Method, system and computer program product that provides virtual assistance in facilitating visual comparison
AssigneeMotorola Solutions, Inc.
InventorsSwee Yee Soo, Choon Kang Wong, Wai Seong Loh, Kuang Lin Chuang
Life of this patent
Estimating the term…
Abstract
A method, system and computer program product that provides virtual assistance in facilitating visual comparison is disclosed. A method in accordance with example embodiments includes determining (by comparison of first metadata of an at least one user-provided image to second metadata of an at least one reference image) difference information as between an unknown object and a known object shown in the at least one user-provided image to the at least one reference image respectively.
Claims20
A system comprising:
- a non-stationary camera configured to:
- capture at least one first image that depicts an unknown object;
- and
- output the at least one first image for generating first metadata elsewhere within the system;
- storage configured to store second metadata generated from at least one second image of a known object;
- and
- at least one processor in communication with the storage and the non-stationary camera, the at least one processor configured to:
- compare the first metadata to the second metadata to determine difference information as between the unknown and known objects, the difference information including at least one of a first information component and a second information component, wherein the first information component relates to appearance, and the second information component relates to size;
- and
- a mobile communications device that includes a speaker, the mobile communications device in communication with the at least one processor and configured to cause the speaker to emit an audio message that:
- includes at least some of the difference information;
- indicates that the unknown object is different than the known object;
- and explains why, consistent with the at least some of the difference information, there is no match between the unknown object and the known object.
A computer-implemented method for providing live virtual assistance to a user of the live virtual assistance, the method comprising:
- receiving, at an at least one processor, first metadata generated from at least one user-provided image that depicts an unknown object;
- providing, to the at least one processor, second metadata generated from at least one reference image of a known object;
- comparing, using the at least one processor, the first metadata to the second metadata to determine difference information as between the unknown and known objects, the difference information including at least one of a first information component and a second information component, wherein the first information component relates to appearance, and the second information component relates to size;
- and
- causing an audio message to be generated for delivery to the user, and
- wherein the audio message:
- includes at least some of the difference information;
- indicates that the unknown object is different than the known object;
- and explains why, consistent with the at least some of the difference information, there is no match between the unknown object and the known object.
A computer-implemented method for providing live virtual assistance to a user of the live virtual assistance, the method comprising:
- receiving, at an at least one processor:
- first metadata generated from a first region of at least one user-provided image that depicts a first unknown object;
- and
- second metadata generated from a second region of the at least one user-provided image that depicts a second unknown object;
- providing, to the at least one processor, third metadata generated from at least one reference image of a known object;
- processing the first metadata, the second metadata and the third metadata to determine, using the at least one processor, that the first unknown object is more similar than the second unknown object to the known object;
- comparing, using the at least one processor, the first metadata to the third metadata to determine difference information as between the first unknown object and the known object;
- and
- generating a customized be on the lookout message that includes at least some of the difference information, and explains why, consistent with the at least some of the difference information, there is no match between the first unknown object and the known object.
Dependencies are inferred from the claim text.