Dainippon Screen Mfg. Co., Ltd.

Screen Holdings Co., Ltd.

Dainippon Screen Manufacturing Co., Ltd.

Ricoh Company, Ltd.

Dainippon Screen Mfg., Ltd.

Atsushi Imamura

Nobuaki Usui

Hiroshi Sano

Junichi Shiomi

Eiji Nishihara

Hiroki Fujimoto

Tomotaka Kato

Shiro Koike

Hiroshi Asai

Seiya Nomura

Takuya Yasuda

Kazutaka Taniguchi

Yuji Kurokawa

Kazuhiro Kitamura

Yasuhiro Takemoto

Toshihiro Sato

Yumi Hayakawa

Toshiriro Sato

Shirou Koike

Tomohisa Mizuta

After a difference image between original image and calibration image is generated, a candidate image of an edge region is generated. Thereafter, an edge image is generated based on the original image, the calibration image, and the candidate image. At that time, the processing target pixel (pixel constituting the candidate image) is determined to be a pixel constituting the edge region when a difference between a pixel value of at least one of nine comparison target pixels in the original image and a pixel value of the processing target pixel in the calibration image is less than or equal to a first threshold value, and when a difference between a pixel value of at least one of nine comparison target pixels in the calibration image and a pixel value of the processing target pixel in the original image is less than or equal to the first threshold value.

Image comparison method, image comparison device, and non-transitory computer-readable recording medium recording image comparison program

A printing apparatus includes a head part, an encoder, a tension sensor, a head part temperature sensor, an edge sensor, an estimation part, a storage, and an output part. The estimation part estimates print quality in terms of a page printed by the head part on the basis of variation elements detected by the encoder, the tension sensor, the head part temperature sensor, and the edge sensor. The storage stores print quality information containing the printed page and the print quality estimated by the estimation part in association with each other. The output part outputs the print quality information to a display, a post-processing device, and a printer controller section.

Printing apparatus and printing system for detecting print quality based upon a detected variation

A method for building an image determination model that determines whether a print image is a good image or a failure image includes a step of determining whether the print image is a high-density image or a low-density image; a step of generating teaching data by combining pseudo-failure data with to-be-combined image data, based on a result of the determination; and a step of performing machine learning. Regarding the combining of the pseudo-failure data, for a print image determined to be the high-density image, low-density pseudo-failure data is combined with to-be-combined image data, and for a print image determined to be the low-density image, high-density pseudo-failure data is combined with to-be-combined image data.

Method for building image determination model, image determination model, and image determination method

Disclosed is an inkjet printing apparatus including a printing head, an overcoating head discharging an overcoating agent, and a controller operating the printing head and the overcoating head to perform printing to a print medium. The controller operates in a normal discharge mode having a printing rate in the print medium relative to a given area of less than 100% for printing to the print medium, and an inspecting discharge mode having a printing rate in the print medium relative to the given area higher than the printing rate of the normal discharge mode for confirming a discharge state of the overcoating agent. In the inspecting discharge mode, the controller operates the printing head to form an inspecting region on the print medium, and operates the overcoating head to discharge the overcoating agent onto the inspecting region, whereby an overcoating inspecting chart is formed.

Inkjet printing apparatus and printing method of inspecting chart therewith

A mask generating unit generates a show-through area mask in accordance with inverted front printed image data, obtained by inverting front printed image data in a horizontal direction, and back printed image data. Then, a determining unit inspects a show-through area of the back inspecting image data corresponding to the show-through area mask with a show-through inspection threshold. Consequently, an area where the show-through exists with high possibility is inspected with the looser show-through inspection threshold. This achieves suppression of determination error due to the show-through. On the other hand, an area where no show-through exists with high possibility is inspected with a tight normal inspection threshold. This achieves accurate determination of printing error. As a result, accurate printing inspection is obtainable even to web paper with the show-through.

Printed image inspecting apparatus and printed image inspecting method

An image reading apparatus includes two color line cameras and one monochrome line camera and captures a linear imaging area on printing paper. The imaging area is irradiated with illumination light by a line illumination part. When inspecting a printed image, a color image captured with the color line cameras and an original image are compared. An information element image such as a bar code is clipped from a monochrome image captured with the monochrome line camera, and target information indicated by an information element(s) is acquired. In the image reading apparatus, since the color image and the monochrome image are acquired from the same imaging area, it is possible to realize downsizing of the line illumination part and downsizing of the image reading apparatus.

Image reading apparatus, image inspection apparatus, printing apparatus, and camera position adjustment method

An image inspection apparatus includes a pre-printed element reduction section that reduces influence of a pre-printed element on inspection and generates an inspection object image, and a comparative inspection section that compares the inspection object image with the additionally-recorded data, to inspect a performance level of a result of overprinting. Captured image data of the pre-printed paper image and the overprinted image is given to the pre-printed element reduction section. By using the captured image data of the pre-printed paper image, the pre-printed element reduction section reduces the pre-printed element included in the captured image data of the overprinted image and newly prepares the inspection object image.

Apparatus and method for analyzing the performance level of overprinting

A head in a printer has an outlet row including a plurality of outlets arranged in a width direction perpendicular to a scan direction. A threshold matrix is stored in a main body control part, and sleep elements representing sleep of ejection of ink are arranged in the threshold matrix at a regular interval in each element row which is a plurality of elements arranged in a row direction corresponding to the width direction. The threshold matrix is compared with a grayscale original image to generate data of a halftone image where during printing, the number of outlets included in each outlet group not brought into sleep state continuously in the width direction is made equal to or larger than 1 and equal to or smaller than a predetermined number. Thus, it is possible to easily suppress occurrence of unevenness in a printed image, caused by cross talk between outlets.

Image data generating method, printing method, image data generating apparatus, and printer

The present invention provides a technique to identify layout of surface regions of an object by image area segmentation. A plurality of images is acquired by imaging an object under a plurality of mutually different illumination conditions. By performing area segmentation on this plurality of images, the layouts of the plurality of image areas which is different from the layout of the object surface regions is obtained. Then, the layout of the surface regions on the object is identified based on the layouts of the plurality of image areas.

Surface region identification by image area segmentation

A pattern-element extractor (), one of functions implemented by a computer, extracts a plurality of pattern elements from a reference image, a region of which is displayed on a display (). An input part () accepts an operator's selection of one out of the plurality of pattern elements as a reference pattern element, and a distinguishability checker () checks whether the selected pattern element is distinguishable from the other pattern elements and usable as the reference pattern element for pattern matching. A result of the check is notified to the operator, and an appropriate one out of the pattern elements in the reference image can be selected as the reference pattern element, by referring to the result of the check made by the distinguishability checker (). Thus, misrecognition of the reference pattern element used for detecting a position of a target image relative to the reference image in pattern matching is prevented.

Apparatus, method, and program for assisting in selection of pattern element for pattern matching

The present invention provides a technique to improve reliability of area segmentation result of an image into a plurality of image areas. A plurality of representative colors and a weight associated with each of the representative colors are determined. A weighted color difference index values associated with the representative colors are calculated according to the weights, respectively, with respect to each pixel constituting the image. The weighted color difference represents difference in color between an individual color representing color of each pixel constituting the image and each of the representative colors. Then, according to the weighted color difference index values, color of each pixel is classified into one of representative color regions associated with the representative colors, to perform segmentation of the image into the plurality of image areas.

Segmentation technique of an image

A color image of a circuit board is divided into respective color regions. Plural representative colors are set, and angle indices and distance indices are calculated for each pixel color in the color image in a predetermined color space. The angle indices for a particular pixel color represent angles between an individual color vector representing the particular pixel color and plural representative color vectors of the plural representative colors. The distance indices for a particular pixel color represent distances between the particular pixel color and the plural representative colors. Composite distance indices are then calculated for each pixel color in the color image, based on the distance indices and the angle indices. Each pixel in the color image is classified into plural representative color regions associated with the plural representative colors according to the composite distance indices, thereby dividing the image region of the color image into the plural representative color regions.

Region segmentation of color image

A two-dimensional image of a substrate surface targeted for polishing is periodically picked up, and the image is analyzed to obtain an entropy H, Hof the two-dimensional image. An end point of polishing is then determined according to the entropy H, H. Alternatively, other image characteristic value such as a difference statistic of the image may be employed instead of the entropy H, H

Detection of an end point of polishing a substrate

An illuminance spectrum I of reflected light from a color print of an N-order color having an arbitrary dot percent d.sub.1-N is defined by a diffuse reflection coefficient Sb(d.sub.1-N,.lambda.) and a specular reflection coefficient Ss(d.sub.1-N,.lambda.). These reflection coefficients are obtained in the following manner. A plurality of reference colors are specified on each of N.times.2.sup.(N-1) sides that constitute an N-dimensional color space including the N-order target color. Each reflection coefficient is expressed by a linear combination of a plurality of reference reflection coefficients Sb and Ss, which are set in advance for the plurality of reference colors. The illuminance spectrum of reflected light is then determined according to these reflection coefficients Sb and Ss. Color data representing the colors of the print in a colorimetric system suitable for an output device are subsequently generated from the illuminance spectrum.

Method and apparatus for simulating color print

An N-dimensional correction space is constructed with weighting coefficients .xi. and .eta. that are used for determining reflection coefficients for an N-order target color, where the weighting coefficients .xi. and .eta. specify the lengths of the sides constituting the N-dimensional correction space, and where 2.sup.N reference colors are located at the corners of the N-dimensional correction space. The N-dimensional correction space is divided by N pieces of (N-1)-dimensional spaces that run through the target color, into 2.sup.N partial N-order correction spaces. The reflection coefficient for the target color is determined by multiplying a reference reflection coefficient with respect to each of the 2.sup.N reference colors by the volume of a partial N-dimensional correction space that is located at a diagonal position against a coordinate point of each reference color and summing up the results of multiplication for the 2.sup.N reference colors.

Growing community of inventors

Kyoto, Japan

Atsushi Imamura