C
Chitra Dorai
Researcher at IBM
Publications - 126
Citations - 3789
Chitra Dorai is an academic researcher from IBM. The author has contributed to research in topics: Film grammar & Semantic gap. The author has an hindex of 33, co-authored 126 publications receiving 3748 citations.
Papers
More filters
Journal ArticleDOI
COSMOS-A representation scheme for 3D free-form objects
Chitra Dorai,Anil K. Jain +1 more
TL;DR: This work proposes a new and general surface representation scheme for recognizing objects with free-form (sculpted) surfaces, and introduces the shape spectrum of an object, a novel concept, within the framework of COSMOS for object view grouping and matching.
Proceedings ArticleDOI
Automatic genre identification for content-based video categorization
Ba Tu Truong,Chitra Dorai +1 more
TL;DR: This research goes beyond the existing work with a systematic analysis of trends exhibited by each of the features in genres such as cartoons, commercials, music, news, and sports, and it enables an understanding of the similarities, dissimilarities, and also likely confusion between genres.
Proceedings ArticleDOI
New enhancements to cut, fade, and dissolve detection processes in video segmentation
TL;DR: A new adaptive threshold determination method is proposed that is shown to reduce artifacts created by noise and motion in scene cut detection and introduced a method for eliminating false positives from a list of detected candidate transitions.
Patent
System and method for multi-party validation, authentication and/or authorization via biometrics
TL;DR: In this article, a system and method for multi-party authentication is described, which uses synchronous and persistent biometrics signals received from parties to a transaction, based on a policy, to approve a transaction request.
Patent
Rapid business support of insured property using image analysis
TL;DR: In this paper, a method of providing rapid business support of insured property using image analysis can include the step of receiving at least one digital image of damaged property, which can be automatically accessed for insurance purposes based upon the received images.