Scale-invariant feature transform (SIFT or Scale-invariant feature transform) is a computer vision algorithms to detect and describe local features in images, it find extremum points in the scale, and extract its location, scale and rotation invariant, this algorithm is published by David Lowe in 1999, 2004 perfect summary. Perception applications include object recognition, robotic mapping and navigation, image stitching, 3D modeling, gesture recognition, video tracking and action than on.