N
Neil Alldrin
Researcher at Google
Publications - 24
Citations - 2113
Neil Alldrin is an academic researcher from Google. The author has contributed to research in topics: Image processing & Feature detection (computer vision). The author has an hindex of 12, co-authored 22 publications receiving 1917 citations. Previous affiliations of Neil Alldrin include Vision-Sciences, Inc. & University of California, Berkeley.
Papers
More filters
Patent
Method for image modification
Richard Mark Friedhoff,Casey Arthur Smith,Bruce Maxwell,Neil Alldrin,Steven Joseph Bushell,Timothy King Rodgers +5 more
TL;DR: In this article, an automated computerized method for processing an image is presented. The method includes the steps of providing an image file depicting an image, in a computer memory, performing an image segregation operation on the image file to generate a set of intrinsic images corresponding to the image, modifying a preselected one of the set of intrinsically images according to a setof preselected operations and merging the modified image relative to the other intrinsic images to provide a modified output image.
Proceedings ArticleDOI
A Planar Light Probe
Neil Alldrin,David J. Kriegman +1 more
TL;DR: A novel technique for measuring lighting that exploits the interaction of light with a set of custom BRDFs enables the construction of a planar light probe with certain advantages over existing methods forasuring lighting.
Patent
Refining image annotations
TL;DR: In this paper, a set of high confidence labels are determined for each image in the set of images, and images having a corresponding set of labels that include at least a respective threshold number of high-confidence labels are identified as high confidence images.
Patent
Assigning labels to images
Neil Alldrin,Thomas J. Duerig,Zhen Hao Zhou,Maks Ovsjanikovs,Charles J. Rosenberg,Samy Bengio,Maya R. Gupta +6 more
TL;DR: In this paper, a method for assigning labels to images is described, which includes determining, for an image, a first set of labels, each label being determined to be indicative of subject matter of the image based on content feature values of the images.