• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.3
• /
• pp.645-650
• /
• 2015

Image restoration is required when the image is blurred due to out of focus or motion during the image acquisition. This type of image restoration is known as ill-posed inverse problem because the estimate of an original image should be derived from only one blurred image. This paper introduces a reference image to facilitate the restoration process. The experimental result shows that computation time is significantly reduced, compared with other methods. The proposed method obtains the estimate of the kernel used in blurring processing. New cost function is defined to update both the image and the kernel alternately. In the last stage, Wiener filter produces the estimate of an original image using the kernel and the reference image.

• 전자공학회논문지 IE
• /
• v.49 no.2
• /
• pp.75-81
• /
• 2012

In this paper, restoration methods were applied to restore analog medicine images with an aged image added and then blurred by noises. To restore the aged image blurred by the blurring function and added by noises, it was applied to the restoration methods which are inverse filtering and wiener filtering which are linear restoration techniques and Lucy-Richardson's algorithm which is nonlinear restoration technique. Moreover, ROC curve, a subjective evaluation method, was applied to evaluate the image quality of the restoration image. The wiener filtering using the ratio of constants acquired better image than the inverse filtering, but both of them couldn't improve ability to make a diagnosis. The restoration image applied to Lucy-Richardson algorithm was the best performance of the applied techniques and its sensitivity and specitivity were improved by 15[%] as much performance as the original aged image.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.264-272
• /
• 2010

Example-based super resolution is a method to restore a high resolution image from low resolution images through training and retrieval of image patches. It is not only good in its performance but also available for a single frame low-resolution image. However, its time complexity is very high because it requires lots of comparisons to retrieve image patches in restoration process. In order to improve the restoration speed, an efficient patch retrieval algorithm is essential. In this paper, we applied various high-dimensional feature retrieval methods, available for the patch retrieval, to a practical example-based super resolution system and compared their speed. As well, we propose to apply the multi-phase candidate reduction approach to the patch retrieval process, which was successfully applied in character recognition fields but not used for the super resolution. In the experiments, LSH was the fastest among conventional methods. The multi-phase candidate reduction method, proposed in this paper, was even faster than LSH: For $1024{\times}1024$ images, it was 3.12 times faster than LSH.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.9
• /
• pp.1759-1771
• /
• 1994

We proposed the iterative image restoration method based on the method of steepest descent with a regularization constraint for restoring the noisy motion-blurred images. The conventional method proposed by Jan Biemond et al, had drawback to amplify the additive noise and make ringing effects in the restored images by determining the value of regularization parameter experimentally from the degraded image to be restored without considering local information of the restored one. The method we proposed had a merit to suppress the noise amplification and restoration error by using the regularization parameter which estimate the value of it adaptively from each pixels of the image being restored in order to reduce the noise amplification and ringing effects efficiently. Also we proposed the termination rule to stop the iteration automatically when restored results approach into or diverse from the original solution in satisfaction. Through the experiments, proposed method showed better result not only in a MSE of 196 and 453 but also in the suppression of the noise amplification in the flat region compared with those proposed by Jan Biemond et al. of which MSE of 216 and 467 respectively when we used 'Lean' and 'Jaguar' images as original images.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.3
• /
• pp.173-180
• /
• 2004

In this paper we provide a new image restoration method based on the multiscale regularization in the redundant wavelet transform domain. The proposed method uses the redundant wavelet transform to decompose the single-scale image restoration problem to multiscale ones and applies scale dependent regularization to the decomposed restoration problems. The proposed method recovers sharp edges by applying rather less regularization to wavelet related restorations, while suppressing the resulting noise magnification by the wavelet shrinkage algorithm. The improved performance of the proposed method over more traditional Wiener filtering is shown through numerical experiments.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.04a
• /
• pp.137-140
• /
• 2000

카메라의 렌즈 등 광학장비의 성능 제한으로 인하여 초점이 맞지 않아 흐려지고 잡음으로 훼손된 영상을 복원하는데 일반적으로 반복복원방법이 사용된다. 이 경우에 가속변수는 훼손영상에 관계없이 영상전체에 일률적으로 적용되기 때문에 흐려짐 훼손이 심한 윤곽부분도 훼손이 작은 평면영역이 같이 일정하게 처리되어 수렴속도가 느려지고 시각적으로 중요한 윤곽부분의 복원에는 효율적이지 못하다. 이러한 문제점을 해결하기 위하여 본 논문에서는 흐려짐 훼손이 작은 평면영역은 가속변수를 작게하고 훼손이 큰 윤곽영역은 가속변수를 크게 하여 영상의 국부적인 특성에 따라 적응적으로 반복 복원하는 방법을 제안하였다. 제안한 복원방법은 기존의 방법과 비교하여 수렴속도가 빨라지고 시각적으로 중요한 윤곽정보의 복원에도 효율적임을 실험결과를 통해 할 수 있었으며, MSE면에서도 우수하였다.

• Journal of Korea Multimedia Society
• /
• v.15 no.5
• /
• pp.624-631
• /
• 2012

For many medical imaging systems, volume datasets are stored as a compressed form, so that the dataset has to be decompressed before it is visualized. Since the decompression process takes quite a long time, we present an acceleration method for medical volume decompression using GPU. Our method supports that both lossy and lossless compression and progressive refinement is possible to satisfy variable user requirements. Moreover, our decompression method is well parallelized for GPU so that the decompression takes a very short time. Finally, we designed that the decompression and volume rendering work in one framework so that the selective decompression is available. As a result, we gained additional improvement in volume decompression.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.66-68
• /
• 2018

본 논문에서는 비디오로부터 추출된 프레임에서 3D 인체 모델의 복원하고 이를 부드럽게 재생될 수 있도록 보정하는 기법을 제안한다. 매개변수 기반의 모델을 사용하여 자세 및 체형을 복원하도록 접근하고 있다. 매개변수 기반의 인체 모델은 다양한 인체 데이터의 학습을 통해 만들어지며 입력 영상으로부터 최적의 자세와 체형 매개변수 값을 찾아 복원하게 된다. 자세 복원은 CNN 을 사용하여 영상으로부터 인체의 관절 위치를 추정하고 3D 모델로부터 2D 로 투영을 통해 관절 간의 거리가 최소화되는 매개변수 값을 찾아 복원한다. 형상 복원은 2D 영상으로부터 취득된 사람의 윤곽 데이터와 3D 모델의 윤곽 데이터 간의 매칭을 통해 복원된다. 이러한 단일 입력 영상에서 비디오와 같은 다중 입력 영상으로 확장하여 칼만 필터를 적용하여 오류 프레임을 검출하고 이전, 이후 프레임의 매개변수와의 보간을 통해 보다 자연스럽고 정확한 모델을 생성한다.

• Korean Journal of Optics and Photonics
• /
• v.19 no.6
• /
• pp.389-393
• /
• 2008

Enhanced reconstruction of heavy occluded objects was represented using estimation of variance in computational integral imaging. The system is analyzed to extract information of enhanced reconstruction from an elemental images set. To obtain elemental images with enhanced resolution, low focus error, and large depth of focus, synthetic aperture integral imaging (SAII) utilizing a digital camera has been adopted. The focused areas of the reconstructed image are varied with the distance of the reconstruction plane. When an occluded object is occluded heavily, an occluded object can not be reconstructed by removing the occluding object. To obtain reconstruction of the occluded object by remedying the effect of heavy occlusion, the statistical technique has been adopted.

• 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.