摘要
传统的图像复原方法在重建被噪声污染的图像时,都只是将噪声作为一种干扰加以消除。当噪声增强、图像信号减弱时,由于受方法本身消噪能力的限制,图像的恢复变得非常困难,因此,基于Hodgkin-Huxley神经元阈上非周期随机共振原理,提出了一种通过自适应调节和添加最优噪声的方法来实现图像随机共振,以取得最佳的复原效果。实验结果表明,该方法对于被噪声污染的灰度图像,特别是对于强噪声背景下的灰度图像,其复原的效果优于传统的方法。由于该方法具有较强的鲁棒性,因此为强噪声背景下的图像复原、目标识别等工程应用提供了一种新的思路。
As to typical noisy image restoration methods, noise is regarded as a disturbed source. As long as noise becomes strong and image signals become weak, it is difficulty to restore noisy image because of the limitation of these methods. Based on theory of suprathreshold aperiodic stochastic resonance in Hodgkin-Huxley model, a new self-adaptive adjusting adding optimum noise image restoration method is proposed. Results indicate that, as to the restoration effect of gray-scale noisy image, especially strong noisy image, this new method is better than other typical methods used. Thus, this study suggests a new approach in engineering application where under strong noise background, such as image restoration and target identification, given that this new method is of good robustness.
出处
《中国图象图形学报》
CSCD
北大核心
2009年第1期77-81,共5页
Journal of Image and Graphics
基金
国家自然科学基金项目(60872090)
作者简介
第一作者简介：向学勤（1981～），男。现为杭州电子科技大学模式识别与智能系统专业硕士研究生。主要研究方向为模式识别、神经信息学、生物信息非线性处理。E-mail：xxueq@yahoo．com．cn
