NL-means Method Research Articles

Enhancement of fault diagnosis of rolling element bearing using maximum kurtosis fast nonlocal means denoising

Abstract In this paper, a modified nonlocal means denoising (NL-means) algorithm is proposed for rolling element bearing fault diagnosis. Although, nonlocal means denoising is widely used in image processing, this algorithm is rarely used in 1-D signal processing. The present work deals with application of 1-D nonlocal means denoising method for enhancement of fault signature in rolling element bearings. The parameters for the NL-means method are obtained by maximizing kurtosis value of bearing vibration signal. The proposed method is compared with minimum entropy deconvolution (MED) technique and the results indicate that the proposed method performs better for bearing fault diagnosis. The method is shown to be robust against various noise levels. Further, envelope spectrum of bearing vibration signal is also used to obtain characteristic bearing defect frequencies.

Imaging and measuring methods for coating layer thickness of TRISO-coated fuel particles with high accuracy

TRISO-coated fuel particles are the main innovation of high-temperature gas-cooled reactors (HTGRs), which effectively improve the safety of reactors for higher stability at high temperature. The structure of the typical ball-type TRISO-coated fuel particle comprises a nuclear fuel particle as a kernel and four outer coating layers. These layers play an important role as a barrier against fission product diffusion, and ensuring the integrity of the particles. As one of the key quality parameters of TRISO particles, the coating layer thickness must be measured accurately by non-destructive means. Conventional X-ray radiography, which is based on attenuation contrast, is a non-destructive alternative to measure the coating layer thickness. However, the attenuation contrast is determined by the density difference of the material. For the weakly absorbing material of coating layers composed of carbon and silicon, the variations of the thickness and density of different coating layers are not large enough to realize accurate thickness measurement. In order to obtain ideal images with enhanced boundaries, we applied in-line phase contrast imaging (PCI) based on a micro-focus X-ray source for the inspection of fuel particles. The method is more powerful for acquiring radiographs with sharper edges than conventional X-ray radiography. An improved NL-means method was adopted to decrease the image noise while preserving the detailed information effectively. Finally, based on the denoised DR image with sharper boundaries obtained by PCI, edge detection with sub-pixel accuracy and thickness measurement results are shown.

Special issue on parallel computing for real-time image processing

The performance requirements of image processing applications have continuously increased, especially when they are executed under real-time constraints. We have organized this special issue on parallel computing for real-time image processing to present the current state-of-the-art in the field of parallel programming and the future trends in real-time image and video processing as related to parallel computing or real-time implementation of embedded image processing applications on parallel architectures including multi-core platforms, GPUs and dedicated parallel architectures. Due to the overwhelming number and their wide scope of submissions received for this special issue and thus the difficulty associated with finding expert reviewers, we have decided to offer this special issue in two or possibly three parts to meet the planned appearance of this special issue. The papers that are currently under review will appear in a second or a third part of this special issue immediately after their reviews and re-reviews are concluded. We are very grateful to the reviewers who provided valuable comments and suggestions to improve the quality of the accepted papers. This first part of the special issue on parallel computing for real-time image processing presents articles addressing GPU/Multi-GPU programming and is dedicated to parallel architectures based on FPGA and/or CMOS VLSI technologies for real-time image processing applications. Six papers appear in this first part. Brief outlines of these papers are stated below: The first paper by Anis Rahman, Dominique Houzet, Denis Pellerin, Sophie Marat and Nathalie Guyader describes a parallel implementation of a spatio-temporal visual saliency model with multi-GPU reaching a real-time throughput. This article focuses on the algorithms of this model and details several parallel optimizations. The second paper by Fernanda Palhano, Guillermo Andrade-Barroso and Pierre Hellier presents a method for real-time denoising of ultrasound images discussing a modified version of the NL-means method that incorporates an ultrasound dedicated noise model. It addresses a GPU implementation of this algorithm. Results demonstrate that the proposed method is quite efficient in terms of denoising quality and real-time performance. The third paper by Harald Jordan, Walter van Dyck and Rene Smodic describes a new approach for a contourtracking algorithm targeting a low power smart camera for industrial inspection. This embedded system consists of the three major components: CMOS sensor, FPGA and microprocessor. The fourth paper by Mathieu Thevenin, Michel Paindavoine, Laurent Letellier, Renaud Schmit, and Barthelemy Heyrman describes the eISP, a programmable processing architecture that combines enough computational efficiency for 1080p HD video with silicon area and power characteristics suitable for the next generation of mobile phones (lower than $1 mm and 500 mW in TSMC 65 nm technology). The fifth paper by Loic Sieler, Lionel Damez, Landrault Alexis and Jean-Pierre Derutin presents the parallelization and the embedding of a real-time image stabilization algorithm on SoPC platform. The overall hardware implementation method is based upon meeting algorithm M. Akil (&) L. Perroton Universite Paris-Est, LIGM, Equipe A3SI, ESIEE Paris Cite Descartes, BP 99, 93162 Noisy-le-Grand Cedex, France e-mail: akilm@esiee.fr

Homogeneity similarity based image denoising

This paper presents a homogeneity similarity based method, which is a new patch-based image denoising method. In traditional patch-based methods, such as the NL-means method, block matching mainly depends on structure similarity. The homogeneity similarity is defined in adaptive weighted neighborhoods, which can find more similar points than the structure similarity, and so it is more effective, especially for points with less repetitive patterns, such as corner and end points. Comparative results on synthetic and real image denoising indicate that our method can effectively remove noise and preserve effective information, such as edges and contrast, while avoiding artifacts. The application on medical image denoising also demonstrates that our method is practical.

Real time ultrasound image denoising

Image denoising is the process of removing the noise that perturbs image analysis methods. In some applications like segmentation or registration, denoising is intended to smooth homogeneous areas while preserving the contours. In many applications like video analysis, visual servoing or image-guided surgical interventions, real-time denoising is required. This paper presents a method for real-time denoising of ultrasound images: a modified version of the NL-means method is presented that incorporates an ultrasound dedicated noise model, as well as a GPU implementation of the algorithm. Results demonstrate that the proposed method is very efficient in terms of denoising quality and is real-time.