基于再模糊理论的模糊图像检测方法

Fuzzy image detection method based on re-fuzzy theory

图像作为当今人们获取信息、感知世界的重要载体,不仅是生活重要组成部分之一,还在各个行业发挥着重要作用。常见的图像模糊分为运动模糊与失焦模糊,严重影响图片质量与观看体验。针对这一问题,对图像质量的检测进行研究,设计一种基于再模糊理论的图像质量检测方法。将待测图像经过再模糊化处理后,对再模糊前后的图像提取边缘并计算图像间差异,以此评判图像是否模糊。利用Canny算子进行边缘检测并利用Otsu算法进行双阈值抑制。最后,在公开的LIVE图像数据集上进行实验。结果表明,该方法能有效检测图像是否模糊,且优于其他无参考图像质量评估算法,符合肉眼主观评价。

As an important carrier for people to obtain information and perceive the world,images are not only one of the important parts of life,but also play an important role in various industries.Common image blur is divided into motion blur and out-of-focus blur,which seriously affects the picture quality and viewing experience.To solve this problem,the detection of image quality is studied,and an image quality detection method based on re-fuzzy theory is proposed.The image to be measured is subjected for re-fuzzy process,the edge of the image is extracted from the image before and after the process,and the difference between the images is calculated to judge whether the image is blurred.The Canny operator is used for edge detection and the Otsu algorithm is used for double threshold suppression.The result shows that the method can effectively detect whether the image is blurry,and is better than other reference image quality evaluation algorithms,which is in line with the subjective evaluation of the naked eye.