A controller of an image reading device performs search for an edge candidate position inward from an edge portion in a main scanning direction of analysis image data in an extraction process of extracting a document region from read image data. When the retrieved edge candidate position corresponds to a dirt position, the search is continued whereas when the retrieved edge candidate position does not correspond to the dirt position, the document region is extracted from the read image data at the retrieved edge candidate position.

A controller of an image reading device performs search for an edge candidate position inward from an edge portion in a main scanning direction of analysis image data in an extraction process of extracting a document region from read image data. When the retrieved edge candidate position corresponds to a dirt position, the search is continued whereas when the retrieved edge candidate position does not correspond to the dirt position, the document region is extracted from the read image data at the retrieved edge candidate position.

Use of improved image acquisition for a medical dose preparation system. The medical dose preparation system may include a work station for capturing medical dose preparation images (e.g., to document preparation of a mediation dose). The medical dose preparation image may be captured by a video data stream processor capable of performing an auto cropping technique on a video data stream received from an image device. Accordingly, memory resources may be more efficiently employed while maintaining high quality medical dose preparation images.

Use of improved image acquisition for a medical dose preparation system. The medical dose preparation system may include a work station for capturing medical dose preparation images (e.g., to document preparation of a mediation dose). The medical dose preparation image may be captured by a video data stream processor capable of performing an auto cropping technique on a video data stream received from an image device. Accordingly, memory resources may be more efficiently employed while maintaining high quality medical dose preparation images.

A CNN of an image forming apparatus includes: an encoder which compresses, for each tile image obtained by dividing an image into specific size pieces, information of the tile image; a decoder which restores the information of the tile image compressed by the encoder; and a blank sheet determination portion which determines whether the tile image corresponds to a blank sheet image. A segmentation image generation portion uses, when the blank sheet determination portion determines the tile image as being the blank sheet image, the blank sheet image for an image of a part corresponding to the tile image in a segmentation image, and uses, when the blank sheet determination portion determines the tile image as not being the blank sheet image, an output image of the decoder for an image of a part corresponding to the tile image in the segmentation image.

A CNN of an image forming apparatus includes: an encoder which compresses, for each tile image obtained by dividing an image into specific size pieces, information of the tile image; a decoder which restores the information of the tile image compressed by the encoder; and a blank sheet determination portion which determines whether the tile image corresponds to a blank sheet image. A segmentation image generation portion uses, when the blank sheet determination portion determines the tile image as being the blank sheet image, the blank sheet image for an image of a part corresponding to the tile image in a segmentation image, and uses, when the blank sheet determination portion determines the tile image as not being the blank sheet image, an output image of the decoder for an image of a part corresponding to the tile image in the segmentation image.

A multi-mode scanning device for scanning an original includes a non-transparent element, a first light source, a second light source and an optical module. The first light source outputs visible light to irradiate the non-transparent element and the original to generate first light and second light, respectively. The second light source outputs invisible light to irradiate a combination of the non-transparent element and the original to generate third light and fourth light. The optical module receives the first light, the second light, the third light and the fourth light and generates sensing signals representative of visible light information and invisible light information of the original. The original is disposed between the non-transparent element and the optical module. The first light source and the optical module are disposed on a same side of the non-transparent element.

Some implementations relate to determining whether glare is present in captured image(s) of an object (e.g., a photo) and/or to determining one or more attributes of any present glare. Some of those implementations further relate to adapting one or more parameters for a glare removal process based on whether the glare is determined to be present and/or based on one or more of the determined attributes of any glare determined to be present. Some additional and/or alternative implementations disclosed herein relate to correcting color of a flash image of an object (e.g., a photo). The flash image is based on one or more images captured by a camera of a client device with a flash component of the client device activated. In various implementations, correcting the color of the flash image is based on a determined color space of an ambient image of the object.

Some implementations relate to determining whether glare is present in captured image(s) of an object (e.g., a photo) and/or to determining one or more attributes of any present glare. Some of those implementations further relate to adapting one or more parameters for a glare removal process based on whether the glare is determined to be present and/or based on one or more of the determined attributes of any glare determined to be present. Some additional and/or alternative implementations disclosed herein relate to correcting color of a flash image of an object (e.g., a photo). The flash image is based on one or more images captured by a camera of a client device with a flash component of the client device activated. In various implementations, correcting the color of the flash image is based on a determined color space of an ambient image of the object.

An inspection apparatus performs dropout color processing on a first inspection area set for an image generated by reading a print product and then performs first recognition processing on the first inspection area, and further performs second recognition processing on a second inspection area set for the image and then performs an inspection of whether sufficient margin areas are allocated on the second inspection area, without performing dropout color processing.