Autoframing: A Recommendation System for Detecting Undesirable Elements and Cropping Automatically Photos

In this paper, we present a recommendation system for automatically recentering and cropping digital still pictures that exhibit capturing artefacts. Autoframing images not only yields better visual pictures but more importantly allows us to remove undesirable artefacts such as lens obstructions by fingers, cellphone straps, or back heads. We report on our real-time prototype system that is targeted to consumer digital still cameras

[1]  B. S. Manjunath,et al.  Region of interest extraction and virtual camera control based on panoramic video capturing , 2005, IEEE Transactions on Multimedia.

[2]  Harry Shum,et al.  Image completion with structure propagation , 2005, ACM Trans. Graph..

[3]  B. S. Manjunath,et al.  Edge flow: A framework of boundary detection and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Frank Nielsen,et al.  Statistical region merging , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Liang-Tien Chia,et al.  Robust subspace analysis for detecting visual attention regions in images , 2005, MULTIMEDIA '05.

[6]  B. S. Manjunath,et al.  Texture Features for Browsing and Retrieval of Image Data , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Seiji Inokuchi,et al.  An attractiveness evaluation model based on the physical features of image regions , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[8]  Liang-Tien Chia,et al.  Attention region selection with information from professional digital camera , 2005, MULTIMEDIA '05.

[9]  Marc Levoy,et al.  Fast texture synthesis using tree-structured vector quantization , 2000, SIGGRAPH.

[10]  Frank Nielsen.  Visual computing : geometry, graphics, and vision , 2005 .