Seiko Epson Corporation

Yuko Yamamoto

Mitsuhiro Yamashita

Takahiro Kamada

Takuya Ono

Akito Sato

Satoshi Yamazaki

Koichi Yoshizawa

Yuichi Yoneyama

Yoshifumi Arai

Takumi Shimomukai

Keiko Yamada

Ryoki Watanabe

Kenji Matsuzaka

Katsuyuki Tanaka

Shotaro Matsuda

Tsuyoshi Sano

Hiroyuki Onishi

Shinichi Kato

Satoru Ono

Shuichi Kataoka

Takeshi Tanoue

Nao Kaneko

Masayuki Seko

Naoki Hagihara

Sa Liu

The print medium identification method includes (a) a step of obtaining first physical property information about a print medium, (b) a step of obtaining second physical property information which is different from the first physical property information about the print medium, (c) a step of obtaining first discrimination information for discriminating a type of print medium by inputting the first physical property information to a first discriminator, (d) a step of obtaining second discrimination information for discriminating the type of print medium by inputting second physical property information to a second discriminator, and (e) a step of identifying the type of print medium by using the first discrimination information and the second discrimination information.

Print medium identification method and print medium identification system

A print image is acquired as first image data represented in a first color space used for forming an image on a first print medium. Second image data is acquired by performing, on the first image data, conversion into representation in a profile connection space using a first conversion table and white point conversion using the information on appearance in a redetermined observation environment, of a base color section where an image is not formed on the first print medium. The second image data is converted by using a second conversion table into converted image data represented in a second color space used for forming an image on a second print medium and an image corresponding to the print image is formed on the second print medium by using the converted image data.

Image processing device and image processing program

Prepare a learning model that has been trained to output similarity for each defect species by machine learning using a teacher image that is an image containing a defect occurring during printing and that is associated with a defect species in advance. Then, a target image is prepared for inspection by acquiring an image of printed matter that has been printed. By using the learning model with respect to this target image, the similarity of the defect present in the target image to a known defect species is acquired, and this similarity is used to discriminate the defect present in the target image as at least one of the known defect species. When updating the learning model based on this discrimination result, the learning model is made to perform machine learning for a defect species that is different from the discriminated defect species or that is associated with an unknown defect.

Defect discrimination apparatus for printed images and defect discrimination method

An image processing device converts image data, which is data of an image expressed in a first color space, into an expression in a second color space used in rendering by using a color conversion profile prepared in advance, generates a converted image data, and generates a rendering image corresponding to the appearance of the printed-on print medium in a virtual space by performing physical based rendering of the printed-on print medium on which the image has been printed, using the converted image date and parameters necessary for performing physical based rendering of the print medium as a 3D object.

Image processing device for previewing image to be printed on 3D object

Provided is an image processing device coupled to a printing device that performs printing on a medium by ejecting ink having a plurality of colors, and configured to convert image data into ink amount data. The image processing device includes: an input unit configured to input a search condition; an acquisition unit configured to acquire a plurality of search values based on the search condition input by the input unit; a table storage unit storing a plurality of image conversion tables for converting the image data into the ink amount data; and a search unit configured to search the plurality of image conversion tables for a target image conversion table based on the plurality of search values acquired by the acquisition unit.

Image processing device, image processing method, and image processing program

An image processing device includes an image data acquisition section configured to acquire image data of an image to be printed on a print medium; a parameter acquisition section configured to acquire parameters for performing physical based rendering of the print medium on which the image is to be printed as a 3D object, the parameters including a normal line map representing a normal line direction of an irregularities surface of the print medium related to a reflection direction of light incident on the print medium; a correction section configured to correct strength of an application effect of the normal line map corresponded with the 3D object; and a rendering execution section for generating a rendering image representing the print medium on which the image is printed by executing the physical based rendering using the image data and the parameters.

Image processing device, printing system, and non-transitory computer-readable storage medium storing image processing program that render three dimensional (3D) object

An image processing device includes: an image data acquisition unit that acquires image data; a print condition acquisition unit that acquires a print condition including a type of a print medium on which an image is printed; a parameter acquisition unit that acquires a texture parameter indicating a texture of the print medium; a color conversion unit that performs color conversion corresponding to the print condition, on the image data; and a rendering unit that executes rendering, causing the image data on which the color conversion is performed, to correspond to at least one of a front face and a back face of a 3D object representing a shape of the print medium, and causing the texture parameter to correspond to the front face and the back face of the 3D object, and thus generates a rendered image representing the print medium with the image printed thereon.

Image processing device, printing system, and non-transitory computer-readable storage medium storing image processing program

A printing method includes: a color space conversion step; a gradation determination step of determining whether a pixel group forms a gradation; and a gradation region ink amount calculation step of calculating an ink amount of the pixel group determined to form the gradation. The gradation region ink amount calculation step includes an array information acquisition step of acquiring whether pixel values are arranged linearly, in a planar manner, or in a polyhedron manner in a uniform color space, a grating color value calculation step of determining a grating color value which is a color value of a grating point in the array, a grating ink amount calculation step of calculating, using the determined grating color value, a grating ink amount which is an ink amount of the grating point in the array, and an interpolation calculation step of calculating an ink amount of the pixel group determined to form the gradation by interpolation using the calculated grating ink amount.

Printing method including gradation region ink amount calculation step

An image analyzer includes an in-use ink information determination section that determines an ink type to be used for printing and an ink quantity to be used for printing for the ink type as in-use ink information by using image data in accordance with conditions set in advance, a printed image quality information acquisition section that acquires at least one item of printed image quality information on image quality specified in advance and provided when the image data is printed by using the determined in-use ink information, and a display section that displays at least one of the in-use ink information and the printed image quality information.

Image analyzer determines in-use ink information using image data according to preset conditions and acquires prespecified image quality information when image is printed

For a plurality of types of print media, a pre-trained model is prepared, the pre-trained model being generated by machine learning based on spectroscopic information of an unprinted area on the print medium and an identifier indicating the type of the print medium and using the identifier as a trainer. The spectroscopic information of the unprinted area on the print medium to print on is acquired. The acquired spectroscopic information is applied to the pre-trained model. Using a result thereof, auxiliary information about the type of the print medium is outputted. A specification of the type of the print medium using the outputted auxiliary information is accepted. When the type of the print medium is thus specified, printing is performed using a print condition suitable for the print medium.

Printing system, print medium specifying method, and medium information providing device

A printing condition setting method is a printing condition setting method of setting printing conditions in a printing apparatus, including a learning step of performing machine learning by using ink physical characteristics and ink type information, a similarity score calculation step of calculating a similarity score indicating a similarity of a use ink used for printing in the printing apparatus with respect to a learned ink learned in the learning step, and a printing condition setting step of setting the printing conditions according to the use ink based on the similarity score.

Printing condition setting method, printing condition setting system

A printing system includes a terminal device, a plurality of printers, a first server, and a second server. The first server calculates a round-trip accuracy of each printer using a color conversion profile supplied from the second server with respect to target color information included in a printing command provided from the terminal device, and selects one or more printers among the plurality of printers according to the round-trip accuracy to cause the printers to execute printing.

Printing system and printing method

A color value prediction system includes a color-value predicting section configured to receive an input of information representing ink amounts of a first apparatus and output spectral reflectance, a receiving section configured to receive an input of information representing a designated color gamut, a preparing section configured to prepare first teacher information representing a plurality of sets of combinations of ink amounts of the first apparatus and second teacher information, which is a plurality of sets of spectral reflectance respectively associated with the plurality of sets of combinations of ink amounts of the first teacher information, and a generating section configured to generate the color-value predicting section with machine learning in which the first teacher information serving as an input value and the second teacher information serving as an output value are used as teacher data. The first teacher information includes designated teacher information representing a combination of ink amounts of the first apparatus representing a color included in the designated color gamut.

Color value prediction system and generation method for color value predictor

A color prediction model creation device configured to create a color prediction model for predicting color values of a device-independent color system from an ink amount set includes: a first color prediction model creation unit configured to acquire a first spectral reflectance of a color chart printed on a first printing medium by using a first ink amount set, and create a first color prediction model for the first printing medium by learning a correspondence relationship between the first ink amount set and the first spectral reflectance; and a second color prediction model creation unit configured to acquire a second spectral reflectance of a color chart printed on a second printing medium by using a second ink amount set having a smaller number of combinations than that of the first ink amount set, and create a second color prediction model for the second printing medium by learning using the second ink amount set, the second spectral reflectance and the first color prediction model.

Color prediction model creation using a first model to create a second model

A method of creating teacher data used for creating a color prediction model that predicts a spectral reflectance of a printed matter printed using an ink amount set from the ink amount set that is a combination of ink amounts of inks used for printing, includes, in an ink amount space in which a plurality of lattice points are disposed, selecting an ink amount set from an ink amount set associated with each lattice point, according to a predetermined selection rule, acquiring a spectral reflectance of a color chart printed on a printing medium using the selected ink amount set, and setting the teacher data using the selected ink amount set as an input value and the acquired spectral reflectance as an output value.

Growing community of inventors

Nagano-ken, Japan

Yuko Yamamoto