Mobile and server-side computational photography
AssigneeMicrosoft Corporation
InventorsBilly Chen, Eyal Ofek
Life of this patent
Estimating the term…
Abstract
Automated photographic capture assistance and analysis is effectuated to assist users in capturing sufficient and optimal images of a desired image scene for use in a photographic end product. Photographic capture assistance is implemented on the device that includes a user's camera. Photographic capture assistance can include audio and/or graphic information generated in real time locally on the device that includes the user's camera and informs the user where additional images of the image scene ought to be captured and/or whether or not sufficient captured images currently exist for the image scene.
Claims18
A method for assisting a user in capturing images of an image scene utilizing a camera of a mobile device, the method comprising:
- identifying at least two captured images on the mobile device of the image scene;
- mining meta data from at least two captured images of the image scene;
- communicating with a computing device requesting at least one captured image of the image scene that is not currently stored on the mobile device;
- receiving a captured image of the image scene that is not currently stored on the mobile device from the computing device and storing the received captured image of the image scene on the mobile device;
- executing a capture algorithm with at least two captured images including the received captured image, wherein the execution of the capture algorithm comprises using meta data mined from at least two captured images of the image scene to generate information identifying a region of the image scene for which at least one image is recommended to be captured;
- and
- informing a user of the location of the region of the image scene for at least one image that is recommended to be captured.
A method for supporting the capture of images of an image scene on a mobile device that includes a camera having a camera lens, the captured images to be used to create a photographic end product, the method comprising:
- identifying a set of at least two captured images of the image scene that are stored on the mobile device;
- searching the internet for at least one image of the image scene;
- retrieving at least one image of the image scene that is discovered from a search of the internet;
- and
- storing the at least one image retrieved from the internet on the mobile device as captured images in the set of the at least two captured images,
- executing a capture algorithm to generate information regarding the sufficiency of the set of captured images for creating the photographic end product;
- and
- outputting information on the mobile device regarding the sufficiency of the set of captured images for creating the photographic end product;
- wherein outputting information on the mobile device regarding the sufficiency of the set of captured images for creating the photographic end product comprises:
- outputting an indication that the set of captured images are insufficient for creating the photographic end product;
- and
- outputting information comprising the sufficiency of the set of images for creating the photographic end product.
A mobile device photo capture application for assisting a user in capturing images of an image scene, the mobile device photo capture application comprising:
- a component comprising the capability to direct the capture and processing of images of the image scene;
- a component comprising stored captured images of the image scene;
- a component comprising the capability to mine meta data from stored captured images of the image scene;
- a component comprising the capability to control at least one sensor of a camera;
- a component comprising the capability to analyze stored captured images of the image scene;
- a component comprising the capability to generate an analysis that comprises information that identifies when there are sufficient stored captured images of the image scene to generate a photographic end product without the need to capture any additional images of the image scene;
- a component that communicates with a computing device for obtaining and storing at least one captured image of the image scene from the computing device;
- a component comprising the capability to execute a comparison algorithm using at least two captured images of the image scene, including the at least one captured image obtained from the computing device, wherein the execution of the comparison algorithm comprises the generation of information comprising an identification of a region of the image scene that at least one image is recommended to be captured for;
- and
- a component comprising the capability to output a display comprising information that can be referred to locate a region of the image scene that at least one image is recommended to be captured for.
Dependencies are inferred from the claim text.