We develop a framework for learning generic, expressive image priors that capture the statistics of natural scenes and can be used for a variety of machine vision tasks. The approach extends traditional Markov Random Field (MRF) models by learning potential functions over extended pixel neighborhoods. Field potentials are modeled using a Products-of-Experts framework that exploits nonlinear functions of many linear filter responses. In contrast to previous MRF approaches all parameters, including the linear filters themselves, are learned from training data. We demonstrate the capabilities of this Field of Experts model with two example applications, image denoising and image inpainting, which are implemented using a simple, approximate inference scheme. While the model is trained on a generic image database and is not tuned toward a specific application, we obtain results that compete with and even outperform specialized techniques. 1.

We propose a complex wavelet domain image similarity measure, which is simultaneously insensitive to luminance change, contrast change and spatial translation. The key idea is to make use of the fact that these image distortions lead to consistent magnitude and/or phase changes of local wavelet coefficients. Since small scaling and rotation of images can be locally approximated by translation, the proposed measure also shows robustness to spatial scaling and rotation when these geometric distortions are small relative to the size of the wavelet filters. Compared with previous methods, the proposed measure is computationally efficient, and can evaluate the similarity of two images without a precise registration process at the front end. 1.

Reduced-reference (RR) image quality measures aim to predict the visual quality of distorted images with only partial information about the reference images. In this paper, we propose an RR image quality assessment method based on a natural image statistic model in the wavelet transform domain. We use the Kullback-Leibler distance between the marginal probability distributions of wavelet coefficients of the reference and distorted images as a measure of image distortion. A generalized Gaussian model is employed to summarize the marginal distribution of wavelet coefficients of the reference image, so that only a relatively small number of RR features are needed for the evaluation of image quality. The proposed method is easy to implement and computationally efficient. In addition, we find that many well-known types of image distortions lead to significant changes in wavelet coefficient histograms, and thus are readily detectable by our measure. A Matlab implementation of the method has been made available online at

Media hashing is an alternative approach to many applications previously accomplished with watermarking. The major disadvantage of the existing media hashing technologies is their poor resistance togeometric attacks. In this paper, a novel geometric distortion-invariant image hashing scheme which can be employed to perform copy detection and content authentication of digital images, is proposed. Our major contributions are threefold: (i) mesh-based robust hashing function is proposed � (ii) sophisticated hash database for error-resilient and fast matching is constructed� and (iii) the application scalability of our scheme for content copy tracing and authentication is studied. In addition, we further investigate several media hashing issues, including robustness and discrimination, error analysis, and complexity, for the proposed image hashing system. Exhaustive experimental results obtained from benchmark attacks con rm the excellent performance of the proposed method.

Abstract—In this paper, we present the computational tools and a hardware prototype for 3D face recognition. Full automation is provided through the use of advanced multistage alignment algorithms, resilience to facial expressions by employing a deformable model framework, and invariance to 3D capture devices through suitable preprocessing steps. In addition, scalability in both time and space is achieved by converting 3D facial scans into compact metadata. We present our results on the largest known, and now publicly available, Face Recognition Grand Challenge 3D facial database consisting of several thousand scans. To the best of our knowledge, this is the highest performance reported on the FRGC v2 database for the 3D modality. Index Terms—Face and gesture recognition, information search and retrieval. 1

Abstract not found

Motion is one of the most important types of information contained in natu-ral video, but direct use of motion information in the design of video quality assessment algorithms has not been deeply investigated. Here we propose to in-corporate a recent model of human visual speed perception [Stocker & Simon-celli, Nature Neuroscience 9, 578-585 (2006)] and model visual perception in an information communication framework. This allows us to estimate both the motion information content and the perceptual uncertainty in video signals. Improved video quality assessment algorithms are obtained by incorporating the model as spatiotemporal weighting factors, where the weight increases with the information content and decreases with the perceptual uncertainty. Consistent improvement over existing video quality assessment algorithms is observed in our validation with the video quality experts group Phase I test data set.

ABSTRACT. This paper presents a novel method for fast and quantified estimation of the Perceived Quality of Service (PQoS) for MPEG-4 video content, encoded at constant bitrates. Taking into account the instant PQoS variation due to the Spatial and Temporal (S-T) activity within a given MPEG-4 encoded content, this paper introduces the Mean PQoS (MPQoS) as a function of the video encoding rate and the picture resolution, and exploits it as a metric for objective video quality assessment. The validity of this metric is assessed by comparing PQoS experimental curves to the theoretical benefit functions vs. allocated resources. Based on the proposed metric, and taking into account the qualitative similarity between theoretical and experimental curves, the paper presents a prototype method for preencoding PQoS assessment based on the fast estimation of the S-T activity level of a video signal.

Abstract—In this paper, we present a method for removing noise from digital images corrupted with additive, multiplicative, and mixed noise. An image patch from an ideal image is modeled as a linear combination of image patches from the noisy image. We propose to fit this model to the real-world image data in the total least square (TLS) sense, because the TLS formulation allows us to take into account the uncertainties in the measured data. We develop a method to reduce the contribution from the irrelevant image patches, which will sharpen the edges and reduce edge artifacts at the same time. Although the proposed algorithm is computationally demanding, the image quality of the output image demonstrates the effectiveness of the TLS algorithms. Index Terms—Image denoising, image restoration, total least squares, signal-dependent noise. I.

Quality assessment plays a very important role in almost all aspects of multimedia signal processing such as acquisition, coding, display, processing etc. Several objective quality metrics have been proposed for images, but video quality assessment has received relatively little attention and most video quality metrics have been simple extension of metrics for images. In this paper, we propose a novel quality metric for video sequences that utilizes motion information in video sequences, which is the main difference in moving from images to video. This metric is capable of capturing temporal artifacts in video sequences in addition to spatial distortions. Results are presented that demonstrate the efficacy of our quality metric by comparing model performance against subjective scores on the database developed by the Video Quality Experts Group.