In this work, we are mainly dealing with the stitching of panoramic images. However, the methods described and evaluated here can also be used for different applications in image mosaicing.

Abstract – Panoramic image stitching is the process of combining multiple photographic images with overlapping fields of view to produce a panorama. First, salient features are robustly detected from the input images by a robust algorithm called Scale Invariant Feature Transform (SIFT). SIFT features are invariant to rotation, translation, image scaling and partially invariant to 3D viewpoint, illumination changes and image noise. These features are matched between the successive images and hence image transformation is estimated. Image blending technique is used to blend the images together to get a panoramic view. Potential applications of panoramic view include creating virtual environment for virtual reality, modeling the 3D environment using images acquired from the real world. Keywords- Panoramic view, SIFT, homography, image blending, image processing 1) Image acquisition: Typically for panoramic imaging, images can be acquired by three methods namely translating a camera parallel to the scene or rotating a camera about its vertical axis keeping optical centre fixed or by a handheld camera. Each image in the series acquired for panoramic image stitching partially overlaps the previous and the following images. Images acquired by translating a camera does not give 3D feel to the panoramic image and is generally not preferred. Rotation of camera provides this 3D feel [5]. Due to the simplicity of the set-up and the operations, rotation method is preferred in acquiring images for the generation of panoramic view. Use of handheld I.

Engineering for Women,