Carlo Gatta

Unsupervised Deep Feature Extraction for Remote Sensing Image Classification

This paper introduces the use of single-layer and deep convolutional networks for remote sensing data analysis. Direct application to multi- and hyperspectral imagery of supervised (shallow or deep) convolutional networks is very challenging given the high input data dimensionality and the relatively small amount of available labeled data. Therefore, we propose the use of greedy layerwise unsupervised pretraining coupled with a highly efficient algorithm for unsupervised learning of sparse features. The algorithm is rooted on sparse representations and enforces both population and lifetime sparsity of the extracted features, simultaneously. We successfully illustrate the expressive power of the extracted representations in several scenarios: classification of aerial scenes, as well as land-use classification in very high resolution or land-cover classification from multi- and hyperspectral images. The proposed algorithm clearly outperforms standard principal component analysis (PCA) and its kernel counterpart (kPCA), as well as current state-of-the-art algorithms of aerial classification, while being extremely computationally efficient at learning representations of data. Results show that single-layer convolutional networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels and are preferred when the classification requires high resolution and detailed results. However, deep architectures significantly outperform single-layer variants, capturing increasing levels of abstraction and complexity throughout the feature hierarchy.

A Spatially Variant White-Patch and Gray-World Method for Color Image Enhancement Driven by Local Contrast

Starting from the revolutionary Retinex by Land and McCann, several further perceptually inspired color correction models have been developed with different aims, e.g. reproduction of color sensation, robust features recognition, enhancement of color images. Such models have a differential, spatially-variant and non-linear nature and they can coarsely be distinguished between white-patch (WP) and gray-world (GW) algorithms. In this paper we show that the combination of a pure WP algorithm (RSR: random spray Retinex) and an essentially GW one (ACE) leads to a more robust and better performing model (RACE). The choice of RSR and ACE follows from the recent identification of a unified spatially-variant approach for both algorithms. Mathematically, the originally distinct non-linear and differential mechanisms of RSR and ACE have been fused using the spray technique and local average operations. The investigation of RACE allowed us to put in evidence a common drawback of differential models: corruption of uniform image areas. To overcome this intrinsic defect, we devised a local and global contrast-based and image-driven regulation mechanism that has a general applicability to perceptually inspired color correction algorithms. Tests, comparisons and discussions are presented.

From Retinex to Automatic Color Equalization: issues in developing a new algorithm for unsupervised color equalization

We present a comparison between two color equalization algorithms: Retinex, the famous model due to Land and McCann, and Automatic Color Equalization (ACE), a new algorithm recently presented by the authors. These two algorithms share a common approach to color equalization, but different computational models. We introduce the two models focusing on differences and common points. An analysis of their computational characteristics illustrates the way the Retinex approach has influenced ACE structure, and which aspects of the first algorithm have been modified in the second one and how. Their interesting equalization properties, like lightness and color constancy, image dynamic stretching, global and local filtering, and data driven dequantization, are qualitatively and quantitatively presented and compared, together with their ability to mimic the human visual system.

SRBF: SPECKLE REDUCING BILATERAL FILTERING

Speckle noise negatively affects medical ultrasound image shape interpretation and boundary detection. Speckle removal filters are widely used to selectively remove speckle noise without destroying important image features to enhance object boundaries. In this article, a fully automatic bilateral filter tailored to ultrasound images is proposed. The edge preservation property is obtained by embedding noise statistics in the filter framework. Consequently, the filter is able to tackle the multiplicative behavior modulating the smoothing strength with respect to local statistics. The in silico experiments clearly showed that the speckle reducing bilateral filter (SRBF) has superior performances to most of the state of the art filtering methods. The filter is tested on 50 in vivo US images and its influence on a segmentation task is quantified. The results using SRBF filtered data sets show a superior performance to using oriented anisotropic diffusion filtered images. This improvement is due to the adaptive support of SRBF and the embedded noise statistics, yielding a more homogeneous smoothing. SRBF results in a fully automatic, fast and flexible algorithm potentially suitable in wide ranges of speckle noise sizes, for different medical applications (IVUS, B-mode, 3-D matrix array US).

A Multiscale Framework for Spatial Gamut Mapping

Image reproduction devices, such as displays or printers, can reproduce only a limited set of colors, denoted the color gamut. The gamut depends on both theoretical and technical limitations. Reproduction device gamuts are significantly different from acquisition device gamuts. These facts raise the problem of reproducing similar color images across different devices. This is well known as the gamut mapping problem. Gamut mapping algorithms have been developed mainly using colorimetric pixel-wise principles, without considering the spatial properties of the image. The recently proposed multilevel gamut mapping approach takes spatial properties into account and has been demonstrated to outperform spatially invariant approaches. However, they have some important drawbacks. To analyze these drawbacks, we build a common framework that encompasses at least two important previous multilevel gamut mapping algorithms. Then, when the causes of the drawbacks are understood, we solve the typical problem of possible hue shifts. Next, we design appropriate operators and functions to strongly reduce both haloing and possible undesired over compression. We use challenging synthetic images, as well as real photographs, to practically show that the improvements give the expected results.

Standardized evaluation methodology and reference database for evaluating IVUS image segmentation

This paper describes an evaluation framework that allows a standardized and quantitative comparison of IVUS lumen and media segmentation algorithms. This framework has been introduced at the MICCAI 2011 Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop, comparing the results of eight teams that participated. We describe the available data-base comprising of multi-center, multi-vendor and multi-frequency IVUS datasets, their acquisition, the creation of the reference standard and the evaluation measures. The approaches address segmentation of the lumen, the media, or both borders; semi- or fully-automatic operation; and 2-D vs. 3-D methodology. Three performance measures for quantitative analysis have been proposed. The results of the evaluation indicate that segmentation of the vessel lumen and media is possible with an accuracy that is comparable to manual annotation when semi-automatic methods are used, as well as encouraging results can be obtained also in case of fully-automatic segmentation. The analysis performed in this paper also highlights the challenges in IVUS segmentation that remains to be solved.

Accurate Coronary Centerline Extraction, Caliber Estimation, and Catheter Detection in Angiographies

Segmentation of coronary arteries in X-ray angiography is a fundamental tool to evaluate arterial diseases and choose proper coronary treatment. The accurate segmentation of coronary arteries has become an important topic for the registration of different modalities, which allows physicians rapid access to different medical imaging information from computed tomography (CT) scans or magnetic resonance imaging (MRI). In this paper, we propose an accurate fully automatic algorithm based on Graph-cuts for vessel centerline extraction, caliber estimation, and catheter detection. Vesselness, geodesic paths, and a new multiscale edgeness map are combined to customize the Graph-cuts approach to the segmentation of tubular structures, by means of a global optimization of the Graph-cuts energy function. Moreover, a novel supervised learning methodology that integrates local and contextual information is proposed for automatic catheter detection. We evaluate the method performance on three datasets coming from different imaging systems. The method performs as good as the expert observer with respect to centerline detection and caliber estimation. Moreover, the method discriminates between arteries and catheter with an accuracy of 96.5%, sensitivity of 72%, and precision of 97.4%.

Semantic pyramids for gender and action recognition.

Person description is a challenging problem in computer vision. We investigated two major aspects of person description: 1) gender and 2) action recognition in still images. Most state-of-the-art approaches for gender and action recognition rely on the description of a single body part, such as face or full-body. However, relying on a single body part is suboptimal due to significant variations in scale, viewpoint, and pose in real-world images. This paper proposes a semantic pyramid approach for pose normalization. Our approach is fully automatic and based on combining information from full-body, upper-body, and face regions for gender and action recognition in still images. The proposed approach does not require any annotations for upper-body and face of a person. Instead, we rely on pretrained state-of-the-art upper-body and face detectors to automatically extract semantic information of a person. Given multiple bounding boxes from each body part detector, we then propose a simple method to select the best candidate bounding box, which is used for feature extraction. Finally, the extracted features from the full-body, upper-body, and face regions are combined into a single representation for classification. To validate the proposed approach for gender recognition, experiments are performed on three large data sets namely: 1) human attribute; 2) head-shoulder; and 3) proxemics. For action recognition, we perform experiments on four data sets most used for benchmarking action recognition in still images: 1) Sports; 2) Willow; 3) PASCAL VOC 2010; and 4) Stanford-40. Our experiments clearly demonstrate that the proposed approach, despite its simplicity, outperforms state-of-the-art methods for gender and action recognition.

Color correction between gray world and white patch

Color equalization algorithms exhibit a variety of behaviors described in two differing types of models: Gray World and White Patch. These two models are considered alternatives to each other in methods of color correction. They are the basis for two human visual adaptation mechanisms: Lightness Constancy and Color Constancy. The Gray World approach is typical of the Lightness Constancy adaptation because it centers the histogram dynamic, working the same way as the exposure control on a camera. Alternatively, the White Patch approach is typical of the Color Constancy adaptation, searching for the lightest patch to use as a white reference similar to how the human visual system does. The Retinex algorithm basically belongs to the White Patch family due to its reset mechanism. Searching for a way to merge these two approaches, we have developed a new chromatic correction algorithm, called Automatic Color Equalization (ACE), which is able to perform Color Constancy even if based on Gray World approach. It maintains the main Retinex idea that the color sensation derives from the comparison of the spectral lightness values across the image. We tested different performance measures on ACE, Retinex and other equalization algorithms. The results of this comparison are presented.

HoliMAb: A holistic approach for Media–Adventitia border detection in intravascular ultrasound

We present a fully automatic methodology for the detection of the Media-Adventitia border (MAb) in human coronary artery in Intravascular Ultrasound (IVUS) images. A robust border detection is achieved by means of a holistic interpretation of the detection problem where the target object, i.e. the media layer, is considered as part of the whole vessel in the image and all the relationships between tissues are learnt. A fairly general framework exploiting multi-class tissue characterization as well as contextual information on the morphology and the appearance of the tissues is presented. The methodology is (i) validated through an exhaustive comparison with both Inter-observer variability on two challenging databases and (ii) compared with state-of-the-art methods for the detection of the MAb in IVUS. The obtained averaged values for the mean radial distance and the percentage of area difference are 0.211 mm and 10.1%, respectively. The applicability of the proposed methodology to clinical practice is also discussed.