A statistical analysis of the kernel-based MMSE estimator with application to image reconstruction
Introduction
Multimedia signal reconstruction is an active research area which plays an important role in a number of applications such as signal enhancement, inpainting or error concealment. The aim of signal reconstruction is to fill in a missing signal block with a set of samples so that a reasonable signal, according to a certain criterion and to the available samples surrounding the missing area, is obtained. There exist several approaches to signal reconstruction like interpolation, linear prediction or estimation [1], [2].
Recently, we have developed a novel reconstruction framework for image/video error concealment where the signal is reconstructed by sparse linear prediction [3], [4]. We also showed that the prediction coefficients can be approximated by exponential functions so that the resulting procedure can be interpreted as a multivariate non-parametric kernel-based reconstruction. In particular, the proposed method, called kernel-based minimum mean square error (KMMSE) estimation, can be viewed as a minimum mean square error (MMSE) estimation where the required probability density function (pdf) is obtained through kernel density estimation (KDE) [5], [6]. The use of non-parametric pdf estimates avoids the decision about a particular pdf model and naturally adapts the MMSE estimator to the local statistics. In addition, KMMSE can benefit from the formalism established for other well-known kernel-based estimation methods such as the Nadaraya-Watson (NW) or the local linear estimator [7]. The better performance yielded by KMMSE with respect a number of state-of-the-art image error concealment techniques is demonstrated in [6]. Moreover, it must be pointed out that KMMSE allows an efficient, scalable implementation as recently proposed in [8].
Multivariate kernel-based estimation suffers from the so-called curse of dimensionality [7]. This means that, in a multidimensional space, we can expect to frequently find regions where the available data is quite sparse, which leads to bad estimates. Thus, the NW estimator shows significant bias and covariance in these sparse regions. In principle, bias can be mitigated if a local linear estimator is used instead of NW (which is a local constant estimator) [7]. However, local linear estimation must be avoided in sparse regions of the signal space since it suffers from numerical instability as it is described in [9]. In a signal reconstruction application this is not a choice since an estimate must be provided for every missing sample. In this context, KMMSE becomes an attractive option since it is as numerically stable as NW but with a smaller bias. Furthermore, it can straightforwardly deal with vector estimates which means that, in certain applications (e.g., image reconstruction), it is able to further exploit signal correlations, outperforming other state-of-the-art reconstruction techniques [3], [6].
The first goal of this paper will be the use of the powerful mathematical framework associated to kernel-based estimators to carry out a statistical error analysis of the KMMSE estimator. We will pay special attention to the case of linear (or locally linear) signals, which play an important role in signal processing [10]. As a result of this error analysis, we will be able to derive a couple of error risk measures and to establish confidence intervals. Furthermore, the statistical analysis of the estimation error is the basis for the development of bandwidth estimation strategies. There is a wide literature on this topic but it is focused on regression. However, the goal of signal reconstruction is not to derive a certain function but to obtain a replacement for a specific missing sample. It is well known that signal reconstruction benefits from a sparsity criterion [3], [4], [11] more than from a minimum square error criterion, which may lead to signal oversmoothing or numerical instability. We will demonstrate that the bandwidth estimation procedure that we proposed for KMMSE in [6] provides an approximation to sparse estimation and it is therefore more suitable for reconstruction.
In the rest of the paper we focus on the application of the error analysis previously developed to the problem of reconstructing large blocks of images. While several techniques recover the whole missing block at once [12], [13], [14], it has been shown that a recursive recovery of smaller image blocks (patches, in the following), proceeding from outer to inner patches and reusing the already estimated samples, can yield better reconstruction quality [3], [15], [16], [17]. In order to apply this strategy, we must consider that a recursive recovery may propagate estimation errors from already estimated samples to the subsequent ones. We will evaluate this propagation error for the KMMSE estimator in Section 4.
As an application of the concepts introduced along this work, we will tackle the problem of spatial error concealment (SEC), that is, the reconstruction of image blocks lost during transmission, by means of a KMMSE recursive recovery. Recursive image reconstruction requires a filling ordering (FO) procedure in order to decide at every step which patch should be estimated next. Although a fixed ordering like a raster or concentric scan is possible, there are other choices for FO based on a more reasonable criteria. First, we can take into account that the larger the number of available surrounding pixels, the better the estimate will be [15], [16]. Since the reconstruction of a given patch will be based on these surrounding pixels, we should also take into account their reliability. For example, as we have already proposed in [3], we can distinguish between correctly received pixels and already estimated pixels through a fixed reliability factor, although this leads to a fixed ordering (for a given shape of the lost area). This fact is also considered in [16] through a confidence parameter. However, the procedure of this latter reference uses isophotes so that linear structures are prioritized, which may lead to considerable error propagation. This confidence factor is combined in [18] with another parameter based on a fractional derivative. This can provide strong edges which may be useful for inpainting, but not for SEC. In fact, it must be pointed out that most of the work developed on FO corresponds to image inpainting (where the resulting reconstruction must be subjectively evaluated), while it has been less studied for SEC, where our goal is to obtain a reconstructed image as similar as possible to the original one. In a recent work [19], and in the context of SEC, we have shown that, for those SEC methods that can yield some measure of the reconstruction error, an improved reconstruction can be obtained when the error associated to the already-reconstructed pixels is heuristically employed in the FO as a reliability measure. In this paper, we will show that the estimation and propagation error measures developed along the paper for KMMSE can be also used as reliability factors (obtained from the concept of soft data) to make an accurate FO decision.
This paper is organized as follows. Section 2 provides a brief review of the KMMSE estimator. Section 3 is devoted to presenting the statistical analysis of the KMMSE estimator, including an in-depth study for the special case of signals with a locally linear behavior. Error propagation in recursive estimation is dealt with in Section 4. The reliability-based filling ordering procedure for image reconstruction is proposed and tested in Section 5. Finally, Section 6 is devoted to conclusions.
Section snippets
Fundamentals
Let us consider a random vector variable , where we will refer to and as target (dimension Nx) and context (dimension Ny) vectors, respectively. Our goal is to obtain an estimate of an unknown target subvector , given its known context , through the MMSE criterion, that is, . In order to do so, the conditional probability density function (pdf) is required. When a set of observed vectors is available, KDE provides us with the following
Statistical analysis of the KMMSE estimator
In this section we develop first a set of general expressions for the mean square error of the KMMSE estimator in terms of bias and covariance, establishing relationships with the simpler NW estimator. Then, we will see that, for the case of smooth (locally linear) functions, KMMSE exhibits a bias cancelation capability under a suitable BE procedure. This capability will allow the derivation of useful estimation error measures, which are the basis of the FO procedure developed in Section 5.1,
Error propagation in recursive KMMSE estimation
In the previous section we have analyzed the error associated to KMMSE estimation and how it can be evaluated. Nevertheless, we must also take into account that the reconstruction of large signal blocks may require reusing some already estimated samples for the estimation of others which are placed in the inner missing area. This recursive procedure is oriented to avoid oversmoothing and it is quite common in image reconstruction applications such as SEC or inpainting [3], [16], [35]. However,
Recursive image reconstruction based on KMMSE error risk measures
The recursive reconstruction of a large image block requires a criterion to decide the order in which the missing block is filled in with estimates . In this section we will propose a filling ordering (FO) procedure to this end which will be tested in a series of spatial error concealment (SEC) experiments. Since the goal of SEC is to obtain a reconstructed image as close as possible to the original one, the proposed FO procedure turns out to be a suitable framework for testing the MSE and
Conclusions and future work
In this paper we have developed a statistical analysis of the multivariate KMMSE estimator. This analysis provides useful tools for a better understanding of this estimator. Thus, we have derived a couple of approximate measures for predicting the KMMSE mean square error in the case of signals which have a locally linear behavior. The statistical analysis has also allowed us to demonstrate the bias cancellation feature of the estimator and also that the bandwidth estimation procedure employed
Acknowledgements
This work has been supported by the Spanish MINECO/FEDER project TEC2013-46690-P and by the Research Training Group 1773 “Heterogeneous Image Systems”, funded by the German Research Foundation (DFG).
References (41)
- et al.
Multivariate online kernel density estimation with gaussian kernels
Pattern Recognit.
(2011) - Y. Wang, Q. Zhu, Error control and concealment for video communication: A review, Proceedings of the IEEE 86...
A survey of packet loss recovery techniques for streaming audio
IEEE Netw.
(1998)- et al.
Sequential error concealment for video/images by sparse linear prediction
IEEE Trans. Multimed.
(2013) - J. Koloda, A.M. Peinado, V. Sanchez, Speech reconstruction by sparse linear prediction, in: Advances in Speech and...
- R. Bailey, J. Addison, A smoothed-distribution form of Nadaraya-Watson estimation, Estudos do GEMF (Grupo de Estudos...
- et al.
Kernel-based MMSE multimedia signal reconstruction and its application to spatial error concealment
IEEE Trans. Multimed.
(2014) - et al.
Nonparametric and Semiparametric Models
(2004) - J. Koloda, J. Seiler, A. Peinado, A. Kaup, Scalable kernel-based minimum mean square error estimator for accelerated...
- et al.
Challenging the curse of dimensionality in multivariate local linear regression
Comput. Stat.
(2013)
On MMSE estimation: a linear model under gaussian mixture statistics
IEEE Trans. Signal Process.
Sparse and Redundant Representations: from Theory to Applications in Signal and Image Processing
Complex-valued frequency selective extrapolation for fast image and video signal extrapolation
IEEE Signal Process. Lett.
Region filling and object removal by exemplar-based image inpainting
IEEE Trans. Image Process.
Novel sequential error concealment techniques using orientation adaptive interpolation
IEEE Trans. Circuits Syst. Video Tech.
Cited by (2)
A hybrid spatial error concealment using human face and image edge over H.264/AVC video sequences
2023, Multimedia Tools and Applications