In this paper, against Hsu R L skin tone detection algorithm, which has high missing detection ratio when the facial brightness of an image is high, we introduce a new nonlinear transformation method of the YCb "...
详细信息
In this paper, against Hsu R L skin tone detection algorithm, which has high missing detection ratio when the facial brightness of an image is high, we introduce a new nonlinear transformation method of the YCb "Cr" color skin space, which is the color segmentation of the human face for regional analysis and extraction; Then implement image rotation and template matching. Experimental results indicate that when the facial brightness of an image is high, the new proposed nonlinear color space conversion algorithm based on YCbCr color space is better than the simple method, which wipes off the effect of the brightness directly, and Hsu R L skin detection algorithm. The series of experimental results demonstrate clearly that our new method has a higher detection ratio on high bright facial images, and can drop the false or missing detection ratio on high luminance images. Besides, we have more detailed testing results on the eyes, eyebrows, mouth and other parts.
This paper not only proposes the detection algorithm of traditional ring signal tones, but also researches the Color Ring Back Tone which is well popular recent years. Different testing methods are given according to ...
详细信息
This paper not only proposes the detection algorithm of traditional ring signal tones, but also researches the Color Ring Back Tone which is well popular recent years. Different testing methods are given according to the difference of music color ring tone and voice prompt color ring tone. Tested on RMTS (Real-world Multi-channel Telephone Speech) database, experiments show that the detection rates of ring tone, music color ring tone, voice prompt color ring tone and virtual speech reach 100%, 98.5%, 98% and 97.5% respectively, 98.5% totally.
One of the most promising applications of synthetic aperture radar (SAR) imagery is change detection. However, the success of change detection algorithms is highly dependent on the type of change being detected. With ...
详细信息
One of the most promising applications of synthetic aperture radar (SAR) imagery is change detection. However, the success of change detection algorithms is highly dependent on the type of change being detected. With the advent of multi-channel SAR systems (multi-frequency and/or polarimetric) new algorithms to improve change detection are being developed to take advantage of the additional information. However, these algorithms are still hindered by the speckle phenomena of radar imaging. Adaptive neighborhood filtering techniques have been shown to be effective to reduce speckle, but the impact on change detection has not been explored. The research presented explores the impact of an adaptive filtering algorithm on the probability of detection for synthesized changes.
The storage operation of normal process in host system is analyzed and an anomaly intrusion detection method based on d-s evidence theory for storage system is proposed. The detector fuses multiple signatures of stora...
详细信息
The storage operation of normal process in host system is analyzed and an anomaly intrusion detection method based on d-s evidence theory for storage system is proposed. The detector fuses multiple signatures of storage data to decide whether the storage operation flow is normal. Furthermore, six groups of light-computation signatures of storage operation data are used to develop an efficient fusion mechanism to guarantee high performance of the algorithm. Experiment shows that high detection rate can be achieved by such fusion.
In this paper, a detection algorithm with parallel partial candidate-search algorithm is presented. Two fully independent partial search processes are simultaneously employed for two groups of transmit antennas based ...
详细信息
In this paper, a detection algorithm with parallel partial candidate-search algorithm is presented. Two fully independent partial search processes are simultaneously employed for two groups of transmit antennas based on QR and QL decompositions of the channel matrix. Proposed QRD- QLD detection algorithm is compared with well-known QRD-M scheme adopted for several emerging wireless standards. Latency of the QRD-QLD candidate search is about twice as small for similar error-rate performance and for identical hardware resources. Total detection latency of QRD-QLD algorithm that also includes computation of soft information for outer decoder is also substantially smaller.
Citation graph analysis has been used to evaluate the significance of documents and authors, or to estimate the impact of publication venues. In this paper, we investigate its new application in topic identification. ...
详细信息
Citation graph analysis has been used to evaluate the significance of documents and authors, or to estimate the impact of publication venues. In this paper, we investigate its new application in topic identification. We first model the communities in the citation graph as related documents on a specific topic. And then, a scientific theme detection algorithm is proposed based on community partition, attempting to identify the emergency of a new theme by tracking the change of the community where the top cited nodes lie in. Experimental results on real dataset show that the proposed method can detect new topic timely with only a subset of data.
We address the issue of classification problems in the following situation: test data include data belonging to unlearned classes. To address this issue, most previous works have taken two-stage strategies where uncle...
详细信息
We address the issue of classification problems in the following situation: test data include data belonging to unlearned classes. To address this issue, most previous works have taken two-stage strategies where unclear data are detected using an anomaly detection algorithm in the first stage while the rest of data are classified into learned classes using a classification algorithm in the second stage. In this study, we propose anomaly detection support vector machine (ADSVM) which unifies classification and anomaly detection. ADSVM is unique in comparison with the previous work in that it addresses the two problems simultaneously. We also propose a multiclass extension of ADSVM that uses a pairwise voting strategy. We empirically present that ADSVM outperforms two-stage algorithms in application to an real automobile fault dataset, as well as to UCI benchmark datasets.
Presently, outlier mining is used for many areas such as telecommunication, finance and intrusion detection. However, finding outliers needs amounts of computation with most traditional algorithms. Thus, we propose a ...
详细信息
Presently, outlier mining is used for many areas such as telecommunication, finance and intrusion detection. However, finding outliers needs amounts of computation with most traditional algorithms. Thus, we propose a modified density based outlier mining algorithm in this paper. For every object in dataset, our algorithm need not judge whether there are core objects within the epsiv-neighborhood of it. In addition, the module information of data object is introduced in our algorithm and it can avoid large numbers of unnecessary computation to finding all outliers. The algorithm is applied on the intrusion dataset and experimental results show it obtains efficient performance for outlier mining while maintaining stable detection rates.
This paper investigates a two-dimensionally spread orthogonal frequency and code division multiplexing (OFCDM) system with multi-code transmission and multiple input multiple output (MIMO) multiplexing, where desired ...
详细信息
This paper investigates a two-dimensionally spread orthogonal frequency and code division multiplexing (OFCDM) system with multi-code transmission and multiple input multiple output (MIMO) multiplexing, where desired data signals are interfered by not only co-channel signals from other transmit antennas (or multi-antenna interference (MAI)), but also multi- code interference (MCI) from other code channels on the same antenna. Combining the iterative detection in the space domain and the hybrid MCI cancellation and minimum mean square error (MMSE) detection in the frequency domain, a joint iterative detection algorithm is proposed to cancel out MAI and MCI. For the 0 th loop of the joint iterative detection, a 2-stage hybrid detection is needed in the frequency domain, while for later loops, a 0-stage hybrid detection or pure MMSE is sufficient. The system performance improves as the number of loops in the joint iterative detection increases. Moreover, using joint iterative detection, larger frequency diversity gain can be achieved and the performance improves as the frequency domain spreading factor increases.
Biorthogonal spline wavelet is used to detect the QRS complex of ECG signal. Mallat algorithm is applied in the decomposition of ECG signal by using the equivalent filter of a biorthogonal spline wavelet. Lipschitz ex...
详细信息
Biorthogonal spline wavelet is used to detect the QRS complex of ECG signal. Mallat algorithm is applied in the decomposition of ECG signal by using the equivalent filter of a biorthogonal spline wavelet. Lipschitz exponent is introduced to investigate the relationship between the signal singularity (R Peak) and the zero-crossing point of the modulus maximum pair of the signal's wavelet transform. Adaptive threshold, refractory period and expiating are applied to improve the anti-interference performance. Experimental results demonstrated that this method is robust against time varying characteristics of QRS complex and noise. A correct detection rate of 99.905% has been achieved when the MIT-BIH arrhythmia database is used to test the proposed QRS complex detection algorithm.
暂无评论