Some Time Division Multiple Access (TDMA) wireless cooperative relay protocols and their Symbol Error Rate (SER) performance have recently been developed. These works, however, are limited to SER upper bounds or SER f...
详细信息
Strong rebar echo which can't be eliminated in tx domain directly will disturb the detection and discrimination of the interested targets like cryptic disasters. This paper presents the application of Hyp-curvelet...
详细信息
An algorithm for detection of the air maneuvering target based on the reconstruction of time sampling is proposed. Space sampling is used to reconstruct time sampling, which is equivalent to increasing the number of t...
详细信息
Take multi-time-phase Landstat TM/ETM+ Remote Sensing images (1990,2002,2007) of Nanning City as data source and use RS and GIS intergration technology to extract the informa-tion of city. The paper analyses the prope...
详细信息
People often feel the limitation of time to read the continuously increasing articles they need to read. It is a grand challenge to handle the explosion of articles. To understand how humans read articles and get the ...
详细信息
Abstract-Brain-computer interface (BCI) which transforms signals from the brain into control signals can help people with disabilities communicate with others. In this paper, posteriori probability support vector mach...
详细信息
Abstract-Brain-computer interface (BCI) which transforms signals from the brain into control signals can help people with disabilities communicate with others. In this paper, posteriori probability support vector machine (PPSVM) for patterns recognition was developed. For the classification of the left or right hand motor imagery, this method was used to expend the training set by adding samples with great probability output. For the dataset from 2003 BCI Competition, AR model was adopted to extract feature vectors and SVM with posteriori probabilistic output was used to classify the dataset. The results proved that, by adding samples with big probability, the performance of BCI was improved and higher accuracy was achieved.
To improve the quality of recovered images, a self-embedding fragile watermarking scheme is proposed based on the bicubic prediction. To take into account the PFA and the watermark payload, the 6-bit recovery data of ...
详细信息
To improve the quality of recovered images, a self-embedding fragile watermarking scheme is proposed based on the bicubic prediction. To take into account the PFA and the watermark payload, the 6-bit recovery data of a 2×2 block and the 8-bit key-based data of a 4×4 block are generated and inserted in the other 2×2 block and 4×4 block based on secret key, respectively. The validity of a 2×2 image block is determined by combining the recovery data with the key-based data. To improve the recovery quality, the recovery method based on bicubic prediction is designed to reconstruct the invalid blocks whose recovery watermark embedded in the other block is also destroyed. Simulation results demonstrate that the proposed scheme allows image recovery with an acceptable visual quality (PSNR ≈ 25 dB) up to 75% tampering.
Word alignment is a fundamental step in machine translation. Current statistical machine translation systems suffer from a major drawback: they only extract rules from 1-best alignments, which adversely affects the ru...
详细信息
Large-scale semantic concept detection from large video database suffers from the large variations among different semantic concepts as well as their corresponding effective low-level features. In this paper, we propo...
详细信息
Large-scale semantic concept detection from large video database suffers from the large variations among different semantic concepts as well as their corresponding effective low-level features. In this paper, we propose a novel framework to deal with this obstacle. The proposed framework consists of four major components: feature pool construction, pre-filtering, modeling, and classification. First, a large low-level feature pool is constructed, from which a specific set of features are selected for the latter steps automatically or semi-automatically. Then, to deal with the unbalance problem in training set, a pre-filtering classifier is generated, which aim at achieving a high recall rate and a certain precision rate nearly 50% for a certain concept. Thereafter, from the pre-filtered training samples, a SVM classifier is built based on the selected features in the feature pool. After that, the SVM classifier is applied to classification of semantic concept. This framework is flexible and extensible in terms of adding new features into the feature pool, introducing human interactions on selecting features, building models for new concepts and adopting active learning.
An efficient SAR image fusion algorithm for multi-polarimetric images based on Directionlets transform is proposed. Directionlets transform is a new lattice-based multi scale analysis anisotropic multi-directional wav...
详细信息
ISBN:
(纸本)9781612847719
An efficient SAR image fusion algorithm for multi-polarimetric images based on Directionlets transform is proposed. Directionlets transform is a new lattice-based multi scale analysis anisotropic multi-directional wavelet transform. Firstly, several polarimetric images can be decomposed into low frequency coefficients and high-frequency coefficients with multi scales and multi-directions using the Directionlets transform. For the low-frequency coefficients, the average fusion method is used. For the each directional high frequency sub-band coefficients, the directive contrast and the larger value of region variance information measurement is used to select the better coefficients for fusion. At last the fused image can be obtained by utilizing inverse transform for fused Directionlets coefficients. Experimental results show that compared with traditional algorithm, the proposed algorithm can get better visual effect and the significant information of original image like textures and contour details is well maintained.
暂无评论