SIFTPPT.pptVIP

SIFT (Scale Invariant Feature Transform) SIFT SIFT is an carefully designed procedure with empirically determined parameters for the invariant and distinctive features. SIFT stages: Scale-space extrema detection Keypoint localization Orientation assignment Keypoint descriptor 1. Detection of scale-space extrema For scale invariance, search for stable features across all possible scales using a continuous function of scale, scale space. SIFT uses DoG filter for scale space because it is efficient and as stable as scale-normalized Laplacian of Gaussian. DoG filtering Convolution with a variable-scale Gaussian Scale space Detection of scale-space extrema Keypoint localization Decide scale sampling frequency It is impossible to sample the whole space, tradeoff efficiency with completeness. Decide the best sampling frequency by experimenting on 32 real image subject to synthetic transformations. (rotation, scaling, affine stretch, brightness and contrast change, adding noise…) Decide scale sampling frequency Decide scale sampling frequency Pre-smoothing 2. Accurate keypoint localization Reject points with low contrast (flat) and poorly localized along an edge (edge) Fit a 3D quadratic function for sub-pixel maxima 2. Accurate keypoint localization Reject points with low contrast and poorly localized along an edge Fit a 3D quadratic function for sub-pixel maxima 2. Accurate keypoint localization Taylor series of several variables Two variables Accurate keypoint localization Taylor expansion in in matrix form, x is a vector, f maps x to a scalar 2D illustration 2D example Derivation of matrix form Derivation of matrix form Derivation of matrix form Accurate keypoint localization x is a 3-vector Change sample point if offset is larger than 0.5 Throw out low contrast (0.03) Accurate keypoint localization Throw out low contrast Eliminating edge responses Maxima in D Remove low contrast and edges Keypoint detector 3. Orientation assignment By assigning a consistent