基于稀疏编码和各向异性滤波的超分辨率重建

针对基于非局部稀疏自相似性的超分辨率重建方法存在的图像边缘保持性能不佳的问题,提出了一种基于稀疏编码和各向异性滤波的超分辨率重建算法。该算法利用卷积神经网络和各向异性引导滤波训练了一个各向异性特征模型,然后利用该特征模型构建一个局部的结构先验,以和非局部稀疏先验形成互补,从而提高算法的边缘保持能力。该算法训练后的模式使用通用测试集进行测试,测试结果表明算法SR性能较好,能很好地保持边缘细节,提供视觉效果更好的图像。     

Multi-frame image super-resolution reconstruction via low-rank fusion combined with sparse coding

The sparse coding method has been successfully applied to multi-frame super-resolution in recent years. In this paper, we propose a new multi-frame super-resolution framework which combines low-rank fusion with sparse coding to improve the performance of multi-frame super-resolution. The proposed method gets the high-resolution image by a three-stage process. First, a fused low-resolution image is obtained from multi-frame image by the method of registration and low-rank fusion. Then, we use the jointly training method to train a pair of learning dictionaries which have good adaptive ability. Finally, we use the learning dictionaries combined with sparse coding theory to realize super-resolution reconstruction of the fused low-resolution image. As the experiment results show, this method can recover the lost high frequency information, and has good robustness.

     

Sparse coding and dictionary learning with class-specific group sparsity

In recent years, sparse coding via dictionary learning has been widely used in many applications for exploiting sparsity patterns of data. For classification, useful sparsity patterns should have discrimination, which cannot be well achieved by standard sparse coding techniques. In this paper, we investigate structured sparse coding for obtaining discriminative class-specific group sparsity patterns in the context of classification. A structured dictionary learning approach for sparse coding is proposed by considering the \(\ell _{2,0}\) norm on each class of data. An efficient numerical algorithm with global convergence is developed for solving the related challenging \(\ell _{2,0}\) minimization problem. The learned dictionary is decomposed into class-specific dictionaries for the classification that is done according to the minimum reconstruction error among all the classes. For evaluation, the proposed method was applied to classifying both the synthetic data and real-world data. The experiments show the competitive performance of the proposed method in comparison with several existing discriminative sparse coding methods.

     

基于四通道卷积稀疏编码的图像超分辨率重建方法

针对图像分辨率较低的问题,提出了一种基于四通道卷积稀疏编码的图像超分辨率重建方法。首先,该方法将输入图像依次翻转90°作为四通道的各自输入,通过低通滤波和梯度算子将输入图像分解成高频和低频部分;接着,分别利用卷积稀疏编码方法和三次插值方法对各通道低分辨率图像的高频部分和低频部分进行重建;最后,对四通道输出图像加权求均值获得重建的高分辨率图像。实验结果表明,所提方法比一些经典的超分辨率重建方法在峰值信噪比（PSNR）、结构相似度（SSIM）和抗噪性上具有更好的重建效果。所提方法不仅克服了重叠补丁破环图像补丁间一致性的缺陷,还提高了重建图像的细节轮廓,加强了重建图像的稳定性。     

基于预测稀疏编码的快速单幅图像超分辨率重建

针对经典的基于稀疏编码的图像超分辨率算法在重建过程中运算量大、计算效率低的缺点,提出一种基于预测稀疏编码的单幅图像超分辨率重建算法。训练阶段,该算法在传统的稀疏编码误差函数基础上叠加编码预测误差项构造目标函数,并采用交替优化过程最小化该目标函数;测试阶段,仅需将输入的低分辨图像块和预先训练得到的低分辨率字典相乘就能预测出重建系数,从而避免了求解稀疏回归问题。实验结果表明,与经典的基于稀疏编码的单幅图像超分辨率算法相比,该算法能够在显著减少重建阶段运算时间的同时几乎完全保留超分辨率视觉效果。     

Continuous speech recognition with sparse coding

Sparse coding is an efficient way of coding information. In a sparse code most of the code elements are zero; very few are active. Sparse codes are intended to correspond to the spike trains with which biological neurons communicate. In this article, we show how sparse codes can be used to do continuous speech recognition. We use the TIDIGITS dataset to illustrate the process. First a waveform is transformed into a spectrogram, and a sparse code for the spectrogram is found by means of a linear generative model. The spike train is classified by making use of a spike train model and dynamic programming. It is computationally expensive to find a sparse code. We use an iterative subset selection algorithm with quadratic programming for this process. This algorithm finds a sparse code in reasonable time if the input is limited to a fairly coarse spectral resolution. At this resolution, our system achieves a word error rate of 19%, whereas a system based on Hidden Markov Models achieves a word error rate of 15% at the same resolution.     

Discriminative sparse neighbor coding

Sparse coding has received extensive attention in the literature of image classification. Traditional sparse coding strategies tend to approximate local features in terms of a linear combination of basis vectors, without considering feature neighboring relationships. In this scenario, similar instances in the feature space may result in totally different sparse codes. To address this shortcoming, we investigate how to develop new sparse representations which preserve feature similarities. We commence by establishing two modules to improve the discriminative ability of sparse representation. The first module selects discriminative features for each class, and the second module eliminates non-informative visual words. We then explore the distribution of similar features over the dominant basis vectors for each class. We incorporate the feature distribution into the objective function, spanning a class-specific low dimensional subspace for effective sparse coding. Extensive experiments on various image classification tasks validate that the proposed approach consistently outperforms several state-of-the-art methods.     

Single-image super-resolution reconstruction based on global non-zero gradient penalty and non-local Laplacian sparse coding

Methods based on sparse coding have been successfully used in single-image super-resolution reconstruction. However, they tend to reconstruct incorrectly the edge structure and lose the difference among the image patches to be reconstructed. To overcome these problems, we propose a new approach based on global non-zero gradient penalty and non-local Laplacian sparse coding. Firstly, we assume that the high resolution image consists of two components: the edge component and the texture component. Secondly, we develop the global non-zero gradient penalty to reconstruct correctly the edge component and the non-local Laplacian sparse coding to preserve the difference among texture component patches to be reconstructed respectively. Finally, we develop a global and local optimization on the initial image, which is composed of the reconstructed edge component and texture component, to remove possible artifacts. Experimental results demonstrate that the proposed approach can achieve more competitive single-image super-resolution quality compared with other state-of-the-art methods.     

利用GPGPU进行快速稀疏磁共振数据重建

利用GPGPU（General Purpose GPU）强大的并行处理能力,基于NVIDIA CUDA框架对已有的稀疏磁共振（Sparse MRI）重建算法进行了并行化改造,使其能够适应实际应用的要求。稀疏磁共振成像的重建算法包含大量的浮点运算,计算耗时严重,难以应用于实际,必须对其进行加速和优化。实验结果显示,NVIDIA GTX275 GPU使运算时间从4分多钟缩短到3.4秒左右,与Intel Q8200 CPU相比,达到了76倍的加速。     

结合稀疏编码和金字塔匹配的视频检索

针对金字塔匹配下的视频检索系统中基础特征用矢量量化方法表示不够精确的问题,结合稀疏编码方法进行视频检索。视频的基础特征通过稀疏编码表示后,用金字塔方法进行多次匹配,将多次匹配结果线性合并,作为修正后的相似性度量结果。通过对UCF50的检索实验表明,该方法能显著提高检索的准确率。     

Visual tracking using convolutional features with sparse coding

Artificial Intelligence Review - Visual object tracking has become one of the most active research topics in computer vision, and it has been applied in several commercial...     

基于稀疏编码的人脸识别算法

介绍了一种基于稀疏编码的人脸识别算法。先对10副自然图像应用稀疏编码,学习到基函数和图像稀疏表示的拟合分布的参数。在人脸识别中,用稀疏编码和已得到的基函数表示图像的稀疏,再经过拟合分布函数得到人脸图像的最终表示,然后应用多分类线性支持向量机（SVM）来完成识别算法。通过在人脸数据库上的实验表明,该算法具有很高的识别正确率。     

自适应稀疏重构的双频预失真结构

针对双频功放预失真系统采样率过高的问题,提出一种基于压缩感知的自适应稀疏预失真结构,先通过基于分段多项式模型的记忆效应补偿器,再将信号融合理解为压缩感知采样重构问题,即在预失真反馈回路,利用自适应稀疏算法高精度重构遗失的五阶及高阶交调信号,使系数权值的最小均方解逼近最优,降低采集误差提升线性化效果。实验结果表明,在提高系统稳定性的同时,NMSE显示较2D-MP、2D-CPWL提高了约2~3 dB,ACPR大约改善20 dBc。对降低双频带预失真采样率同时提升功放线性度具有重大意义。     

Speech enhancement with a GSC-like structure employing sparse coding

Speech comnmnication is often influenced by various types of interfering signals. To improve the quality of the desired signal, a generalized sidelobe canceller （GSC）, which uses a reference signal to estimate the interfering signal, is attracting attention of researchers. However, the interference suppression of GSC is limited since a little residual desired signal leaks into the reference signal. To overcome this problem, we use sparse coding to suppress the residual desired signal while preserving the reference signal. Sparse coding with the learned dictionary is usually used to reconstruct the desired signal. As the training samples of a desired signal for dictionary learning are not observable in the real environment, the reconstructed desired signal may contain a lot of residual interfering signal. In contrast, the training samples of the interfering signal during the absence of the desired signal for interferer dictionary learning can be achieved through voice activity detection （VAD）. Since the reference signal of an interfering signal is coherent to the interferer dictionary, it can be well restructured by sparse coding, while the residual desired signal will be removed. The performance of GSC will be improved since the estimate of the interfering signal with the proposed reference signal is more accurate than ever. Simulation and experiments on a real acoustic environment show that our proposed method is effective in suppressing interfering signals.     

Bilinear sparse coding for invariant vision

Recent algorithms for sparse coding and independent component analysis (ICA) have demonstrated how localized features can be learned from natural images. However, these approaches do not take image transformations into account. We describe an unsupervised algorithm for learning both localized features and their transformations directly from images using a sparse bilinear generative model. We show that from an arbitrary set of natural images, the algorithm produces oriented basis filters that can simultaneously represent features in an image and their transformations. The learned generative model can be used to translate features to different locations, thereby reducing the need to learn the same feature at multiple locations, a limitation of previous approaches to sparse coding and ICA. Our results suggest that by explicitly modeling the interaction between local image features and their transformations, the sparse bilinear approach can provide a basis for achieving transformation-invariant vision.     

Click data guided query modeling with click propagation and sparse coding

Multimedia Tools and Applications - We address the problem of fine-grained image recognition using user click data, wherein each image is represented as a semantical query-click feature vector....     

Dynamic sparse coding for sparse time-series modeling via first-order smooth optimization

Sparse coding, often called dictionary learning, has received significant attention in the fields of statistical machine learning and signal processing. However, most approaches assume iid data setup, which can be easily violated when the data retains certain statistical structures such as sequences where data samples are temporally correlated. In this paper we formulate a novel dynamic sparse coding problem, and propose an efficient algorithm that enforces smooth dynamics for the latent state vectors (codes) within a linear dynamic model while imposing sparseness of the state vectors. We overcome the added computational overhead originating from smooth dynamic constraints by adopting the recent first-order smooth optimization technique, adjusted for our problem instance. We demonstrate the improved prediction performance of our approach over the conventional sparse coding on several interesting real-world problems including financial asset return data forecasting and human motion estimation from silhouette videos.     

非负局部Laplacian稀疏编码和上下文信息的图像分类

目的 稀疏编码是图像特征表示的有效方法,但不足之处是编码不稳定,即相似的特征可能会被编码成不同的码字。且在现有的图像分类方法中,图像特征表示和图像分类是相互独立的过程,提取的图像特征并没有有效保留图像特征之间的语义联系。针对这两个问题,提出非负局部Laplacian稀疏编码和上下文信息的图像分类算法。方法 图像特征表示包含两个阶段,第一阶段利用非负局部的Laplacian稀疏编码方法对局部特征进行编码,并通过最大值融合得到原始的图像表示,从而有效改善编码的不稳定性;第二阶段在所有图像特征表示中随机选择部分图像生成基于上下文信息的联合空间,并通过分类器将图像映射到这些空间中,将映射后的特征表示作为最终的图像表示,使得图像特征之间的上下文信息更多地被保留。结果 在4个公共的图像数据集Corel-10、Scene-15、Caltech-101以及Caltech-256上进行仿真实验,并和目前与稀疏编码相关的算法进行实验对比,分类准确率提高了约3%~18%。结论 本文提出的非负局部Laplacian稀疏编码和上下文信息的图像分类算法,改善了编码的不稳定性并保留了特征之间的相互依赖性。实验结果表明,该算法与现有算法相比的分类效果更好。另外,该方法也适用于图像分割、标注以及检索等计算机视觉领域的应用。     

Unsupervised scene segmentation using sparse coding context

This paper presents an approach to image understanding on the aspect of unsupervised scene segmentation. With the goal of image understanding in mind, we consider ‘unsupervised scene segmentation’ a task of dividing a given image into semantically meaningful regions without using annotation or other human-labeled information. We seek to investigate how well an algorithm can achieve at partitioning an image with limited human-involved learning procedures. Specifically, we are interested in developing an unsupervised segmentation algorithm that only relies on the contextual prior learned from a set of images. Our algorithm incorporates a small set of images that are similar to the input image in their scene structures. We use the sparse coding technique to analyze the appearance of this set of images; the effectiveness of sparse coding allows us to derive a priori the context of the scene from the set of images. Gaussian mixture models can then be constructed for different parts of the input image based on the sparse-coding contextual prior, and can be combined into an Markov-random-field-based segmentation process. The experimental results show that our unsupervised segmentation algorithm is able to partition an image into semantic regions, such as buildings, roads, trees, and skies, without using human-annotated information. The semantic regions generated by our algorithm can be useful, as pre-processed inputs for subsequent classification-based labeling algorithms, in achieving automatic scene annotation and scene parsing.