Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

A Method and System for Advanced Image Search and Filtering based on Natural Language Queries

IP.com Disclosure Number: IPCOM000234672D
Publication Date: 2014-Jan-28
Document File: 3 page(s) / 124K

Publishing Venue

The IP.com Prior Art Database

Related People

Cyril Sebastian: INVENTOR [+3]

Abstract

A method and system is disclosed for enabling a user to search one or more publicly available photos of one or more of contacts using Natural Language Processing (NLP). The method and system provides an interface to the user to search for and filter the one or more publicly available photos based on one or more of geographic locations, camera models and photography techniques.

This text was extracted from a Microsoft Word document.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 52% of the total text.

A Method and System for Advanced Image Search and Filtering based on Natural Language Queries

Abstract

A method and system is disclosed for enabling a user to search one or more publicly available photos of one or more of contacts using Natural Language Processing (NLP).  The method and system provides an interface to the user to search for and filter the one or more publicly available photos based on one or more of geographic locations, camera models and photography techniques. 

Description

Disclosed is a method and system for enabling a user to search one or more publicly available photos of one or more of contacts using Natural Language Processing (NLP).  The method and system provides an interface to the user to search for and filter the one or more publicly available photos based on one or more of geographic locations, camera models and photography techniques.  The interface assists the user to enter a query by providing auto completion of keywords and entities.  Auto completion of keywords is enabled by performing a quick lookup in an indexed database.  In response to receiving a query from the user, the method and system tokenizes and validates the query against a pre-defined list of keywords.  Subsequently, the tokens are translated into a proprietary query such as a Flickr* query.  Thereafter the proprietary query can be used to retrieve the one or more publicly available photos.

Consider a scenario wherein a query entered by a user is “photos of San Francisco taken using Canon** EOS*** 7D in 2013” or "photos of rain taken with bokeh effect".  In response to the user query, a back end NLP retrieves one or more photos to be displayed to the user based on the camera model (i.e. Canon EOS 7D), the geographic location (i.e. San Francisco) and the photography...