Abstract: In a collection technique, a user (such as a taxpayer) provides information (such as income-tax information) by submitting an image of a document, such as an income-tax summary or form. In particular, the user may provide a description of the document. In response, the user is prompted for the information associated with the field in the document. Then, the user provides the image of a region in the document that includes the field. Based on the image, the information is extracted, and the field in the form is populated using the extracted information. The prompting, receiving, extracting and populating operations may be repeated for one or more additional fields in the document.

Abstract: A technique for collecting income-tax information is described. This collection technique allows a user (such as a taxpayer) to provide income-tax information by submitting an image of a document, such as an income-tax summary or form. After receiving the image, the income-tax information is extracted from the document, and a subset of the income-tax information that is relevant to the user is determined. This subset of the income-tax information is then provided to the user for validation, and the user subsequently provides feedback about the subset of the income-tax information, such as acceptance of the subset or correction of any errors. Furthermore, after receiving the user feedback, fields in an income-tax return of the user may be populated using the subset of the income-tax information.

Abstract: A technique for providing feedback about an image of a financial document to a user is described. During this feedback technique, the user provides the image of a financial document, such as W-2 form. For example, the user may take a picture of or may scan the financial document. This image may be analyzed using predefined information in a set of financial documents (such as different types of income-tax documents), and a quality metric for the image may be determined using the analysis. Moreover, the feedback, which is based on the determined quality metric, may be provided to the user. For example, the user may be instructed to retake the image, and the instructions may include an image of the desired orientation and content. In this way, the user may be advised as to how to improve the quality metric in the revised image.