Scalable visual search system simplifying access to network and device functionality

Abstract

In one embodiment, an indication of information desired by a user is received, and a list of candidates for the desired information is provided for presentation on a mobile device of the user.

1 . (canceled) 
     
     
         2 . A method comprising:
 continuously receiving, via an optical sensor of a device, live media content showing one or more objects;   creating at least one intermediate representation of the live media content;   causing a transmission of the live media content, the at least one intermediate representation, or a combination thereof via a network to a server for image recognition to identify the one or more objects with one or more tags associated one or more existing objects; and   receiving and causing a presentation of at least one of the one or more existing objects on a user interface of the device.   
     
     
         3 . The method of  claim 2 , wherein the image recognition applied on the one or more objects includes object-recognition, face-recognition, bar-code recognition, optical character recognition, or a combination thereof. 
     
     
         4 . The method of  claim 2 , further comprising:
 determining meta-information based on sensor data from one or more sensors of the device,   wherein the one or more objects are identified with the one or more tags further based on the meta-information.   
     
     
         5 . The method of  claim 4 , wherein the one or more sensors include one or more audio sensors, one or more proximity sensor, one or more wireless interface sensors, one or more temperature sensors, one or more smell sensors, one or more body parameter sensors, one or more motion sensors, one or more accelerometers, one or more brightness sensors, one or more optical sensors, or a combination thereof. 
     
     
         6 . The method of  claim 2 , wherein the presentation of the at least one existing object further includes information of the at least one existing object, information for ordering the at least one existing object, or a combination thereof. 
     
     
         7 . The method of  claim 2 , further comprising:
 causing a translation of at least one of the one or more objects into a predetermined language, wherein the presentation of the at least one existing object further includes the translation.   
     
     
         8 . The method of  claim 2 , wherein the one or more existing objects include one or more products, one or more services, one or more points of interest, one or more point of interest reviews, one or more people, one or more social networking profiles associated with the one or more existing objects, or a combination thereof. 
     
     
         9 . The method of  claim 2 , further comprising:
 estimating a size, a position, or a combination thereof of one of the objects as pointed by the device based on the live media content, metadata associated with the live media content, or a combination thereof.   
     
     
         10 . The method of  claim 9 , further comprising:
 automatically zooming to the one object based on the size, the position, or a combination thereof.   
     
     
         11 . The method of  claim 9 , further comprising:
 automatically retrieving a preview associated with the one object based on a corresponding one of the tags.   
     
     
         12 . An apparatus comprising:
 at least one processor; and   at least one memory including computer program code for one or more programs,   the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,
 continuously receive, via an optical sensor of a device, live media content showing one or more objects; 
 cause a transmission of the live media content via a network to a server for image recognition to identify the one or more objects with one or more tags associated one or more existing objects; and 
 receive and cause a presentation of at least one of the one or more existing objects on a user interface of the device. 
   
     
     
         13 . The apparatus of  claim 12 , wherein the apparatus is further caused to:
 create at least one intermediate representation of the live media content; and   cause a transmission of the at least one intermediate representation via the network to the server, wherein the one or more objects are identified with the one or more tags based on the at least one intermediate representation.   
     
     
         14 . The apparatus of  claim 12 , wherein the image recognition applied on the one or more objects includes object-recognition, face-recognition, bar-code recognition, optical character recognition, or a combination thereof. 
     
     
         15 . The apparatus of  claim 12 , wherein the apparatus is further caused to:
 determine meta-information based on sensor data from one or more sensors of the device,   wherein the one or more objects are identified with the one or more tags further based on the meta-information.   
     
     
         16 . The apparatus of  claim 15 , wherein the one or more sensors include one or more audio sensors, one or more proximity sensor, one or more wireless interface sensors, one or more temperature sensors, one or more smell sensors, one or more body parameter sensors, one or more motion sensors, one or more accelerometers, one or more brightness sensors, one or more optical sensors, or a combination thereof. 
     
     
         17 . The apparatus of  claim 12 , wherein the presentation of the at least one existing object further includes information of the at least one existing object, information for ordering the at least one existing object, or a combination thereof. 
     
     
         18 . The apparatus of  claim 12 , further comprising:
 cause a translation of at least one of the one or more objects into a predetermined language, wherein the presentation of the at least one existing object further includes the translation.   
     
     
         19 . A non-transitory computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to perform:
 continuously receiving via a network live media content showing one or more objects, wherein the live media content is captured via an optical sensor of a device;   applying image recognition on the live media content to identify the one or more objects with one or more tags;   searching a database for one or more existing objects associated with the one or more tags; and   causing a presentation of at least one of the one or more existing objects on a user interface of the device.   
     
     
         20 . The non-transitory computer-readable storage medium of  claim 19 , wherein the image recognition applied on the one or more objects includes object-recognition, face-recognition, bar-code recognition, optical character recognition, or a combination thereof. 
     
     
         21 . The non-transitory computer-readable storage medium of  claim 19 , wherein the one or more existing objects include one or more products, one or more services, one or more points of interest, one or more point of interest reviews, one or more people, one or more social networking profiles associated with the one or more existing objects, or a combination thereof.