Categorizing captured images for subsequent search

• Main Authors: Morris Cheryl, Silberman Gabriel M
• Format: Patent
• Language: English
• Published: 07.11.2017
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

Systems and methods are described to identify in the images text, people, landmarks, objects, or any combination thereof and to store and search for images based on extracted data. A portable computing device, such as a wireless phone or tablet computer, may capture an image, determine context data associated with the image, and send the image and context data to an analyzer. The analyzer may extract data from the image and send the extracted data to the portable computing device. For example, the analyzer may determine if the image includes alphanumeric characters and perform character recognition (e.g., using optical character recognition (OCR) or similar technology). A format of the characters that are recognized in the image may be analyzed to determine additional information, such as whether the characters are a phone number, a uniform resource locator (URL), a name of a person, a name of a location, or the like. The analyzer may determine if the image includes a person, a landmark, an object, etc. by comparing at least a portion of the image with other images. The analyzer may send the extracted data to the portable computing device for storage. The portable computing device may associate the context data and the extracted data with a downsampled (e.g., thumbnail) version of the image to enable a user to query the context data and extracted data.