Intuit, Inc.

Kimia Hassanzadeh

Richard J Becker

Cole MacKenzie

Gregory Kenneth Coulombe

Greg Coulombe

Richard Becker

Cole Mackenzie

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).

Simulating image capture

Field extraction from a form image includes identifying a target field of the form image, defining a patch from the form image based on the target field, and encoding the patch using a color encoding scheme to obtain an encoded patch. Field extraction further includes applying a trained classifier to the encoded patch to identify a relationship between a field value and a field identifier, and extracting the field value from the form image according to the relationship.

Form image field extraction

A method for schematizing fields in documents involves segmenting an image of a document into snippets, classifying a first, a second, and a third snippet of the snippets as a first label, a second label, and a data field, respectively. The method further includes generating, for a combination of the first label and the data field, a first image to be classified, and classifying the first image to be classified to obtain a first classification score. The method further includes generating, for a combination of the second label and the data field, a second image to be classified, and classifying the second image to be classified to obtain a second classification score. The method also includes determining that the first classification score is greater than the second classification score and identifying, based on the determining step, that the data field is associated with the first label.

Growing community of inventors

Edmonton, Canada

Kimia Hassanzadeh