We present efficient algorithms for image restoration by means of Good's roughness penalty. We assume Gaussian or Poisson statistics for the noise and derive an algorithm for each case. Performance is tested by simulated three-dimensional imaging with a fluorescence confocal laser scanning microscope. Results are compared with those for algorithms that use Gaussian or entropy penalty terms, which we derived previously [J. Opt. Soc. Am. A 14, 1696 (1997)]. The algorithms based on Good's roughness yield superior results. An example is given of the restoration of an image of a biological specimen. # 1998 Optical Society of America [S0740-3232(98)02605-2] OCIS codes: 100.1830, 100.3020, 100.3190, 100.6890, 170.1790, 170.2520.
展开▼
机译:我们提出了一种有效的算法,用于通过Good's粗糙度惩罚算法进行图像恢复。我们假设噪声为高斯统计或泊松统计,并针对每种情况推导一种算法。通过使用荧光共聚焦激光扫描显微镜进行的三维模拟成像来测试性能。将结果与我们先前推导的使用高斯或熵罚项的算法的结果进行比较[J.选择。 Soc。上午。 A 14,1696(1997)]。基于Good's粗糙度的算法产生了优异的结果。给出了恢复生物样本图像的例子。 1998年美国光学学会[S0740-3232(98)02605-2] OCIS代码:100.1830、100.3020、100.3190、100.6890、170.1790、170.2520。
展开▼