Title :
Analysis and enhancements to piecewise linear comparametric image registration
Author :
Candocia, Frank M.
Author_Institution :
Dept. of Electr. & Comput. Eng., Florida Int. Univ., Miami, FL, USA
Abstract :
This correspondence details enhancements to previous work on piecewise linear comparametric image registration. The enhancements come in the form of slope constraints and knots´ location selection in the comparametric modeling. An analysis of the properties of comparametric functions leads to two general slope constraints that, along with a knot location selection based on the reference image´s pixel value distribution, serves to reduce error and sensitivity to the number of segments considered as well as allow for the solution to cases in which there are gaps in the comparagram. Results on real images are presented.
Keywords :
image registration; piecewise linear techniques; comparagram; comparametric function; image pixel value distribution; knot location selection method; piecewise linear comparametric image registration; slope constraint; Cameras; Equations; Image analysis; Image registration; Image segmentation; Lead; Least squares approximation; Piecewise linear approximation; Piecewise linear techniques; Pixel; Comparametric equations; constrained optimization; exposure analysis; image registration; piecewise linear regression; Algorithms; Artificial Intelligence; Computer Graphics; Computer Simulation; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Linear Models; Numerical Analysis, Computer-Assisted; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Subtraction Technique;
Journal_Title :
Image Processing, IEEE Transactions on
DOI :
10.1109/TIP.2004.840705