Multiple Blur Images Restoration -- A Parallel Computing Approach

Image restoration is the process of recovering the original image from the degraded image. Aspire of the project is to restore the blurred/degraded images using Blind Deconvolution algorithm. The fundamental task of Image deblurring is to de-convolute the degraded image with the PSF that exactly describe the distortion. Firstly, the original image is degraded using the Degradation Model. It can be done by Gaussian filter which is a low-pass filter used to blur an image. In the edges of the blurred image, the ringing effect can be detected using Canny Edge Detection method and then it can be removed before restoration process. Blind Deconvolution algorithm is applied to the blurred image. It is possible to renovate the original image without having specific knowledge of degradation filter, additive noise and PSF. To get the effective results, the Penalized Maximum Likelihood (PML) Estimation Technique is used with our proposed Blind Deconvolution Algorithm.

In recent years most of researcher’s has done tremendous work in the field of medical image applications such as Magnetic Resonance Imaging (MRI), Ultra Sound, CT scan but still there are many research and experiments in medical imaging field and diagnosing of human health by Health Care Institutes. There is a growing interest for medical imaging de-noising as a hot area of research and also imaging equipment as a device. It is used for better image processing and highlighting the important features. These images are affected with random noise during acquisition, analyzing and Transmission process. This results in blurry image visible in low contrast. Wavelet transforms have effective method to separate the noise from the original medical image by using threshold techniques without affecting the important data of an image. Wavelet transform enables us to use the forward wavelet transform to represent sub-band of the original image in decomposition process then reconstructing this sub band coefficients to original image using inverse wavelet transform. In this work, the quality of medical image has been evaluated using filter assessment parameters like Variance, standard deviation, the squared difference error between original medical image & de-noised image (MSE) and the ratio between original image & noisy image. From numerical results, we can see that the algorithm is efficient de-noising of noisy medical image. When, investigating with Baye’s threshold techniques it achieved the Best value of peak signal to noise ratio (PSNR). For best medical image de-noising, the wavelet based de-noising algorithm has been investigated and results of Baye’s techniques and hard & soft threshold methods have been compared.

In this paper, we propose a novel defect inspection method by considering the advantage that the same pattern is repeatedly transferred onto a large number of areas in resist pattern fabrication. This approach consists of following two steps. The first step is to obtain a high-resolution pattern image from multiple low-resolution images of the same pattern on an observed noisy SEM image using a reconstruction-based super-resolution technique where the B-spline interpolation is utilized. It can reconstruct a high-resolution image from the low resolution and noisy images with a high degree of accuracy. The next step is to inspect defects by comparing the high-resolution pattern image with lowresolution images to be verified. We applied our method to model and SEM images to show its validity.

Image denoising, a classic ill-posed problem, aims to recover a latent image from a noisy measurement. Over the past few decades, a considerable number of denoising methods have been studied extensively. Among these methods, supervised deep convolutional networks have garnered increasing attention, and their superior performance is attributed to their capability to learn realistic image priors from a large amount of paired noisy and clean images. However, if the image to be denoised is significantly different from the training images, it could lead to inferior results, and the networks may even produce hallucinations by using inappropriate image priors to handle an unseen noisy image. Recently, deep image prior (DIP) was proposed, and it overcame this drawback to some extent. The structure of the DIP generator network is capable of capturing the low-level statistics of a natural image using an unsupervised method with no training images other than the image itself. Compared with a supervised denoising model, the unsupervised DIP is more flexible when processing image content that must be denoised. Nevertheless, the denoising performance of DIP is usually inferior to the current supervised learning-based methods using deep convolutional networks, and it is susceptible to the over-fitting problem. To solve these problems, we propose a novel deep generative network with multiple target images and an adaptive termination condition. Specifically, we utilized mainstream denoising methods to generate two clear target images to be used with the original noisy image, enabling better guidance during the convergence process and improving the convergence speed. Moreover, we adopted the noise level estimation (NLE) technique to set a more reasonable adaptive termination condition, which can effectively solve the problem of over-fitting. Extensive experiments demonstrated that, according to the denoising results, the proposed approach significantly outperforms the original DIP method in tests on different databases. Specifically, the average peak signal-to-noise ratio (PSNR) performance of our proposed method on four databases at different noise levels is increased by 1.90 to 4.86 dB compared to the original DIP method. Moreover, our method achieves superior performance against state-of-the-art methods in terms of popular metrics, which include the structural similarity index (SSIM) and feature similarity index measurement (FSIM). Thus, the proposed method lays a good foundation for subsequent image processing tasks, such as target detection and super-resolution.

In this paper, a new noise reduction algorithm is proposed. In general, an edge-high frequency information in an image-would be filtered or suppressed after image smoothing. The noise would be attenuated, but the image would lose its sharp information. This defect makes the post-processing harder. One new algorithm performs connectivity analysis on edge-data to make sure that only isolated edge information that represents noise gets filtered out, hence preserving the overall edge structure of the original image. The steps of new algorithm are as follows. First, find the edge from the noisy image by multi-resolution analysis. Second, use connectivity analysis to direct a mean filter to suppress the noise while preserving the edge information. In the first step, we propose a new algorithm to find edges in a very noisy image. The algorithm is based on the analysis of a group of multi-resolution images obtained by processing the original noisy image by different Gaussian filters. After applied to a sequence of images of the same scene but with different signal-noise-ratio (snr), this method is robust to remove noise and keep the edge. Also, through statistic analysis, there exists the regularity that the parameters of the algorithm would be constant with varying images under the same snr.

Edge detection is often used in image processing to find the edge boundaries of image objects and this is important for selecting the edges of image parts. The image edge detection used in this study counts coins in an image, so that it can easily pass through the human eye but not by a computer. In a computer system, it is necessary to provide programs and test data so that the computer can read and count coins like a human. The purpose of this study is to count coins in an image using Canny edge detection and Gaussian filtering methods. The images used in this study are in the form of *jpg and tested using the Visual Studio Code application using OpenCV and Python. The results of this study indicate that the results of the number of coins read from the images inputted to the system can be read properly, with a data accuracy of 90%. Canny's edge detection method can be used to count the number of coins in an image.Keywords: Pengolahan Citra; Deteksi tepi Canny; Gaussian filtering; OpenCV;

A novel approach to speckle noise filtering based on Artificial Bee Colony algorithm: An ultrasound image application

We propose and simulate an iterative maximum-likelihood image reconstruction method that uses multiple images taken through the turbulent atmosphere under photon-limited conditions. The method assumes that the point-spread function corresponding to each image has been measured by a guide star or other technique. Although a guide star is still required, wave-front correction is achieved through postprocessing instead of by the mechanical methods currently used with adaptive optics. A restored image of greatly increased quality was found to be produced after only 10 iterations. Additional iterations continued to reduce the mean-square error.

It is a feasible and meaningful way to preserve the precious murals by using digitization technology. However, it may need to stitch multiple images to get a complete mural panorama. It poses great challenges to stitch and blend these multiple images in a seamless and visually pleasant way. In this paper, we propose an image stitching and blending method based on image pyramid, including Gaussian and Laplacian pyramid, for obtaining a natural stitched images of Dunhuang murals. In special, Gaussian pyramid is used to down-sample the images and get multiple images of different scales through using Gaussian filters. Laplacian pyramid is applied to generate the difference image between each levels of the Gaussian pyramid. Finally, the images can be blended in an adjustable way by specifying the weights of different images. In this way, the stitched images can be presented with reasonable image fusion. Through using the real Dunhuang murals images, the efficiency of the proposed method has been validated.

In this paper, a new reversible data hiding scheme has been proposed using lagrange’s interpolating polynomial on interpolated sub-sampled images. First, we generate sub-sampled images from original image and enlarge its size using image interpolation. Now, we convert secret message using lagrange interpolating polynomial and generate new secret message. The new secret message is divided and stored within interleaved pixel of each interpolated sub-sampled images. At the receiver end, new secret message is extracted from interleaved pixel of each sub-sampled stego images and then lagrange’s interpolation is applied to generate original secret message. The security has been enhanced due to the distributive nature of hidden data within multiple images. The original pixels are not effected during data embedding which assure reversibility. The proposed scheme provides average embedding capacity with good visual quality measured by peak signal to noise ratio (PSNR) which is greater than 50 dB. It is observed that the proposed scheme provides better performance than other existing data hiding schemes in terms of data embedding capacity, visual quality and security. We have analyzed our stego images through RS analysis, calculate relative entropy, standard deviation and correlation coefficient of original and stego image to show the robustness under various steganographic attacks.

A camera shake of the relative motion between cameras and original scenes often occurs during a shoot, resulting in blurred images. This paper presents a method of restoring blurred images based on patch-based PSF (Point Spread Function) estimation and channel-dependent image deblurring. Initially, a pair of noisy and blurred images is acquired by consecutive shooting under short and long exposures to more accurately estimate the 2D trajectory formed by the camera shake, which is also known as PSF. From the noisy image, one patch with strong edges is extracted using gradient operators and the corresponding blurry patch is found within the blurry image. The boundaries of both patches are padded in a specified tile pattern to prevent the appearance of vertical or horizontal lines due to boundary discontinuity. Tikhonov regularization is then iteratively conducted on Gaussian pyramid images with adaptive noise thresholding to get the optimized PSF. Finally, the color conversion of the blurred image into a luminance and two chrominance images is done to apply the channel dependent image deblurring where the spatial resolution of the chrominance images is reduced based on the natural gradient distribution to abandon the valueless data regardless of the restoration quality. Moreover, another artificially blurred image made by the convolution of the known Gaussian PSF and the noisy image is used to reduce undesirable ringing-artifacts and increase the sharpness. The experimental results show that the proposed method can provide more improved PSFs and restored images accompanied by the reduction of computing time and ring artifacts.

The noise is any undesired signal that contaminates an image. This paper proposes an algorithm for color image noise detection of several types of noise, namely; Gaussian, Salt and Pepper and Speckle. This algorithm uses a method of generating a square matrix from original image, called a Recursive Matrix (RM) This RM was used successfully in detecting the noisy or noisy-free image. The first step is to analyze the three bands monochrome image (color image) to Red, Green and Blue images, then deal with each image as a grey-scale image which is represented as 2-Dimenssion matrix. The second Step is to construct the RM to each monochrome image, then to calculate the standard deviation (std.) for each RM to distinguish between noisy and pure image by using objective testdepending on Std. threshold. In the third step, the subjective test is used to the same image by plotting the image with its RM in 3-Dimensions, for both pure and noisy images. The proposed algorithm gives a perfect detection of noise in 50 color images as a case study used in this algorithm.

Image super-resolution is the process of combining multiple images into a single image that has higher resolution than any of the original images. We present a variational framework for fusing multiple co-registered images using the Total Variation (TV) and Mumford-Shah regularizations. We also propose an alternating minimization strategy for aligning and fusing multiple images in the case when the co-registration parameters are unknown. We discuss applications to video enhancement and present two novel applications to barcode scanning and Magnetic Resonance Imaging (MRI).

With the fast increasingly use of image and video processing in many aspects, the requirements for high performance and high-quality systems lead to the use of reconfigurable computing to accelerate traditional image processing platforms. In this work, an efficient runtime adaptable floating-point Gaussian filtering core is proposed to achieve not only high performance and quality but also kernel runtime adaptability. The architecture allows both filtering kernel size and values to be redefined on-the-fly. Moreover, the core can process up to one pixel per cycle with a 1D Gaussian filtering. The core is developed with Verilog-HDL and can be built on various FPGA families. Experimental results with multiple images at different resolutions show that the core is able to perform a 2D Gaussian filtering for 48 1080 × 1920-pixel or 313 512 × 512-pixel images per second with an 11 × 11 floating-point kernel.

Line Array Time Delay Integral CCD Sweep Image Non-Uniformity Correction Method