Automatic summarization for personal digital photos

With the rapid development and wide spread of digital cameras, sizable personal digital image libraries would become mainstay of our digital assets for recording pictorial memories in our lives. As a matter of fact, most consumers cannot afford the time to annotate and organize their personal digital photos, they would face genuine problem of accessing them effectively and efficiently. More often than not, consumers wish to share a selective summary of their images with their relatives and friends, increasingly using remote repository services and messaging services (emails, multimedia message service). In this paper, we address this issue with automatic organization based on analysis of time stamps and image content to facilitate browsing and summarization of personal digital photos. In particular, both photo creation time and image content are exploited to efficiently partition related images in two stages. From the partitions, key photos are selected to represent the partition based on content analysis and then collated to generate a summary, which can be enjoyed as a slide show for visual communication. We demonstrate our approach on genuine heterogeneous personal digital photos with encouraging results. We also develop a photo summarization application with multimedia message service on Nokia 7650 camera phone emulator.

[1]  HongJiang Zhang,et al.  MSR-Asia at TREC-10 Video Track: Shot Boundary Detection Task , 2001, TREC.

[2]  Joo-Hwee Lim Building Visual Vocabulary for Image Indexation and Query Formulation , 2001, Pattern Analysis & Applications.

[3]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.

[4]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Atreyi Kankanhalli,et al.  Automatic partitioning of full-motion video , 1993, Multimedia Systems.

[6]  Takeo Kanade,et al.  Rotation Invariant Neural Network-Based Face Detection , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[7]  J. C. Platt AutoAlbum: clustering digital photographs using probabilistic model merging , 2000, 2000 Proceedings Workshop on Content-based Access of Image and Video Libraries.

[8]  Andreas Paepcke,et al.  Time as essence for photo browsing through personal digital libraries , 2002, JCDL '02.

[9]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[10]  Kerry Rodden,et al.  How do people manage their digital photographs? , 2003, CHI '03.

[11]  Monson H. Hayes,et al.  Face Recognition Using An Embedded HMM , 1999 .

[12]  Shih-Fu Chang,et al.  Real-time personalized sports video filtering and summarization , 2001, MULTIMEDIA '01.