A comparative study of Fourier descriptors and Hu's seven moment invariants for image recognition
A comparative study of Fourier descriptors and Hu's seven moment invariants for image recognition
复制标题
图像识别中傅里叶描述符与胡七矩不变量的比较研究
DOI：
10.1109/ccece.2004.1344967
复制
发表时间：
2004
期刊：
影响因子：
--
通讯作者：
Xiaoli Yang
中科院分区：
文献类型：
--
作者：
Qing Chen;E. Petriu;Xiaoli Yang
本文评估并比较了傅立叶描述符和胡氏七矩不变量在识别不同空间分辨率的图像方面的性能。傅里叶描述符和胡氏七矩不变量都具有针对图像变换（包括尺度变化、平移和旋转）的首选不变性。然而，它们两者都存在空间分辨率阈值。在我们的图像识别引擎实验中，对于傅立叶描述符，特征向量由序列的前10个元素组成，空间分辨率不应小于64/spl times/64才能实现100%识别。对于 Hu 的七个矩不变量，最小空间分辨率为 128/spl 次/128。
The paper evaluates and compares the performance of Fourier descriptors and Hu's seven moment invariants for recognizing images with different spatial resolutions. Both Fourier descriptors and Hu's seven moment invariants have the preferred invariance property against image transformations, including scale change, translation and rotation. However, spatial resolution thresholds exist for both of them. In our experiment with the image recognition engine, for Fourier descriptors, with feature vectors composed by the first 10 elements of the series, the spatial resolution should not be less than 64/spl times/64 to achieve 100% recognition. For Hu's seven moment invariants, the minimum spatial resolution is 128/spl times/128.