通过分析系统图像的噪声特征，采用多帧平均叠加法、邻域处理法，取得了较好的效果。
Aim at the characteristic of system image noise, using the algorithms of image noise filtering, multi-frame mean, neighborhood processing, we have obtained good results.
然后提出了基于多特征点平均矩特征的概念，该特征不仅具有良好的鲁棒性，而且对于噪声以及图像边缘的细微变化并不敏感，非常适合用来描述商标这种特定的图像。
After that, the new idea of average moments of these feature points is proposed. This feature descriptor has good robustness and is not so sensitive to noise and the delicate changes in image's edges.
对多聚焦图像和多光谱彩色图像分别采用计算图像信息熵和均方根误差、计算图像平均梯度的方法对融合的性能进行评价。
There is explicit characteristic of correspondence reflecting the droplet transfer among the electric, spectral and image information based on time information fusion.
应用推荐