1,721,083 research outputs found
SSIM based signature of facial micro-expressions
No full textFacial microexpressions (MEs) play a crucial role in the non verbal communication. Their automatic detection and recognition on a real video is a topic of great interest in different fields. However, the main difficulty in automatically capturing this kind of feature consists in its rapid temporal evolution, i.e. MEs occur in very few frames of video acquired by a conventional camera. In this paper a first study concerning the perceptual characteristics of ME is performed. The study is based on the observation that MEs are visible by a human observer, even though they are very rapid, and almost independently of the context. The Structural SIMilarity index (SSIM), which is a common perception-based metric, has been then used to detect a sort of fingerprint of MEs, that will be indicated as PES (Perceptual Expression Signature). The latter is able to efficiently guide the preprocessing step for MEs recognition procedure, as it allows for a fast video segmentation by providing only those frames where a ME occurs with high probability. Preliminary empirical studies on MEs in the wild have confirmed the feasibility of such an approach
Costi e risultati della distribuzione diretta dei farmaci: valutazioni da un caso aziendale
No full textI consorzi per lo sviluppo industriale in provincia di Udine. Condizioni attuali e prospettive evolutive
No full textA fast preprocessing method for micro-expression spotting via perceptual detection of frozen frames
Full text linkThis paper presents a preliminary study concerning a fast preprocessing method for facial microexpression (ME) spotting in video sequences. The rationale is to detect frames containing frozen expressions as a quick warning for the presence of MEs. In fact, those frames can either precede or follow (or both) MEs according to ME type and the subject’s reaction. To that end, inspired by the Adelson–Bergen motion energy model and the instinctive nature of the preattentive vision, global visual perception-based features were employed for the detection of frozen frames. Preliminary results achieved on both controlled and uncontrolled videos confirmed that the proposed method is able to correctly detect frozen frames and those revealing the presence of nearby MEs—independently of ME kind and facial region. This property can then contribute to speeding up and simplifying the ME spotting process, especially during long video acquisitions
Simultaneous bilateral renal cell adenocarcinoma. One-stage surgical treatment
No full textReview of a very well documented case with very complete iconography, and of the literature led to the following conclusions. First, it is preferable to treat these patients by a one-stage operation involving nephrectomy on one side and, if possible, conservative treatment to other kidney. Second, that the prognosis in synchronous bilateral renal cancer is much better than that of metachronous bilateral cancers (5-year survival 69% and 37.5% respectively), probably beause the former are usually of low grade and early stage. This justifies the most audacious surgical tentatives and, in this respect, this paper is of very high interest
Fractal properties of 4-point interpolatory subdivision schemes and wavelet scattering transform for signal classification
Full text linkWavelet scattering is a recent time-frequency transform that shares the convolutional architecture with convolutional neural networks, but it allows for a faster training and it often requires smaller training sets. It consists of a multistage non-linear transform that allows us to compute the deep spectrum of a signal by cascading convolution, non-linear operator and pooling at each stage, resulting a powerful tool for signal classification when embedded in machine learning architectures. One of the most delicate parameters in convolutional architectures is the temporal sampling that strongly affects the computational load as well as the classification rate. In this paper the role of sampling in the wavelet scattering transform is studied for signal classification purposes. In particular, the role of subdivision schemes in properly compensating the information lost when using sampling at each stage of the transform is investigated. Preliminary experimental results show that, starting from coarse grids, interpolatory subdivision schemes reproduce copies of the original scattering coefficients at a fixed full grid that still represent distinctive features for signal classes. In fact, thanks to the ability of the scheme in reproducing similar fractal properties of the transform through an efficient iterative refinement procedure, the reproduced coefficients enable to obtain classification rates similar to those provided by the native wavelet scattering transform. The relationships between the tension parameter of the scheme and the fractal dimension of its limit curve are also investigated
An entropy-based speed up for hyperspectral data classification via CNN
No full textThe paper presents an empirical study concerning the use of Convolutional Neural Networks (CNN) for hyperspectral data classification. The type and the size of input data have been analyzed to both optimize accuracy and training time. An entropy-based method for selecting the number of CNN input features has also been adopted; for fixed operational setup, it allows to preserve accuracy rate, while greatly decreasing the training time. Experimental results refer to source spectra and their reduced version through principal components analysis (PCA) and show that a proper selection of principal components allows to greatly reduce the computing time, while still guaranteeing high classification accuracies
Coherence of PRNU weighted estimations for improved source camera identification
Full text linkThis paper presents a method for Photo Response Non Uniformity (PRNU) pattern noise based camera identification. It takes advantage of the coherence between different PRNU estimations restricted to specific image regions. The main idea is based on the following observations: different methods can be used for estimating PRNU contribution in a given image; the estimation has not the same accuracy in the whole image as a more faithful estimation is expected from flat regions. Hence, two different estimations of the reference PRNU have been considered in the classification procedure, and the coherence of the similarity metric between them, when evaluated in three different image regions, is used as classification feature. More coherence is expected in case of matching, i.e. the image has been acquired by the analysed device, than in the opposite case, where similarity metric is almost noisy and then unpredictable. Presented results show that the proposed approach provides comparable and often better classification results of some state of the art methods, showing to be robust to lack of flat field (FF) images availability, devices of the same brand or model, uploading/downloading from social networks
Unsupervised perception-based image restoration of semi-transparent degradation using Lie group transformations
No full textThis paper presents a generalized model for the removal of semi-transparent defects from images of historical or artistic value. Its main feature is the combination of Lie group transformations with human perception rules that makes restoration more flexible and adaptive to defects having different physical or mechanical causes. Specifically, Lie groups allow to define a redundant set of transformations from which it is possible to automatically select the ones that better invert the physical formation of the defect. Hence, the restoration process consists of an iterative procedure whose main goal is to reduce defect visual perception. The proposed restoration method has been successfully tested on original movies and photographs, affected by line-scratches and semi-transparent blotches
- …
