a novel genetic algorithms and surf-based approach for image retargeting：一种新的遗传算法和基于surf的图像重定向的方法.pdfVIP

ARTICLE IN PRESS JID: ESWA [m5G;September 26, 2015;21:19] Expert Systems With Applications xxx (2015) xxx–xxx Contents lists available at ScienceDirect Expert Systems With Applications journal homepage: /locate/eswa A novel Genetic Algorithms and SURF-Based approach for image retargeting Q1 ∗ Saulo A.F. Oliveira , Ajalmar R. Rocha Neto, Francisco N. Bezerra Q2 Federal Institute of Ceará, Department of Teleinformatics, Fortaleza, Ceará, Brazil a r t i c l e i n f o a b s t r a c t Keywords: Seam Carving is a method which aims at retargeting images, i.e., adjusting input images into arbitrary di- Genetic Algorithms mensions by removing pixel paths (seams) with minimal visual impact. The standard method is based on an Image retargeting exhaustive searching method for minimal cost seams according to a pixel relevance function also named en- Genetic Seam Carving ergy function. In this work, we propose a new method to retarget images based on both Genetic Algorithms Feature extraction Feature preservation (GAs) and a high-performance scale and rotation-invariant interest point descriptor, the well-known method,