The embodiments herein relate to a method performed by a system (100) for handling variations in a mark (110) printed by a group (105) of industrial printers (101). The system (100) obtains images of the printed mark (110) printed by each of the printers (101) in the group (105). The system (100) creates a composite image from the obtained images. The printed marks (110) appear as a repeating pattern in the composite image. The system (100) compares the printed marks (110) in the composite image to each other or to another mark. The system (100) detects variations with a first resolution in the printed marks (110) in the composite image as a result of the comparison. The system (100) creates an augmented image in which the detected variations are augmented to a second resolution. The first resolution is lower than the second resolution.

A first conversion into pixels of an obtained object, for which the processing for widening the width of the object is performed, is performed, and a second conversion into pixels of the object, for which the processing for widening the width of the object is not performed, is performed. When the first conversion is performed, a pixel is filled or is not filled with color depending on a position of a boundary of the object in the pixel. When the second conversion is performed, a pixel is filled with color if the position of the boundary of the object exists in the pixel.

A first conversion into pixels of an obtained object, for which the processing for widening the width of the object is performed, is performed, and a second conversion into pixels of the object, for which the processing for widening the width of the object is not performed, is performed. When the first conversion is performed, a pixel is filled or is not filled with color depending on a position of a boundary of the object in the pixel. When the second conversion is performed, a pixel is filled with color if the position of the boundary of the object exists in the pixel.

At the time of registering an image in units of documents, which is obtained by performing multi-cropping processing for a scanned image, and value information extracted from each image in a database in association with each other, there is a case where it is not possible to extract the value information successfully because of an overlap between documents during a scan. In a case where this fact is noticed after registration, it becomes necessary for a user to perform the entire work from the beginning. In a case where there is a possibility that the value information is hidden by an overlap between documents during a scan or the like, a display is produced for prompting a user to scan the document again.

At the time of registering an image in units of documents, which is obtained by performing multi-cropping processing for a scanned image, and value information extracted from each image in a database in association with each other, there is a case where it is not possible to extract the value information successfully because of an overlap between documents during a scan. In a case where this fact is noticed after registration, it becomes necessary for a user to perform the entire work from the beginning. In a case where there is a possibility that the value information is hidden by an overlap between documents during a scan or the like, a display is produced for prompting a user to scan the document again.

An image processing apparatus includes circuitry to determine a type of a document based on a determination result of a character area and a non-character area in an input image of the document; select a model to be used in top-bottom determination from a plurality of models based on the type of the document; reduce the input image, to generate a reduced image; and cut out a part of the input image as a partial image. The circuitry outputs a top-bottom determination result of the input image using the selected model and one of the reduced image and the partial image corresponding to the model.

An image processing apparatus includes circuitry to determine a type of a document based on a determination result of a character area and a non-character area in an input image of the document; select a model to be used in top-bottom determination from a plurality of models based on the type of the document; reduce the input image, to generate a reduced image; and cut out a part of the input image as a partial image. The circuitry outputs a top-bottom determination result of the input image using the selected model and one of the reduced image and the partial image corresponding to the model.

A method, non-transitory computer readable medium and apparatus for generating an output image are disclosed. For example, the method includes receiving an image, applying a first filter, applying a second filter, calculating a difference between the image with the second filter that was applied and the image with the first filter that was applied and transmitting the difference to a sharpening module and a segmentation module to generate the output image.

A method, non-transitory computer readable medium and apparatus for generating an output image are disclosed. For example, the method includes receiving an image, applying a first filter, applying a second filter, calculating a difference between the image with the second filter that was applied and the image with the first filter that was applied and transmitting the difference to a sharpening module and a segmentation module to generate the output image.

In one example, an image processing device includes a reduction scaler unit that reduces or maintains the image data of an input image. An enlargement scaler unit enlarges or maintains the image data and outputs the image data as the image data of an output image. The reduction scaler unit converts the resolution of the input image to an intermediate resolution in accordance with first image parameters related to an image to be supplied from the enlargement scaler unit, the intermediate resolution being a resolution for performing writing on the memory unit. The enlargement scaler unit converts the intermediate resolution of a memory-held image read from the memory unit to the resolution of the output image, in accordance with second image parameters related to an image to be supplied from the reduction scaler unit.