propose an improved version of the computational integral imaging reconstruction (CIIR) for visualizing a partially occluded object by utilizing an image inpainting technique. In the proposed method the elemental images for a partially occluded three-dimensional (3D) object are recorded through the integral imaging pickup process. Next, the depth of occlusion within the elemental images is estimated using two different CIIR methods, and the weight mask pattern for occlusion is generated. After that, we apply our image inpainting technique to the recorded elemental images to fill in the occluding area with reliable data, using information from neighboring pixels. Finally, the inpainted elemental images for the occluded region are reconstructed using the CIIR process. To verify the validity of the proposed system, we carry out preliminary experiments in which faces are the objects. The experimental results reveal that the proposed system can dramatically improve the quality of a reconstructed CIIR image.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.200-203
• /
• 2021

본 논문에서는 Stereoscopic VR 영상안의 Hole 을 제거하기 위한 효과적인 Inpainting 기술을 소개한다. 본 논문은 Mesh-based warping 과 Blending 기술을 적용하여 Hole 을 제거하는 새로운 Inpainting 알고리즘을 기술하였고, 성능 평가를 통해 제안 방법이 고품질의 Stereoscopic VR 영상을 생성시킬 수 있음을 확인하였다.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2006.06a
• /
• pp.49-52
• /
• 2006

오늘날 컴퓨터의 발달과 인터넷의 확산으로 멀티미디어 컨텐츠의 보급이 급격히 확대되고 있으며, 이들 컨텐츠에는 원거리 화상회의, 감시시스템, 주문형 비디오(VOD), 주문형 뉴스(NOD), 디지털 편집 시스템 등 동영상이 포함되어 있다. 이처럼 동영상은 정보교환과 정보표현의 매개물로서 중요한 역할을 한다. 그러나 이와 같은 동영상은 노이즈나 전송과정 중 발생하는 문제 등으로 인해 항상 좋은 품질을 보장되지 않는다. 이런 훼손된 영상을 원영상으로 복원하거나 사용자가 제거 혹은 복원하고자 하는 영역을 지정 처리함으로서 다양한 정보를 획득할 수 있다. 일반적으로 pc에서 사용되어지는 대부분의 동영상은 $15fps{\sim}30fps$이다. 대부분의 동영상 편집 기술은 각각의 frame을 추출하여 수동적으로 처리하므로 비용과 시간이 많이 든다. 이런 단점을 해결하기 위해 여러 방법이 기존에 시도되고 있다. 제거 혹은 복원하고자 하는 영역을 전 frame에서 처리하기 위해 움직임 검출 및 추적기법이 사용되며, 제거 혹은 복원하기 위해 median filtering, image inpainting 처리 방법들이 있다. 본 연구에서는 사용자에 의해 미리 정의된 바운딩 박스내의 객체를 추적하여 객체의 중심값을 찾는 mean-shift algorithm을 이용하여 움직이는 객체를 추적하였고 image Inpainting algorithm을 이용하여 훼손된 영역을 복원하거나 제거하고자 하는 객체를 제거하였다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.24 no.4
• /
• pp.363-374
• /
• 2020

Fingerprint authentication identifies a user based on the individual's unique fingerprint features. Fingerprint authentication methods are used in various real-life devices because they are convenient and safe and there is no risk of leakage, loss, or oblivion. However, fingerprint authentication methods are often ineffective when there is contamination of the given image through wet, dirty, dry, or wounded fingers. In this paper, a method is proposed to remove noise from fingerprint images using a convolutional neural network. The proposed model was verified using the dataset from the ChaLearn LAP Inpainting Competition Track 3-Fingerprint Denoising and Inpainting, ECCV 2018. It was demonstrated that the model proposed in this paper obtains better results with respect to the methods that achieved high performances in the competition.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.4
• /
• pp.249-254
• /
• 2007

This paper describes a technique for detecting the boundary of the optic disk in digital image of the retina using inward and outward curve evolution. Optic disk boundary offers medical information about glaucoma progresses. For accurate boundary detection, image inpainting based on PDE removes blood vessels crossing the optic disk. For removing noises and preserving boundary of optic disk in image inpainting process, the anisotropic diffusion filtering is developed. After pre-processing, the optic disk boundary is determined using inward and outward curve evolution. Experimental results show that blurring effect of original region and optic disk boundary is reduced considerably. By the proposed method, we can detect correct disk boundary compare to conventional method.