3模糊运动方向检测-中国图象图形学报.doc

中图法分类号：TP301.6 文献标识码：A 文章编号：1006-8961(200 ) - - 论文引用格式： 频谱预处理模糊运动方向鉴别的改进算法 孔勇奇1, 卢敏2，潘志庚3 （1.浙江商业职业技术学院, 杭州 310053； 2. 丽水学院工学院, 丽水 323000； 3. 杭州师范大学 数字媒体与人机交互研究中心 摘 要：为了提高匀速直线运动模糊图像的运动方向检测精度,提出一种基于频谱预处理的模糊运动方向鉴别改进算法。首先，通过对模糊图像的频谱图执行两次傅里叶对数变换，实现频谱图的亮条细化处理；然后，以亮条细化后的频谱图为研究对象，采用滑动邻域操作实施频谱图的二值化处理，剔除图像中的噪声和十字亮线，得到频谱图的预处理图像；最后，对预处理图像执行Radon变换，检测图像中的直线成分，并将检测结果映射为模糊图像的运动方向。实验数据显示，在不同模糊尺度和运动方向环境下，本文算法始终能够将运动方向的检测误差控制在0.5°的有效范围之内；比较实验表明，该算法的运动方向检测精度优于其他同类的 Motion blur direction detection based on pre-processing of spectrum image Kong Yongqi1, Lu Min2, Pan Zhigeng3 (1. Institute of information technology, Zhejiang Vocational College of Commerce, Hangzhou 310053; 2. Cillege of Technology, Lishui University, Lishui 323000) 3. Digital Media and HCI Research Center, Hangzhou Normal University, Hangzhou 310036) Abstract: In order to improve the detection quality of direction of the objects moving in fixed direction from blurred image, this paper proposes a new algorithm for detection of moving direction, which is based on the pre-processing of spectrum image. Firstly, the spectrum image of motion-blur image is transformed twice with Fourier logarithmic to meet refinment of bright lines. Secondly, with the previous spectrum as input, the image is bi-value processing with slipping neighbour operation, eliminating image noise and cross bright line. Finally, the pre-processed image is performed with Radon transform, detecting image linear characteristic, and mapping the detection results into direction of the blurred image. The experimental results show that (1) in different fuzzy scale and direction of the environment, the proposed algorithm can always limit the movement direction detection error under 0.5 °, (2) our algorithm can obtain better movement direction detection than other related algorithms. Key words: Spectrum analysis; Detection of motion direction; High brightness fringe refinement; Cross bright line 0 引 言 运动模糊图像的恢复是图像处理的一个热点和难点，高质量的恢复模糊图像是图像后续处理的前提和