An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

An image reading device includes a document placing table, and a cover. The cover is rotatably attached to the document placing table, and includes a receptacle for a portable terminal with a camera, the receptacle being configured to hold the portable terminal so that the camera faces the document placing table.

An image processing method for processing a display image includes using an image forming apparatus which includes a position detector detecting a position of contact with a display screen and forms an image on a recording medium based on a display image displayed on the display screen. The display image includes an object image indicative of an object for an image formation and a medium image indicative of the recording medium, and the image processing method includes modifying magnification of the object image with respect to the medium image, without modifying the medium image, based on contact positions of two points detected by the position detector.

Embodiments of the present disclosure include methods and systems for altering an orientation of a logical cell at a multi-function device. In one embodiment, before rasterization, a user submits a job having multiple pages and an initial instruction to arrange n number of pages on a single medium. Each page has a pre-defined orientation. Another instruction is received to alter a pre-defined orientation of a selected page in the corresponding logical cell. An N-up operation is performed to arrange the n number of pages on the single medium. Each page arranged on the single medium represents a logical cell. While performing the N-up operation, the pre-defined orientation of a logical cell corresponding to the selected page is altered. The logical cell with the altered orientation is printed and the remaining logical cells with respective pre-defined orientation are printed on the single medium.

Embodiments relate to automatic perspective and horizon correction. Generally, a camera captures an image as an image file. Capture-time orientation data from one or more sensors is used to determine the camera's attitude with respect to a defined reference frame. The orientation data and/or attitude can be registered into metadata of the image file and used to generate axis lines representative of the camera's reference frame. A reference line such as a horizon can be automatically identified from detected line segments in the image that align with one of the axis lines within a predetermined angular threshold. The reference line can be used to generate a camera transformation from a starting orientation reflected by the camera attitude to a transformed orientation that aligns the reference line with the reference frame. The transformation can be applied to the image to automatically correct perspective distortion and/or horizon tilt in the image.

Sonic embodiments provide an image editing application that edits an image. The image editing application displays an image in a display area. The image editing application displays a rotatable user interface item. In response to receiving a user input, the image editing application rotates the rotatable user interface item. The image editing application rotates the image displayed in the display area based on the rotation of the rotatable user interface item.

An image forming apparatus capable of making a match between the orientation of a reference side of a sheet along which punched holes are formed and the orientation of an output image on the sheet in double-sided printing. It is determined whether or not to rotate an image based on whether the image is printed in a single-sided printing mode or a double-sided printing mode. In the double-sided printing mode, a reverse-side image is printed on a first surface of the sheet, the sheet is conveyed into the printing section through a double-sided conveying path, a front-side image is printed on a second surface of the sheet, and the sheet is discharged. In the single-sided printing mode, an image for single-sided printing is printed on a first surface of the sheet, and the sheet is discharged.

A system and process are disclosed which provide users with a user-defined or custom-shaped print job from scanned data. A document may be scanned and an image object may be extracted from the scanned data which may be used as a print template from which the shape of a cut page is formed. Text and/or graphics may be applied to the page space occupied by the page shape area that will be cut. In an exemplary embodiment, the text and/or graphics may be automatically scaled or sized to fit within the boundary of the print template area. Once the page is cut, the text and/or graphics will automatically fit within the page's shape.

An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

A printing apparatus, including a printing device, a communication interface, a memory, and a controller, is provided. In a case where the controller determines that an image in image data is to be rotated and that a predetermined condition is satisfied, the controller conducts rotation of the image in the image data concurrently with rasterization of the image data and stores raster data including the rotated image in the memory. In a case where the controller determines that the image in the image data is to be rotated and that the predetermined condition is not satisfied, the controller conducts rasterization of the image data without rotating the image in the image data, and rotates a raster image in the raster data stored in the memory and generates the print data from the raster data including the rotated raster image.