subimage
英
美
网络 子图象; 子图像; 子影像
双语例句
- Compared with the usual method based on single reference subimage, the new method has a lot larger measuring range.
与常用的基于单一参考子图像的波前重构方法相比，新方法的动态范围有了很大提高。 - Extracting subimage from an image represented by GD method
图象的GD表示法的子图象抽取方法 - Meanwhile, the subimage pattern classifier is designed based on BP artificial neural network, all of the subimage pattern classifying results are arrayed a matrix, and the pavement surface distress image feature is represented by this matrix.
同时，设计了基于BP人工神经网络的子块图像模式分类器，利用子块图像模式分类结果所组成的矩阵作为路面破损图像分割结果。 - Finally, to the face database by ORL, the method is utilized to segment face image space into several non-overlapping subimage spaces so that the pixel number has uniform distribution in each subimage space.
采用ORL人脸数据库进行仿真实验，利用阈值最优分层法将人脸图象空间划分成不相重叠的子图象空间，使每层子图象空间象素数均匀分布。 - We have studied the statistical distribution of wavelet subimage coefficients and concluded that the distribution of wavelet subimage coefficients is very much similar to that of Laplacian distribution. Based on the statistical properties of image wavelet decomposition, an image quantization algorithm is proposed.
研究了小波子带图像系数的统计分布，发现小波子带图像系数分布和拉普拉斯分布非常相似，继而提出了一种基于其统计特征的图像量化编码算法。 - Empirical formulas predicting the spatial channels of the human visual motion system at different velocities and contrasts of the objects being observed are presented. The subimage contains more texture information by the criterion.
给出了不同运动速度和对比度下预测人眼空间频率通道的经验公式。这两部分都反映了纹理图像的纹理特征，前五个主频率通道注意表示该虹膜纹理特征。 - In this algorithm, we selected the sample-standard-deviation as the key quantization threshold in every wavelet subimage.
该算法以小波子带图像样本标准差为选择量化编码阈值的重要依据。 - Furthermore, the multi-frame accumulation infrared subimage target detection model, image space transformation, segmented region recognition and infrared subimage tracking model are proposed in the dissertation.
论文提出了多帧累积亚图像目标检测模型、图像空间变换、分割区域的识别和亚图像跟踪模型。 - Experiments show that the trademark image retrieval algorithm based on the subimage feature fusion is superior to that based on the global image feature, and that the subimage feature fusion weighted criterions are better than the normal criterions, among which the minimum weighted average criterion is best.
实验表明，基于子图像特征融合的商标图像检索算法优于基于全局图像特征的检索算法，子图像特征融合加权准则优于未经加权的子图像特征融合准则，其中最小加权平均准则最优。 - Using the subimage of an unknown target as feature vector and minimum distance rule for target recognition, experiments on simulated data are done.
对未知目标，以其子像对库矢量的欧氏距离最小为分类准则，进行了识别模拟实验。 - Approach of Target Subimage Extraction Based on integer Wavelet transform
基于整数小波的目标子图像提取方法 - Character segmentation is a special application in printed character segmentation. Image is segmented into many subimages to facilitate character recognition with only one character in each subimage in the course of character segmentation.
字符分割是印刷体字符分割的一个特殊应用，是把车牌图像分成单个的字符图像，以便进行字符识别。 - This paper puts forward the trademark image retrieval algorithm based on the subimage feature fusion, and does research on the subimage feature fusion criterions.
本文提出了基于子图像特征融合的商标图像检索算法，并对子图像特征融合准则进行了研究。 - When we want to look up a target on the image, we first browse the lowest resolution subimage ( LL subimage) and locate mesh which the target belongs to.
检索时，先从图象的最低分辨率子图象（即LL子图象）的预览开始，一旦发现目标，则锁定目标； - Firstly, discrete wavelet transform ( DWT) was applied to one subimage extracted from the original image according to one chaotic sequence label and multiple independent chaotic watermark signals were generated and embedded into the middle wavelet frequency coefficients adaptively.
首先根据一个混沌标签序列从原图像中抽取一子图像，并对其进行小波分解，然后将多个互相独立的混沌水印信号依次嵌入到子图像的中频小波系数中，并自适应确定嵌入强度。 - In the second, the image is divided into one low resolution lowpass subimage and several highpass subimages having different resolution.
其二，原始图像通过连续的多次正交子波变换，最终可分解成一幅低频子带图像和各个分辨率下的高频子带图像。 - By segmenting the lowest frequency subimage of wavelet decomposition of the frame into static and motive regions, the computation complexity is reduced effectively and the motion vector coding efficiency is improved farther;
通过对视频帧小波分解后的低通子图像进行静止和运动区域分割，以分割结果指导运动估值过程，在有效地减少运动估值时间消耗的同时，进一步提高了运动矢量的编码效率； - Utilizing the human visual texture masking and luminance masking models, watermark is embedded into the largest coefficient of third level detail subimage.
利用视觉系统的纹理掩蔽及照度掩蔽特性，在第三级细节子图块的最大系数中嵌入水印信号。 - Then, the image grey level of every subimage is approximated by low-order polynomial according to least-square criterion.
然后各子图内像素灰度值以低阶多项式表示，依最小二乘准则以多项式逼近原图像的子图像。 - The method is applied in the removing cloud cover of the subimage of lower frequency which is got with wavelet transform.
将上面的方法运用到小波变换中低频子带的去云。