ID 原文 译文
1753 为了提高高分辨率图像分割效率，解决复杂图案中待分割目标边缘附近前景与背景区分度小而造成的分割目标不完整问题，本文通过引入超像素 HOG 特征，提出了一种基于超像素多特征融合(superpixel multi-feature fu-sion，SMFF)的快速图像分割算法。 In order to improve the efficiency of high-resolution image segmentation and solve the problem of incom-plete segmentation caused by small discrimination of foreground and background in the complex pattern near the edge of thetarget to be segmented, we propose a fast image segmentation algorithm based on superpixel multi-feature fusion (SMFF).
1754 首先采用目前最有效的超像素算法对待分割图像进行超像素预分割， Firstly, the most effective superpixel algorithm is used for superpixel processing,
1755 然后提取基于超像素的 HOG 特征、Lab 颜色特征和空间位置特征，设计基于超像素的多特征度量算法， and then the superpixel-based HOG feature, laboratory color feature and spatial position feature are extracted. Lastly, by designing a multi-feature measurement algo-rithm,
1756 最终采用图割理论实现了基于超像素多特征融合的快速图像分割。 the fast image segmentation algorithm based on superpixel multi-feature fusion is implemented.
1757 实验结果验证了本文算法的有效性，其算法性能接近于目前最经典图像分割算法，且本文算法的时间性能要明显优于其它对比算法。 Experimental resultsverify the effectiveness of the proposed algorithm, which is close to the most classical image segmentation algorithm, and the time performance of the proposed algorithm is significantly better than other comparison algorithms.
1758 动态异构冗余结构是拟态防御技术的常用工程模型。 Up to now, the Dynamic Heterogeneous Redundancy (DHR)structure is a kind of important engineering model about the Mimic Defense (MD)technique.
1759 然而，目前尚缺乏对该结构实施形式化分析的手段，因为该结构缺乏形式化建模方法。 However, there is still a lack of way of formal analysis for DHR structuresas there is no formal model available for a DHR structure.
1760 针对此问题，使用有穷状态自动机及其并行组合自动机为一些拟态攻防行为建立计算模型。 To address this problem, we use a Finite State Automaton (FSA)and its Parallel Automaton (PA)to establish a computing model for some attacks and mimic defenses.
1761 首先，使用单个有穷状态自动机为单个执行体建模; First, each FSA isemployed to model each execution body, while there are a number of execution bodies in a DHR structure.
1762 其次，使用有穷状态自动机的并行组合为执行体组合建模; Second, these FSAs are combined in parallel to model the combination of execution bodies.