25 February 1994 Use of collateral text in understanding photos in documents
Author Affiliations +
Proceedings Volume 2103, 22nd AIPR Workshop: Interdisciplinary Computer Vision: Applications and Changing Needs; (1994) https://doi.org/10.1117/12.169469
Event: 22nd Applied Imagery Pattern Recognition Workshop, 1993, Washington, DC, United States
This research explores the interaction of textural and photographic information in document understanding. Specifically, it presents a computational model whereby textural captions are used as collateral information in the interpretation of the corresponding photographs. The final understanding of the picture and caption reflects a consolidation of the information obtained from each of the two sources and can thus be used in intelligent information retrieval tasks. The problem of performing general-purpose vision without a-priori knowledge is very difficult at best. The concept of using collateral information in scene understanding has been explored in systems that use general scene context in the task of object identification. The work described here extends this notion by incorporating picture specific information. A multistage system PICTION, which uses captions to identify humans in an accompanying photograph, is described. This provides a computationally less expensive alternative to traditional methods of face recognition. It does not require a prestored database of face models for all people to be identified. A key component of the system is the utilization of spatial and characteristic constraints (derived from the caption) in labeling face candidates (generated by a face locator).
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Rohini K. Srihari, Rohini K. Srihari, "Use of collateral text in understanding photos in documents", Proc. SPIE 2103, 22nd AIPR Workshop: Interdisciplinary Computer Vision: Applications and Changing Needs, (25 February 1994); doi: 10.1117/12.169469; https://doi.org/10.1117/12.169469


2+2=5: painting by numbers
Proceedings of SPIE (January 15 2006)
What good is visualization: three experiments
Proceedings of SPIE (May 13 1998)
DiRecT: A disaster recovery system
Proceedings of SPIE (August 08 2004)

Back to Top