Abstract
In many algorithms the registration of image pairs is done by feature point matching. After the feature detection is performed, all extracted interest points are usually used for the registration process without further feature point distribution analysis. However, in the case of small and sparse sets of feature points of fixed size, suitable for real-time image mosaicking algorithms, a uniform spatial feature distribution across the image becomes relevant. Thus, in this paper we discuss and analyze algorithms which provide different spatial point distributions from a given set of SURF features. The evaluations show that a more uniform spatial distribution of the point matches results in lower image registration errors, and is thus more beneficial for fast image mosaicking algorithms.
Highlights
Alignment and stitching of images into seamless photomosaics is most widely used in computer vision [1]
Since the estimation of a global image transformation between a given image pair is based on matched feature points, image regions with many interest points will create only small registration errors, whereas the error in regions with feature clusters becomes larger
Many Speeded Up Robust Features (SURF) features show a high filter response value in the tree region of the tree-clinic sequence, since the dark branches have a high contrast against the bright background
Summary
Alignment and stitching of images into seamless photomosaics is most widely used in computer vision [1]. Many different feature-based algorithms, like SIFT [2], SURF [3], GLOH [4], MOPs [5] or [6] have been proposed for extracting distinctive image features Their robustness, repeatability and invariance to different illumination changes and image transformations have been widely evaluated by [4, 7, 8, 9]. While in many natural image scenes feature points can usually be extracted across the whole image, spatial distribution is often a relevant consideration for medical images, e.g. endoscopic images of the internal urinary bladder wall These images often show only sparsely located structures with high contrast, e.g. vasculature or lesions (see Fig. 1), and impede robust image mosaicking.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
