密度峰值聚类(clustering by fast search and find of density peaks,DPC)算法在应对大规模聚类时效率不高。k近邻密度支配域小团簇加速技巧可以很好地改善该短板,但存在代表点代表能力不足的问题,从而影响聚类质量。代表团采样策略可...密度峰值聚类(clustering by fast search and find of density peaks,DPC)算法在应对大规模聚类时效率不高。k近邻密度支配域小团簇加速技巧可以很好地改善该短板,但存在代表点代表能力不足的问题,从而影响聚类质量。代表团采样策略可作为上述问题的改进方式。由此形成的新算法不仅继承了原有密度支配域小团簇加速技巧的高效特性,还保证了聚类的质量。算法构建k近邻图。再利用k近邻图进行核密度估计并构建若干个密度支配域。对各密度支配域分别从高低密度区域采样支配域代表团。利用代表团的近邻关系计算域间相似度。将各支配域视为新样本点,执行DPC算法完成聚类。实验证明,引入代表团策略对DPC算法有一定的提升,聚类效果比部分密度聚类算法更好。展开更多
Incremental image compression techniques using priori information are of significance to deal with the explosively increasing remote-sensing image data. However, the potential benefi ts of priori information are still...Incremental image compression techniques using priori information are of significance to deal with the explosively increasing remote-sensing image data. However, the potential benefi ts of priori information are still to be evaluated quantitatively for effi cient compression scheme designing. In this paper, we present a k-nearest neighbor(k-NN) based bypass image entropy estimation scheme, together with the corresponding mutual information estimation method. Firstly, we apply the k-NN entropy estimation theory to split image blocks, describing block-wise intra-frame spatial correlation while avoiding the curse of dimensionality. Secondly, we propose the corresponding mutual information estimator based on feature-based image calibration and straight-forward correlation enhancement. The estimator is designed to evaluate the compression performance gain of using priori information. Numerical results on natural and remote-sensing images show that the proposed scheme obtains an estimation accuracy gain by 10% compared with conventional image entropy estimators. Furthermore, experimental results demonstrate both the effectiveness of the proposed mutual information evaluation scheme, and the quantitative incremental compressibility by using the priori remote-sensing frames.展开更多
文摘密度峰值聚类(clustering by fast search and find of density peaks,DPC)算法在应对大规模聚类时效率不高。k近邻密度支配域小团簇加速技巧可以很好地改善该短板,但存在代表点代表能力不足的问题,从而影响聚类质量。代表团采样策略可作为上述问题的改进方式。由此形成的新算法不仅继承了原有密度支配域小团簇加速技巧的高效特性,还保证了聚类的质量。算法构建k近邻图。再利用k近邻图进行核密度估计并构建若干个密度支配域。对各密度支配域分别从高低密度区域采样支配域代表团。利用代表团的近邻关系计算域间相似度。将各支配域视为新样本点,执行DPC算法完成聚类。实验证明,引入代表团策略对DPC算法有一定的提升,聚类效果比部分密度聚类算法更好。
基金supported by National Basic Research Project of China(2013CB329006)National Natural Science Foundation of China(No.61622110,No.61471220,No.91538107)
文摘Incremental image compression techniques using priori information are of significance to deal with the explosively increasing remote-sensing image data. However, the potential benefi ts of priori information are still to be evaluated quantitatively for effi cient compression scheme designing. In this paper, we present a k-nearest neighbor(k-NN) based bypass image entropy estimation scheme, together with the corresponding mutual information estimation method. Firstly, we apply the k-NN entropy estimation theory to split image blocks, describing block-wise intra-frame spatial correlation while avoiding the curse of dimensionality. Secondly, we propose the corresponding mutual information estimator based on feature-based image calibration and straight-forward correlation enhancement. The estimator is designed to evaluate the compression performance gain of using priori information. Numerical results on natural and remote-sensing images show that the proposed scheme obtains an estimation accuracy gain by 10% compared with conventional image entropy estimators. Furthermore, experimental results demonstrate both the effectiveness of the proposed mutual information evaluation scheme, and the quantitative incremental compressibility by using the priori remote-sensing frames.
