AMMAI reading and notes

efficiency? yes

dimension length? (yes but usually long for image and video)

invariant? !! scale, rotation

*local feature began widely used about when '01

bag of feature points

problem: efficiency, thousands of them need to be matched

Local Feature = Detector + Descriptor (where are them, how to represent)

Detector:

point-based

region-based

scale invariant: LoG, DoG(for low quality), Harris-Laplace

affine invariant: Harris-Affine, Hessian-Affine, ..., etc

*DoG(Difference of Gaussian) detector:

apply various kernels and scales

deal with scale-invariant

Descriptor:

*SIFT: empirically 4x4(windows)x8(bins)=128 dimensions

deal with rotation-invariant

Visual Word
  quantized local descriptor (by clustering) e.g. SIFT
*some issues
  the more, the better?
    yes, but saturates in object retrieval, or even degrade in classification
  efficiency issue.
    Algorithm-wise or Parallelize
  sampling method
    sparse, dense, or random
  feature selection and reduction
    pLSA and LDA
  low recalls
    soft-assignment, query expansion