Balancing Exploration and Exploitation: A New Algorithm for Active Machine Learning

Active machine learning algorithms are used when large numbers of unlabeled examples are available and getting labels for them is costly (e.g. requiring consulting a human expert). Many conventional active learning algorithms focus on refining the decision boundary, at the expense of exploring new regions that the current hypothesis misclassifies. We propose a new active learning algorithm that balances such exploration with refining of the decision boundary by dynamically adjusting the probability to explore at each step. Our experimental results demonstrate improved performance on data sets that require extensive exploration while remaining competitive on data sets that do not. Our algorithm also shows significant tolerance of noise.

Growth and Characterization of Silicon Carbide Thin Films Using a Nontraditional Hollow Cathode Sputtering Technique

Silicon carbide (SiC) is considered a suitable candidate for high-power, high-frequency devices due to its wide bandgap, high breakdown field, and high electron mobility. It also has the unique ability to synthesize graphene on its surface by subliming Si during an annealing stage. The deposition of SiC is most often carried out using chemical vapor deposition (CVD) techniques, but little research has been explored with respect to the sputtering of SiC. Investigations of the thin film depositions of SiC from pulse sputtering a hollow cathode SiC target are presented. Although there are many different polytypes of SiC, techniques are discussed that were used to identify the film polytype on both 4H-SiC substrates and Si substrates. Results are presented about the ability to incorporate Ge into the growing SiC films for the purpose of creating a possible heterojunction device with pure SiC. Efforts to synthesize graphene on these films are introduced and reasons for the inability to create it are discussed. Analysis mainly includes crystallographic and morphological studies about the deposited films and their quality using x-ray diffraction (XRD), reflection high energy electron diffraction (RHEED), transmission electron microscopy (TEM), scanning electron microscopy (SEM), atomic force microscopy (AFM), Auger electron spectroscopy (AES) and Raman spectroscopy. Optical and electrical properties are also discussed via ellipsometric modeling and resistivity measurements. The general interpretation of these analytical experiments indicates that the films are not single crystal. However, the majority of the films, which proved to be the 3C-SiC polytype, were grown in a highly ordered and highly textured manner on both (111) and (110) Si substrates.

Texture descriptor based on partially self-avoiding deterministic walker on networks

Texture image analysis is an important field of investigation that has attracted the attention from computer vision community in the last decades. In this paper, a novel approach for texture image analysis is proposed by using a combination of graph theory and partially self-avoiding deterministic walks. From the image, we build a regular graph where each vertex represents a pixel and it is connected to neighboring pixels (pixels whose spatial distance is less than a given radius). Transformations on the regular graph are applied to emphasize different image features. To characterize the transformed graphs, partially self-avoiding deterministic walks are performed to compose the feature vector. Experimental results on three databases indicate that the proposed method significantly improves correct classification rate compared to the state-of-the-art, e.g. from 89.37% (original tourist walk) to 94.32% on the Brodatz database, from 84.86% (Gabor filter) to 85.07% on the Vistex database and from 92.60% (original tourist walk) to 98.00% on the plant leaves database. In view of these results, it is expected that this method could provide good results in other applications such as texture synthesis and texture segmentation. (C) 2012 Elsevier Ltd. All rights reserved.

The immediate effects of local and adjacent acupuncture on the tibialis anterior muscle: a human study

Abstract Background This study compares the immediate effects of local and adjacent acupuncture on the tibialis anterior muscle and the amount of force generated or strength in Kilogram Force (KGF) evaluated by a surface electromyography. Methods The study consisted of a single blinded trial of 30 subjects assigned to two groups: local acupoint (ST36) and adjacent acupoint (SP9). Bipolar surface electrodes were placed on the tibialis anterior muscle, while a force transducer was attached to the foot of the subject and to the floor. An electromyograph (EMG) connected to a computer registered the KGF and root mean square (RMS) before and after acupuncture at maximum isometric contraction. The RMS values and surface electrodes were analyzed with Student's t-test. Results Thirty subjects were selected from a total of 56 volunteers according to specific inclusion and exclusion criteria and were assigned to one of the two groups for acupuncture. A significant decrease in the RMS values was observed in both ST36 (t = -3.80, P = 0,001) and SP9 (t = 6.24, P = 0.001) groups after acupuncture. There was a decrease in force in the ST36 group after acupuncture (t = -2.98, P = 0.006). The RMS values did not have a significant difference (t = 0.36, P = 0.71); however, there was a significant decrease in strength after acupuncture in the ST36 group compared to the SP9 group (t = 2.51, P = 0.01). No adverse events were found. Conclusion Acupuncture at the local acupoint ST36 or adjacent acupoints SP9 reduced the tibialis anterior electromyography muscle activity. However, acupuncture at SP9 did not decrease muscle strength while acupuncture at ST36 did.

Dynamic texture segmentation based on deterministic partially self-avoiding walks

Recently there has been a considerable interest in dynamic textures due to the explosive growth of multimedia databases. In addition, dynamic texture appears in a wide range of videos, which makes it very important in applications concerning to model physical phenomena. Thus, dynamic textures have emerged as a new field of investigation that extends the static or spatial textures to the spatio-temporal domain. In this paper, we propose a novel approach for dynamic texture segmentation based on automata theory and k-means algorithm. In this approach, a feature vector is extracted for each pixel by applying deterministic partially self-avoiding walks on three orthogonal planes of the video. Then, these feature vectors are clustered by the well-known k-means algorithm. Although the k-means algorithm has shown interesting results, it only ensures its convergence to a local minimum, which affects the final result of segmentation. In order to overcome this drawback, we compare six methods of initialization of the k-means. The experimental results have demonstrated the effectiveness of our proposed approach compared to the state-of-the-art segmentation methods.

Barshalder 1 : A cemetery in Grötlingbo and Fide parishes, Gotland, Sweden, c. AD 1-1100. Excavations and finds 1826-1971

The prehistoric cemetery of Barshalder is located along the main road on the boundary between Grötlingbo and Fide parishes, near the southern end of the island of Gotland in the Baltic Sea. The cemetery was used from c. AD 1-1100. The level of publication in Swedish archaeology of the first millennium AD is low compared to, for instance, the British and German examples. Gotland’s rich Iron Age cemeteries have long been intensively excavated, but few have received monographic treatment. This publication is intended to begin filling this gap and to raise the empirical level of the field. It also aims to make explicit and test the often somewhat intuitively conceived results of much previous research. The analyses deal mainly with the Migration (AD 375–540), Vendel (AD 520–790) and Late Viking (AD 1000–1150) Periods. The following lines of inquiry have been prioritised. 1. Landscape history, i.e. placing the cemetery in a landscape-historical context. (Vol. 1, section 2.2.6) 2. Migration Period typochronology, i.e. the study of change in the grave goods. (Vol. 2, chapter 2) 3. Social roles: gender, age and status. (Vol. 2, chapter 3) 4. Religious identity in the 11th century, i.e. the study of religious indicators in mortuary customs and grave goods, with particular emphasis on the relationship between Scandinavian paganism and Christianity.. (Vol. 2, chapter 4) Barshalder is found to have functioned as a central cemetery for the surrounding area, located on peripheral land far away from contemporary settlement, yet placed on a main road along the coast for maximum visibility and possibly near a harbour. Computer supported correspondence analysis and seriation are used to study the gender attributes among the grave goods and the chronology of the burials. New methodology is developed to distinguish gender-neutral attributes from transgressed gender attributes. Sub-gender grouping due to age and status is explored. An independent modern chronology system with rigorous type definitions is established for the Migration Period of Gotland. Recently published chronology systems for the Vendel and Viking Periods are critically reviewed, tested and modified to produce more solid models. Social stratification is studied through burial wealth with a quantitative method, and the results are tested through juxtaposition with several other data types. The Late Viking Period graves of the late 10th and 11th centuries are studied in relation to the contemporary Christian graves at the churchyards. They are found to be symbolically soft-spoken and unobtrusive, with all pagan attributes kept apart from the body in a space between the feet of the deceased and the end of the over-long inhumation trench. A small number of pagan reactionary graves with more forceful symbolism are however also identified. The distribution of different 11th century cemetery types across the island is used to interpret the period’s confessional geography, the scale of social organisation and the degree of allegiance to western and eastern Christianity. 11th century society on Gotland is found to have been characterised by religious tolerance, by an absence of central organisation and by slow piecemeal Christianisation.

Identificación visual en ambientes subacuáticos

[ES] Los erizos de mar han servido como modelo prototípico de organismo en el desarrollo de la Biología. La irrupción de este animal como especie invasora en los fondos canarios, combinada con el éxito reproductivo que ha tenido en nuestras aguas, ha creado un problema medioambiental importante que se ha intentado atajar con la puesta en marcha de proyectos e iniciativas orientados a su erradicación (matanzas masivas) o su contención con intentos de estimular su explotación comercial para uso gastronómico. En el transcurso de este trabajo se pretende explorar la robustez con la que se pueden clasificar visualmente diferentes tipos de erizos (principalmente Diadema antillarumy y Erizos autóctonos) a partir tanto de imágenes estáticas como de secuencias de vídeo para evaluar si, mediante el empleo de técnicas de visión por computador, es posible resolver estas tareas mediante la inspección automática de vídeos e imágenes.

Optical flow estimation with consistent spatio-temporal coherence models

[EN] In this work we propose a new variational model for the consistent estimation of motion fields. The aim of this work is to develop appropriate spatio-temporal coherence models. In this sense, we propose two main contributions: a nonlinear flow constancy assumption, similar in spirit to the nonlinear brightness constancy assumption, which conveniently relates flow fields at different time instants; and a nonlinear temporal regularization scheme, which complements the spatial regularization and can cope with piecewise continuous motion fields. These contributions pose a congruent variational model since all the energy terms, except the spatial regularization, are based on nonlinear warpings of the flow field. This model is more general than its spatial counterpart, provides more accurate solutions and preserves the continuity of optical flows in time. In the experimental results, we show that the method attains better results and, in particular, it considerably improves the accuracy in the presence of large displacements.

Direct estimation of the backward flow

[EN] The aim of this work is to propose a new method for estimating the backward flow directly from the optical flow. We assume that the optical flow has already been computed and we need to estimate the inverse mapping. This mapping is not bijective due to the presence of occlusions and disocclusions, therefore it is not possible to estimate the inverse function in the whole domain. Values in these regions has to be guessed from the available information. We propose an accurate algorithm to calculate the backward flow uniquely from the optical flow, using a simple relation. Occlusions are filled by selecting the maximum motion and disocclusions are filled with two different strategies: a min-fill strategy, which fills each disoccluded region with the minimum value around the region; and a restricted min-fill approach that selects the minimum value in a close neighborhood. In the experimental results, we show the accuracy of the method and compare the results using these two strategies.

A variational approach to camera motion smoothing

[EN] In this paper we study a variational problem derived from a computer vision application: video camera calibration with smoothing constraint. By video camera calibration we meanto estimate the location, orientation and lens zoom-setting of the camera for each video frame taking into account image visible features. To simplify the problem we assume that the camera is mounted on a tripod, in such case, for each frame captured at time t , the calibration is provided by 3 parameters : (1) P(t) (PAN) which represents the tripod vertical axis rotation, (2) T(t) (TILT) which represents the tripod horizontal axis rotation and (3) Z(t) (CAMERA ZOOM) the camera lens zoom setting. The calibration function t -> u(t) = (P(t),T(t),Z(t)) is obtained as the minima of an energy function I[u] . In thIs paper we study the existence of minima of such energy function as well as the solutions of the associated Euler-Lagrange equations.

A variational approach to 3D cylindrical geometry reconstruction from multiple views

[EN] In this paper we present a variational technique for the reconstruction of 3D cylindrical surfaces. Roughly speaking by a cylindrical surface we mean a surface that can be parameterized using the projection on a cylinder in terms of two coordinates, representing the displacement and angle in a cylindrical coordinate system respectively. The starting point for our method is a set of different views of a cylindrical surface, as well as a precomputed disparity map estimation between pair of images. The proposed variational technique is based on an energy minimization where we balance on the one hand the regularity of the cylindrical function given by the distance of the surface points to cylinder axis, and on the other hand, the distance between the projection of the surface points on the images and the expected location following the precomputed disparity map estimation between pair of images. One interesting advantage of this approach is that we regularize the 3D surface by means of a bi-dimensio al minimization problem. We show some experimental results for large stereo sequences.

A variational approach to 3D geometry reconstruction from two or multiple views

[EN] In the last years we have developed some methods for 3D reconstruction. First we began with the problem of reconstructing a 3D scene from a stereoscopic pair of images. We developed some methods based on energy functionals which produce dense disparity maps by preserving discontinuities from image boundaries. Then we passed to the problem of reconstructing a 3D scene from multiple views (more than 2). The method for multiple view reconstruction relies on the method for stereoscopic reconstruction. For every pair of consecutive images we estimate a disparity map and then we apply a robust method that searches for good correspondences through the sequence of images. Recently we have proposed several methods for 3D surface regularization. This is a postprocessing step necessary for smoothing the final surface, which could be afected by noise or mismatch correspondences. These regularization methods are interesting because they use the information from the reconstructing process and not only from the 3D surface. We have tackled all these problems from an energy minimization approach. We investigate the associated Euler-Lagrange equation of the energy functional, and we approach the solution of the underlying partial differential equation (PDE) using a gradient descent method.

Prototipo de herramienta para el inventariado automático de piezas de Lego basado en visión artificial

Permitida la difusión del código bajo los términos de la licencia BSD de tres cláusulas.

Gender classification in large databases

[EN]In this paper, we address the challenge of gender classi - cation using large databases of images with two goals. The rst objective is to evaluate whether the error rate decreases compared to smaller databases. The second goal is to determine if the classi er that provides the best classi cation rate for one database, improves the classi cation results for other databases, that is, the cross-database performance.

Improving gender classification accuracy in the wild

[EN]In this paper, we focus on gender recognition in challenging large scale scenarios. Firstly, we review the literature results achieved for the problem in large datasets, and select the currently hardest dataset: The Images of Groups. Secondly, we study the extraction of features from the face and its local context to improve the recognition accuracy. Diff erent descriptors, resolutions and classfii ers are studied, overcoming previous literature results, reaching an accuracy of 89.8%.