Data access based on con lent of image recorded by a mobile device
View Patent ↗Embodiments of the invention are directed to using image data and contextual data to determine information about a scene, based on one or more previously obtained images. Contextual data, such location of image capture, can be used to determine previously obtained images related to the contextual data and other location-related information, such as billboard locations. With even low resolution devices, such as cell phone, image attributes, such as a histogram or optically recognized characters, can be compared between the previously obtained images and the newly captured image. Attributes matching within a predefined threshold indicated matching images. Information on the content of matching previously obtained images can be provided back to a user who captured the new image. User profile data can refine the content information. The content information can also be used as search terms for additional searching or other processing.
1. A method comprising:
receiving image data representing an image captured by a mobile device of a user, the image data including a location;
calculating a first image histogram associated with the image data;
identifying a plurality of previously captured images from various databases, each previously captured image having a pre-computed image histogram;
filtering the plurality of previously captured images based on criteria, the criteria comprising a number of captured images with a highest resolution, being associated with a location within a pre-defined radius to the location, having contextual information related to the image data and being associated with a certain set of mobile identifiers, the filtering comprising selecting a set of previously captured images from the plurality of previously captured image based on the criteria, the set being a narrowed down number from the plurality;
calculating a similarity metric between the first image histogram and each of the pre-computed image histograms for the selected set of previously captured images, the calculation comprising identifying a number of overlapping colors included in both the first image histogram and each of the pre-computed image histograms;
identifying a matching image from the selected set of previously captured images, the matching image having a calculated similarity metric to the captured image meeting a predetermined threshold;
identifying user profile information related to the user; and
determining search terms based on the user profile information, the image data of the captured image and the contextual information associated with the matching image.
2. The method of claim 1 , the calculating a first image histogram associated with the image data further comprising calculating a number of pixels associated with at least one color value appearing in the image data.
3. The method of claim 1 , the calculating a first image histogram associated with the image data further comprising identifying a number of salient points in the image data.
4. The method of claim 3 , the identifying a number of salient points in the image data further comprising identifying a color, local texture, and orientation of the salient points.
5. The method of claim 3 , the calculating a similarity metric for each previously captured image further comprising comparing a number and orientation of a set of salient points in the first image histogram to a number and orientation of a set of salient points in each of the pre-computed image histograms.
6. The method of claim 1 wherein calculating a first image histogram associated with the image data comprises calculating the first image histogram for a subset of the image data.
7. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a processor associated with a computing device, performs a method comprising:
receiving image data representing an image captured by a mobile device of a user, the image data including a location;
calculating a first image histogram associated with the image data;
identifying a plurality of previously captured images from various databases, each previously captured image having a pre-computed image histogram;
filtering the plurality of previously captured images based on criteria, the criteria comprising a number of captured images with a highest resolution, being associated with a location within a pre-defined radius to the location, having contextual information related to the image data and being associated with a certain set of mobile identifiers, the filtering comprising selecting a set of previously captured images from the plurality of previously captured image based on the criteria, the set being a narrowed down number from the plurality;
calculating a similarity metric between the first image histogram and each of the pre-computed image histograms for the selected set of previously captured images, the calculation comprising identifying a number of overlapping colors included in both the first image histogram and each of the pre-computed image histograms;
identifying a matching image from the selected set of previously captured images, the matching image having a calculated similarity metric to the captured image meeting a predetermined threshold;
identifying user profile information related to the user; and
determining search terms based on the user profile information, the image data of the captured image and the contextual information associated with the matching image.
8. The non-transitory computer-readable storage medium of claim 7 , the calculating an image histogram associated with the image data further comprising calculating a number of pixels associated with at least one color value appearing in the image data.
9. The non-transitory computer-readable storage medium of claim 7 , the calculating an image histogram associated with the image data further comprising identifying a number of salient points in the image data.
10. The non-transitory computer-readable storage medium of claim 9 , the identifying a number of salient points in the image data further comprising identifying a color, local texture, and orientation of the salient points.
11. The non-transitory computer-readable storage medium of claim 9 , the calculating a similarity metric for each previously captured image further comprising comparing a number and orientation of a set of salient points in the first image histogram to a number and orientation of a set of salient points in each of the pre-computed image histograms.
12. The non-transitory computer-readable storage medium of claim 7 , the calculating a first image histogram associated with the image data further comprising calculating the first image histogram for a subset of the image data.
13. A computing device comprising:
a processor; and
a non-transitory computer-readable storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
logic executed by the processor for receiving image data representing an image captured by a mobile device of a user, the image data including a location;
logic executed by the processor for calculating a first image histogram associated with the image data;
logic executed by the processor for identifying a plurality of previously captured images from various databases, each previously captured image having a pre-computed image histogram;
logic executed by the processor for filtering the plurality of previously captured images based on criteria, the criteria comprising a number of captured images with a highest resolution, being associated with a location within a pre-defined radius to the location, having contextual information related to the image data and being associated with a certain set of mobile identifiers, the filtering comprising selecting a set of previously captured images from the plurality of previously captured image based on the criteria, the set being a narrowed down number from the plurality;
logic executed by the processor for calculating a similarity metric between the first image histogram and each of the pre-computed image histograms for the selected set of previously captured images, the calculation comprising identifying a number of overlapping colors included in both the first image histogram and each of the pre-computed image histograms;
logic executed by the processor for identifying a matching image from the selected set of previously captured images, the matching image having a calculated similarity metric to the captured image meeting a predetermined threshold;
logic executed by the processor for identifying user profile information related to the user; and
logic executed by the processor for determining search terms based on the user profile information, the image data of the captured image and the contextual information associated with the matching image.
14. The computing device of claim 13 , the logic for calculating a first image histogram associated with the image data further comprising logic for identifying a number of salient points in the image data and the logic for calculating a similarity metric for each previously captured image further comprising logic for comparing a number and orientation of a set of salient points in the first image histogram to a number and orientation of a set of salient points in each of the pre-computed image histograms.
15. The computing device of claim 13 , the logic for calculating an image histogram associated with the image data further comprising logic for calculating the image histogram for a subset of the image data.