Spatially invariant image sequences

The authors define linearly additive spatially invariant image sequences and present an explicit mathematical model for describing them. In such a sequence, all objects are positionally invariant in each image of the sequence but have varying gray-scale contributions to the successive images of the sequence. The various components (features or processes) of the scene or object contribute additively to each image of the sequence, but each component has a characteristic variation (signature) from image to image due to the variation of the function, parameter or spectral band over the sequence. Objects with different spectral characteristics will have different image sequence signatures which can be used to distinguish them. Also presented are the general formulation, derivation, and explicit expression for the linear filter, called the simultaneous diagonalization (SD) filter, that calculates a single new image from the sequence such that a desired process is emphasized and any number of undesired processes is suppressed in the filtered image.     

Spatially adaptive wavelet-based multiscale image restoration

In this paper, we present a new spatially adaptive approach to the restoration of noisy blurred images, which is particularly effective at producing sharp deconvolution while suppressing the noise in the flat regions of an image. This is accomplished through a multiscale Kalman smoothing filter applied to a prefiltered observed image in the discrete, separable, 2-D wavelet domain. The prefiltering step involves constrained least-squares filtering based on optimal choices for the regularization parameter. This leads to a reduction in the support of the required state vectors of the multiscale restoration filter in the wavelet domain and improvement in the computational efficiency of the multiscale filter. The proposed method has the benefit that the majority of the regularization, or noise suppression, of the restoration is accomplished by the efficient multiscale filtering of wavelet detail coefficients ordered on quadtrees. Not only does this lead to potential parallel implementation schemes, but it permits adaptivity to the local edge information in the image. In particular, this method changes filter parameters depending on scale, local signal-to-noise ratio (SNR), and orientation. Because the wavelet detail coefficients are a manifestation of the multiscale edge information in an image, this algorithm may be viewed as an "edge-adaptive" multiscale restoration approach.     

Spatially adaptive multiplicative noise image denoising technique

A new image denoising technique in the wavelet transform domain for multiplicative noise is presented. Unlike most existing techniques, this approach does not require prior modeling of either the image or the noise statistics. It uses the variance of the detail wavelet coefficients to decide whether to smooth or to preserve these coefficients. The approach takes advantage of wavelet transform property in generating three detail subimages each providing specific information with certain feature directivity. This allows the ability to combine information provided by different detail subimages to direct the filtering operation. The algorithm uses the hypothesis test based on the F-distribution to decide whether detail wavelet coefficients are due to image related features or they are due to noise. The effectiveness of the proposed technique is tested for orthogonal as well as biorthogonal mother wavelets in order to study the effect of the smoothing process under different wavelet types.     

Spatially adaptive high-resolution image reconstruction of DCT-based compressed images

The problem of recovering a high-resolution image from a sequence of low-resolution DCT-based compressed observations is considered in this paper. The introduction of compression complicates the recovery problem. We analyze the DCT quantization noise and propose to model it in the spatial domain as a colored Gaussian process. This allows us to estimate the quantization noise at low bit-rates without explicit knowledge of the original image frame, and we propose a method that simultaneously estimates the quantization noise along with the high-resolution data. We also incorporate a nonstationary image prior model to address blocking and ringing artifacts while still preserving edges. To facilitate the simultaneous estimate, we employ a regularization functional to determine the regularization parameter without any prior knowledge of the reconstruction procedure. The smoothing functional to be minimized is then formulated to have a global minimizer in spite of its nonlinearity by enforcing convergence and convexity requirements. Experiments illustrate the benefit of the proposed method when compared to traditional high-resolution image reconstruction methods. Quantitative and qualitative comparisons are provided.     

Spatially adaptive block-based super-resolution

Super-resolution technology provides an effective way to increase image resolution by incorporating additional information from successive input images or training samples. Various super-resolution algorithms have been proposed based on different assumptions, and their relative performances can differ in regions of different characteristics within a single image. Based on this observation, an adaptive algorithm is proposed in this paper to integrate a higher level image classification task and a lower level super-resolution process, in which we incorporate reconstruction-based super-resolution algorithms, single-image enhancement, and image/video classification into a single comprehensive framework. The target high-resolution image plane is divided into adaptive-sized blocks, and different suitable super-resolution algorithms are automatically selected for the blocks. Then, a deblocking process is applied to reduce block edge artifacts. A new benchmark is also utilized to measure the performance of super-resolution algorithms. Experimental results with real-life videos indicate encouraging improvements with our method.     

High-order image subsampling using feedforward artificial neuralnetworks

We propose a method for high-order image subsampling using feedforward artificial neural networks (FANNs). In our method, the high-order subsampling process is decomposed into a sequence of first-order subsampling stages. The first stage employs a tridiagonally symmetrical FANN, which is obtained by applying the design algorithm introduced by Dumitras and Kossentini (see IEEE Trans. Signal Processing, vol.48, p.1446-55, 2000). The second stage employs a small fully connected FANN. The algorithm used to train both FANNs employs information about local edges (extracted using pattern matching) to perform effective subsampling of both high detail and smooth image areas. We show that our multistage first-order subsampling method achieves excellent speed-performance tradeoffs, and it consistently outperforms traditional lowpass filtering and subsampling methods both subjectively and objectively.     

基于子采样方法的DCT域盲水印技术

提出了一种增强水印鲁棒性的盲水印算法.算法在DCT(离散余弦变换)变换域,采用子采样的方法,选择嵌入水印的位置;以视觉感知模型调节嵌入水印的强度.算法的提取不需要原始图像,实现了盲提取.实验结果表明,算法不仅具有较好的不可见性,水印信息在噪声干扰、滤波、图像压缩等攻击下具有较好的鲁棒性.     

Fast and high performance image subsampling using feedforwardneural networks

We introduce a fast and high performance image subsampling method using feedforward artificial neural networks (FANNs). Our method employs a pattern matching technique to extract local edge information within the image, in order to select the FANN desired output values during the supervised training stage. Subjective and objective evaluations of experimental results using still images and video frames show that our method, while less computationally intensive, outperforms the standard lowpass filtering and subsampling method.     

基于亚取样分形插值预测的混合图像编码方法

提出了一种基于亚取样分形插值预测的混合图像编码方法。将原始图像在水平方向和垂直方向皆作１／２抽取得到一幅“亚抽图像”，对亚抽图像进行分形编码得到亚抽图像的分形码，采用分形插值方法由亚抽图像的分形码解码得到原始图像的分形预测图像，然后对预测误差图像进行基于ＤＣＴ的自适应补偿编码。实验表明，这种方法的编码速度有了很大提高，而且恢复图像的质量具有较高的保真度。     

Spatially adaptive wavelet thresholding with context modeling forimage denoising

The method of wavelet thresholding for removing noise, or denoising, has been researched extensively due to its effectiveness and simplicity. Much of the literature has focused on developing the best uniform threshold or best basis selection. However, not much has been done to make the threshold values adaptive to the spatially changing statistics of images. Such adaptivity can improve the wavelet thresholding performance because it allows additional local information of the image (such as the identification of smooth or edge regions) to be incorporated into the algorithm. This work proposes a spatially adaptive wavelet thresholding method based on context modeling, a common technique used in image compression to adapt the coder to changing image characteristics. Each wavelet coefficient is modeled as a random variable of a generalized Gaussian distribution with an unknown parameter. Context modeling is used to estimate the parameter for each coefficient, which is then used to adapt the thresholding strategy. This spatially adaptive thresholding is extended to the overcomplete wavelet expansion, which yields better results than the orthogonal transform. Experimental results show that spatially adaptive wavelet thresholding yields significantly superior image quality and lower MSE than the best uniform thresholding with the original image assumed known.     

Two-dimensional adaptive image stabilisation

A new effective digital image stabilisation algorithm is presented. The proposed method adaptively compensates hand jitter in a two-dimensional framework. Performance evaluation based on the motion diagram and coding efficiency substantiates the superiority of the proposed algorithm     

Spatially variant apodization for image reconstruction from partialFourier data

Sidelobe artifacts are a common problem in image reconstruction from finite-extent Fourier data. Conventional shift-invariant windows reduce sidelobe artifacts only at the expense of worsened mainlobe resolution. Spatially variant apodization (SVA) was previously introduced as a means of reducing sidelobe artifacts, while preserving mainlobe resolution. Although the algorithm has been shown to be effective in synthetic aperture radar (SAR), it is heuristically motivated and it has received somewhat limited analysis. In this paper, we show that SVA is a version of minimum-variance spectral estimation (MVSE). We then present a complete development of the four types of two-dimensional SVA for image reconstruction from partial Fourier data. We provide simulation results for various real-valued and complex-valued targets and point out some of the limitations of SVA. Performance measures are presented to help further evaluate the effectiveness of SVA.     

Region adaptive subband image coding

We present a region adaptive subband image coding scheme using the statistical properties of image subbands for various subband decompositions. Motivated by analytical results obtained when the input signal to the subband decomposition is a unit step function, we analyze the energy packing properties toward the lower frequency subbands, edges, and the dependency of energy distribution on the orientation of the edges, in subband decomposed images. Based on these investigations and ideal analysis/synthesis filtering done in the frequency domain, the region adaptive subband image coding scheme extracts suitably shaped regions in each subband and then uses adaptive entropy-constrained quantizers for different regions under the assumption of a generalized Gaussian distribution for the image subbands. We also address the problem of determining an optimal subband decomposition among all possible decompositions. Experimental results show that visual degradations in the reconstructed image are negligible at a bit rate of 1.0 b/pel and reasonable quality images are obtainable at rates as low as 0.25 b/pel.     

Locally adaptive perceptual image coding

Most existing efforts in image and video compression have focused on developing methods to minimize not perceptual but rather mathematically tractable, easy to measure, distortion metrics. While nonperceptual distortion measures were found to be reasonably reliable for higher bit rates (high-quality applications), they do not correlate well with the perceived quality at lower bit rates and they fail to guarantee preservation of important perceptual qualities in the reconstructed images despite the potential for a good signal-to-noise ratio (SNR). This paper presents a perceptual-based image coder, which discriminates between image components based on their perceptual relevance for achieving increased performance in terms of quality and bit rate. The new coder is based on a locally adaptive perceptual quantization scheme for compressing the visual data. Our strategy is to exploit human visual masking properties by deriving visual masking thresholds in a locally adaptive fashion based on a subband decomposition. The derived masking thresholds are used in controlling the quantization stage by adapting the quantizer reconstruction levels to the local amount of masking present at the level of each subband transform coefficient. Compared to the existing non-locally adaptive perceptual quantization methods, the new locally adaptive algorithm exhibits superior performance and does not require additional side information. This is accomplished by estimating the amount of available masking from the already quantized data and linear prediction of the coefficient under consideration. By virtue of the local adaptation, the proposed quantization scheme is able to remove a large amount of perceptually redundant information. Since the algorithm does not require additional side information, it yields a low entropy representation of the image and is well suited for perceptually lossless image compression.     

Fast wavelet-based image characterization for highly adaptive image retrieval

Adaptive wavelet-based image characterizations have been proposed in previous works for content-based image retrieval (CBIR) applications. In these applications, the same wavelet basis was used to characterize each query image: This wavelet basis was tuned to maximize the retrieval performance in a training data set. We take it one step further in this paper: A different wavelet basis is used to characterize each query image. A regression function, which is tuned to maximize the retrieval performance in the training data set, is used to estimate the best wavelet filter, i.e., in terms of expected retrieval performance, for each query image. A simple image characterization, which is based on the standardized moments of the wavelet coefficient distributions, is presented. An algorithm is proposed to compute this image characterization almost instantly for every possible separable or nonseparable wavelet filter. Therefore, using a different wavelet basis for each query image does not considerably increase computation times. On the other hand, significant retrieval performance increases were obtained in a medical image data set, a texture data set, a face recognition data set, and an object picture data set. This additional flexibility in wavelet adaptation paves the way to relevance feedback on image characterization itself and not simply on the way image characterizations are combined.     

Estimating motion in image sequences

We have reviewed the estimation of 2D motion from time-varying images, paying particular attention to the underlying models, estimation criteria, and optimization strategies. Several parametric and nonparametric models for the representation of motion vector fields and motion trajectory fields have been discussed. For a given region of support, these models determine the dimensionality of the estimation problem as well as the amount of data that has to be interpreted or transmitted thereafter. Also, the interdependence of motion and image data has been addressed. We have shown that even ideal constraints may not provide a well-defined estimation criterion. Therefore, the data term of an estimation criterion is usually supplemented with a smoothness term that can be expressed explicitly or implicitly via a constraining motion model. We have paid particular attention to the statistical criteria based on Markov random fields. Because the optimization of an estimation criterion typically involves a large number of unknowns, we have presented several fast search strategies     

Nonlinear interpolation of TV image sequences

A 3-D nonlinear filter for the interpolation of skipped frames in the transmission of TV image sequences at low bit rates is presented. The results obtained show that the nonlinear approach is convenient in the presence of moderate movements of the objects in the observed scene     

Fast adaptive wavelet packet image compression

Wavelets are ill-suited to represent oscillatory patterns: rapid variations of intensity can only be described by the small scale wavelet coefficients, which are often quantized to zero, even at high bit rates. Our goal is to provide a fast numerical implementation of the best wavelet packet algorithm in order to demonstrate that an advantage can be gained by constructing a basis adapted to a target image. Emphasis is placed on developing algorithms that are computationally efficient. We developed a new fast two-dimensional (2-D) convolution decimation algorithm with factorized nonseparable 2-D filters. The algorithm is four times faster than a standard convolution-decimation. An extensive evaluation of the algorithm was performed on a large class of textured images. Because of its ability to reproduce textures so well, the wavelet packet coder significantly out performs one of the best wavelet coder on images such as Barbara and fingerprints, both visually and in term of PSNR.