Abstract: The Diagnosis of Left Ventricle (LV) pathologies is related to regional wall motion analysis. Health indicator scores such as the rotation and the torsion are useful for the diagnose of the Left Ventricle (LV) function. However, this requires proper identification of LV segments. On one hand, manual segmentation is robust, but it is slow and requires medical expertise. On the other hand, the tag pattern in Tagged Magnetic Resonance (TMR) sequences is a problem for the automatic segmentation of the LV boundaries. Consequently, we propose a method based in the classical formulation of parametric Snakes, combined with Active Shape models. Our semantic definition of the LV is tagged tissue that experiences motion in the systolic cycle. This defines two energy potentials for the Snake convergence. Additionally, the mean shape corrects excessive deviation from the anatomical shape. We have validated our approach in 15 healthy volunteers and two short axis cuts. In this way, we have compared the automatic segmentations to manual shapes outlined by medical experts. Also, we have explored the accuracy of clinical scores computed using automatic contours. The results show minor divergence in the approximation and the manual segmentations as well as robust computation of clinical scores in all cases. From this we conclude that the proposed method is a promising support tool for clinical analysis.

Abstract: The assessment of Myocardial Blush Grade after primary angioplasty is a precious diagnostic tool to understand if the patient needs further medication or the use of specifics drugs. Unfortunately, the assessment of MBG is difficult for non highly specialized staff. Experimental data show that there is poor correlation between MBG assessment of low and high specialized staff, thus reducing its applicability. This paper proposes a method able to achieve an objective measure of MBG, or a set of parameters that correlates with the MBG. The method tracks the blush area starting from just one single frame tagged by the physician. As a consequence, the blush area is kept isolated from contaminating phenomena such as diaphragm and arteries movements. We also present a method to extract four parameters that are expected to correlate with the MBG. Preliminary results show that the method is capable of extracting interesting information regarding the behavior of the myocardial perfusion.

Abstract: Color is a powerful visual cue for many computer vision applications such as image segmentation and object recognition. However, most of the existing color models depend on the imaging conditions affecting negatively the performance of the task at hand. Often, a reflection model (e.g., Lambertian or dichromatic reflectance) is used to derive color invariant models. However, those reflection models might be too restricted to model real-world scenes in which different reflectance mechanisms may hold simultaneously. Therefore, in this paper, we aim to derive color invariance by learning from color models to obtain diversified color invariant ensembles. First, a photometrical orthogonal and non-redundant color model set is taken on input composed of both color variants and invariants. Then, the proposed method combines and weights these color models to arrive at a diversified color ensemble yielding a proper balance between invariance (repeatability) and discriminative power (distinctiveness). To achieve this, the fusion method uses a multi-view approach to minimize the estimation error. In this way, the method is robust to data uncertainty and produces properly diversified color invariant ensembles. Experiments are conducted on three different image datasets to validate the method. From the theoretical and experimental results, it is concluded that the method is robust against severe variations in imaging conditions. The method is not restricted to a certain reflection model or parameter tuning. Further, the method outperforms state-of- the-art detection techniques in the field of object, skin and road recognition.

Abstract: The median graph has been shown to be a good choice to infer a representative of a set of graphs. It has been successfully applied to graph-based classification and clustering. Nevertheless, its computation is extremely complex. Several approaches have been presented up to now based on different strategies. In this paper we present a new approximate recursive algorithm for median graph computation based on graph embedding into vector spaces. Preliminary experiments on three databases show that this new approach is able to obtain better medians than the previous existing approaches.

Abstract: Document classification usually requires of structural features such as the physical layout to obtain good accuracy rates on complex documents. This paper introduces a descriptor of the layout and a distance measure based on the cyclic dynamic time warping which can be computed in O(n2). This descriptor is translation invariant and can be easily modified to be scale and rotation invariant. Experiments with this descriptor and its rotation invariant modification are performed on the Girona archives database and compared against another common layout distance, the minimum weight edge cover. The experiments show that these methods outperform the MWEC both in accuracy and speed, particularly on rotated documents.

Abstract: In this paper we present a method for document categorization which processes incoming document images such as invoices or receipts. The categorization of these document images is done in terms of the presence of a certain graphical logo detected without segmentation. The graphical logos are described by a set of local features and the categorization of the documents is performed by the use of a bag-of-words model. Spatial coherence rules are added to reinforce the correct category hypothesis, aiming also to spot the logo inside the document image. Experiments which demonstrate the effectiveness of this system on a large set of real data are presented.

Abstract: In this paper, we argue that only using behavioural motion information, we are able to predict the interest of observers when looking at face-to-face interactions. We propose a set of movement-related features from body, face, and mouth activity in order to define a set of higher level interaction features, such as stress, activity, speaking engagement, and corporal engagement. Error-Correcting Output Codes framework with an Adaboost base classifier is used to learn to rank the perceived observer's interest in face-to-face interactions. The automatic system shows good correlation between the automatic categorization results and the manual ranking made by the observers. In particular, the learning system shows that stress features have a high predictive power for ranking interest of observers when looking at of face-to-face interactions.