A content-adaptive sharpness enhancement algorithm using 2D FIR filters trained by pre-emphasis

This paper proposes a content-adaptive sharpening algorithm using two-dimensional (2D) FIR filters trained by pre-emphasis for various image pairs. In the learning stage, all low-quality (LQ) and high-quality (HQ) image pairs are first pre-emphasized, i.e., properly sharpened. Then selective 2D FIR filter coefficients for high-frequency synthesis are trained using the pre-emphasized LQ–HQ image pairs, and then are stored in a dictionary that resembles an LUT (look-up table). In the inference stage, each input image is pre-emphasized in the same manner as in the learning stage. The best-matched 2D filter for each LQ patch is then found in the dictionary, and an HQ patch corresponding to the input LQ patch is synthesized using the resultant 2D FIR filter. The experiment results show that the proposed algorithm visually outperforms existing ones and that the mean of absolute errors (MAEs) and MSSSIM (multi-scale structure similarity) of the proposed algorithm are about 10% to 60% lower and about 0.002–0.053 higher, respectively than those of the existing algorithms.     

Text-image super-resolution through anchored neighborhood regression with multiple class-specific dictionaries

In the dictionary-based image super-resolution (SR) methods, the resolution of the input image is enhanced using a dictionary of low-resolution (LR) and high-resolution (HR) image patches. Typically, a single dictionary is learned from all the patches in the training set. Then, the input LR patch is super-resolved using its nearest LR patches and their corresponding HR patches in the dictionary. In this paper, we propose a text-image SR method using multiple class-specific dictionaries. Each dictionary is learned from the patches of images of a specific character in the training set. The input LR image is segmented into text lines and characters, and the characters are preliminarily classified. Likewise, overlapping patches are extracted from the input LR image. Then, each patch is super-resolved through the anchored neighborhood regression, using n class-specific dictionaries corresponding to the top-n classification results of the character containing the patch. The final HR image is generated by aggregating all the super-resolved patches. Our method achieves significant improvements in visual image quality and OCR accuracy, compared to the related dictionary-based SR methods. This confirms the effectiveness of applying the preliminary character classification results and multiple class-specific dictionaries in text-image SR.     

自适应聚类的全耦合稀疏学习算法

在图像处理领域,基于稀疏表示理论的图像超分辨力算法、高低分辨力字典与稀疏编码之间的映射关系是其中的2个关键环节。由于丰富多样的图像类型,单一字典并不能很好地表示图像。而在稀疏编码之间的映射关系上,严格相等的约束关系也限制了图像重建的效果。针对上述两个方面,采用包容性更强的多个字典与约束条件更为宽松的全耦合稀疏关系进行图像的超分辨力重建。在图像非局部自相似性的基础上,进行多次自适应聚类;挑选出最优的聚类,通过全耦合稀疏学习的图像超分辨力算法,得到多个字典;最后,对输入的低分辨力图像进行分类重建,得到高分辨力图片。实验结果表明,在图像Leaves,Barbara,Room上,本文的聚类算法比原全耦合稀疏学习算法在峰值信噪比(PSNR)上分别提升了0.51 dB,0.21 dB,0.15 dB。     

Joint learning for single-image super-resolution via a coupled constraint

The neighbor-embedding (NE) algorithm for single-image super-resolution (SR) reconstruction assumes that the feature spaces of low-resolution (LR) and high-resolution (HR) patches are locally isometric. However, this is not true for SR because of one-to-many mappings between LR and HR patches. To overcome or at least to reduce the problem for NE-based SR reconstruction, we apply a joint learning technique to train two projection matrices simultaneously and to map the original LR and HR feature spaces onto a unified feature subspace. Subsequently, the k -nearest neighbor selection of the input LR image patches is conducted in the unified feature subspace to estimate the reconstruction weights. To handle a large number of samples, joint learning locally exploits a coupled constraint by linking the LR-HR counterparts together with the K-nearest grouping patch pairs. In order to refine further the initial SR estimate, we impose a global reconstruction constraint on the SR outcome based on the maximum a posteriori framework. Preliminary experiments suggest that the proposed algorithm outperforms NE-related baselines.     

Image super-resolution with sparse neighbor embedding

Until now, neighbor-embedding-based (NE) algorithms for super-resolution (SR) have carried out two independent processes to synthesize high-resolution (HR) image patches. In the first process, neighbor search is performed using the Euclidean distance metric, and in the second process, the optimal weights are determined by solving a constrained least squares problem. However, the separate processes are not optimal. In this paper, we propose a sparse neighbor selection scheme for SR reconstruction. We first predetermine a larger number of neighbors as potential candidates and develop an extended Robust-SL0 algorithm to simultaneously find the neighbors and to solve the reconstruction weights. Recognizing that the k-nearest neighbor (k-NN) for reconstruction should have similar local geometric structures based on clustering, we employ a local statistical feature, namely histograms of oriented gradients (HoG) of low-resolution (LR) image patches, to perform such clustering. By conveying local structural information of HoG in the synthesis stage, the k-NN of each LR input patch is adaptively chosen from their associated subset, which significantly improves the speed of synthesizing the HR image while preserving the quality of reconstruction. Experimental results suggest that the proposed method can achieve competitive SR quality compared with other state-of-the-art baselines.     

图约束字典和加权稀疏表示人脸超分辨率算法

针对低分辨率、低质量人脸图像重建问题,提出了一种新的基于稀疏表示的人脸超分辨率算法。在训练阶段,人脸的位置特征被用于保持人脸块的全局信息,人脸块间的几何结构被用于保持高低分辨率超完备冗余字典的流形结构,从而提高字典的表达能力;在重建阶段,K近邻加权稀疏表示被用于消除稀疏编码噪声,以提高高分辨率人脸图像重建系数的精度。实验结果表明,提出的方法取得了较好的主客观质量。     

自适应稀疏约束图像超分辨力重建方法

简要介绍了基于稀疏字典约束的超分辨力重建算法,提出了具有低复杂度的基于K均值聚类的自适应稀疏约束图像超分辨力重建算法。所提算法从两个方面降低其计算复杂度:分类训练字典,对图像块归类重建,降低每个图像块所用字典的大小;对图像块的特征进行分析,自适应地选择重建方法。实验结果表明,提出的快速重建方法在重建质量与原算法相当的前提下,可以较大程度地降低重建时间。     

A novel common-subexpression-elimination method for synthesizing fixed-point FIR filters

We propose a common-subexpression-elimination (CSE) method for the synthesis of fixed-point finite-impulse response (FIR) filters. The proposed CSE algorithm considers both the redundancy among the canonic-signed-digit (CSD) filter coefficients and the length of the critical path in the multiplier block of a transposed-form FIR filter. Therefore, the proposed CSE method can perform tradeoff designs between complexity and the throughput rate. The number of adders synthesized by our method is commensurate with that by the graph-dependence algorithms. On the other hand, our method can synthesize a high-order complicated FIR filter in a few seconds.     

Video super resolution based on non-local regularization and reliable motion estimation

Video super-resolution (SR) is a process for reconstructing high-resolution (HR) images by utilizing complementary information among multiple low-resolution (LR) images. Accurate estimation of the motion among the LR images significantly affects the quality of the reconstructed HR image. In this paper, we analyze the possible reasons for the inaccuracy of motion estimation and then propose a multi-lateral filter to regularize the process of motion estimation. This filter can adaptively correct motion estimation according to the estimation reliability, image intensity discontinuity, and motion dissimilarity. Furthermore, we introduce a non-local prior to solve the ill-posed problem of HR image reconstruction. This prior can fully utilize the self-similarities existing in natural images to regularize the HR image reconstruction. Finally, we employ a Bayesian formulation to incorporate the two regularizations into one Maximum a Posteriori (MAP) estimation model, where the HR image and the motion estimation can be refined progressively in an alternative and iterative manner. In addition, an algorithm that estimates the blur kernel by analyzing edges in an image is also presented in this paper. Experimental results demonstrate that the proposed approaches are highly effective and compare favorably to state-of-the-art SR algorithms.     

基于FPGA的FIR滤波器设计

数字滤波器在数字信号处理中占有很重要的地位,该文介绍了FIR滤波器的两种实现算法：乘累加算法和优化的分布式算法,其中分布式算法作为优化算法进行研究。其次,根据FIR滤波器理论,采用线性相位结构优化滤波器的设计。并给出了FIR滤波器的模块划分和FIR滤波器的主要模块的实现,最后对FIR滤波器进行了系统仿真和验证。     

基于压缩感知与结构自相似性的遥感图像超分辨率方法

本文提出了一种基于压缩感知、结构自相似性和字典学习的遥感图像超分辨率方法,其基本思路是建立能够稀疏表示原始高分辨率图像块的字典。实现超分辨率所必需的附加信息来源于遥感图像中广泛存在的自相似结构,该信息可在压缩感知框架下通过字典学习而得到。这里,本文采用K-SVD方法构建字典、并采用OMP方法获取用于稀疏表达的相关系数。与现有基于样本的超分辨率方法的最大不同在于,本文方法仅使用了低分辨率图像及其插值图像,而不需要使用其它高分辨率图像。另外,为了评价方法的效果,本文还引入了一个衡量图像结构自相似性程度的新型指标SSSIM。对比实验结果表明,本文方法具有更好的超分辨率重构效果和运算效率,并且SSSIM指标与超分辨率重构效果具有较强的相关性。      

Design of Linear Phase FIR Filters in Subexpression Space Using Mixed Integer Linear Programming

In this paper, a novel optimization technique is proposed to optimize filter coefficients of linear phase finite-impulse response (FIR) filter to share common subexpressions within and among coefficients. Existing approaches of common subexpression elimination optimize digital filters in two stages: first, an FIR filter is designed in a discrete space such as finite wordlength space or signed power-of-two (SPT) space to meet a given specification; in the second stage, an optimization algorithm is applied on the discrete coefficients to find and eliminate the common subexpressions. Such a two-stage optimization technique suffers from the problem that the search space in the second stage is limited by the finite wordlength or SPT coefficients obtained in the first stage optimization. The new proposed algorithm overcomes this problem by optimizing the filter coefficients directly in subexpression space for a given specification. Numerical examples of benchmark filters show that the required number of adders obtained using the proposed algorithm is much less than those obtained using two-stage optimization approaches.     

基于卷积稀疏自编码的图像超分辨率重建

针对卷积稀疏编码算法中特征映射的准确性的问题,为了进一步提高图像超分辨率重建的的质量,文中提出一种基于卷积稀疏自编码的图像超分辨率重建算法。该算法首先在预训练阶段利用稀疏自编码器对输入高低分辨率图像分别进行训练,得到对应的图像稀疏特征表示;然后再由卷积神经网络根据得到的稀疏系数共同训练相应的滤波器及特征映射函数并更新到最优解;最后由高分辨率滤波器和对应的稀疏表示系数卷积求和,得到高分辨率重建图像估计。实验结果显示,改进算法的峰值信噪比（PSNR）结果较卷积稀疏编码算法提高了近0.1 dB,有效提高了重建图像的质量。     

Cross-view information interaction and feedback network for face hallucination

Hallucinating a photo-realistic frontal face image from a low-resolution (LR) non-frontal face image is beneficial for a series of face-related applications. However, previous efforts either focus on super-resolving high-resolution (HR) face images from nearly frontal LR counterparts or frontalizing non-frontal HR faces. It is necessary to address all these challenges jointly for real-world face images in unconstrained environment. In this paper, we develop a novel Cross-view Information Interaction and Feedback Network (CVIFNet), which simultaneously handles the non-frontal LR face image super-resolution (SR) and frontalization in a unified framework and interacts them with each other to further improve their performance. Specifically, the CVIFNet is composed of two feedback sub-networks for frontal and profile face images. Considering the reliable correspondence between frontal and non-frontal face images can be crucial and contribute to face hallucination in a different manner, we design a cross-view information interaction module (CVIM) to aggregate HR representations of different views produced by the SR and frontalization processes to generate finer face hallucination results. Besides, since 3D rendered facial priors contain rich hierarchical features, such as low-level (e.g., sharp edge and illumination) and perception level (e.g., identity) information, we design an identity-preserving consistency loss based on 3D rendered facial priors, which can ensure that the high-frequency details of frontal face hallucination result are consistent with the profile. Extensive experiments demonstrate the effectiveness and advancement of CVIFNet.     

Image super-resolution by textural context constrained visual vocabulary

Example-based super-resolution (SR) approach hallucinates the missing high-resolution (HR) details by learning the example image patches. This approach implicitly assumes that the similarity of the low-resolution (LR) patches can infer the similarity of the corresponding HR patches. However, this similarity preserving assumption may not be held in practice. Thus the example-based super-resolved image inevitably contains artifacts not close to the ground truth. In this paper, we propose a novel single-image SR method by integrating an enforced similarity preserving process by using visual vocabulary into example-based SR approach. By jointly learning the HR and LR visual vocabularies, we can obtain a geometric co-occurrence prior to make the geometric similarity preserved within each visual word. We further propose a two-step framework for SR. The first step estimates the optimum visual word using textural context cue while the second step enforces the visual word subspace constraint and reconstruction constraint for estimating the final result. Experiments demonstrate the effectiveness of our method for recovering the missing HR details, especially texture.     

Low-Resolution and Low-Quality Face Super-Resolution in Monitoring Scene via Support-Driven Sparse Coding

Monitoring cameras are now widely used to monitor everything from a room in a house to an entire warehouse. However, in real monitoring scenarios, a variety of factors, such as underexposure, optical blurring, defocusing, have an impact on the quality of images, which leads to low-quality and low-resolution (LR) of the individual of interest. Reconstruction of a high-resolution (HR) face image with detailed facial features, from a LR observation based on a set of HR and LR training image pairs, plays an important role in computer vision and face image analysis applications. To super-resolve an HR face given a LR face image, the key issue is how to effectively encode the LR image patch. However, due to stability and accuracy issues, the coding approaches proposed so far are far from satisfactory. In this paper, we present a novel sparse coding method via exploiting the support information on the coding coefficients. According to the distances between the input patch and bases in the dictionary, we first assign different weights to the coding coefficients and then obtain the coding coefficients by solving a weighted sparse problem. Experiments on commonly used databases and some face images on the real monitoring conditions demonstrate that our method outperforms state-of-the-art.     

Reduced order IIR approximation to FIR digital filters

An algorithm for designing an infinite-impulse-response (IIR) stable filter using a finite-impulse-response (FIR) given filter, with the objective of reducing the delay and order, is described. The design is in the time domain using the least-squares-inverse algorithm, which is briefly described. In this method, the numerator of the approximated filter is part of the FIR filter itself and no calculations and minimization are needed to find the numerator coefficients (except finding the FIR roots). An error analysis between the given FIR and approximated IIR filters is provided. This error analysis enables the designer to fix a design parameter, often unnoted, keeping the energies of the approximated and original filters equal. Results and two illustrative examples are presented     

Multiframe super-resolution based on half-quadratic prior with artifacts suppress

The multiframe super-resolution (SR) technique aims to obtain a high-resolution (HR) image by using a set of observed low-resolution (LR) images. In the reconstruction process, artifacts may be possibly produced due to the noise, especially in presence of stronger noise. In order to suppress artifacts while preserving discontinuities of images, in this paper a multiframe SR method is proposed by involving the reconstruction properties of the half-quadratic prior model together with the quadratic prior model using a convex combination. Moreover, by analyzing local features of the underlined HR image, these two prior models are combined by using an automatically calculated weight function, making both smooth and discontinuous pixels handled properly. A variational Bayesian inference (VBF) based algorithm is designed to efficiently and effectively seek the solution of the proposed method. With the VBF framework, motion parameters and hyper-parameters are all determined automatically, leading to an unsupervised SR method. The efficiency of the hybrid prior model is demonstrated theoretically and practically, which shows that our SR method can obtain better results from LR images even with stronger noise. Extensive experiments on several visual data have demonstrated the efficacy and superior performance of the proposed algorithm, which can not only preserve image details but also suppress artifacts.     

Optical half-band filters

This paper proposes two kinds of novel 2×2 circuit configuration for finite-impulse response (FIR) half-band filters. These configurations can be transformed into each other by a symmetric transformation and their power transmittance is identical. The configurations have only about half the elements of conventional FIR lattice-form filters. We derive a design algorithm for achieving desired power transmittance spectra. We also describe 2×2 circuit configurations for infinite-impulse response (IIR) half-band filters. These configurations are designed to realize arbitrary-order IIR half-band filter characteristics by extending the conventional half-band circuit configuration used in millimeter-wave devices. We discuss their filter characteristics and confirm that they have a power half-band property. We demonstrate design examples including FIR maximally flat half-band filters, an FIR Chebyshev half-band filter, and an IIR elliptic half-band filter     

基于链路选择学习算法的无设备目标定位

针对压缩感知框架下无设备目标定位(device-free localization,DFL)的字典失配问题,提出一种基于链路选择学习(link selection learning,LSL)算法的DFL方式.由于传统基于阴影模型的字典无法准确表达接收信号强度(received signal strength,RSS)变化与目标位置间的对应关系,本文算法首先在训练阶段通过字典学习的方式更新初始字典; 同时该算法在更新字典的过程中,仅选取置信区域中的链路参与计算,这样既加速了字典学习过程,提高了算法实时性,又滤除了野值链路的影响.室内外实验结果表明,该方法可以有效地消除现有基于阴影模型字典所带来的模型误差,提高定位精度,同时具有运算速度快的优点.