Image processing using multiple aspect ratios

P Natarajan, A Sikka, R Prasad - US Patent 9,418,283, 2016‏ - Google Patents
(57) ABSTRACT A system to recognize text, objects, or symbols in a captured image using
machine learning models reduces computational overhead by generating a plurality of …

Identifying payment card categories based on optical character recognition of images of the payment cards

X Wang, G Berntson - US Patent 9,904,956, 2018‏ - Google Patents
(57) ABSTRACT A user captures an image of a payment card via a user computing device
camera. An optical character recognition system receives the payment card image from the …

Leveraging image context for improved glyph classification

P Natarajan - US Patent 9,576,196, 2017‏ - Google Patents
A system to recognize text or symbols contained in a captured image using machine
learning models leverages context information about the image to improve accuracy …

Method of perspective correction for devanagari text

HP Acharya, PK Baheti - US Patent 9,171,204, 2015‏ - Google Patents
An electronic device and method identify regions that are likely to be text in a natural image
or video frame, followed by processing as follows: lines that are nearly vertical are auto …

Extracting card data with card models

S Kumar, HA Rowley, X Wang… - US Patent 8,831,329, 2014‏ - Google Patents
Embodiments herein provide computer-implemented tech niques for allowing a user
computing device to extract finan cial card information using optical character recognition …

Systems and methods for achieving and maintaining behavioral fitness

A Thorpe, M Janasik, S Erdmann, M Nair… - US Patent App. 14 …, 2016‏ - Google Patents
2015-09-23 Assigned to CAMBIA HEALTH SOLUTIONS, INC. reassignment CAMBIA
HEALTH SOLUTIONS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT …

Identifying a maximally stable extremal region (MSER) in an image by skip** comparison of pixels in the region

PK Baheti, KK Barman, R Krishnamoorthi… - US Patent …, 2015‏ - Google Patents
(57) ABSTRACT A difference in intensities of a pair of pixels in an image is repeatedly
compared to a threshold, with the pair of pixels being separated by at least one pixel (" …

Method of handling complex variants of words through prefix-tree based decoding for Devanagiri OCR

KK Barman, PK Baheti, RKK Kumar - US Patent 9,262,699, 2016‏ - Google Patents
An electronic device and method identify a block of text in a portion of an image of real world
captured by a camera of a mobile device, slice sub-blocks from the block and identify …

Hierarchical classification in credit card data extraction

S Kumar, HA Rowley, X Wang… - US Patent 9,213,907, 2015‏ - Google Patents
Embodiments herein provide computer-implemented tech niques for allowing a user
computing device to extract finan cial card information using optical character recognition …

Parameter selection and coarse localization of interest regions for MSER processing

PK Baheti, KK Barman, DA Gore… - US Patent 9,183,458, 2015‏ - Google Patents
An attribute is computed based on pixel intensities in an image of the real world, and
thereafter used to identify at least one input for processing the image to identify at least a first …