- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Quaternion-based weighted nuclear norm minimization for color image denoising
摘要： The quaternion method plays an important role in color image processing, because it represents the color image as a whole rather than as a separate color space component, thus naturally handling the coupling among color channels. The weighted nuclear norm minimization (WNNM) scheme assigns different weights to different singular values, leading to more reasonable image representation method. In this paper, we propose a novel quaternion weighted nuclear norm minimization (QWNNM) model and algorithm under the low rank sparse framework. The proposed model represents the color image as a low rank quaternion matrix, where quaternion singular value decomposition can be calculated by its equivalent complex matrix. We solve the QWNNM by adaptively assigning different singular values with different weights. Color image denoising is implemented by QWNNM based on non-local similarity priors. In this new color space, the inherent color structure can be well preserved during image reconstruction. For high noise levels, we apply a Gaussian lowpass filter (LPF) to the noisy image as a preprocessing before QWNNM, which reduces the iteration numbers and improves the denoised results. The experimental results clearly show that the proposed method outperforms K-SVD, QKSVD and WNNM in terms of both quantitative criteria and visual perceptual.
关键词： Quaternion singular value decomposition,Non-local similarity priors,Quaternion weighted nuclear norm minimization,Low rank,Color image denoising
更新于2025-09-23 15:23:52
-
norm constraint
摘要： Current zero shot learning methods mostly focus on applying the knowledge learnt by seen images to the unseen images. However, there is a big distribution difference between seen and unseen data, also called source and target domain. Thus, there are many irrelevant seen samples for unseen samples. We want to partially transfer the seen samples to target domain by selecting relevant seen samples. In this paper, we propose a method, zero shot learning by partial transfer from source domain with L2,1 norm constraint, called ZSLPT which embeds visual similarity and semantic similarity to transfer partial source samples. The relevant source samples are selected, while the irrelevant are eliminated. What’s more, we train source classification model used for transferring to target domain with the selected source samples, making the transferred target model more accurate. We have experimented on the state-of-the-art zero shot learning datasets, demonstrating that ZSLPT has good performance.
关键词： Zero shot learning,L2,1 norm,Partial transfer,Semantic similarity,Visual similarity
更新于2025-09-23 15:23:52
-
: A Novel Similarity Measure for Matching Local Image Descriptors
摘要： mp-dissimilarity is a recently proposed data-dependence similarity measure. In the literature, how mp-dissimilarity is generally used for matching local image descriptors has been formalized, and three matching strategies have been proposed by incorporating (cid:96)p-norm distance and mp-dissimilarity. Each of these three matching strategies is essentially a two-round matching process that utilizes (cid:96)p-norm distance and mp-dissimilarity individually. This paper presents two novel similarity measures for matching local image descriptors. The first similarity measure normalizes and weights the similarities that are calculated using (cid:96)p-norm distance and mp-dissimilarity, respectively. The second similarity measure involves a novel calculation that takes into account both spatial distance and data distribution between descriptors. The proposed similarity measures are extensively evaluated on a few image registration benchmark data sets. Experimental results will demonstrate that the proposed similarity measures achieve higher matching accuracy and are able to attain better recall results when registering multi-modal images compared with the existing matching strategies that combine (cid:96)p-norm distance and mp-dissimilarity.
关键词： local descriptors,accuracy,mp-dissimilarity,image registration,(cid:96)p-norm distance,Similarity measure
更新于2025-09-23 15:23:52
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - An Interior Point Method for Nonnegative Sparse Signal Reconstruction
摘要： We present a primal-dual interior point method (IPM) with a novel preconditioner to solve the (cid:96)1-norm regularized least square problem for nonnegative sparse signal reconstruction. IPM is a second-order method that uses both gradient and Hessian information to compute effective search directions and achieve super-linear convergence rates. It therefore requires many fewer iterations than first-order methods such as iterative shrinkage/thresholding algorithms (ISTA) that only achieve sub-linear convergence rates. However, each iteration of IPM is more expensive than in ISTA because it needs to evaluate an inverse of a Hessian matrix to compute the Newton direction. We propose to approximate each Hessian matrix by a diagonal matrix plus a rank-one matrix. This approximation matrix is easily invertible using the Sherman-Morrison formula, and is used as a novel preconditioner in a preconditioned conjugate gradient method to compute a truncated Newton direction. We demonstrate the efficiency of our algorithm in compressive 3D volumetric image reconstruction. Numerical experiments show favorable results of our method in comparison with previous interior point based and iterative shrinkage/thresholding based algorithms.
关键词： nonnegative sparse,3d volumetric image reconstruction,primal-dual preconditioned interior point method,(cid:96)1-norm regularized optimization,compressive sensing
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE 10th Sensor Array and Multichannel Signal Processing Workshop (SAM) - Sheffield (2018.7.8-2018.7.11)] 2018 IEEE 10th Sensor Array and Multichannel Signal Processing Workshop (SAM) - Super-Resolution Pulse-Doppler Radar Sensing via One-Bit Sampling
摘要： This paper investigates the delay-Doppler estimation problem of a pulse-Doppler radar which samples and quantizes the noisy echo signals to one-bit measurements. By applying a multichannel one-bit sampling scheme, we formulate the delay-Doppler estimation as a structured low-rank matrix recovery problem. Then the one-bit atomic norm soft-thresholding method is proposed to recover the low-rank matrix, in which a surrogate matrix is properly designed to evaluate the proximity of the recovered data to the sampled one. With the recovered low-rank matrix, the delays and Doppler frequencies can be determined and paired. Numerical experiments are performed to demonstrate the effectiveness of our method compared with the one-bit sparse signal recovery method based on discrete dictionary.
关键词： Delay-Doppler estimation,atomic norm,compressive sensing,1-bit quantization
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) - Rochester, NY, USA (2018.10.5-2018.10.5)] 2018 IEEE Western New York Image and Signal Processing Workshop (WNYISPW) - INCREMENTAL COMPLEX L1-PCA FOR DIRECTION-OF-ARRIVAL ESTIMATION
摘要： In wireless-node localization, the receiver processes snapshots collected by its antenna array in order to estimate the direction-of-arrival (DoA) of a source of interest. High-resolution direction finding is commonly carried out by principal-component analysis (PCA) of the collected complex-valued snapshots (subspace-based methods). Standard PCA was recently replaced by corruption-resistant L1-PCA in order to counteract the detrimental impact of unexpected, intermittent jamming. In this paper, we present the first incremental method for complex L1-PCA and employ it for online direction finding, as snapshots naturally arrive in a streaming fashion. Our numerical studies corroborate the computational efficiency and jamming/corruption resistance of the proposed method.
关键词： SVD,Array processing,corrupted data,L1-norm,L1-PCA,direction finding
更新于2025-09-23 15:22:29
-
Experimental test of the relation between coherence and path information
摘要： Quantum coherence stemming from the superposition behaviour of a particle beyond the classical realm, serves as one of the most fundamental features in quantum mechanics. The wave-particle duality phenomenon, which shares the same origin, has a strong relationship with quantum coherence. Recently, an elegant relation between quantum coherence and path information has been theoretically derived. Here, we experimentally test such new duality by l1-norm measure and the minimum-error state discrimination. We prepare three classes of two-photon states encoded in polarisation degree of freedom, with one photon serving as the target and the other photon as the detector. We observe that wave-particle-like complementarity and Bagan’s equality, defined by the duality relation between coherence and path information, is well satisfied. Our results may shed new light on the original nature of wave-particle duality and on the applications of quantum coherence as a fundamental resource in quantum technologies.
关键词： wave-particle duality,minimum-error state discrimination,Bagan's equality,path information,quantum coherence,l1-norm measure
更新于2025-09-23 15:22:29
-
Infrared Small Target Detection via Non-Convex Rank Approximation Minimization Joint l2,1 Norm
摘要： To improve the detection ability of infrared small targets in complex backgrounds, a novel method based on non-convex rank approximation minimization joint l2,1 norm (NRAM) was proposed. Due to the defects of the nuclear norm and l1 norm, the state-of-the-art infrared image-patch (IPI) model usually leaves background residuals in the target image. To fix this problem, a non-convex, tighter rank surrogate and weighted l1 norm are instead utilized, which can suppress the background better while preserving the target efficiently. Considering that many state-of-the-art methods are still unable to fully suppress sparse strong edges, the structured l2,1 norm was introduced to wipe out the strong residuals. Furthermore, with the help of exploiting the structured norm and tighter rank surrogate, the proposed model was more robust when facing various complex or blurry scenes. To solve this non-convex model, an efficient optimization algorithm based on alternating direction method of multipliers (ADMM) plus difference of convex (DC) programming was designed. Extensive experimental results illustrate that the proposed method not only shows superiority in background suppression and target enhancement, but also reduces the computational complexity compared with other baselines.
关键词： infrared image,structured norm,non-convex rank approximation minimization,small target detection
更新于2025-09-23 15:22:29
-
Joint Weighted Tensor Schatten p-norm and Tensor lp-norm Minimization for Image Denoising
摘要： In the traditional non-local similar patches based denoising algorithms, the image patches are firstly flatted into a vector. The structure information within the image patches are ignored, however, the spatial layout information can be used for improving the denoising performance. To solve this problem, this paper treats the image patches as matrice and proposes a low rank tensor recovery model for image denoising, and thus makes full use of spatial information within the image. Meanwhile, the proposed model can realize joint weighted tensor Schatten p-norm and tensor lp-norm minimization, which has two advantages: (1) it can deal with zero mean Gaussian noise, impulse noise and any other noise that can be approximated by mixing these two kinds of noise; (2) the employed norms require relatively weak incoherence conditions than l1 norm and nuclear norm, and thus are more robust against outliers and noise. Experimental results show that the proposed algorithm outperforms other state-of-the-art denoising algorithms in both visual perception quality and quantitative measures.
关键词： Image denoising,low-rank tensor recovery,tensor Schatten p-norm
更新于2025-09-23 15:22:29
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - An Iterative Adaptive Reweighted Norm Minimization Sparsity Autofocus Algorithm via Bayesian Recovery for Array SAR Imaging
摘要： The influence of phase error in echo signal is rarely considered or corrected by most classical compressed sensing (CS) algorithms, and reduces the quality of imaging results. In order to improve the quality of array synthetic aperture radar (ASAR) imaging, a new CS algorithm called Iterative Adaptive Reweighted Norm Minimization Sparsity Autofocus algorithm via Bayesian Recovery (IARNSABR) was proposed in this paper. Based on the principle of Bayesian Recovery, the iterative adaptive reweighted norm minimization method has been used in the process of reconstruction. The theoretical model and the process of imaging of IARNSABR has been established. And the proposed algorithm can correct the influence of phase error more effectively, and has stronger ability of eliminating the false targets. Through simulation and experiment results, IARNSABR can achieve higher quality imaging than SAFBRIM.
关键词： Compressed Sensing,Sparse autofocus,Iterative Reweighted Adaptive Norm Minimization,ASAR
更新于2025-09-23 15:22:29