• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.1B
• /
• pp.141-147
• /
• 2000

In the restoration of degraded noisy motion blurred image, we have trade-off problem between smoothing the noise and restoration of the edge region. While the noise is smoothed, die edge or details will be corrupted. On the other hand, restoring the edge will amplify the noise. To solve this problem we propose an adaptive algorithm which uses I- H regularization operator for flat region and Laplacian regularization operator for edge region. Through the experiments, we verify that the proposed method shows better results in the suppression of the noise amplification in flat region, introducing less ringing artifacts in edge region and better ISNR than those of the conventional ones.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.7
• /
• pp.1696-1705
• /
• 1996

The theory of stack filtering, which is a generalization of median filtering, is used to the detection of intensity edges in noisey images. The proposed approach, called the Difference of Estimates(DoE) approach, is a new formulation of a morphological scheme which has been very sensitive to impulse noise. In this approach, stack filters are applied to a noisy image to obtain local estimates of the dilated and eroded versions of the noise-free image. Thresholding the difference between these two estimates yields the binary edge map. We find that this approach yields results comparable to those obtained with the Canny operator for images with additive Gaussian noise, burt works much better when the noise is impulsive.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.3C
• /
• pp.327-335
• /
• 2003

Cellular Automata is discrete dynamical systems which natural phenomena may be specified completely in terms of local relation. In this Paper we Propose noise removal and edge detection algorithm using a Potts Automata which is based on Cellular Automata. The proposed method is aimed to locally increase or decrease the differences in gray level values between pixel of the image without loss of the main characteristics of the image. The dynamical behavior of these automata is determined by Lyapunov operators for sequential and parallel update. We have found that proposed automata rules Present very fast convergence to fixed points, stability in front of random noisy images. Based on the experimental results we discuses the advantage and efficiency.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.674-677
• /
• 2017

The Hough transform is the most representative algorithm for a straight line detection based on edge pixels. It shows excellent performance in a simple linear image but requires a considerable amount of computation in a noisy or complex image and has a problem of detecting a pseudo straight line easily. In this paper, we propose a straight line detection algorithm to solve the problem of the conventional Hough transform. The proposed algorithm detects the straight line information of edge pixels by using principal component analysis (PCA) before performing Hough transform and performs the Hough transform of the limited slope area in the valid edge pixels based on the detected straight line information of edge pixels. Simulation results show that the proposed algorithm reduces the amount of computation as well as eliminates pseudo straight lines.

• International journal of advanced smart convergence
• /
• v.8 no.1
• /
• pp.141-146
• /
• 2019

These days, there are many applications using neural networks as parts of their system. On the other hand, adversarial examples have become an important issue concerining the security of neural networks. A classifier in neural networks can be fooled and make it miss-classified by adversarial examples. There are many research to encounter adversarial examples by using denoising methods. Some of them using GAN (Generative Adversarial Network) in order to remove adversarial noise from input images. By producing an image from generator network that is close enough to the original clean image, the adversarial examples effects can be reduced. However, there is a chance when adversarial noise can survive the approximation process because it is not like a normal noise. In this chance, we propose a research that utilizes high-level representation in the classifier by combining GAN network with a trained U-Net network. This approach focuses on minimizing the loss function on high representation terms, in order to minimize the difference between the high representation level of the clean data and the approximated output of the noisy data in the training dataset. Furthermore, the generated output is checked whether it shows minimum error compared to true label or not. U-Net network is trained with true label to make sure the generated output gives minimum error in the end. At last, the remaining adversarial noise that still exist after low-level approximation can be removed with the U-Net, because of the minimization on high representation terms.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.795-797
• /
• 2014

Image treatment has grown in its necessity in many fields due to the development of display technology used in smart phones and tablet computers. In digital imaging technology, noise is created by many causes during the process of acquiring, transmitting and treating image data. Therefore, this paper suggests a median filter that is more competent in removing noise by taking into account the direction when restoring noisy images that have been damaged by impulse noise. In order to verify the noise removal characteristics, PSNR(peak signal to noise ratio) was used for comparison against existing methods.

• Applied Microscopy
• /
• v.50
• /
• pp.23.1-23.9
• /
• 2020

We propose an effective deep learning model to denoise scanning transmission electron microscopy (STEM) image series, named Noise2Atom, to map images from a source domain 𝓢 to a target domain 𝓒, where 𝓢 is for our noisy experimental dataset, and 𝓒 is for the desired clear atomic images. Noise2Atom uses two external networks to apply additional constraints from the domain knowledge. This model requires no signal prior, no noise model estimation, and no paired training images. The only assumption is that the inputs are acquired with identical experimental configurations. To evaluate the restoration performance of our model, as it is impossible to obtain ground truth for our experimental dataset, we propose consecutive structural similarity (CSS) for image quality assessment, based on the fact that the structures remain much the same as the previous frame(s) within small scan intervals. We demonstrate the superiority of our model by providing evaluation in terms of CSS and visual quality on different experimental datasets.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.16 no.6
• /
• pp.16-21
• /
• 1979

Two dimensional kernels which reconstruct a tomographic image from a blurred one formed by simple back-projection are investigated in the frequency domain and their performances are compared. The kernels are derived from a point spread function of the tomographic system and have the form of a ramp filter modified by several window functions to suppress ringings or artifacts in the reconstruction. Computer simulation using computer-generated phantom image data with different filter functions has been carried out. In this simulation, it is found that the computation time for 2-D reconstruction is much less than that of 1-D convolution method by a factor of ten or more whereas the reconstructed image quality of the former is far poorer than the latter. In 2-D reconstruction heavy windowing results in less noisy reconstruction but details smear out in this case. The trade-offs between these points are considered.

• 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.

• Investigative Magnetic Resonance Imaging
• /
• v.20 no.4
• /
• pp.215-223
• /
• 2016

Purpose: The management of metal-induced field inhomogeneities is one of the major concerns of distortion-free magnetic resonance images near metallic implants. The recently proposed method called "Slice Encoding for Metal Artifact Correction (SEMAC)" is an effective spin echo pulse sequence of magnetic resonance imaging (MRI) near metallic implants. However, as SEMAC uses the noisy resolved data elements, SEMAC images can have a major problem for improving the signal-to-noise ratio (SNR) without compromising the correction of metal artifacts. To address that issue, this paper presents a novel reconstruction technique for providing an improvement of the SNR in SEMAC images without sacrificing the correction of metal artifacts. Materials and Methods: Low-rank approximation in each coil image is first performed to suppress the noise in the slice direction, because the signal is highly correlated between SEMAC-encoded slices. Secondly, SEMAC images are reconstructed by the best linear unbiased estimator (BLUE), also known as Gauss-Markov or weighted least squares. Noise levels and correlation in the receiver channels are considered for the sake of SNR optimization. To this end, since distorted excitation profiles are sparse, $l_1$ minimization performs well in recovering the sparse distorted excitation profiles and the sparse modeling of our approach offers excellent correction of metal-induced distortions. Results: Three images reconstructed using SEMAC, SEMAC with the conventional two-step noise reduction, and the proposed image denoising for metal MRI exploiting sparsity and low rank approximation algorithm were compared. The proposed algorithm outperformed two methods and produced 119% SNR better than SEMAC and 89% SNR better than SEMAC with the conventional two-step noise reduction. Conclusion: We successfully demonstrated that the proposed, novel algorithm for SEMAC, if compared with conventional de-noising methods, substantially improves SNR and reduces artifacts.