需要读SURF的论文,里面作者提到了为什么选Hessian矩阵
From studying the existing detectors and from published
comparisons [29,30], we can conclude that Hessian-based
detectors are more stable and repeatable than their Harris-
based counterparts. Moreover, using the determinant of the
Hessian matrix rather than its trace (the Laplacian) seems
advantageous, as it res less on elongated, ill-localised
structures. We also observed that approximations like the
DoG can bring speed at a low cost in terms of lost accuracy.