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.

Some 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 scanning device has a platen, an openable cover, a cover sensor, a scanning unit, a condition setting unit enabling a user to set a first condition, and a controller. The controller is configured to detect an opening state of the cover based on a detection signal output by the cover sensor and obtain the image data representing a partial image which is an image of a first end portion of a scannable area of the scanning unit. When the cover is in the closed state, the controller applies an image processing based on the first condition set through the condition setting unit, and when the cover is in the opened state, the controller applies the image processing based on a second condition which is a particular condition set in advance and different from the first condition.

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 forming apparatus and method for rotating a generated print image are provided. The image forming apparatus includes a print engine to form an image on a printing paper and a processor to generate a print image corresponding to print data, rotate the generated print image so that the generated print image corresponds to a user setting orientation if a default output orientation of the image forming apparatus is different from the user setting orientation, and control the print engine to print the rotated print image.

An image processing apparatus includes an image input unit and a control unit. Through the image input unit, a first image including an insertion area and a second image different from the first image are input. The control unit functions as an image acquisition section, an insertion area detection section, an insertion image detection section, and an image processing section. The image acquisition section acquires the first image and the second image input through the image input unit. The insertion area detection section detects the insertion area from the first image. The insertion image detection section detects an insertion image from the second image. The image processing section generates a third image by inserting the insertion image into the insertion area.

An image forming apparatus performs a halftone process using plural dither matrices. Generated is calibration data to calculate a color registration error amount corresponding to a primary scanning directional position of an image forming available width. An image area dividing unit determines an image boundary position that is identical to any of matrix boundaries of plural dither matrices arranged in an image forming target area, and divides the image forming target area into plural image adjustment areas using the image boundary position. A correction processing unit corrects secondary scanning directional positions of the plural image adjustment areas, using respective correction amounts calculated with the calibration data. Further, the image area dividing unit determines the image boundary position using a remainder left by dividing in the primary scanning direction the number of pixels of the image adjustment area by the number of pixels of the dither matrix.

Dyslexic friendly and readable images are provided. Each image includes one or more positioned, non-linear (i.e., curved) boundaries and a plurality of textual objects, where each object is positioned at a distance from the boundaries and follows a boundary.

Some embodiments of the present disclosure provide a Contact Image Sensor (CIS), including a light source, a lens, a light-sensing portion receiving light converged by the lens, a sensor substrate carrying photosensitive Integrated Circuits (IC) arranged linearly, a frame accommodating the lens and the sensor substrate, and a light-transmitting plate provided on an upper part of the frame and configured to carry an original pattern. The CIS further includes a linear magnifying lens, provided between the light-transmitting plate and the lens, the linear magnifying lens having a characteristic of linearly magnifying an object in a single direction. The CIS involved in some embodiments of the present disclosure is capable of enhancing resolution in a single direction.

An application that transmits a print job to an image forming apparatus includes: an image obtaining unit that obtains an image to be edited; a print setting obtaining unit that obtains print setting information; a display control unit that displays an image edit screen including the image and a print range frame based on the print setting information; an arrangement edit accepting unit that accepts an edit operation of arrangement of the image in the image edit screen; an output image data generating unit that generates image data in which a predetermined image is combined in a region where no image is arranged in the print range frame, in response to input of a print instruction after the edit operation; and a print job transmitting unit that transmits the generated image data and the print setting information to the image forming apparatus as the print job.