This paper describes a recently created image database, TID2013, intended for evaluation of full-reference visual quality assessment metrics. With respect to TID2008, the new database contains a larger number (3000) of test images obtained from 25 reference images, 24 types of distortions for each reference image, and 5 levels for each type of distortion. Motivations for introducing 7 new types of distortions and one additional level of distortions are given; examples of distorted images are presented. Mean Opinion Scores (MOS) for the new database have been collected by performing 985 subjective experiments with volunteers (observers) from five countries (Finland, France, Italy, Ukraine, and USA). The availability of MOS allows the use of the designed database as a fundamental tool for assessing the effectiveness of visual quality. Furthermore, existing visual quality metrics have been tested with the proposed database and the collected results have been analyzed using rank order correlation coefficients between MOS and considered metrics. These correlation indices have been obtained both considering the full set of distorted images and specific image subsets, for highlighting advantages and drawbacks of existing, state of the art, quality metrics. Approaches to thorough performance analysis for a given metric are presented to detect practical situations or distortion types for which this metric is not adequate enough to human perception. The created image database and the collected MOS values are freely available for downloading and utilization for scientific purposes

International audienc

International audienceA maximum-likelihood method for estimating hyperspectral sensors random noise components, both dependent and independent from the signal, is proposed. A hyperspectral image is locally jointly processed in the spatial and spectral dimensions within a multicomponent scanning window (MSW), as small as 7 x 7 x 7 spatial-spectral pixels. Each MSW is regarded as an additive mixture of spectrally correlated fractal Brownian motion (fBm)-samples and random noise. The main advantage of the proposed method is its ability to accurately estimate band noise variances locally by using spatial and spectral texture correlations from a single textural MSW. For each spectral band, both additive and signal-dependent band noise components are estimated by linear fit of local noise variances obtained from many MSWs distributed over the whole band intensity range. CRLB-based analysis of the estimator performance shows that a good compromise is to jointly process seven adjacent spectral bands. The proposed method performance is assessed first on synthetic fBm-data and on real images with synthesized noise. Finally, four different AVIRIS datasets from 1997 flying season are considered. Good coincidence between additive and signal-dependent AVIRIS random noise components estimates obtained by our method and the estimates retrieved from AVIRIS calibration data is demonstrated. These experiments suggest that it is worth taking into account noise signal-dependency hypothesis for processing AVIRIS data

International audienceWe address the problem of unsupervised band reduction in hyperspectral remote sensing imagery. We propose the use of an information theoretic criterion to automatically separate the sensor's spectral range into disjoint subbands without ground truth knowledge. Our approach, named BandClust, preserves the physical sense of the spectral data and automatically provides relevant spectral subbands, i.e., of maximal informational complementarity. Experiments using real hyperspectral images are conducted to compare BandClust with four other unsupervised approaches. The comparison of the selected dimensionality reduction methods is performed via supervised classification using support vector machines and shows the potential of the proposed approach

Image segmentation is an essential process for image analysis. Several methods were developed to segment multicomponent images, and the success of these methods depends on several factors including 1) the characteristics of the acquired image and 2) the percentage of imperfections in the process of image acquisition. The majority of these methods require a priori knowledge, which is difficult to obtain. Furthermore, they assume the existence of models that can estimate its parameters and fit to the given data. However, such a parametric approach is not robust, and its performance is severely affected by the correctness of the utilized parametric model. In this letter, a new multicomponent image segmentation method is developed using a nonparametric unsupervised artificial neural network called Kohonen's selforganizing map (SOM) and hybrid genetic algorithm (HGA). SOM is used to detect the main features that are present in the image; then, HGA is used to cluster the image into homogeneous regions without any a priori knowledge. Experiments that are performed on different satellite images confirm the efficiency and robustness of the SOM-HGA method compared to the Iterative Self-Organizing DATA analysis technique (ISODATA).Index Terms-Aerial image, genetic algorithm (GA), image segmentation, neural network, satellite image, unsupervised classification.