Year: 2007
Type: conference-paper
Abstract: We present a fully automatic method for eliminating misalignments between a sequence of hand-held photographs\ntaken at different exposures. The key component of the technique is the SIFT method that is employed to search\nfor key-points (or feature-points) in consecutive images. The key-points are used to find matrices, that transform\na set of images to a single coordinate system and eliminate any global misalignments (including general planar\nhomography). We employ this technique to capture high dynamic range images from a set of photographs taken at\ndifferent exposures, wheremisalignments can cause blurring and artifacts, and prevent achieving high quality HDR\nimages. The proposed alignment technique works well for over- and under-exposed images and is not sensitive\nto an image content. We present our implementation of the technique and the results of tests made for variety of\nphotographs.
Authors: Anna Tomaszewska, Radosław Mantiuk
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2792476095