7 research outputs found
Occlusion and visible background and foreground areas in stereo:a Bayesian approach
No full textEfficient techniques are introduced in this paper for the identification of the occlusion and visible background and foreground areas in a noisy stereoscopic image pair. Three different Bayes decision methods are tested for this purpose. The first, and simplest, uses three hypotheses for the formulation of the Bayes decision rules, adopting the right image as a reference. After performing a dual-Bayes decision test having each time as a different image of the stereo pair as reference, consistency checking is added to these tests to form the second method. Finally, four compound hypotheses are used in the third method, which is the most accurate but also the more detailed and computationally involved of the three. Experimental results illustrating the performance of the proposed techniques are presented and evaluated.</p
Social Media: Trends, Events, and Influential Users
No full textThe streaming nature of the social media content, the increasing population of social media users, and the all-connected devices have significantly amplified the amounts of shared content. Navigating through these vast amounts of content and extracting meaningful information and knowledge has become an extremely interesting research topic in recent years. Many researchers have proposed algorithms and methods to organize the shared content into meaningful ways and thus enable efficient navigation through and exploration of the shared content. In this entry, we discuss the progress in three different but overlapping topics: detection of social trends, detection of events, and detection of influential users
Blocking artifact detection and reduction in compressed data
No full textA novel frequency-domain technique for image blocking artifact detection and reduction is presented in this paper. The algorithm first detects the regions of the image which present visible blocking artifacts. This detection is performed in the frequency domain and uses the estimated relative quantization error calculated when the discrete cosine transform (DCT) coefficients are modeled by a Laplacian probability function. Then, for each block affected by blocking artifacts, its dc and ac coefficients are recalculated for artifact reduction. To achieve this, a closed-form representation of the optimal correction of the DCT coefficients is produced by minimizing a novel enhanced form of the mean squared difference of slope for every frequency separately. This correction of each DCT coefficient depends on the eight neighboring coefficients in the subband-like representation of the DCT transform and is constrained by the quantization upper and lower bound. Experimental results illustrating the performance of the proposed method are presented and evaluated.</p
Mobile Tele-Echography:User interface design
No full textUltrasound imaging allows the evaluation of the degree of emergency of a patient. However, in some instances, a well-trained sonographer is unavailable to perform such echography. To cope with this issue, the Mobile Tele-Echography Using an Ultralight Robot (OTELO) project aims to develop a fully integrated end-to-end mobile tele-echography system using an ultralight remote-controlled robot for population groups that are not served locally by medical experts. This paper focuses on the us er interface of the OTELO system, consisting of the following parts: an ultrasound video transmission system providing real-time images of the scanned area, an audio/video conference to communicate with the paramedical assistant and with the patient, and a virtual-reality environment, providing visual and haptic feedback to the expert, while capturing the expert's hand movements. These movements are reproduced by the robot at the patient site while holding the ultrasound probe against the patient skin. In addition, the user interface includes an image processing facility for enhancing the received images and the possibility to include them into a database.</p
