“阿蒂”头骨(左)及手部(右)的数字复原图。
Digital representations of Ardi's skull (left) and hand (right).
本文提出了用迭代计算直接解成像方程以复原图像的方法。
AH image restoration method of directly solving the image formation equation by iterative procedure is presented in this paper.
这些算法在复原图像保边缘方面比经典复原算法有更好的表现。
These algorithms have better performance than classical restoration algorithms in image edge-preserving.
周期性误差是匀速直线运动降质图像复原中普遍存在的现象，它严重影响复原图像质量。
Periodic error commonly appear in restoring uniform motion blurred picture, its appearance degrade the quality of restored image heavily.
计算结果表明，该方法可有效复原图像，在客观标准评价和主观视觉效果方面都有明显的改善。
Numerical results show that these methods can effectively restore original image, and the objective standard evaluation and subjective visual effect are improved significantly.
实验结果表明，不论是插值放大图像，还是超分辨率复原图像都具有较高的视觉质量和峰值信噪比。
Numerous experiment results demonstrate the effectiveness of our approach, both in the visual effect and the PSNR value.
其次利用NAS - RIF进行盲复原算法复原图像时，在每次复原迭代过程中加入低通滤波环节。
Secondly, when image is restored by the NAS-RIF algorithm, in each iteration of restoration, it adds the low-pass filter link.
维纳波是一种常见的图像复原方法，该方法的思想是使复原的图像与原图像的均方误差最小原则采复原图像。
The principle of the method expects to minimize the mean square error between the recovered image and original image.
图像压缩编码的目的就是要以尽量少的比特数表征图像，同时保持复原图像的质量，使它符合特定应用场合的要求。
The purpose of image compression coding is to represent images with few bits, maintain the quality of recovering images according to the requirements of certain application situations.
基于空间域共轭梯度算法的盲目图像复原方法由于在复原过程中追求了充分平滑，使得复原图像中的边缘细节信息有所损失。
The restored image obtained by using the space domain conjugate gradient algorithm is too smooth and loses some information about the edge detail.
在将他的图片和其他的古代和现代猿人的图片进行对比之后，诹访重建了一个虚拟头骨，并利用部分脸部的镜像图，绘制出遗失的左半边头骨的复原图(褐色部分)。
Checking his work against other ancient and modern primates, Suwa rebuilt a virtual skull and made a mirror image of part of the face to create its missing left side (brown section).
由运动模糊图像复原出原图像关键问题是获取点扩展函数和噪声信息，其中噪声通常假设为高斯白噪声。
The key problem in image restoration is to get the point spread function of motion-blurred images and the knowledge about noise. Gaussian white noise is commonly assumed as the noise.
由运动模糊图像复原出原图像关键问题是获取点扩展函数和噪声信息，其中噪声通常假设为高斯白噪声。
The key problem in image restoration is to get the point spread function of motion-blurred images and the knowledge about noise. Gaussian white noise is commonly assumed as the noise.
应用推荐