Simulating image capture
AssigneeIntuit Inc.
InventorsKimia Hassanzadeh, Richard J. Becker, Cole Mackenzie, Greg Coulombe
Life of this patent
Estimating the term…
Abstract
The present disclosure relates to simulating the capture of images. In some embodiments, a document and a camera are simulated using a three-dimensional modeling engine. In certain embodiments, a plurality of images are captured of the simulated document from a perspective of the simulated camera, each of the plurality of images being captured under a different set of simulated circumstances within the three-dimensional modeling engine. In some embodiments, a model is trained based at least on the plurality of images which determines at least a first technique for adjusting a set of parameters in a separate image to prepare the separate image for optical character recognition (OCR).
Claims21
A computer-implemented method for simulating capturing of images, comprising:
- generating a simulated document and a simulated camera using a three-dimensional modeling engine, wherein the simulated document comprises known text;
- capturing a plurality of images of the simulated document from a perspective of the simulated camera, each image of the plurality of images being captured under a different set of simulated circumstances within the three-dimensional modeling engine;
- making an adjustment to a parameter of a given image of the plurality of images;
- performing optical character recognition (OCR) to extract text from the given image;
- making a determination as to whether the adjustment to the parameter resulted in a successful OCR operation by comparing the text extracted from the given image to the known text of the simulated document;
- and
- training a model based at least on the plurality of images, the adjustment to the parameter, and the determination, wherein the model is trained to determine at least a first technique for adjusting a set of parameters comprising the parameter in a separate image to prepare the separate image for OCR.
A system, comprising:
- a processor;
- and
- memory storing instructions which, when executed on the processors, causes the processor to perform a method for simulating capturing of images, the method comprising:
- generating a simulated document and a simulated camera using a three-dimensional modeling engine, wherein the simulated document comprises known text;
- capturing a plurality of images of the simulated document from a perspective of the simulated camera, each image of the plurality of images being captured under a different set of simulated circumstances within the three-dimensional modeling engine;
- making an adjustment to a parameter of a given image of the plurality of images;
- performing optical character recognition (OCR) to extract text from the given image;
- making a determination as to whether the adjustment to the parameter resulted in a successful OCR operation by comparing the text extracted from the given image to the known text of the simulated document;
- and
- training a model based at least on the plurality of images, the adjustment to the parameter, and the determination, wherein the model is trained to determine at least a first technique for adjusting a set of parameters comprising the parameter in a separate image to prepare the separate image for OCR.
A non-transitory computer-readable medium comprising instructions that, when executed on one or more processors of a processing system, cause the processing system to perform a method for simulating capturing of images, the method comprising:
- generating a simulated document and a simulated camera using a three-dimensional modeling engine, wherein the simulated document comprises known text;
- capturing a plurality of images of the simulated document from a perspective of the simulated camera, each image of the plurality of images being captured under a different set of simulated circumstances within the three-dimensional modeling engine;
- making an adjustment to a parameter of a given image of the plurality of images;
- performing optical character recognition (OCR) to extract text from the given image;
- making a determination as to whether the adjustment to the parameter resulted in a successful OCR operation by comparing the text extracted from the given image to the known text of the simulated document;
- and
- training a model based at least on the plurality of images, the adjustment to the parameter, and the determination, wherein the model is trained to determine at least a first technique for adjusting a set of parameters comprising the parameter in a separate image to prepare the separate image for OCR.
Dependencies are inferred from the claim text.