• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1356-1364
• /
• 2016

This paper proposes a novel aesthetic photo recomposition method using a deep convolutional neural network (DCNN). Previous recomposition approaches define the aesthetic score of photo composition based on the distribution of salient objects, and enhance the photo composition by maximizing the score. These methods suffer from heavy computational overheads, and often fail to enhance the composition because their optimization depends on the performance of existing salient object detection algorithms. Unlike previous approaches, we address the photo recomposition problem by utilizing DCNN, which shows remarkable performance in object detection and recognition. DCNN is used to iteratively predict cropping directions for a given photo, thus generating an aesthetically enhanced photo in terms of composition. Experimental results and user study show that the proposed framework can automatically crop the photo to follow specific composition guidelines, such as the rule of thirds.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.1
• /
• pp.1-4
• /
• 2016

In this paper, we present an algorithm for adjusting the position of a user-specified object considering image aesthetics. Specifically, the user-specified object is positioned according to the rule of thirds by inserting or deleting unimportant seam lines from the image. To find such seam lines, a novel weight map is designed using the spatial and color distances from the object. We also design and analyze two approaches to seam carving and insertion. Experimental results show that the proposed method can be used as an effective semi-automatic image recomposition scheme.