A reading device is configured to detect an edge position of a target object to be conveyed in a conveyance direction. The edge position is a position of an edge of the object in a width direction intersecting the conveyance direction. The reading device includes a sensor device, an adder, and an edge position detector. The sensor device includes a pixel array including a plurality of elements arranged in the width direction. The adder is configured to add detection signals output from the elements at respective positions in the width direction. The edge position detector is configured to detect the edge position on basis of a position at which an output of the adder changes to a value larger than a threshold. Each element is configured to output a detection signal based on a reception amount of light in one of different wavelength bands.

A reading apparatus includes: a reading unit reading a document; a determination unit determining whether or not inclination correction of a document image is performed based on a shape of a circumscription image which is a circumscribed rectangle of the document image read from the document; and an output unit outputting an image according to a determination result.

The image forming apparatus sets, as a cutting area, an area containing an image of a double-page spread out of image data obtained by a scan of a book-type document, sets a borderline which divides an area corresponding to one page of the image data and an area corresponding to the other page of the image data from each other, and divides the cutting area cut out from the image data into a one-side area of the borderline and the other-side area of the borderline, thereby generating a first pre-output page in which divided image data of the one-side area is provided and a second pre-output page in which divided image data of the other-side area is provided.

An image processing apparatus includes a line memory, a block outputting unit, a data writing unit, a data reading unit, and a controller. To the line memory, a memory area is allocated, and the memory area has a width of a constant number of words in a static RAM (Random Access Memory). The block outputting unit is configured to output image data of an image block obtained by dividing a document image. The data writing unit is configured to write the image data of the image block into the line memory. The data reading unit is configured to read the image data from the line memory word by word, and output the image data in an order corresponding to a rotation angle. The controller is configured to set a block size of the image block as a value corresponding to the rotation angle.

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.

A read circuit outputs input pixel blocks to a line buffer. An arithmetic processing circuit reads an input pixel block from the line buffer and executes rotation processing to derive an output pixel block. A controller sets an output block height to the largest integer fraction of an output band height so that the output pixel block fits within an input band in an input pixel coordinate system, extends the width of the output pixel block so that the output pixel block fits within a maximum width of the input pixel block in the input pixel coordinate system, reduces the width of the output pixel block according to the size of the output pixel block in the input pixel coordinate system and the number of pixel lines in the line buffer, and sets the size of the input pixel block based on the size of the output pixel block.

A read circuit outputs input pixel blocks to a line buffer. An arithmetic processing circuit reads an input pixel block from the line buffer and executes rotation processing to derive an output pixel block. A controller sets an output block height to the largest integer fraction of an output band height so that the output pixel block fits within an input band in an input pixel coordinate system, extends the width of the output pixel block so that the output pixel block fits within a maximum width of the input pixel block in the input pixel coordinate system, reduces the width of the output pixel block according to the size of the output pixel block in the input pixel coordinate system and the number of pixel lines in the line buffer, and sets the size of the input pixel block based on the size of the output pixel block.

An image forming apparatus including: an exposure head including light emitting elements arranged in an intersecting direction intersecting with a rotation direction of a photosensitive member to form an image at a first resolution corresponding the light emitting elements in the intersecting direction; a data generating unit configured to generate pixel data corresponding to a second resolution higher than the first resolution associating with positions of the pixel data; a correction unit configured to correct associations between the positions and the pixel data to adjust a position of an image in the intersecting direction; a conversion unit configured to convert the pixel data corresponding to the second resolution to pixel data corresponding to the first resolution; and a drive unit configured to drive the light emitting elements based on the pixel data corresponding to the first resolution.

An image processing apparatus includes a processor configured to: extract a first target image corresponding to a reading target having a glossy portion and a non-glossy portion from a first read image acquired by optically reading the reading target in a first reading environment, and extract a second target image corresponding to the reading target from a second read image acquired by optically reading the reading target in a second reading environment in which specular light acquired from the reading target by an image sensor is of higher intensity compared to the first reading environment; execute an alignment of the first target image and the second target image if positions of the first and second target images do not coincide with each other and if the first and second target images are alignable by translating or rotating at least one of the first target image or the second target image; and form a composite image by executing a composition process that composites a non-glossy region corresponding to the non-glossy portion extracted from the first target image with a glossy region corresponding to the glossy portion extracted from the second target image.

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.