Techniques Supported by Registration Estimator App
Feature-based registration techniques automatically detect distinct image features such as sharp corners, blobs, or regions of uniform intensity. The moving image undergoes a single global transformation to provide the best alignment of corresponding features with the fixed image.
FAST detects corner features, especially in scenes of human origin such as streets and indoor rooms. FAST supports single-scale images and point-tracking.
MinEigen also detects corner features. MinEigen supports single-scale images and point-tracking.
Harris also detects corner features, using a more efficient algorithm than MinEigen. Harris supports single-scale images and point-tracking.
BRISK also detects corner features. Unlike the preceding algorithms, BRISK supports changes in scale and rotation, and point-tracking.
ORB detects corners in images with changes in scale and/or rotation.
SURF detects blobs in images and supports changes in scale and rotation.
KAZE detects multiscale blob features from a scale space constructed using nonlinear diffusion.
MSER detects regions of uniform intensity. MSER supports changes in scale and rotation, and is more robust to affine transformations than the other feature-based algorithms.
In Registration Estimator, you can register images and generate functions for all feature-based techniques without a Computer Vision Toolbox™ license. However, to run an autogenerated function that uses a feature-based registration technique, you must have Computer Vision Toolbox. For more information, see Export Results from Registration Estimator App.
Intensity-based registration techniques correlate image intensity in the spatial or frequency domain. The moving image undergoes a single global transformation to maximize the correlation of its intensity with the intensity of the fixed image.
Monomodal intensity registers images with similar brightness and contrast that are captured on the same type of scanner or sensor. For example, use monomodal intensity to register MRI scans taken of similar subjects using the same imaging sequence.
Multimodal intensity registers images with different brightness and contrast. These images can come from two different types of devices, such as two camera models or two types of medical imaging systems (such as CT and MRI). These images can also come from a single device. For example, use multimodal intensity to register images taken with the same camera using different exposure settings, or to register MRI images acquired during a single session using different imaging sequences.
Phase correlation registers images in the frequency domain. Like multimodal intensity, phase correlation is invariant to image brightness. Phase correlation is more robust to noise than the other intensity-based registration techniques.
Phase correlation provides better results when the aspect ratio of each image is square.
Nonrigid registration applies nonglobal transformations to the moving
image. Nonrigid transformations generate a displacement field, in which each pixel location
in the fixed image is mapped to a corresponding location in the moving image. The moving
image is then warped according to the displacement field and resampled using linear
interpolation. For more information about estimating a displacement field for nonrigid