Aesthetic photo composition by optimal crop-and-warp

We present a high-efficiency approach to optimally enhance image composition using a crop-and-warp-based algorithm. We have designed a piecewise quadratic aesthetic energy function with linear inequality constraints that measures the distance between original positions and the aesthetic target positions of visual elements, to assess the target image composition. The target image is cropped by a sub-window that can zoom and move within the original image window. The optimal cropped window position can be obtained by solving a piecewise quadratic program that attempts to minimize the energy function. The salient object and feature line locations in the cropped image are further optimally adjusted by adopting a triangular mesh-based warping technique, which also allows fitting the proposed approach for image retargeting. A quadratic optimization controls the mesh warping and can be achieved by solving a sparse linear system. We illustrate the effectiveness of our approach in several experimental results and compare them to previous approaches.

Figure optionsDownload high-quality image (461 K)Download as PowerPoint slideHighlights
► We present a high efficiency approach to optimally enhancing the image composition.
► Our method is composed with a crop operator and a warp operator.
► Any saliency map and visual element extraction method can be adopted to perform the algorithm.
► The proposed method is valuable to be integrated in to image processing systems.