IDENTIFYING PERSON RE-OCCURRENCES FOR PERSONAL PHOTO MANAGEMENT APPLICATIONS

Automatic identification of "who" is present in individual digital images within a photo management system using only content-based analysis is an extremely difficult problem. The authors present a system which enables identification of person reoccurrences within a personal photo management application by combining image content-based analysis tools with context data from image capture. This combined system employs automatic face detection and body-patch matching techniques, which collectively facilitate identifying person re-occurrences within images grouped into events based on context data. The authors introduce a face detection approach combining a histogram-based skin detection model and a modified BDF face detection method to detect multiple frontal faces in colour images. Corresponding body patches are then automatically segmented relative to the size, location and orientation of the detected faces in the image. The authors investigate the suitability of using different colour descriptors, including MPEG-7 colour descriptors, color coherent vectors (CCV) and color correlograms for effective body-patch matching. The system has been successfully integrated into the MediAssist platform, a prototype Web-based system for personal photo management, and runs on over 13000 personal photos.

[1]  Ramin Zabih,et al.  Histogram refinement for content-based image retrieval , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.

[2]  Jing Huang,et al.  Image indexing using color correlograms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Michael L. Creech,et al.  FotoFile: a consumer multimedia organization and retrieval system , 1999, CHI '99.

[4]  Ben Shneiderman,et al.  Visualization methods for personal photo collections: browsing and searching in the PhotoFinder , 2000, 2000 IEEE International Conference on Multimedia and Expo. ICME2000. Proceedings. Latest Advances in the Fast Changing World of Multimedia (Cat. No.00TH8532).

[5]  Dean S. Messing,et al.  The MPEG-7 colour structure descriptor: image description using colour and local spatial information , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[6]  B. S. Manjunath,et al.  Color and texture descriptors , 2001, IEEE Trans. Circuits Syst. Video Technol..

[7]  B. S. Manjunath,et al.  An efficient color representation for image retrieval , 2001, IEEE Trans. Image Process..

[8]  Timo Ojala,et al.  Semantic image retrieval with hsv correlograms , 2001 .

[9]  Chengjun Liu,et al.  A Bayesian Discriminating Features Method for Face Detection , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  LONGBIN CHEN,et al.  Face Annotation for Family Photo Album Management , 2003, Int. J. Image Graph..

[11]  Mingjing Li,et al.  Automated annotation of human faces in family albums , 2003, MULTIMEDIA '03.

[12]  Yuxiao Hu,et al.  Efficient propagation for face annotation in family albums , 2004, MULTIMEDIA '04.

[13]  Benjamin B. Bederson,et al.  Semi-Automatic Image Annotation Using Event and Torso Identification , 2004 .

[14]  Mohamed Abdel-Mottaleb,et al.  Content-based photo album management using faces' arrangement , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[15]  Noel E. O'Connor,et al.  A hybrid technique for face detection in color images , 2005, IEEE Conference on Advanced Video and Signal Based Surveillance, 2005..

[16]  Mor Naaman,et al.  Leveraging context to resolve identity in photo albums , 2005, Proceedings of the 5th ACM/IEEE-CS Joint Conference on Digital Libraries (JCDL '05).

[17]  A. Smeaton,et al.  Combination of content analysis and context features for digital photograph retrieval. , 2005 .

[18]  Longbin Chen,et al.  Content-Based Photo Album Management Using Faces , 2008, Encyclopedia of Multimedia.