A novel set of rotationally and translationally invariant features for images based on the non-commutative bispectrum
msra(2007)
摘要
We propose a new set of rotationally and translationally invariant features
for image or pattern recognition and classification. The new features are cubic
polynomials in the pixel intensities and provide a richer representation of the
original image than most existing systems of invariants. Our construction is
based on the generalization of the concept of bispectrum to the
three-dimensional rotation group SO(3), and a projection of the image onto the
sphere.
更多查看译文
关键词
three dimensional,pattern recognition,artificial intelligent
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要