PROJECT TITLE :

Casair: Content And Shape-Aware Image Retargeting And Its Applications - 2017

ABSTRACT:

This paper proposes a unique image-retargeting algorithm that can retarget images to a massive family of non-rectangular shapes. Specifically, we tend to study image retargeting from a broader perspective that has the content furthermore the form of a picture, and therefore the proposed content and form-aware image-retargeting (CASAIR) algorithm is driven by the twin objectives of image content preservation and image domain transformation, with the latter defined by an application-specific target shape. The algorithm is predicated on the thought of seam phase carving that successively removes low-price seam segments from the image to simultaneously achieve the 2 objectives, with the choice of seam segments determined by a price function incorporating inputs from image content and target form. To provide a complete characterization of shapes that may be obtained using CASAIR, we introduce the notion of bhv-convex shapes, and we tend to show that bhv-convex shapes are precisely the family of shapes that can be retargeted to by CASAIR. The proposed algorithm is easy in both its design and implementation, and in observe, it offers an efficient and effective retargeting platform that has its users with considerable flexibility in choosing target shapes. To demonstrate the potential of CASAIR for broadening the application scope of image retargeting, this paper also proposes a smart camera-projector system that comes with CASAIR. In the context of ubiquitous display, CASAIR equips the camera-projector system with the capability of retargeting images on-line so as to maximize the standard and fidelity of the displayed images whenever matters demands.