• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2005년도 추계학술대회 논문집
• /
• pp.221-224
• /
• 2005

대부분의 영상은 다양한 이유(노이즈, 전송과정 중 발생하는 문제 등)로 인해 항상 좋은 품질을 보여주진 못한다. 이렇게 훼손된 영상의 복원은 다양한 정보를 제공한다. 이런 훼손된 영상을 복원하기 위해 Median filtering과 같은 기존의 처리 방법들은 주변 화소(Pixel)를 평활화(Smoothing) 처리를 하기 때문에 noise 처리에는 좋으나 원 영상의 중요한 에지 성분까지도 평활화 처리를 함으로써 에지 부분의 공간적 이동을 초래할 수 있다. 이러한 문제점을 해결하기 위하여 image inpainting 방법이 제안되고 있으며, inpainting 기법에는 편미분 방정식(PDE)을 이용한 방법, 텍스쳐 병합 기반의 방법들이 있다. 그러나 이러한 inpainting 기법들은 연산 수행시간이 많이 소요되는 단점이 있다. 따라서 본 연구에서는 image inpainting을 수행시 소요되는 연산시간을 줄이는 fast image inpainting 알고리즘을 제안한다.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1129-1144
• /
• 2020

The thangka image inpainting method based on wavelet transform is not ideal for contour curves when the high frequency information is repaired. In order to solve the problem, a new image inpainting algorithm is proposed based on edge structural constraints and wavelet transform coefficients. Firstly, a damaged thangka image is decomposed into low frequency subgraphs and high frequency subgraphs with different resolutions using wavelet transform. Then, the improved fast marching method is used to repair the low frequency subgraphs which represent structural information of the image. At the same time, for the high frequency subgraphs which represent textural information of the image, the extracted and repaired edge contour information is used to constrain structure inpainting in the proposed algorithm. Finally, the texture part is repaired using texture synthesis based on the wavelet coefficient characteristic of each subgraph. In this paper, the improved method is compared with the existing three methods. It is found that the improved method is superior to them in inpainting accuracy, especially in the case of contour curve. The experimental results show that the hierarchical method combined with structural constraints has a good effect on the edge damage of thangka images.

• 방송공학회논문지
• /
• 제24권1호
• /
• pp.186-189
• /
• 2019

영상 인페인팅(image inpainting)이란 입력 영상에 훼손되거나 빈 영영이 존재할 경우 이 영역을 자연스럽게 채워 영상을 복원해내는 영상처리 기법이다. 본 논문에서는 기존의 예제 기반(exemplar-based) 영상 인페인팅의 단점 중 하나인 텍스쳐 가비지(texture garbage)의 생성을 억제할 수 있는 새로운 영상 인페인팅 기법을 제시한다. 기존 기법과 달리 영상의 텍스쳐는 통계적으로 정적(stationary)이라는 가정 하에 정적인 소스 패치만을 후보 패치로 샘플링 한다. 이를 통해 주변 신호와 일치하지 않는 신호인 텍스쳐 가비지가 타겟 영역에 복사되는 것을 방지할 수 있다. 실험을 통해 제안 기법을 이용한 텍스쳐 합성이 기존 기법에 비해 더욱 자연스러운 영상 인페인팅 결과를 생성함을 확인한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2009년도 추계학술발표대회
• /
• pp.349-350
• /
• 2009

In this paper, we describe an error concealment techniques based on image inpainting for the image impairments due to the packet loss. Image inpainting is to remove or restore the damaged sections from the images, which is usually old images, paintings, or video films. Inpainting has a long history which goes back to the era when the paintings come out. Manual inpainting is no more used, and we can use digital inpainting for the digitally impaired images and video sequences. In this paper, we review the error concealment techniques for the packet loss recovery and propose our inpainting based image impairment recovery scheme for video communication over packet networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.877-893
• /
• 2022

With the development of deep learning, face inpainting has been significantly enhanced in the past few years. Although image inpainting framework integrated with generative adversarial network or attention mechanism enhanced the semantic understanding among facial components, the issues of reconstruction on corrupted regions are still worthy to explore, such as blurred edge structure, excessive smoothness, unreasonable semantic understanding and visual artifacts, etc. To address these issues, we propose a Learnable Structure Knowledge of Fusion Network (LSK-FNet), which learns a prior knowledge by edge generation network for image inpainting. The architecture involves two steps: Firstly, structure information obtained by edge generation network is used as the prior knowledge for face inpainting network. Secondly, both the generated prior knowledge and the incomplete image are fed into the face inpainting network together to get the fusion information. To improve the accuracy of inpainting, both of gated convolution and region normalization are applied in our proposed model. We evaluate our LSK-FNet qualitatively and quantitatively on the CelebA-HQ dataset. The experimental results demonstrate that the edge structure and details of facial images can be improved by using LSK-FNet. Our model surpasses the compared models on L1, PSNR and SSIM metrics. When the masked region is less than 20%, L1 loss reduce by more than 4.3%.

• Journal of the Optical Society of Korea
• /
• 제19권4호
• /
• pp.390-396
• /
• 2015

We propose a partial occlusion removal method for computational integral imaging reconstruction (CIIR) based on the usage of the exemplar based inpainting technique. The proposed method is an improved version of the original linear inpainting based CIIR (LI-CIIR), which uses the inpainting technique to fill in the data missing region. The LI-CIIR shows good results for images which contain objects with smooth surfaces. However, if the object has a textured surface, the result of the LI-CIIR deteriorates, since the linear inpainting cannot recover the textured data in the data missing region well. In this work, we utilize the exemplar based inpainting to fill in the textured data in the data missing region. We call the proposed method the neighboring elemental image exemplar based inpainting (NEI-exemplar inpainting) method, since it uses sources from neighboring elemental images to fill in the data missing region. Furthermore, we also propose an automatic occluding region extraction method based on the use of the mutual constraint using depth estimation (MC-DE) and the level set based bimodal segmentation. Experimental results show the validity of the proposed system.

• 전자공학회논문지CI
• /
• 제48권1호
• /
• pp.8-16
• /
• 2011

영상 인페인팅(Image Inpainting)은 영상에서 손상된 영역을 제거하고 제거한 영역을 주변 영역과 유사하게 채워 넣어 자연스럽게 만E는 영상 복원의 한 기법이다. 그러나 제거할 영액이 클 경우, 복원한 결과의 구조가 자연스럽지 않아 원하지 않는 영상을 획득할 수 있는 문제가 발생한다. 본 논문에서는 화소 값 차이뿐만 아니라 거리 정보를 고려한 다중 패치들을 사용하는 향상된 예제 기반 영상 인페인팅 기법을 제안한다. 일반적인 예제 기반 영상 인페인팅 기법에서는 패치를 잘못 선택함으로써 블록 현상 같은 부자연스러운 결과들이 발생할 수 있다. 이런 문제점을 개선하기 위해 채워질 패치와 원본 영역에서의 패치들 간의 공간상 거리와 화소 값 차이를 둘 다 고려하여 여러 후보 패치들을 선택하고 선택된 패치들의 가중치를 적용하여 새로운 구조와 질감 정보를 생성하는 것을 제안한다. 실험 결과를 통해 제안하는 방법을 이용한 결과가 기존의 방법을 이용한 결과보다 구조와 질감 정보가 보다 향상된 결과를 보여준다.

• 한국방사선학회논문지
• /
• 제11권7호
• /
• pp.655-661
• /
• 2017

방사선 치료 전 환자 위치 확인을 위해 수행하는 콘빔 CT 촬영에서 환자 선량 감소를 위해 Sparse view CT가 사용되고 있다. 본 연구는 시뮬레이션과 실험을 통해 선형보간법과 inpainting 방법을 이용하여 사이노그램의 sparse 데이터 복원하고 평가하는 것이다. 사이노그램 복원은 여러 간격의 각도로 획득된 영상에 적용되었다. 복원된 사이노그램은 역투영재구성법으로 재구성되었고, 그 결과를 평균제곱근오차와 영상의 프로파일로 나타내었다. 결과에 따르면, 평균제곱근오차와 영상 프로파일은 투영 각도와 복원법에 의존하였다. 시뮬레이션과 실험 결과에서 inpainting 복원법은 선형보간법에 비해 사이노그램의 복원 측면에서 개선된 결과를 보여주었다. 따라서, inpainting 방법은 환자 선량을 감소시키면서 영상화질을 유지시키는데 기여할 수 있을 것이다.

• Journal of Information Processing Systems
• /
• 제13권5호
• /
• pp.1183-1202
• /
• 2017

Image restoration has been carried out by texture synthesis mostly for large regions and inpainting algorithms for small cracks in images. In this paper, we propose a new approach that allows for the simultaneous fill-in of different structures and textures by processing in a wavelet domain. A combination of structure inpainting and patch-based texture synthesis is carried out, which is known as patch-based inpainting, for filling and updating the target region. The wavelet transform is used for its very good multiresolution capabilities. The proposed algorithm uses the wavelet domain subbands to resolve the structure and texture components in smooth approximation and high frequency structural details. The subbands are processed separately by the prioritized patch-based inpainting with isophote energy driven texture synthesis at the core. The algorithm automatically estimates the wavelet coefficients of the target regions of various subbands using optimized patches from the surrounding DWT coefficients. The suggested performance improvement drastically improves execution speed over the existing algorithm. The proposed patch optimization strategy improves the quality of the fill. The fill-in is done with higher priority to structures and isophotes arriving at target boundaries. The effectiveness of the algorithm is demonstrated with natural and textured images with varying textural complexions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권12호
• /
• pp.5170-5188
• /
• 2015

This paper proposes a novel progressive secret image-hiding scheme based on the inpainting technique, the vector quantization technique (VQ) and the exploiting modification direction (EMD) technique. The proposed scheme first divides the secret image into non-overlapping blocks and categorizes the blocks into two groups: complex and smooth. The blocks in the complex group are compressed by VQ with PCA sorted codebook to obtain the VQ index table. Instead of embedding the original secret image, the proposed method progressively embeds the VQ index table into the cover images by using the EMD technique. After the receiver recovers the complex parts of the secret image by decoding the VQ index table from the shadow images, the smooth parts can be reconstructed by using the inpainting technique based on the content of the complex parts. The experimental results demonstrate that the proposed scheme not only has the advantage of progressive data hiding, which involves more shadow images joining to recover the secret image so as to produce a higher quality steganography image, but also can achieve high hiding capacity with acceptable recovered image quality.