Document information extraction using geometric models

A receipt processing system includes at least one imaging device which generates an image of a paper receipt. At least one processor programmed to acquire the image of a paper receipt from the at least one imaging device, textualize the data from the acquired receipt image, define specific local partial models based on regular expressions and geometric proximity, extract information from the textualized data according to the local partial models, apply rules to the extracted information, and generate receipt data from the application of the rules.