噪声对图像局部特征匹配结果精度的影响

The Effect of Noise on the Result of Image Feature Matching

图像匹配是当前计算机视觉领域的一项重要技术,基于特征点的图像匹配算法是其中较为主流的算法,在物体识别、医学影像分析、三维重建等多个领域都有重要应用。然而在进行图像匹配时,输入图像会不可避免受到噪声污染,为此研究常见噪声对基于特征匹配结果精度的影响。实验表明,噪声会影响图像正确特征点的检测,会导致图像间的匹配数量减少以及误匹配,尤其相对于椒盐噪声,高斯噪声对图像的污染会更严重。

Image matching is an important technology in the field of computer vision at present.Image matching algorithm based on feature points is one of the most popular algorithms,which has important applications in object recognition,medical image analysis,3D reconstruction and other fields.However,in image matching,the input image will inevitably be polluted by noise.Therefore,this paper studies the influence of common noise on the accuracy of feature-based matching results.Experiments show that the noise will affect the detection of the correct feature points of the image,which will lead to the reduction of the number of matching between the images and the mismatch,especially compared with the salt and pepper noise,the Gauss noise will pollute the image more seriously.