Abstract: In this paper we tackle the automatic detection of struts elements (metallic braces of a stent device) in Intravascular Ultrasound (IVUS) sequences. The proposed method is based on context-aware classification of IVUS images, where we use Multi-Class Multi-Scale Stacked Sequential Learning (M2SSL). Additionally, we introduce a novel technique to reduce the amount of required contextual features. The comparison with binary and multi-class learning is also performed, using a dataset of IVUS images with struts manually annotated by an expert. The best performing configuration reaches a F-measure F = 63.97% .

Abstract: Restricted Boltzmann Machines (RBMs) are generative neural networks that have received much attention recently. In particular, choosing the appropriate number of hidden units is important as it might hinder their representative power. According to the literature, RBM require numerous hidden units to approximate any distribution properly. In this paper, we present an experiment to determine whether such amount of hidden units is required in a classification context. We then propose an incremental algorithm that trains RBM reusing the previously trained parameters using a trade-off measure to determine the appropriate number of hidden units. Results on the MNIST and OCR letters databases show that using a number of hidden units, which is one order of magnitude smaller than the literature estimate, suffices to achieve similar performance. Moreover, the proposed algorithm allows to estimate the required number of hidden units without the need of training many RBM from scratch.

Abstract: In this paper we present a hybrid language model for the recognition of handwritten historical documents with a structured syntactical layout. Using a hidden Markov model-based recognition framework, a word-based grammar with a closed dictionary is enhanced by a character sequence recognition method. This allows to recognize out-of-dictionary words in controlled parts of the recognition, while keeping a closed vocabulary restriction for other parts. While the current status is work in progress, we can report an improvement in terms of character error rate.

Abstract: Best paper award
The performance of different feature extraction and shape description methods in trademark image recognition systems have been studied by several researchers. However, the potential improvement in classification through feature fusion by ensemble-based methods has remained unattended. In this work, we evaluate the performance of an ensemble of three classifiers, each trained on different feature sets. Three promising shape description techniques, including Zernike moments, generic Fourier descriptors, and shape signature are used to extract informative features from logo images, and each set of features is fed into an individual classifier. In order to reduce recognition error, a powerful combination strategy based on the Dempster-Shafer theory is utilized to fuse the three classifiers trained on different sources of information. This combination strategy can effectively make use of diversity of base learners generated with different set of features. The recognition results of the individual classifiers are compared with those obtained from fusing the classifiers’ output, showing significant performance improvements of the proposed methodology.

Abstract: Dynamic Time Warping (DTW) is commonly used in gesture recognition tasks in order to tackle the temporal length variability of gestures. In the DTW framework, a set of gesture patterns are compared one by one to a maybe infinite test sequence, and a query gesture category is recognized if a warping cost below a certain threshold is found within the test sequence. Nevertheless, either taking one single sample per gesture category or a set of isolated samples may not encode the variability of such gesture category. In this paper, a probability-based DTW for gesture recognition is proposed. Different samples of the same gesture pattern obtained from RGB-Depth data are used to build a Gaussian-based probabilistic model of the gesture. Finally, the cost of DTW has been adapted accordingly to the new model. The proposed approach is tested in a challenging scenario, showing better performance of the probability-based DTW in comparison to state-of-the-art approaches for gesture recognition on RGB-D data.

Abstract: In this article we provide an analysis of existing methods for the incorporation of color in bag-of-words based image representations. We propose a list of desired properties on which bases fusing methods can be compared. We discuss existing methods and indicate shortcomings of the two well-known fusing methods, namely early and late fusion. Several recent works have addressed these shortcomings by exploiting top-down information in the bag-of-words pipeline: color attention which is motivated from human vision, and Portmanteau vocabularies which are based on information theoretic compression of product vocabularies. We point out several remaining challenges in cue fusion and provide directions for future research.

Abstract: Computational simulations of the heart are a powerful tool for a comprehensive understanding of cardiac function and its intrinsic relationship with its muscular architecture. Cardiac biomechanical models require a vector field representing the orientation of cardiac fibers. A wrong orientation of the fibers can lead to a
non-realistic simulation of the heart functionality. In this paper we explore the impact of the fiber information on the simulated biomechanics of cardiac muscular anatomy. We have used the John Hopkins database to perform a biomechanical simulation using both a synthetic benchmark fiber distribution and the data obtained experimentally from DTI. Results illustrate how differences in fiber orientation affect heart deformation along cardiac cycle.

Abstract: Segmentation of a single image is in general a highly underconstrained problem. A frequent approach to solve it is to somehow provide prior knowledge or constraints on how the objects of interest look like (in terms of their shape, size, color, location or structure). Image co-segmentation trades the need for such knowledge for something much easier to obtain, namely, additional images showing the object from other viewpoints. Now the segmentation problem is posed as one of differentiating the similar object regions in all the images from the more varying background. In this paper, for the first time, we extend this approach to video segmentation: given two or more video sequences showing the same object (or objects belonging to the same class) moving in a similar manner, we aim to outline its region in all the frames. In addition, the method works in an unsupervised manner, by learning to segment at testing time. We compare favorably with two state-of-the-art methods on video segmentation and report results on benchmark videos.