1) multi-scale multiplication
多尺度乘积
1.
The local extrema of multi-scale multiplication were directly defined as candidate corners.
该算法直接把多尺度轮廓方向变化率乘积的局部极值点定义为角点,这是由于多尺度乘积不但融入了多个尺度下轮廓方向变化率的特征信息,而且能极大地增强角点的变化率,抑制受边界和量化噪声影响的边界点的轮廓方向变化率。
2) Multi-scale curvature product
多尺度曲率乘积
3) multiscale pointwise product
多尺度逐点乘积
1.
The method of multiscale pointwise product(MPP)was proposed in the paper for the object detection.
采用多尺度逐点乘积方法(MPP)对SAR图像中的舰船目标进行了精确检测。
4) multi-scale product
尺度乘积
1.
Denoising method based on combining multi-scale product with wavelet shrinkage;
基于尺度乘积与小波收缩相结合的去噪方法
2.
In order to filter the noise in image,a method based on multi-scale product and dependencies using stationary wavelet transform for denoising is proposed.
为了去除图像的噪声,提出了一种基于尺度乘积和尺度相关性的平稳小波变换图像去噪方法。
5) multiscale product
多尺度积
1.
A novel image fusion algorithm named MPLVDDWT(multiscale product local variance of dyadic discrete wavelet transform) is proposed which is based on the local statistic of the multiscale products of wavelet transform.
提出了一种新的基于小波变换多尺度积局部区域统计量的图像融合算法,简称MPLVDDWT(multiscale product local variance of dyadic discrete wavelet transform)算法。
2.
The paper presents a new heart sound denoise method,which uses multiscale product to locate the first sound(S1) and second sound(S2) in each heart beat cycle and the durations of S1 and S2 to estimate these signals and the noise,avoiding the undesirable error caused by using ECG-Gating to locate the S1 and S2.
介绍了一种新的心音去噪方法,利用小波域多尺度积的方法定位第1、第2心音在各个心音周期的位置,并利用其持续时间估计有用信号及噪声,达到去噪的效果,避免了通过ECG-Gating在时域提取噪声时的误差。
6) multi-scale product
多尺度积
1.
The first step is to detected edge image and feature points by using wavelet multi-scale product.
该方法首先利用小波多尺度积准确地提取边缘图像和特征点,然后根据特征点的角度直方图得到的旋转角度,并通过计算所有特征点对在边缘图像中的对齐度来精确地确定匹配点对。
2.
A new approach for image regis-tration based on wavelet multi-scale product.
本文提出了基于小波变换多尺度积的图像配准算法。
3.
In this method,feature points as well as their orientation are extracted using wavelet multi-scale products and the mutual information mapping criteria for the feature points is defined to obtain the matching points.
它首先利用小波多尺度积提取两幅图像的特征点及其角度信息,再根据得到的特征点和角度信息,定义了特征点对互信息匹配准则,得到相应的匹配点对。
补充资料：乘积
1.两个或两个以上的数相乘所得的数。简称积。
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