D
Darryl Greig
Researcher at Hewlett-Packard
Publications - 51
Citations - 676
Darryl Greig is an academic researcher from Hewlett-Packard. The author has contributed to research in topics: Executable & Object detection. The author has an hindex of 13, co-authored 51 publications receiving 674 citations.
Papers
More filters
Patent
Automatic extraction of metadata using a neural network
TL;DR: This paper proposed a method of automatically extracting metadata from a document by using a neural network trained to extract metadata from groupings of data called compounds, where each compound includes the words making up the block, descriptive information about the blocks, and authority information associated with some of the words.
Patent
Dynamic image collage
TL;DR: In this article, a sequence of templates (22) is determined, and each of the templates defines a spatio-temporal layout of regions in a display area (38).
Patent
Automatic categorization of documents using document signatures
TL;DR: In this article, the authors proposed a method of quickly and automatically comparing a new document to a large number of previously seen documents and identifying the document type by calculating the distances between the new document signature and each of the plurality of document type distributions using a Bayesian framework for a Gaussian distribution.
Patent
Face and skin sensitive image enhancement
Hila Nachlieli,Gitit Ruckenstein,Darryl Greig,Doron Shaked,Ruth Bergman,Carl Staelin,Shlomo Harush,Mani Fischer +7 more
TL;DR: In this paper, a system for face and skin sensitive image enhancement is described. And a tone-correction process is tuned in accordance with the facial content measurement value, and the input image (24) is enhanced with an enhancement level that varies pixel-by-pixel.
Patent
Multimedia presentation apparatus, method of selecting multimedia content, and computer program product
TL;DR: In this paper, a multimedia presentation apparatus consisting of a playback module, a sensor module and a processing module is presented for determining a state of the audience based on the characteristic of the at least one individual in an audience.