H
Henry Allan Rowley
Researcher at Google
Publications - 89
Citations - 9695
Henry Allan Rowley is an academic researcher from Google. The author has contributed to research in topics: Optical character recognition & Image processing. The author has an hindex of 33, co-authored 89 publications receiving 9374 citations. Previous affiliations of Henry Allan Rowley include Justsystem Pittsburgh Research Center & University of Minnesota.
Papers
More filters
Patent
Systems and methods for using image duplicates to assign labels to images
TL;DR: In this paper, a system analyzes multiple images to identify similar images using histograms, image intensities, edge detectors, or wavelets, and selectively concatenates the extracted labels.
Patent
Comparing extracted card data using continuous scanning
Sanjiv Kumar,Henry Allan Rowley,Xiaohang Wang,Yakov Okshtein,Farhan Shamsi,Alessandro Bissacco +5 more
TL;DR: In this article, a threshold confidence level for the extracted card data can be employed to determine the accuracy of the extraction, which is further extracted from blended images and three-dimensional models of the card.
Patent
Extracting card data using IIN database
Sanjiv Kumar,Xiaohang Wang,Jose Jeronimo Moreira Rodrigues,Farhan Shamsi,Yakov Okshtein,Henry Allan Rowley,Marcus Quintana Mitchell,Zhifei Li +7 more
TL;DR: Extracting card data comprises receiving, by one or more computing devices, a digital image of a card; perform an image recognition process on the digital representation of the card; identifying an image in the digital representations of the cards; comparing the identified image to an image database comprising a plurality of images and determining that the identified images matches a stored image in image database; determining a card type associated with the stored image and associating the card type with the card based on the determination that the identification image matches the stored images as discussed by the authors.
Patent
Template-based cursive handwriting recognition
TL;DR: In this article, handwritten characters are classified as print or cursive based upon numerical feature values calculated from the shape of an input character, and feature values are applied to inputs of an artificial neural network which outputs a probability of the input character being a print or a cursive.
Proceedings ArticleDOI
The effect of large training set sizes on online Japanese Kanji and English cursive recognizers
TL;DR: The results of training a nearest-neighbor based online Japanese Kanji recognizer and a neural-network based online cursive English recognizer on a wide range of training set sizes, including sizes not generally available are presented.