María E. Buemi

A New Image Quality Index for Objectively Evaluating Despeckling Filtering in SAR Images

Synthetic aperture radar (SAR) images are corrupted with a multiplicative granular-like noise pattern known as speckle. The goal for a despeckling filter consists of suppressing the speckle while preserving all the scene features such as texture, point-type targets, and, especially, edges. There exist several speckle filtering techniques and a relevant number of image quality indexes to evaluate the performances of a filtering operation on an SAR image. However, assessing the superiority of a filter over other is not a trivial issue. In this work, we present a new referenceless estimator (αβ-ratio estimator) based on the ratio edge detector which allows helping in objectively evaluating a filter realization on SAR images. The proposed estimator operates on the ratio image obtained as the point-to-point ratio between the original image (noisy image) and the filtered image. An ideal filter operation on an image implies that, in areas where speckle is fully developed, the ratio image should have the features of pure speckle and no geometric content. The new estimator measures the remaining geometric content within the ratio image. This new estimator is easy to compute and it provides an excellent metric to rank a filtering operation on real SAR images.

Supervised Constrained Optimization of Bayesian Nonlocal Means Filter With Sigma Preselection for Despeckling SAR Images

Speckle reduction is an important problem in synthetic aperture radar (SAR) image analysis. Recent years have seen how Bayesian filters emerge as the natural extension of the nonlocal means filters, providing a general framework to deal with multiplicative (speckle) noise. In this paper, we present an easy-to-use software tool applying an evolutionary algorithm to optimize a Bayesian nonlocal means filter with sigma preselection for denoising SAR images. The desired result is a filtered image having a significative reduction in its variance but preserving the original mean value of the noisy image. A mixed-integer constrained optimization problem is stated and solved with the human intervention, where the user assists the evolutionary algorithm to reduce the noisy image variance under the restriction of keeping the mean value of the noisy SAR image within a predetermined interval of acceptance. We apply the methodology to a set of synthetic and real SAR speckle corrupted images. The results through the evaluation of objective global and local quality criteria show the excellent potential of the proposal.

Speckle reduction with adaptive stack filters

Stack filters are a special case of non-linear filters. They have a good performance for filtering images with different types of noise while preserving edges and details. A stack filter decomposes an input image into stacks of binary images according to a set of thresholds. Each binary image is then filtered by a Boolean function, which characterizes the filter. Adaptive stack filters can be computed by training using a prototype (ideal) image and its corrupted version, leading to optimized filters with respect to a loss function. In this work we propose the use of training with selected samples for the estimation of the optimal Boolean function. We study the performance of adaptive stack filters when they are applied to speckled imagery, in particular to Synthetic Aperture Radar (SAR) images. This is done by evaluating the quality of the filtered images through the use of suitable image quality indexes and by measuring the classification accuracy of the resulting images. We used SAR images as input, since they are affected by speckle noise that makes classification a difficult task.

SAR image processing using adaptive stack filter

Stack filters are a special case of non-linear filters. They have a good performance for filtering images with different types of noise while preserving edges and details. A stack filter decomposes an input image into several binary images according to a set of thresholds. Each binary image is filtered by a Boolean function. The Boolean function that characterizes an adaptive stack filter is optimal and is computed from a pair of images consisting of an ideal noiseless image and its noisy version. In this work the behavior of adaptive stack filters on synthetic aperture radar (SAR) data is evaluated. With this aim, the equivalent number of looks for stack filtered data are calculated to assess the speckle noise reduction capability of this filter. Then a classification of simulated and real SAR images is carried out on data filtered with a stack filter trained with selected samples. The results of a maximum likelihood classification of these data are evaluated and compared with the results of classifying images previously filtered using the Lee and the Frost filters.

Improvement in SAR Image Classification using Adaptive Stack Filters

Stack filters are a special case of non-linear filters. They have a good performance for filtering images with different types of noise while preserving edges and details. A stack filter decomposes an input image into several binary images according to a set of thresholds. Each binary image is filtered by a Boolean function. The Boolean function that characterizes an adaptive stack filter is optimal and is computed from a pair of images consisting of an ideal noiseless image and its noisy version. In this work the behavior of adaptive stack filters is evaluated for the classification of synthetic aperture radar (SAR) images, which are affected by speckle noise. With this aim it was carried out experiment in which simulated and real images are generated and then filtered with a stack filter trained with one of them. The results of their maximum likelihood classification are evaluated and then are compared with the results of classifying the images without previous filtering.

A Simple Geometric-Based Descriptor for Facial Expression Recognition

The identification of facial expressions with human emotions plays a key role in non-verbal human communication and has applications in several areas. In this work, we propose a descriptor based on areas and angles of triangles formed by the landmarks from face images. We test these descriptors for facial expression recognition by means of two different approaches. One is a dynamic approach where recognition is performed by a Conditional Random Field (CRF) classifier. The other approach is an adaptation of the k-Nearest Neighbors classifier called Citation-kNN in which the training examples come in the form of sets of feature vectors. An analysis of the most discriminative landmarks for the CRF approach is presented. We compare both methodologies, analyse their similarities and differences. Comparisons with other state-ofthe- art techniques on the CK+ dataset are shown. Even though both methodologies are different from each other, the descriptor remains robust and precise in the recognition of expressions.

Facial expression recognition based on static and dynamic approaches

The identification of facial expressions with human emotions plays a key role in non-verbal human communication and has applications in several areas. In this work, we analyze two main approaches for expression recognition.

Performance of dynamic texture segmentation using GPU

This work is focused on the assessment of the use of GPU computation in dynamic texture segmentation under the mixture of dynamic textures (MDT) model. In this generative video model, the observed texture is a time-varying process commanded by a hidden state process. The use of mixtures in this model allows simultaneously handling of different visual processes. Nowadays, the use of GPU computing is growing in high-performance applications, but the adaptation of existing algorithms in such a way as to obtain a benefit from its use is not an easy task. In this paper, we made two implementations, one in CPU and the other in GPU, of a known segmentation algorithm based on MDT. In the MDT algorithm, there is a matrix inversion process that is highly demanding in terms of computing power. We make a comparison between the gain in performance obtained by porting to GPU this matrix inversion process and the gain obtained by porting to GPU the whole MDT segmentation process. We also study real-time motion segmentation performance by separating the learning part of the algorithm from the segmentation part, leaving the learning stage as an off-line process and keeping the segmentation as an online process. The results of performance analyses allow us to decide the cases in which the full GPU implementation of the motion segmentation process is worthwhile.

Segmentation with active contours: a comparative study of B-spline and level set techniques

The active contours approach is an oft-used family of techniques in image analysis. This work presents a comparative study between two active contour approaches for image segmentation. The level sets method and deformable contours under B-spline representation are compared. These image segmentation methods have different features and are difficult to compare in terms of performance, accuracy and initialization conditions. Both are implemented and a way to calculate the approximation error is developed. As a conclusion of this work a theoretical comparison and a comparative characterization of the approximation error for each method are presented.

Assessment of SAR image filtering using adaptive stack filters

Stack filters are a special case of non-linear filters. They have a good performance for filtering images with different types of noise while preserving edges and details. A stack filter decomposes an input image into several binary images according to a set of thresholds. Each binary image is then filtered by a Boolean function, which characterizes the filter. Adaptive stack filters can be designed to be optimal; they are computed from a pair of images consisting of an ideal noiseless image and its noisy version. In this work we study the performance of adaptive stack filters when they are applied to Synthetic Aperture Radar (SAR) images. This is done by evaluating the quality of the filtered images through the use of suitable image quality indexes and by measuring the classification accuracy of the resulting images.