• home
• current students
• graduate
• events

Presenter: Ioana Sevcenco
Supervisor: Dr. Pan Agathoklis

Date: Mon, December 12, 2011
Time: 11:00:00 - 00:00:00
Place: EOW 430

ABSTRACT

ABSTRACT

The applications of image stitching and object insertion are considered and two gradient based approaches offering solutions are proposed. An essential part of the proposed algorithms is obtaining an image from a given gradient data set. This is done using an existing Haar wavelet based reconstruction technique. In both stitching and object insertion applications considered, a challenge is posed by the fact that the gradient from which the image must be reconstructed is not a conservative vector field and this is addressed by including a Poisson solver during the reconstruction. The performance of the reconstruction algorithm is evaluated in terms of solution accuracy and computation speed by comparing it with other existing techniques.

The proposed image stitching technique in which the reconstruction algorithm is employed consists of two main parts: registering the images to be combined and blending their gradients over a region of interest. In the object insertion application, we consider the images registered and blend the gradients of the images over a region of interest. The performance of the stitching algorithm is evaluated by presenting the results produced to combine images with varying orientation, scales, illumination, and color conditions. Experimental results illustrate both the stitching and the insertion techniques proposed, and indicate that they yield seamless composite images.