Saliency-based content-aware lifestyle image mosaics

We proposed a novel content-aware lifestyle image mosaic technique based on image saliency.A novel energy map for variable-size tile decomposition is proposed by combining NIF and GBVS.Saliency-weighted image retrieval is introduced to choose the tile images.Seam carving is used to change the tile image's aspect ratio to meet the tile. In this paper, a novel content-aware lifestyle image mosaic technique is proposed based on image saliency. The image saliency is used in the whole process of creating mosaics. Firstly, a novel energy map for variable-size tile decomposition is proposed by combining Neighborhood Inhomogeneity Factor and Graph-Based Visual Saliency. The target image is divided into small tiles with variable sizes based on the energy map. Secondly, saliency-weighted image retrieval is introduced to choose the tile images from a certain image database. Different aspect ratio between the tile and the corresponding tile image may lead to obvious distortion. Therefore, before filled into the tile, the chosen tile image is resized by seam carving to change its aspect ratio. At last, color correction is done on the mosaic result to improve the color similarity. Compared with other mosaic methods, the proposed technique creates much better mosaics in visual aspect.

[1]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[2]  Ariel Shamir,et al.  Improved seam carving for video retargeting , 2008, SIGGRAPH 2008.

[3]  Jing-Yu Yang,et al.  Exploiting Intensity Inhomogeneity to Extract Textured Objects from Natural Scenes , 2009, ACCV.

[4]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[5]  K. N. Balasubramanya Murthy,et al.  A smart automatic thumbnail cropping based on attention driven regions of interest extraction , 2009, ICIS.

[6]  Ariel Shamir,et al.  Seam Carving for Content-Aware Image Resizing , 2007, ACM Trans. Graph..

[7]  Sabine Süsstrunk,et al.  Saliency detection for content-aware image resizing , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[8]  Yoichi Sato,et al.  Sensation-based photo cropping , 2009, ACM Multimedia.

[9]  Oscar de Bruijn,et al.  Rapid serial visual presentation: a space-time trade-off in information presentation , 2000, AVI '00.

[10]  Jinhui Tang,et al.  Saliency-Based Content-Aware Image Mosaics , 2013, MMM.

[11]  Nicholas Tran,et al.  Generating photomosaics: an empirical study , 1999, SAC '99.

[12]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[13]  Luc Van Gool,et al.  The 2005 PASCAL Visual Object Classes Challenge , 2005, MLCW.

[14]  Zhong Jin,et al.  A Two Step Face Alignment Approach Using Statistical Models , 2012 .

[15]  Pietro Perona,et al.  Graph-Based Visual Saliency , 2006, NIPS.

[16]  Fred Stentiford,et al.  Attention Based Auto Image Cropping , 2007, ICVS 2007.

[17]  Pascal Fua,et al.  Image summaries using database saliency , 2009, SIGGRAPH ASIA '09.

[18]  Adam Finkelstein,et al.  Image Mosaics , 1998, EP.

[19]  S. Süsstrunk,et al.  Frequency-tuned salient region detection , 2009, CVPR 2009.