Scale-invariant feature transform (or SIFT) is a computer vision algorithm for extracting distinctive features from images, to be used in algorithms for tasks like matching different views of an object or scene (e.g. for stereo vision) and Object recognition. The features are invariant to image scale, rotation, and partially invariant (i.e. robust) to changing viewpoints, and change in illumination. The name Scale-invariant feature transform was chosen, as the algorithm transforms image data into scale-invariant coordinates relative to local features. However, there also exist other scale invariant image descriptors in the computer vision literature.

The algorithm was devised by David Lowe, who has a US-patent on it, at the University of British Columbia.

First, the original image is progressively Gaussian blurred (see scale-space implementation) with σ in a band from 1 to 2 resulting in a series of Gaussian blurred images (a scale-space produced by cascade filtering). Then, these images are subtracted from their direct neighbors (by σ) to produce a new series of images (with difference of Gaussians which approximate the Laplacian of the Gaussian).

The major steps in the computation of the image features are

1. Scale-space extrema detection - each pixel in the images are compared to its 8 neighbors and the 9 pixels each (corresponding pixel+8 neighbors) of the other pictures in the series.
2. keypoint localization - keypoints are chosen from the extrema in scale space.
3. orientation assignment - for each keypoint, in a 16x16 window, histograms of gradient directions are computed (using bilinear interpolation).
4. keypoint descriptor - representation in a 128-dimensional vector.

For the application of SIFT keypoints in matching and object recognition, Lowe was applying a nearest neighbor algorithm, followed by a Hough transform for object recognition (as described in Lowe, 2004).

SIFT is a fundamental part of the visual pattern recognition (ViPR) and visual simultaneous localization and mapping (vSLAM) algorithms developed by Evolution Robotics. Evolution Robotics also implemented a SIFT-based homing/localization algorithm on Sony's AIBO robot for use in locating its charging station.

The feature representations found by SIFT are thought to be analogous to those of neurons in inferior temporal cortex, a region used for object recognition in primate vision.

See also

• scale space
• ART-SIFT

External links

• libsift: C# implementation of SIFT
• autopano-SIFT: a tool for generating panoramas from multiple images, using SIFT to match features between images
• MATLAB/C implementation of SIFT
• more detailed explanation of the keypoint extraction by the SIFT algorithm
• U.S. Patent 6,711,293: Method and apparatus for identifying scale invariant features in an image and use of same for locating an object in an image - David Lowe's patent for the SIFT algorithm

References

• Lowe, D. G., “Distinctive Image Features from Scale-Invariant Keypoints”, International Journal of Computer Vision, 60, 2, pp. 91-110, 2004.
• Lindeberg, Tony "Feature detection with automatic scale selection", International Journal of Computer Vision, 30, 2, pp 77--116, 1998. (Original reference on scale-space extrema detection and the scale invariant properties it leads to).

Computer visionAlgorithmsTransforms

تبدیل ویژگی مقیاس‌نابسته‌