Image aesthetics enhancement using composition-based saliency detection

Abstract

Visual saliency detection and segmentation are widely used in many applications in image processing and computer vision. However, existing saliency detection methods have not fully taken the spatial information of salient regions into account. Inspired by the basic photographic composition rules, we present a novel saliency detection method, which utilizes the knowledge of photographic composition as priors to improve the saliency detection results. Moreover, an online parameter selection method is proposed when utilizing GrabCut to achieve the saliency segmentation result. Besides, to test the applicability of our method, we present a novel post-processing framework for the photographs to be more artistic. The salient region and depth map are firstly computed. The salient region keeps its sharpness, while other parts in the photograph get blurred based on the depth map. To our best knowledge, this is a novel image-based attempt to enhance aesthetics by post-processing a photograph via realistic blurring. We test our method on the 1,000 benchmark test images and dataset MSRA. Extensive experimental results show the applicability and effectiveness of our method.

Design of an Image Integrated Processing System for Improving Efficiency of Electric Vehicle Supporting Products

“…It leads to the phenomenon of gradient disappearance during the training process, which makes the algorithm fall into the local minimum value and cannot be seen [17][18][19]. erefore, at this stage, deep learning is difficult to solve the problem of complex background removal of auto parts such as brake discs and batteries [20]. e second category is traditional automatic object segmentation methods.…”

Beauty matters: reducing bounce rate by aesthetics of experience product portal page

“…In the context of online experience products selling, this means that, if customers are attracted by images, their attention to textual signals reduces. Aesthetic images have been proven capable of capturing customers' attention at first sight via pleasing visual impacts (Zhao et al, 2015). After landing on a product portal page with a high image aesthetic, customers' attraction to it provokes spontaneous use of this signal to evaluate the product.…”

Propiedades de las representaciones en diseño : una exploración interdisciplinaria de su rol funcional.

“…La repleción está relacionada con la saliencia visual o más ampliamente con la saliencia perceptiva 1 . La mayor saliencia visual de una representación la posee la parte que atrae la atención del observador a primera vista (Zhao et al, 2014). La saliencia perceptual de atributos desempaña un rol importante en las decisiones de compra (Hutchinson & Alba, 1991).…”

“…La saliencia perceptual de atributos desempaña un rol importante en las decisiones de compra (Hutchinson & Alba, 1991). La saliencia visual ha sido utilizada como un mecanismo básico en procesamiento de imágenes y visión artificial (Itti, Koch & Niebur, 1998;Zhao et al, 2014).…”