在许多关于信度网结构的学习文献中，都将交叉熵作为检验算法学习效果的一个指标。
In many papers on learning BN structure, the Crossing Entropy was used as an indicator of measuring the learning accuracy of an algorithm.
针对传统停止迭代准则译码耗费硬件资源的不足，提出了利用外部信息结合交叉熵迭代停止准则作为新的迭代停止准则算法。
Owing to the disadvantage that traditional stopping criteria expend hardware resource too much, USES the combination of cross entropy criteria and exterior information by way of the stopping criteria.
比较了新算法与基于最小交叉熵以及基于传统香农熵的阈值化算法的特点和分割性能。
The new algorithm is compared with a number of traditional algorithms based on Shannon entropy and minimum cross entropy by applying them to various test images.
最后从均值、信息熵、交叉熵、扭曲程度、相关系数等方面对融合后图像进行了评价，验证了算法的可行性。
Finally, evaluation is made from the following aspects: mean, entropy, cross entropy, distortion of the correlation coefficients and the feasibility of the method is verified in this paper.
结合图像亮度归一化和二维交叉熵的思想提出了一种针对光照变化鲁棒性强的运动目标检测算法。
Combining the thoughts of image intensity normalization and two-dimensional cross-entropy, a moving object detection algorithm, which is robust against illumination changes, is presented.
结合图像亮度归一化和二维交叉熵的思想提出了一种针对光照变化鲁棒性强的运动目标检测算法。
Combining the thoughts of image intensity normalization and two-dimensional cross-entropy, a moving object detection algorithm, which is robust against illumination changes, is presented.
应用推荐