Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, to generate a scannable document. In one aspect, a method includes receiving a scan request, wherein the scan request includes a plurality of text images; for each text image of the plurality of text images: rectifying the text image to generate a text image with parallel image lines, generating a plurality of word bounding boxes that enclose one or more connected components in the text image, wherein each word bounding box is associated with a respective word, and generating, for each respective word in the text image, a plurality of points that represent the respective word; combining the plurality of text images to form a single text document; and providing the combined image as a scannable document.

An apparatus for providing guidance for image capture includes a recognition module that recognizes data objects in data available to an image capture device. At least a portion of the data includes characters. The apparatus includes a context module that determines a context associated with a first image available from the image capture device. The context includes one or more expected data objects, where the first image includes at least a portion of the recognized data objects. The apparatus includes a data module that compares the expected data objects for the determined context, with the recognized data objects from the first image to identify missing expected data objects not found in the first image. The apparatus includes a guidance module that, in response to identified missing data, provides guidance for capturing a second image expected to include the missing expected data objects.

The present disclosure is concerned with the technical field of marking objects with optically readable codes and reading out (decoding) the codes. Subjects of the present disclosure are a method, a system and a computer program product for decoding optically readable codes introduced in surfaces of objects.

An information processing apparatus capable of displaying an image on a predetermined display unit, includes: a reception unit that receives a written input on an image according to an operation of a user in a state where the image is displayed on the display unit; a generation unit that generates a written object according to the written input received by the reception unit; a reference detection unit that detects a reference direction of the image displayed on the display unit; a correction unit that corrects the written object on the basis of the reference direction detected by the reference detection unit; and a display control unit that displays the written object generated by the generation unit.

An imaging device in which an imaging sensor that captures an image and a display unit that displays the image are provided includes: an image processing unit configured to perform roll correction on the image; a control unit configured to control an output of the image; and a display control unit configured to display the output image on the display unit. The image processing unit performs the roll correction such that a degree of correction of the roll correction when the image is to be output to only the display unit is less than a degree of correction of the roll correction when the image is to be output to the display unit and an output destination other than the display unit.

A computer-implemented method of identifying a payment card design includes partitioning an image of a detected payment card into a plurality of blocks, the image comprising predetermined portions irreversibly masked; and generating an individual numerical representation of each respective one of the plurality of blocks, thereby generating a collective numerical representation of the design of the detected payment card. The method also includes selecting, from a database storing a plurality of payment card designs, one or more payment card designs based on the collective numerical representation of the design of the detected payment card. The method further includes generating a similarity score between the design of the detected payment card and each of the one or more selected payment card designs; and associating the design of the detected payment card with one of the one or more selected payment card designs based on the similarity score.

Systems and methods for mobile enrollment in automated clearing house (ACH) transactions using mobile-captured images of financial documents are provided. Applications running on a mobile device provide for the capture and processing of images of documents needed for enrollment in an ACH transaction, such as a blank check, remittance statement and driver's license. Data from the mobile-captured images that is needed for enrolling in ACH transactions is extracted from the processed images, such as a user's name, address, bank account number and bank routing number. The user can edit the extracted data, select the type of document that is being captured, authorize the creation of an ACH transaction and select an originator of the ACH transaction. The extracted data and originator information is transmitted to a remote server along with the user's authorization so the ACH transaction can be setup between the originator's and receiver's bank accounts.

A distortion correction component of a mobile device receives an image of a spread open multi-page document, determines a binding edge line of the spread open multi-page document, determines a first set of substantially vertical straight lines lying left of the binding edge line and a second set of substantially vertical straight lines lying right of the binding edge line. The distortion correction component then determines a first vanishing point based on the first set of substantially vertical straight lines and a second vanishing point based on the second set of substantially vertical straight lines. A first quadrangle is determined based on the first vanishing point and a second quadrangle is determined based on the second vanishing point. A corrected image for the first page is generated based on the first quadrangle and a corrected image for the second page is generated based on the second quadrangle.

Image classification techniques are described for adjustment of an image. In one or more implementations, an image is classified by one or more computing device based on suitability of the image for adjustment to correct perspective distortion of the image. Responsive to a classification of the image as not suitable for the adjustment, suitability of the image is detected for processing by a different image adjustment technique by the one or more computing devices.

A computer-implemented method for aligning a set of images which have shared structural characteristics, such as images of an official document. The method comprises acquiring image data comprising a set of images and applying, using a first deep neural network, at least one image transform to the image data to form aligned image data in which each image of the set of images is substantially aligned with a template image. Then, the aligned image data is compressed and the image data reconstructed from the compressed image data, and a set of aligned images is output from the reconstructed image data. The set of aligned images may be annotated for automated official document authentication.