Capturing text from rendered documents using supplement information
A system for processing a text capture operation is described. The system receives text captured from a rendered document in the text capture operation. The system also receives supplemental information distinct from the captured text. The system determines an action to perform in response to the text capture operation based upon both the captured text and the supplemental information.
1. A method comprising:
receiving, at a computing device, text captured from a rendered document during a text capture operation;
receiving, at the computing device, supplemental information relating to circumstances under which the text capture operation was performed, the supplemental information comprising information indicating a geographical location at which the text capture operation occurs, the information indicating a geographical location at which the text capture operation occurs comprising information indicating a location as being indoors or outdoors; and
determining, by the computing device and based on the captured text and the supplemental information, an action to be performed;
wherein a determination of the location as being indoors or outdoors is based on light entering a sensor of an optical capture device.
2. The method of claim 1 , wherein determining the action to be performed comprises determining to discard at least one document from among a plurality of documents identified as having the captured text.
3. The method of claim 2 , wherein determining the action to be performed further comprises determining to prioritize any documents of the plurality of documents remaining after discarding the at least one document.
4. The method of claim 1 , wherein determining the action to be performed comprises determining to select a default action to perform from among a plurality of actions.
5. The method of claim 1 , wherein the information indicating a geographical location at which the text capture operation occurs comprises information expressed in terms of latitude and longitude.
6. The method of claim 1 , further comprising: predicting, by the computing device, context with respect to a user of a capture device that performs the text capture operation,
wherein at least a portion of the supplemental information is based on the predicted context.
7. The method of claim 6 ,
wherein the predicted context is based on information indicating the user is on an airplane being flown to a particular city.
8. A method comprising:
receiving, at a computing device, text captured from a rendered document during a text capture operation;
receiving, at the computing device, supplemental information relating to circumstances under which the text capture operation was performed, the supplemental information comprising information indicating a geographical location at which the text capture operation occurs; and
determining, by the computing device and based on the captured text and the supplemental information, an action to be performed;
wherein the information indicating a geographical location at which the text capture operation occurs comprises information indicating a location deduced from an ambient noise of an audio capture device that performs the text capture operation.
9. A method comprising:
receiving, at a computing device, text captured from a rendered document during a text capture operation;
receiving, at the computing device, supplemental information relating to circumstances under which the text capture operation was performed;
predicting, by the computing device, context with respect to a user of a capture device that performs the text capture operation, wherein at least a portion of the supplemental information is based on the predicted context; and
determining, by the computing device and based on the captured text and the supplemental information, an action to be performed;
wherein the predicted context is based on information indicating the user is on an airplane being flown to a particular city; and
wherein the predicted context indicates the user is reading a document about the particular city.
10. A method comprising:
receiving, at a computing device, text captured from a rendered document during a text capture operation;
receiving, at the computing device, supplemental information relating to circumstances under which the text capture operation was performed;
predicting, by the computing device, context with respect to a user of a capture device that performs the text capture operation, wherein at least a portion of the supplemental information is based on the predicted context; and
determining, by the computing device and based on the captured text and the supplemental information, an action to be performed;
wherein the predicted context is based on schedule information indicating the user is meeting with a particular person.
11. The method of claim 10 , wherein the predicted context indicates the user is reading a document by or about the particular person.
12. A system comprising:
an input receiver operable to receive text captured from a rendered document during a text capture operation, and supplemental information relating to circumstances of performing the text capture operation, the supplemental information comprising information indicating a geographical location at which the text capture operation occurs, the information indicating a geographical location at which the text capture operation occurs comprising information indicating a location as being indoors or outdoors;
a processing unit; and
a computer memory configured to store the captured text, the supplemental information, and computer-readable programs executable by the processing unit;
wherein the computer-readable program instructions are executable by the processing unit to determine, based on the captured text and the supplemental information, an action to be performed; and
wherein a determination of the location as being indoors or outdoors is based on light entering a sensor of an optical capture device.
13. The system of claim 12 , wherein the input receiver comprises a network connection that connects the system to the Internet.
14. The system of claim 12 , wherein the computer-readable program instructions are executable by the processing unit to perform the determined action.
15. The system of claim 12 ,
wherein the computer-readable program instructions are executable by the processing unit to predict context with respect to a user of a capture device that performs the text capture operation, and
wherein at least a portion of the supplemental information is based on the predicted context.
16. A non-transitory computer readable medium having stored therein instructions, that when executed by a computing device, cause the computing device to perform functions comprising:
receiving, at a computing device, text captured from a rendered document during a text capture operation;
receiving, at the computing device, supplemental information relating to circumstances under which the text capture operation was performed, the supplemental information comprising information indicating a geographical location at which the text capture operation occurs, the information indicating a geographical location at which the text capture operation occurs comprising information indicating a location as being indoors or outdoors; and
determining, by the computing device and based on the captured text and the supplemental information, an action to be performed;
wherein a determination of the location as being indoors or outdoors is based on light entering a sensor of an optical capture device.
17. The non-transitory computer readable medium of claim 16 , wherein the stored instructions, when executed by the computing device, further cause performance of the determined action.
18. The non-transitory computer readable medium of claim 16 ,
wherein the stored instructions, when executed by the computing device, further cause the computing device to predict context with respect to a user of a capture device that performs the text capture operation, and
wherein at least a portion of the supplemental information is based on the predicted context.