Albert Dipanda

User Profile Matching in Social Networks

Inter-social networks operations and functionalities are required in several scenarios (data integration, data enrichment, information retrieval, etc.). To achieve this, matching user profiles is required. Current methods are so restrictive and do not consider all the related problems. Particularly, they assume that two profiles describe the same physical person only if the values of their Inverse Functional Property or IFP (e.g. the email address, homepage, etc.) are the same. However, the observed trend in social networks is not fully compatible with this assumption since users tend to create more than one social network account (for personal use, for work, etc.) while using same or different email addresses. In this work, we address the problem of matching user profiles in its globality by providing a suitable matching framework able to consider all the profile’s attributes. Our framework allows users to give more importance to some attributes and assign each attribute a different similarity measure. The set of experiments conducted with our default/recommended attribute/similarity measures shows the superiority of our proposal in comparison with current ones.

Towards a real-time 3D shape reconstruction using a structured light system

This paper deals with 3D shape reconstruction using a structured light system (SLS) which projects a matrix of laser rays onto the scene to be analyzed. The intrinsic problem of such a system is the correspondence problem solving, which in this particular case amounts to matching up the imaged spots and the originating laser rays. In this paper, we propose a method for automatically obtaining configurations of the system (COS) (i.e. the relative positions of the camera, laser projector, and measuring scene) that permit to achieve a direct and unambiguous correspondence. After, we propose a splitting cell algorithm, which efficiently performs a real-time correspondence procedure. Experimental results obtained from both simulated and real data demonstrate that our method provides our SLS with possibilities for real-time applications.

Temporal Denoising of Kinect Depth Data

The release of the Microsoft Kinect has attracted the attention of researchers in a variety of computer science domains. Even though this device is still relatively new, its recent applications have shown some promising results in terms of replacing current conventional methods like the stereo-camera for robotics navigation, multi-camera system for motion detection and laser scanner for 3D reconstruction. While most work around the Kinect is on how to take full advantage of its capabilities, so far only a few studies have been carried out on the limitations of this device and fewer that provide solutions to enhance the precision of its measurements. In this paper, we review and analyse current work in this area, and present and evaluate a temporal denoising algorithm to reduce the instability of the depth measurements provided by the Kinect over different distances.

3-D shape reconstruction in an active stereo vision system using genetic algorithms

Abstract The recovery of 3-D shape information (depth) using stereo vision analysis is one of the major areas in computer vision and has given rise to a great deal of literature in the recent past. The widely known stereo vision methods are the passive stereo vision approaches that use two cameras. Obtaining 3-D information involves the identification of the corresponding 2-D points between left and right images. Most existing methods tackle this matching task from singular points, i.e. finding points in both image planes with more or less the same neighborhood characteristics. One key problem we have to solve is that we are on the first instance unable to know a priori whether a point in the first image has a correspondence or not due to surface occlusion or simply because it has been projected out of the scope of the second camera. This makes the matching process very difficult and imposes a need of an a posteriori stage to remove false matching. In this paper we are concerned with the active stereo vision systems which offer an alternative to the passive stereo vision systems. In our system, a light projector that illuminates objects to be analyzed by a pyramid-shaped laser beam replaces one of the two cameras. The projections of laser rays on the objects are detected as spots in the image. In this particular case, only one image needs to be treated, and the stereo matching problem boils down to associating the laser rays and their corresponding real spots in the 2-D image. We have expressed this problem as a minimization of a global function that we propose to perform using Genetic Algorithms (GAs). We have implemented two different algorithms: in the first, GAs are performed after a deterministic search. In the second, data is partitioned into clusters and GAs are independently applied in each cluster. In our second contribution in this paper, we have described an efficient system calibration method. Experimental results are presented to illustrate the feasibility of our approach. The proposed method yields high accuracy 3-D reconstruction even for complex objects. We conclude that GAs can effectively be applied to this matching problem.

Discovering relationship types between users using profiles and shared photos in a social network

In this paper, we propose a new approach to discover the relationship types between a user and her contacts in a social network. This is of key importance for many applications in the domain of photo sharing, privacy protection, information enriching, etc. Our approach is based, on one hand, on information extracted from users’ profiles and their shared photos, and, on the other hand, on a set of predefined rules validated by the main user before being mined and derived according to her preferences and social network content. The contribution of our method is twofold: 1) it is user-based enabling the user to set her preferences and give her feedbacks on the derived rules and results, and 2) it is multi-criteria that exploits and combines several attributes and features from user profiles and shared photos respectively. It also allows the user to define new relationship types. We conducted a set of experiments to validate our approach. The obtained results show the accuracy of our approach in different scenarios.

Comparative evaluation of methods for filtering Kinect depth data

The release of the Kinect has fostered the design of novel methods and techniques in several application domains. It has been tested in different contexts, which span from home entertainment to surgical environments. Nonetheless, to promote its adoption to solve real-world problems, the Kinect should be evaluated in terms of precision and accuracy. Up to now, some filtering approaches have been proposed to enhance the precision and accuracy of the Kinect sensor, and preliminary studies have shown promising results. In this work, we discuss the results of a study in which we have compared the most commonly used filtering approaches for Kinect depth data, in both static and dynamic contexts, by using novel metrics. The experimental results show that each approach can be profitably used to enhance the precision and/or accuracy of Kinect depth data in a specific context, whereas the temporal filtering approach is able to reduce noise in different experimental conditions.

Matching lines and points in an active stereo vision system using genetic algorithms

A new method using genetic algorithms (GAs) is proposed for reconstructing a 3-D shape from an image. This image is obtained by an active stereo vision system composed of a camera and a light system which projects laser rays on the scene to be analyzed. The depth information is provided by matching the laser rays and the corresponding spots appearing in the image. Experimental results demonstrate that the proposed method is effective for 3-D shapes reconstruction.

Efficient scalable sensor node placement algorithm for fixed target coverage applications of wireless sensor networks

Large applications of sensor networks, such as environmental risk monitoring, require the deployment of hundreds or even thousands of nodes. This study proposes and implements a novel stochastic physics-based optimisation algorithm that is both efficient (guarantees full target coverage with a reduced number of sensors) and scalable (meaning that it can be executed for very large-scale problems in a reasonable computation time). The algorithm employs ‘virtual sensors’ which move, merge, recombine, and ‘explode’ during the course of the algorithm, where the process of merging and recombining virtual sensors reduces the number of actual sensors while maintaining full coverage. The parameters which control sensor merging and explosion are varied during the algorithm to perform the same function as an annealing schedule in simulated annealing. Simulation results illustrate the rapidity and the effectiveness of the proposed method.

Signal processing for image enhancement and multimedia processing

Traditionally, signal processing techniques lay at the foundation of multimedia data processing and analysis. In the past few years, a new wave of advanced signal-processing techniques has delivered exciting results, increasing systems capabilities of efficiently exchanging image data and extracting useful knowledge. Signal Processing for Image Enhancement and Multimedia Processing is written by global experts who have extended the best papers presented at the SITIS 2006 International Conference to chapter versions. This edited book presents research results on the application of advanced signal processing techniques for improving the value of image and video data. In addition, this volume includes discussions on feature-based techniques for deep, feature-oriented analysis of images, plus new results on video coding on the time-honored topic of securing image information. Signal Processing for Image Enhancement and Multimedia Processing is designed for a professional audience of practitioners and researchers in industry. It is also suitable as a reference or secondary text for advanced-level students in computer science and engineering.

Efficient correspondence problem-solving in 3-D shape reconstruction using a structured light system

This paper deals with 3-D object reconstruction using a structured light system (SLS). The SLS is composed of a camera and a laser projector that illuminates spots on the scene of interest. The basic problem of such a system is the correspondence problem. If the correct correspondence between the imaged spots and the projected laser rays is found, the 3-D coordinates of the physical points associated with these spots can be calculated. We propose a method that automatically provides SLS configurations (i.e., the relative positions of both camera and laser projector with respect to the object to be analyzed) that allow performing an unambiguous and direct correspondence procedure. Experimental results are presented that show the validity and the effectiveness of the proposed method.