- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Three-dimensional optical coherence tomography image denoising through multi-input fully-convolutional networks
摘要： In recent years, there has been a growing interest in applying convolutional neural networks (CNNs) to low-level vision tasks such as denoising and super-resolution. Due to the coherent nature of the image formation process, the optical coherence tomography (OCT) images are inevitably affected by noise. This paper proposes a new method named the multi-input fully-convolutional networks (MIFCN) for denoising of OCT images. In contrast to recently proposed natural image denoising CNNs, the proposed architecture allows the exploitation of high degrees of correlation and complementary information among neighboring OCT images through pixel by pixel fusion of multiple FCNs. The parameters of the proposed multi-input architecture are learned by considering the consistency between the overall output and the contribution of each input image. The proposed MIFCN method is compared with the state-of-the-art denoising methods adopted on OCT images of normal and age-related macular degeneration eyes in a quantitative and qualitative manner.
关键词： Multi-input FCN,Optical Coherence Tomography (OCT),Image denoising,Fully convolutional network (FCN)
更新于2025-09-19 17:15:36
-
[IEEE 2019 IEEE 13th International Conference on ASIC (ASICON) - Chongqing, China (2019.10.29-2019.11.1)] 2019 IEEE 13th International Conference on ASIC (ASICON) - A UHF Semi-Passive RFID System with Photovoltaic/Thermoelectric Energy Harvesting for Wireless Sensor Networks
摘要： In this paper, we consider an image decomposition model that provides a novel framework for image denoising. The model computes the components of the image to be processed in a moving frame that encodes its local geometry (directions of gradients and level lines). Then, the strategy we develop is to denoise the components of the image in the moving frame in order to preserve its local geometry, which would have been more affected if processing the image directly. Experiments on a whole image database tested with several denoising methods show that this framework can provide better results than denoising the image directly, both in terms of Peak signal-to-noise ratio and Structural similarity index metrics.
关键词： local variational method,differential geometry,Image denoising,patch-based method
更新于2025-09-19 17:13:59
-
[IEEE 2019 Days on Diffraction (DD) - St. Petersburg, Russia (2019.6.3-2019.6.7)] 2019 Days on Diffraction (DD) - Novel types of mode dispersion of optical vortices in twisted optical fibers
摘要： Nonlocal self-similarity of images has attracted considerable interest in the field of image processing and has led to several state-of-the-art image denoising algorithms, such as block matching and 3-D, principal component analysis with local pixel grouping, patch-based locally optimal wiener, and spatially adaptive iterative singular-value thresholding. In this paper, we propose a computationally simple denoising algorithm using the nonlocal self-similarity and the low-rank approximation (LRA). The proposed method consists of three basic steps. First, our method classifies similar image patches by the block-matching technique to form the similar patch groups, which results in the similar patch groups to be low rank. Next, each group of similar patches is factorized by singular value decomposition (SVD) and estimated by taking only a few largest singular values and corresponding singular vectors. Finally, an initial denoised image is generated by aggregating all processed patches. For low-rank matrices, SVD can provide the optimal energy compaction in the least square sense. The proposed method exploits the optimal energy compaction property of SVD to lead an LRA of similar patch groups. Unlike other SVD-based methods, the LRA in SVD domain avoids learning the local basis for representing image patches, which usually is computationally expensive. The experimental results demonstrate that the proposed method can effectively reduce noise and be competitive with the current state-of-the-art denoising algorithms in terms of both quantitative metrics and subjective visual quality.
关键词： patch grouping,Back projection,low-rank approximation (LRA),singular value decomposition (SVD),image denoising,self-similarity
更新于2025-09-19 17:13:59
-
An Improved Retinal Vessel Segmentation Framework Using Frangi Filter Coupled with the Probabilistic Patch Based Denoiser
摘要： Vessel segmentation has come a long way in terms of matching the experts at detection accuracy, yet there is potential for further improvement. In this regard, the accurate detection of vessels is generally more challenging due to the high variations in vessel contrast, width, and the observed noise level. Most vessel segmentation strategies utilize contrast enhancement as a preprocessing step, which has an inherent tendency to aggravate the noise and therefore, impede accurate vessel detection. To alleviate this problem, we propose to use the state-of-the-art Probabilistic Patch-Based (PPB) denoiser within the framework of an unsupervised retinal vessel segmentation strategy based on the Frangi filter. The PPB denoiser helps preserve vascular structure while effectively dealing with the amplified noise. Also, the modified Frangi filter is evaluated separately for tiny and large vessels, followed by individual segmentation and linear recombination of the binarized outputs. This way, the performance of the modified Frangi filter is significantly enhanced. The performance evaluation of the proposed method is evaluated on two recognized open-access datasets, viz: DRIVE and STARE. The proposed strategy yields competitive results for both preprocessing modalities, i.e., Contrast Limited Adaptive Histogram Equalization (CLAHE) and Generalized Linear Model (GLM). The performance observed for CLAHE over DRIVE and STARE datasets is (Sn = 0.8027, Acc = 0.9561) and (Sn = 0.798, Acc = 0.9561), respectively. For GLM, it is observed to be (Sn = 0.7907, Acc = 0.9603) and (Sn = 0.7860, Acc = 0.9583) over DRIVE and STARE datasets, respectively. Furthermore, based on the conducted comparative study, it is established that the proposed method outperforms various notable vessel segmentation methods available in the existing literature.
关键词： Image segmentation,Modified Frangi filter,Probabilistic patch-based denoiser,Image denoising,Retinal vessels
更新于2025-09-16 10:30:52
-
[IEEE 2018 International Conference on Radiation Effects of Electronic Devices (ICREED) - Beijing, China (2018.5.16-2018.5.18)] 2018 International Conference on Radiation Effects of Electronic Devices (ICREED) - Au Nanoparticles-Decorated Ultraviolet Photodetector on Transparent Mica Substrate
摘要： Images obtained from unconstrained environments may be blurred by unknown kernels and affected due to noise. This paper presents a new total variation minimization-based method for blindly deblurring such images. Unlike the alternating optimization-based algorithms, the proposed algorithm adopts a joint estimation strategy to estimate the unknown blurring kernel and the unknown image in an iterative manner, where each iteration performs two separate image denoising subproblems that admit fast implementation. Experiments are performed on multiple synthetic, grayscale, and color images, and the results demonstrate that the proposed method is effective in blind deblurring.
关键词： image denoising,image deblurring,Blind deconvolution,TV minimization
更新于2025-09-16 10:30:52
-
[IEEE TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON) - Kochi, India (2019.10.17-2019.10.20)] TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON) - Image denoising based on nonsubsampled shearlet transform domain Laplacian mixture model and bilateral filter and its method noise thresholding
摘要： In this paper, we present a spatially-adaptive non subsampled shearlet transform (NSST) based Bayesian technique for denoising the natural images. The NSST can provide better directional selectivity and give nearly optimal approximation for a piecewise smooth function and is approximately shift invariant. The NSST coef?cients of the images are modeled as 2-state Laplacian mixture(LM) distribution that uses local parameters. Through Kolomogrov-Smirnov (KS) goodness of it is shown that a 2-state LM distribution is highly appropriate for modeling the NSST image coef?cients. This prior distribution is then employed to obtain a maximum a posteriori (MAP) estimator. An adaptive bilateral ?ltering (ABF) is applied on the MAP output to smooth out the visual artifacts in the homogeneous regions while preserving the textures. The NSST domain MAP estimator with LMM prior followed by ABF is ?nally implemented in its method noise thresholding framework for image denoising. The performance of proposed denoising framework is validated on a variety of benchmark images at different noise levels. The proposed framework achieves highly encouraging results in terms of ?ne detail preservation and exhibit less distortion compared with some recent relevant methods and BM3D method.
关键词： Image denoising,NSST,Noise thresholding,Bilateral ?lter,Maximum a posteriori,Laplacian mixture
更新于2025-09-16 10:30:52
-
[IEEE 2019 11th International Conference on Knowledge and Systems Engineering (KSE) - Da Nang, Vietnam (2019.10.24-2019.10.26)] 2019 11th International Conference on Knowledge and Systems Engineering (KSE) - A Fast Denoising Algorithm for X-Ray Images with Variance Stabilizing Transform
摘要： We propose a fast denoising algorithm for X-Ray images with variance stabilizing transformations. The variance stabilizing transformations are used to transform Poisson noisy images to Gaussian noisy images. Therefore, we can utilize advantages of the fast denoising algorithm based on the alternative direction method of multipliers. In experiments, we evaluate denoising quality by the Peak signal-to-noise ratio and the Structure Similarity metrics. Comparing results show that our method outperforms other similar denoising methods.
关键词： ROF model,Variance Stabilizing Transformations,Image Denoising,Poisson Noise,Medical Image Processing
更新于2025-09-12 10:27:22
-
[Institution of Engineering and Technology 11th International Conference on Wireless Communications, Networking and Mobile Computing (WiCOM 2015) - Shanghai, China (21-23 Sept. 2015)] 11th International Conference on Wireless Communications, Networking and Mobile Computing (WiCOM 2015) - An improved image denoising method based on the pulse coupled neural network
摘要： In this paper, we proposed an image denoising filtering method based on PCNN (pulse coupled neural network) for images polluted by the pulse noise. The method firstly determined the position of pixels polluted by noise ac- cording to the fire capture features of PCNN. Then, a sim- ilar median filtering step was applied in the processing of noised pixels. Finally, the iterations and the sizes of filter window were chosen according to the noise intensity, which realized the adaptive-filtering of images. The main result stated that, compared to mean filtering, median fil- tering and adapted-median filtering, the method we pro- posed was not only effective in denoising and keeping details of images, but also showing good performances in different SNR conditions.
关键词： Image Denoising,PCNN,Neural Network,Impulse Noise
更新于2025-09-11 14:15:04
-
Wavelet Transforms, Contourlet Transforms and Block Matching Transforms for Denoising of Corrupted Images via Bi-shrink Filter
摘要： Image Denoising refers to the recovery of an image that has been corrupted by noise due to poor quality of image acquisition and transmission. Accordingly, there is a need to reduce the noise present in the image as a consequence of the denoised image formed. This paper presents Image denoising using Wavelet transforms, Contourlet transforms and Block Matching Transforms governed by bivariate shrinkage (Bi-shrink) filter techniques. The Wavelet transform uses up-sampling, down-sampling, low pass filter and high pass filter to perform denoising operation, the Contourlet transform uses up-sampling, down-sampling, low pass filter and high pass filter and directional filter banks to perform denoising operation, the Block Matching Transform uses Haar Transforms, Discrete cosine transforms and Karhunen Loeve transform to perform denoising operation. The performance of wavelet transforms, Contourlet transforms and Block Matching Transforms are evaluated for Reference images (such as towers, shades and ruler images) corrupted by gaussian noise and salt and pepper noise, by computing two error metrics Peak Signal to Noise Ratio (PSNR) and Execution Time (ET) with help of shrinkage function. Programming these using MATLAB R2014a by exploring its wavelet transform, Contourlet transform, image processing and signal processing toolboxes and the values are presented in tabular forms and discussed in the section 6. In this paper the block matching haar discrete cosine transform is proposed for denoising of images (especially for those images possessing detailed textures) that works through haar transform and discrete cosine transform outstrips the basic transform discrete wavelet transform and semi translation invariant contourlet transform. For the images corrupted by Gaussian noise and denoised by the proposed transform outstrips the basic transform “Discrete Wavelet Transform by PSNR=6.71 dB, ET=25.89 sec” and “Semi Translation Invariant Contourlet Transforms by PSNR=5.49 dB, ET=5.89 sec”. For the images corrupted by Salt and Pepper noise and denoised by the proposed transform outstrips the basic transform “Discrete Wavelet Transform by PSNR=21.15 dB, ET= 0.27 sec” and “Semi Translation Invariant Contourlet Transforms by PSNR=20.05 dB, ET= 5.80 sec”. In this paper Block Matching Haar Discrete cosine transform is proposed to overcome the limitations of wavelet transforms and Contourlet transforms, hence to attain the trade-off between high peak signal to noise ratio and less execution time. Results and Discussion section illustrates the efficacy of the proposed transform in terms of peak signal to noise ratio, execution time and visual quality of images.
关键词： Wavelet Transforms,Contourlet Transforms,Bi-variate Shrinkage and Image Denoising,Block Matching Transforms
更新于2025-09-11 14:15:04
-
[IEEE 2018 International Symposium in Sensing and Instrumentation in IoT Era (ISSI) - Shanghai, China (2018.9.6-2018.9.7)] 2018 International Symposium in Sensing and Instrumentation in IoT Era (ISSI) - An Expected Patch Log Likelihood Denoising Method Based on Internal and External Image Similarity
摘要： Natural images always exhibit a certain nonlocal self-similarity property, which implies that the patch matrix formed by similar image patches is low-rank. In this paper, the self-similarity of images is combined with the EPLL (Expected patch log likelihood) method based on external similarity, and an EPLL denoising model based on internal and external image similarity is proposed. The experimental results show that compared with the original EPLL method, the proposed method not only has higher quantization index, but also has a good visual effect.
关键词： image denoising,low-rank,self-similarity,expected patch log likelihood
更新于2025-09-10 09:29:36