Aspects of the present disclosure provide methods and apparatuses for processing a digital image of a document, for example, to determine whether the document is a long document. An exemplary method generally includes obtaining a plurality of digital images of the document, segmenting at least a first digital image of the plurality of images into pixels associated with a foreground of the first digital image and pixels associated with a background of the first digital image, detecting a plurality of contours in the segmented first digital image, deciding, for each detected contour of the plurality of contours, whether that contour is an open contour or a closed contour, and determining that one or more sides of the document is out of bounds based, at least in part, on the decisions.

Provided are systems and methods for identifying, isolating, and/or aligning sheets. An identification system can facilitate accurate identification of a sheet by (i) vacating one or more components of the system that are not the sheet from a zone of detection, and/or (ii) determining a reference axis of the sheet. An isolation system can facilitate accurate isolation of a sheet by (i) providing targeted air flow, and/or (ii) introducing a wave into the sheet. Identification systems and/or isolation systems described herein may facilitate isolation of sheets that were previously fastened together by one or more fasteners. An alignment system can facilitate accurate alignment of a first sheet at an upstream location relative to a second sheet at a downstream location via machine learning.

An image processing device includes a printing unit printing an image on a sheet including first and second tags. The first and second tags have first and second antennas extending along first and second directions. The device further includes a tag reading unit including a third antenna and configured to transmit, towards the sheet from the third antenna, first radio waves polarized in the first direction and second radio waves polarized in the second direction in each of a first period during which the sheet is conveyed towards the third antenna and a second period during which the sheet is conveyed away from the third antenna, and determine an orientation of the sheet based on intensities of third radio waves polarized in the first direction and fourth radio waves polarized in the second direction, which have been received by the third antenna in each of the first and second periods.

An image forming apparatus includes an image reading unit. When printing a postcard is selected, a preview screen including a preview image about an image on a communication side of the postcard read by the image reading unit is displayed on a display. At this occasion, an instruction image indicating an orientation of an address side of the postcard is also displayed. When it is instructed to turn over the preview image on the communication side, the preview screen including the preview image on the address side is displayed on the display. When the orientation of the address side and the orientation of the communication side do not coincide with each other, or when they are not as intended by a user, printing is performed after the image on the communication side is rotated according to the user's operation.

An image reading device includes: a document delivery unit for delivering a document loaded on a document loading platform to a document transport path; a flip-up detector for detecting flip-up of the document when the document is delivered; a metal detector for detecting metal attached to the document when the document is delivered; and a staple determination unit for determining whether or not a stapling process is applied to the document based on detection results of the flip-up detector and the metal detector.

A verification apparatus includes a reading unit configured to read an image of a conveyed sheet. The apparatus obtains a reference image for verification of a sheet, and extracts, from the reference image, feature points to be used for alignment of an image with the reference image. The apparatus aligns, with the reference image, a read image obtained by reading an image of a verification target sheet by the reading unit, and verifies the read image by comparing the aligned read image with the reference image. Based on a number of the feature points extracted from the reference image the alignment is performed using positions of the feature points or using positions of sheet vertices each indicating a corner of the sheet.

A control unit of an image reading apparatus determines, based on results of detection of an original document by a plurality of second detecting units, whether the original document will pass a position at which the original document is to be detected by a first detecting unit that is located downstream of the second detecting units and upstream of a reading unit. When it is determined that the original document will not pass a position at which the original document is to be detected by the first detecting unit, the control unit determines a timing for reading the original document by using the reading unit, relative to a time point at which the original document is detected by the second detecting units. The control unit causes the reading unit to read the original document at the determined reading timing.

Provided are systems and methods for identifying, isolating, and/or aligning sheets. An identification system can facilitate accurate identification of a sheet by (i) vacating one or more components of the system that are not the sheet from a zone of detection, and/or (ii) determining a reference axis of the sheet. An isolation system can facilitate accurate isolation of a sheet by (i) providing targeted air flow, and/or (ii) introducing a wave into the sheet. Identification systems and/or isolation systems described herein may facilitate isolation of sheets that were previously fastened together by one or more fasteners. An alignment system can facilitate accurate alignment of a first sheet at an upstream location relative to a second sheet at a downstream location via machine learning.

An image processing apparatus includes circuitry to: obtain a read image read from an image of a document output from an image reading device; detect an edge between a background area and a document area in the read image; sample a detection result of the edge at each first interval in a first direction to extract a first boundary point group including a plurality of boundary points; sample the detection result of the edge at each second interval in the first direction to extract a second boundary point group including a plurality of boundary points; determine a noise removal condition based on the first boundary point group; remove, from the second boundary point group, a boundary point satisfying the noise removal condition as noise; and calculate a linear equation approximating the second boundary point group from which the noise is removed.

An image processing apparatus includes: an automatic document feeder; a document placement table; a document detector provided on at least one of the automatic document feeder and the document placement table, the document detector being configured to detect a document; and circuitry to cause a display to display one of a first screen that receives an input for selecting an orientation of a document placed on the automatic document feeder and a second screen that receives an input for selecting the orientation of the document placed on the document placement table, based on a detection result of the document detector.