It is challenging to capture a high-dynamic range (HDR) scene using a low-dynamic range (LDR) camera. This paper presents an approach for improving the dynamic range of cameras by using multiple exposure images of sam...
It is challenging to capture a high-dynamic range (HDR) scene using a low-dynamic range (LDR) camera. This paper presents an approach for improving the dynamic range of cameras by using multiple exposure images of same scene taken under different exposure times. First, the camera response function (CRF) is recovered by solving a high-order polynomial in which only the ratios of the exposures are used. Then, the HDR radiance image is reconstructed by weighted summation of the each radiance maps. After that, a novel local tone mapping (TM) operator is proposed for the display of the HDR radiance image. By solving the high-order polynomial, the CRF can be recovered quickly and easily. Taken the local image feature and characteristic of histogram statics into consideration, the proposed TM operator could preserve the local details efficiently. Experimental result demonstrates the effectiveness of our method. By comparison, the method outperforms other methods in terms of imaging quality.
Facial expressions are considered a reliable indicator in neonatal pain *** paper proposes a new neonatal pain expression recognition method,which utilizes the feature descriptors based on weighted Local Binary Patter...
详细信息
Facial expressions are considered a reliable indicator in neonatal pain *** paper proposes a new neonatal pain expression recognition method,which utilizes the feature descriptors based on weighted Local Binary Pattern(LBP)and the classifier based on sparse ***,the normalized facial image is described using a feature vector,which is histogram sequence obtained by concatenating the weighted histograms of the LBP maps of all the local ***,the Principal Component Analysis(PCA)method is used to reduce the dimension of the feature ***,the classifier based on sparse representation is applied to classify test sample into four classes of facial expressions:calm,crying,moderate pain,severe *** objective of this study is to assist the clinicians in assessing neonatal pain by utilizing computer-based image analysis *** experimental results on neonate facial image database show the effectiveness of the proposed *** classification accuracy is up to 85.50%.
The difference of protein sequence or protein structure can be used for the construction of molecular evolutionary tree or phytogenetic tree with certain hierarchy and topology. The divergent points in the tree sugges...
详细信息
In this paper,we applied wavelet permutation entropy to analyze the Ventricular Fibrillation(VF) signals and Sudden Cardiac Death(SCD) signals for making an effective distinction from normal sinus rhythm(NSR) ***,thre...
详细信息
In this paper,we applied wavelet permutation entropy to analyze the Ventricular Fibrillation(VF) signals and Sudden Cardiac Death(SCD) signals for making an effective distinction from normal sinus rhythm(NSR) ***,three different ECG signals are decomposed by wavelet and reconstructed in each single *** highly discriminated frequency band will be chosen as our target ***,under the circumstances of different series length,embedding dimension and delay time,the main work is to distinguish the three ECG signals in different frequency bands based on the permutation entropy(PE).The results show that permutation entropy method can make a distinction between normal and abnormal ECG signals which aren't decomposed,but the effect of decomposing with wavelets is better *** the highest discriminated frequency band is from 15.625 Hz to 31.25 *** the point of different data length,embedding dimension and delay time,it was found that permutation entropy method have different effects and the findings may assist cardiac clinical diagnosis.
Target extraction is a key technology for image measurement of moving particles distributed in fluidic system. In this paper, we propose a novel moving particle extraction method based on multimodal characteristic of ...
详细信息
Though weighted voting matching is one of most successful image matching methods,each candidate correspondence receives voting score from all other candidates,which can not apparently distinguish correct matches and i...
详细信息
Though weighted voting matching is one of most successful image matching methods,each candidate correspondence receives voting score from all other candidates,which can not apparently distinguish correct matches and incorrect matches using voting *** this paper,a new image matching method based on mutual k-nearest neighbor(k-nn) graph is ***,the mutual k-nn graph is constructed according to similarity between candidate ***,each candidate only receives voting score from its mutual k nearest ***,based on voting scores,the matching correspondences are computed by a greedy ranking *** results demonstrate the effectiveness of the proposed method.
Mobility motif is a typical topology structure shared by movement trajectories, which could exhibit multi-scale spatio-temporal patterns in human behavior. There are two types of motifs, frequent, infrequent. The infr...
详细信息
Mobility motif is a typical topology structure shared by movement trajectories, which could exhibit multi-scale spatio-temporal patterns in human behavior. There are two types of motifs, frequent, infrequent. The infrequent one hasn't got enough attention in research. In this paper, we study the relationship between infrequent motifs, mass activities. We have discovered that crowds are more likely to generate abnormal motifs when they attend activities than on ordinary days. Inspired by the discovery, we propose a novel model to incorporate the connection between motif anomalies, mass activities, which is verified by our real-world data driven analysis. Compared to previous mobility analysis, our work facilitates the inspection of human mobility anomalies in a fresh perspective, it is a promising step towards unraveling the actual causation behind human mobility.
Sleep Electroencephalogram(Sleep EEG) detection and treatment can provide the basis for clinical diagnosis and treatment. According to the non-stationary random character of EEG itself, the paper proposed multiscale s...
详细信息
ISBN:
(纸本)9781510806450
Sleep Electroencephalogram(Sleep EEG) detection and treatment can provide the basis for clinical diagnosis and treatment. According to the non-stationary random character of EEG itself, the paper proposed multiscale sign series entropy(MSSE) method and applied it to the state of sleep EEG analysis. Numerical results showed that, MSSE method can effectively differentiate awake period β wave and sleep stage β wave even if under the influence of the noise. The results show that the algorithm can aid in clinical diagnosis of sleep EEG.
Detection of groups of interacting people is a difficult task, especially in an unconstrained and crowded environment. In this paper, as a main contribution, we present a novel and efficient framework for social group...
详细信息
暂无评论