Mutual information (MI) is an important information theoretic concept which has many applications in telecommunications, in blind source separation, and in machine learning. More recently, it has been also employed fo...
详细信息
ISBN:
(纸本)9783800734559
Mutual information (MI) is an important information theoretic concept which has many applications in telecommunications, in blind source separation, and in machine learning. More recently, it has been also employed for the instrumental assessment of speech intelligibility where traditionally correlation based measures are used. In this paper, we address the difference between MI and correlation from the viewpoint of discovering dependencies between variables in the context of speech signals. We perform our investigation by considering the linear predictive approximation and the extrapolation of speech signals as examples. We compare a parametric MI estimation approach based on a Gaussian mixture model (GMM) with the knearest neighbor (KNN) approach which is a well-known non-parametric method available to estimate the MI. We show that the GMM-based MI estimator leads to more consistent results.
Goal-driven top-down mechanism plays an important role in the case of object detection and recognition. In this paper, we propose a top-down computational model for goal-driven saliency detection based on a coding-bas...
详细信息
Over the past decades, a wide attention has been paid to crowd control and management in intelligent video surveillance area. In this paper, the authors propose a novel spatiotemporal viscous fluid field to recognize ...
详细信息
Over the past decades, a wide attention has been paid to crowd control and management in intelligent video surveillance area. In this paper, the authors propose a novel spatiotemporal viscous fluid field to recognize large-scale crowd event with respect to both appearance and driven factor of crowd behavior. Firstly, a spatiotemporal variation matrix is proposed to exploit motion property of a crowd. In particular, the paper exploits characteristics of the matrix with eigenvalue decomposition algorithm and constructs an abstract fluid field to model the crowd motion pattern, which is denoted by spatiotemporal fluid field. Secondly, the paper proposes a spatiotemporal force field to exploit the interaction force between the pedestrians. Furthermore, the fluid and force field constructs a spatiotemporal viscous fluid field. Thirdly, after generating feature with bag of word model, the authors utilize latent Dirichlet allocation model to recognize crowd behavior. The experiments on PETS2009 and UMN datasets show that the proposed method has a better performance for large-scale crowd behavior perception in both robustness and effectiveness comparing with the conventional methods.
Many real life applications often bring much high-dimensional and noise-contaminated data from different sources. In this paper, we consider de-noising as well as dimensionality reduction by proposing a novel method n...
详细信息
During the last two decades, image quality assessment has been a major research area, which considerably helps to promote the development of imageprocessing. Following the tremendous success of Structural SIMilarity ...
详细信息
During the last two decades, image quality assessment has been a major research area, which considerably helps to promote the development of imageprocessing. Following the tremendous success of Structural SIMilarity (SSIM) index in terms of the correlation between the quality predictions and the subjective scores, many improved algorithms have been further exploited, such as Multi-Scale SSIM (MS-SSIM) and Information content Weighted SSIM (IW-SSIM). However, a growing number of researchers have been devoted to the study of the effects of uneven responses to different image distortion categories on prediction accuracy of the quality metrics. Inspired by this, we propose an improved full-reference image quality assessment paradigm based on structure compensation. Experimental results on laboratory for image and Video Engineering (LIVE) database and Tampere image Database 2008 (TID2008) are provided to confirm our introduced approach has superior prediction performance as compared to mainstream image quality metrics. Besides, it is worth emphasizing that our algorithm not introduces other operators but only applies the SSIM function to compensate itself, and furthermore, it also has an effective capability of image distortion classification.
Diffusion tensor imaging (DTI) is known to be the best non-invasive imaging modality in providing anatomical information as white-matter fiber bundles. However, the Gaussian noise introduced into the diffusion tenso...
详细信息
ISBN:
(纸本)9781467321969
Diffusion tensor imaging (DTI) is known to be the best non-invasive imaging modality in providing anatomical information as white-matter fiber bundles. However, the Gaussian noise introduced into the diffusion tensor images can bring serious impacts on tensor calculation and fiber tracking. To decrease the effects of the Gaussian noise, many denoising methods have been presented. In this paper, a shearlet based denosing strategy is introduced. To evaluate the efficiency of the proposed shearlet based denoising method in accounting for the Gaussian noise introduced into the images, the peak to peak signal-to-noise ratio (PSNR), signal-to-mean squared error ratio (SMSE) and edge keeping index (Beta) metrics are adopted. The experiment results acquired from both the synthetic and real data indicate the good performance of our proposed filter.
Short message service (SMS) is now an indispensable way of social communication. However the mobile spam is getting increasingly serious, troubling users' daily life and ruining the service quality. We propose a n...
详细信息
ISBN:
(纸本)9781467322164
Short message service (SMS) is now an indispensable way of social communication. However the mobile spam is getting increasingly serious, troubling users' daily life and ruining the service quality. We propose a novel approach for spam message detection based on mining the underlying social network of SMS activities. Comparing with strategies on keywords or flow detection, our network-based approach is more robust and difficult to defeat by human spammers. Various levels of features are employed to describe multiple aspects of the network, such as static structures, node activities and evolving situations. Experimental results on real dataset illustrate effectiveness of various features, showing our promising results.
Visual comfort assessment for stereoscopic video is playing an important role for stereoscopic safety issue. In this paper, we propose a novel visual comfort assessment metric that utilizes interest regions detection ...
详细信息
Visual comfort assessment for stereoscopic video is playing an important role for stereoscopic safety issue. In this paper, we propose a novel visual comfort assessment metric that utilizes interest regions detection approach, which is called Salient Motion Depth Extraction approach in our algorithm. In stereoscopic video shots, salient motion regions where human subjects focus on should have more weights in visual comfort assessment. To achieve better performance, our approach combines salient cues, motion cues with depth cues in order to extract salient motion regions in consideration of depth context. Our visual comfort assessment utilizes local analytical method based on attention model by analyzing disparity features in interest regions extracted by Salient Motion Depth Extraction approach. The experimental results have demonstrated that our proposed visual comfort assessment improves the correlation with the subjective assessment.
In this paper, we propose a new method for remote sensing image pan-sharpening which is based on weighted red-black (WRB) wavelet and adaptive principal component analysis (PCA), where the adaptive PCA is used to redu...
详细信息
ISBN:
(纸本)9781467322164
In this paper, we propose a new method for remote sensing image pan-sharpening which is based on weighted red-black (WRB) wavelet and adaptive principal component analysis (PCA), where the adaptive PCA is used to reduce spectral distortions and the utilization of WRB wavelet is used to extract the spatial details in PAN images. To reduce the artifacts and spectral distortions in the pan-sharpened images, which were caused by the local instabilities and dissimilarities in the PAN and MS images, a local process strategy incorporating detail enhancement is introduced. The proposed method is tested on two datasets both acquired by QuickBird and compared with the existing methods. Experimental results show that our method can provide promising fused MS images at a high spatial resolution.
暂无评论