Back to results
US 9,286,683 B1Granted
Text detection near display screen edge
AssigneeAmazon Technologies, Inc.
InventorDavid Paul Ramos
Life of this patent
Estimating the term…
Abstract
Approaches to enable a computing device, such as a phone or tablet computer, to detect when text contained in an image captured by the camera is sufficiently close to the edge of the screen and to infer whether the text is likely to be cut off by the edge of the screen such that the text contained in the image is incomplete. If the incomplete text corresponds to actionable text associated with a function that can be invoked on the computing device, the computing device may wait until the remaining portion of the actionable text is captured by the camera and made available for processing before invoking the corresponding function on the computing device.
Claims20
A computing device, comprising:
- a camera configured to capture an image;
- a display screen configured to display the image captured by the camera;
- at least one processor;
- and
- memory including instructions that, when executed by the at least one processor, cause the computing device to:
- detect one or more glyphs in the image;
- determine a distance between a first glyph of the one or more glyphs and an edge of the image;
- transmit the distance and image data containing the one or more glyphs to a server for processing by an optical character recognition (OCR) engine, wherein the server is configured to:
- analyze the image data, determine actionable text corresponding to the one or more glyphs is likely to be incomplete based at least in part on one or more characteristics of the actionable text and the distance, wherein the one or more characteristics of the actionable text include at least one of a character size of the actionable text, a font of the actionable text, a height of the actionable text, or a spacing between each character of the actionable text;
- receive a communication from the server indicating that the actionable text is likely to be incomplete;
- and
- display a graphical indication on the display screen indicating that the actionable text is likely to be incomplete.
9 more elements
A computer implemented method, comprising:
- under the control of one or more computer systems configured with executable instructions,
- receiving image data associated with an image captured by at least one camera of a computing device, the image data containing text;
- determining a distance between a character of the text and an edge of the image;
- determining that actionable text corresponding to the text of the image data may be incomplete based at least in part on one or more characteristics of the actionable text and the distance, wherein the one or more characteristics of the actionable text include at least one of a character size of the actionable text, a font of the actionable text, a height of the actionable text, or a spacing between each character of the actionable text;
- and
- providing an indication that the text of the image data may be incomplete.
3 more elements
A computing device, comprising:
- a camera;
- at least one processor;
- and
- memory including instructions that, when executed by the at least one processor, cause the computing device to:
- capture an image using the camera, the image containing text;
- transmit image data corresponding to the image to a server, wherein the server is configured to determine when the text is likely to correspond to complete actionable text or incomplete actionable text based at least in part on one or more characteristics of the text, and a distance between the text and an edge of the image, wherein the one or more characteristics of the actionable text include at least one of a character size of the actionable text, a font of the actionable text, a height of the actionable text, or a spacing between each character of the actionable text;
- receive a communication from the server, the communication indicating whether the text in the image is likely to correspond to the complete actionable text or the incomplete actionable text;
- in response to the communication indicating that the text is likely to correspond to the complete actionable text, display a graphical component on a display screen, the graphical component actionable to invoke a function on the computing device;
- and
- in response to the communication indicating that the text is likely to correspond to the incomplete actionable text, display no graphical component on the display screen.
7 more elements
A non-transitory computer readable storage medium storing one or more sequences of instructions that, when executed by one or more processors, cause a computing system to:
- capture an image using a camera;
- detect a glyph in the image;
- determine a location of the glyph in the image;
- determine a distance between the glyph and an edge of the image based at least in part on the location of the glyph;
- determine that actionable text corresponding to the glyph is likely to be incomplete based at least in part on one or more characteristics of the actionable text and the distance wherein the one or more characteristics of the actionable text include at least one of a character size of the actionable text, a font of the actionable text, a height of the actionable text, or a spacing between each character of the actionable text;
- and
- display a visual indication based at least in part on a determination that the actionable text corresponding to the glyph is likely to be incomplete.
4 more elements
Dependencies are inferred from the claim text.