1) initializing weights
权重初始化
2) Weights initialize hypersphere
权重初始化超球
3) re-initialization
重初始化
1.
This paper proposes an improved C-V model, which can avoid the step of re-initialization and simplify the formation of the initial level set function, thus the speed of segmentation can be accelerated greatly.
提出了一种改进的C-V模型,完全避免了重初始化步骤并简化了初始水平集函数的构造,大大加快了分割速度。
2.
First,a new internal energy is introduced that forces the level set function to be close to a signed distance function,therefore not only the re-initialization procedure is completely eliminated,but also the level set function can be initialized with general functions.
首先引入一种新的内部能量函数,即以水平集函数与距离函数的偏差作为能量函数,无需重初始化水平集函数,且初始水平集函数可以用一般的分段函数来定义,节省了初始化和重初始化过程所消耗的时间。
4) weight initialization
权值初始化
1.
A novel learning algorithm is proposed that is based on the combination of independent component analysis(ICA)based weight initialization and automatically adjusting the gain parameter of sigmoid activation function.
提出了一种基于独立元分析(ICA)方法的权值初始化方法和动态调整S型激励函数的斜率相结合的神经网络学习算法。
5) re-initialization
重新初始化
1.
New active region contour model without re-initialization;
一种改进的活动区域轮廓模型——无需水平集重新初始化
2.
Firstly,an image segmentation method based on level set evolution without re-initialization is studied.
首先从理论上分析了无需重新初始化的水平集方法的主动轮廓图像分割模型,该模型对一些具有不光滑的尖角的图像分割时,捕捉这些尖角往往不精确甚至失败。
3.
First,added an internal energy term in order to counteract the discrepancy of the level set function and the signed distance function during iteration,so eliminated the troublesome re-initialization process.
首先,在C-V模型的能量函数中加入一个内部能量项,抵消演化过程中水平集函数和符号距离函数的偏差,从而消除分割中周期性重新初始化的过程;其次,提出了梯度加速项,通过感兴趣区域的图像特征,快速得到该区域的边界,且能够提高弱边界的分割精度。
6) Reinitialization
重新初始化
1.
A New Method for the Initialization and Reinitialization of Level Set Function;
一种新的水平截集函数初始化和重新初始化方法——距离函数光滑法
补充资料：因侵害姓名权、肖像权、名誉权、荣誉权产生的索赔权
因侵害姓名权、肖像权、名誉权、荣誉权产生的索赔权：公民、法人的姓名权、名称权，名誉权、荣誉权、受到侵害的有权要求停止侵害，恢复名誉，消除影响，赔礼道歉，并可以要求赔偿损失。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条