In this paper, a pre-classification stage based on global features is incorporated to an online signature verification system for the purposes of improving its performance. The pre-classifier makes use of the discrimi...
详细信息
Motion vector estimation of image seqence is one of the important process in image coding, robot vision etc. A useful method of motion vector estimation in the gradient-based method which uses the relationship between...
详细信息
In many conventional voice activity detection (VAD) methods, speech signal is assumed to be acquired in high quality. However, human-machine interface based on speech is usually employed in indoor environment where va...
详细信息
Recursive identification algorithms for the parameter estimation of linear systems from multilevel quantized outputs are introduced in this paper. The proposed algorithms are proved to be optimal in the sense that the...
详细信息
In this research, we propose a method to estimate both direction of arrival (DOA) and time of arrival (TOA) using stepped FM radar system. The method uses beamformer and MUSIC algorithm with respect to time and space....
详细信息
In this research, we propose a method to estimate both direction of arrival (DOA) and time of arrival (TOA) using stepped FM radar system. The method uses beamformer and MUSIC algorithm with respect to time and space. The multiple target fs directions and distances are estimated accurately, and they are combined to represent the parameter of each target. Some simulations are performed and they show the validity of our method.
Code division multiplex access with cyclic prefix (CP-CDMA) is regarded as one of the best candidates for the broadband wireless communication systems in the uplink. This paper proposes a selective parallel interferen...
详细信息
In recent years, to achieve robust speech recognition against noises, Audio-Visual Speech Recognition (AVSR) system utilizing not only audio but also visual information of lip has been studied. This paper proposes a d...
详细信息
This paper proposes a novel solution to the problem of pose estimation of three-dimensional objects using feature maps. Our approach relies on quaternions as the mathematical representation of object orientation. We i...
详细信息
One of the most challenging problems in online signature verification is to select the best features to model the signatures. A widely used technique to address this problem is to combine different feature sets select...
详细信息
ISBN:
(纸本)9781509016341
One of the most challenging problems in online signature verification is to select the best features to model the signatures. A widely used technique to address this problem is to combine different feature sets selected by different criteria. In this paper, the combination of three different feature sets, viz., an automatically selected feature set, a feature set relevant to Forensic Handwriting Experts (FHEs), and a global feature set, on the basis of a score level fusion scheme, is proposed. In order to address the problem of conflicting results appearing when several classifiers are being used, the proposed combination is performed within the framework of the Belief Function Theory (BFT). Two different models, namely, the Denoeux and the Appriou models, are used to embed the problem within this framework, where the fusion is performed resorting to two well-known combination rules, namely, the Dempster-Shafer (DS) and the Proportional Conflict Redistribution (PCR5) one. Experimental results on a publicly availab.e database, prove that the proposed fusion scheme allows the system to have a very good trade-off between verification results and reliability.
Brain electrical activity is widely accepted as the typical non-stationary signal. In addition, there exist more evidences that both EEG and ERP signals are chaotic signal produced by the nonlinear dynamicssystem. To...
详细信息
暂无评论