[IP3-9-2] Scale invariant feature transformation (SIFT)

Scale Invariant Feature Transform (SIFT) is an image descriptor for image-based matching and it is used for a large number of purposes in computer vision related to point matching between different views of a 3-D scene and view-based object recognition. The SIFT descriptor is invariant to translations, rotations and scaling transformations in the image domain and robust to moderate perspective transformations and illumination variations. Experimentally, the SIFT descriptor has been proven to be very useful in practice for robust image matching and object recognition under real-world conditions.

Introduction

External resources

• Lowe, David G. (1999). Object recognition from local scale-invariant features. Proc. 7th International Conference on Computer Vision (ICCV'99) (Corfu, Greece): 1150-1157. doi:10.1109/ICCV.1999.790410.

Learning outcomes

• 2328 - Explain how SIFT algorithms can be used for enhancing orthorectification

  Explain how SIFT algorithms can be used for enhancing orthorectification

Self assessment

Outgoing relations

• [IP3-9-2] Scale invariant feature transformation (SIFT) (proposed relation) [IP3-2-3] Keypoint detection
• [IP3-9-2] Scale invariant feature transformation (SIFT) subclassof [IP3-9] Scale space analysis