Abstract: An imaging device includes two cameras capturing transmission images of an article from opposite directions, a first light source emitting light that is transmitted through the article in a first direction, and a second light source emitting light that is transmitted through the article in a second direction. The first camera captures a first image that is a transmission image of the article. The second camera captures a second image that is a transmission image of the article. The first half mirror reflects first transmitted light toward the first camera while the second light source is turned off, and permits transmission of light traveling from the second light source toward the article. The second half mirror reflects second transmitted light toward the second camera while the first light source is turned off, and also permits transmission of light traveling from the first light source toward the article.

Abstract: An alpha channel is added in addition to multiple channels forming an image of an item. A second pixel value differing from a first pixel value, which is assigned to a defect-free region, is assigned to a region corresponding to a defect region in the alpha channel. The image including the alpha channel is divided into multiple image segments. A defect label is assigned to the image segment in which the second pixel value is included in the alpha channel, and a non-defect label is assigned to the image segment, in which the second pixel value is not included in the alpha channel. The alpha channel is removed from the image segments to generate labeled image segment data.

Abstract: An imaging device includes a camera, light sources, an optical bandpass filter, and a conversion unit. The camera includes an image sensor including a N-band color filter (where N is a natural number greater than or equal to 3). The M types of light sources (where M is a natural number that satisfies 2?M?N) have the emission spectral characteristics of having respective peaks in mutually different wavelength ranges within a visible light range and a near-infrared range. The conversion unit generates image signals of M bands each having spectral sensitivity to the corresponding one of the mutually different wavelength ranges by performing a matrix operation on an N-band imaging signal obtained by the image sensor when an article is photographed with the camera. The light application direction and the emission intensity are individually selected for each of the light sources.

Abstract: A print inspection device includes a camera that captures a character printed on an inspection target, a shape matching processor, a deformation pattern generator, and an inspection processor. The shape matching processor checks a shape of a captured character pattern included in a captured image obtained by the camera against a shape of a preset reference character pattern while changing a deformation degree of the shape of the reference character pattern and searches for a matched character. The deformation pattern generator generates a deformed character pattern obtained by deforming the reference character pattern at the deformation degree to which the character is matched in the shape matching process. The inspection processor inspects whether a printed state of the character is satisfactory from a result of the comparison between the deformed character pattern and the captured character pattern.

Abstract: An alpha channel is added in addition to multiple channels forming an image of an item. A second pixel value differing from a first pixel value, which is assigned to a defect-free region, is assigned to a region corresponding to a defect region in the alpha channel. The image including the alpha channel is divided into multiple image segments. A defect label is assigned to the image segment in which the second pixel value is included in the alpha channel, and a non-defect label is assigned to the image segment, in which the second pixel value is not included in the alpha channel. The alpha channel is removed from the image segments to generate labeled image segment data.

Abstract: A container inspection device includes an inlet conveyor, an outlet conveyor, a mounting table having a mounting surface, a chamber portion having an opening in a section of the chamber portion, in which a receiving space is formed when the mounting surface contacts the chamber portion to close the opening, and a transfer. The transfer is movable in the certain direction at a speed greater than the conveying speed of the cartons by the inlet conveyor. The transfer holds multiple ones of the cartons that have been conveyed by the inlet conveyor collectively and conveys the cartons to the mounting surface of the mounting table, and holds the multiple ones of the cartons mounted on the mounting surface collectively and conveys the cartons to the outlet conveyor.

Abstract: A container inspection device includes an inlet conveyor, an outlet conveyor, a mounting table having a mounting surface a chamber portion having an opening in a section of the chamber portion, in which a receiving space is formed when the mounting surface contacts the chamber portion to close the opening, and a transfer. The transfer is movable in the certain direction at a speed greater than the conveying speed of the cartons by the inlet conveyor. The transfer holds multiple ones of the cartons that have been conveyed by the inlet conveyor collectively and conveys the cartons to the mounting surface of the mounting table, and holds the multiple ones of the cartons mounted on the mounting surface collectively and conveys the cartons to the outlet conveyor.

Abstract: A method for detecting microorganisms, which comprises: a training step for forming, by a classifier, feature vectors based on color data on individual points within a subject region of training in a culture medium, mapping the points in the culture medium, that are specified by the feature vectors, on a high-dimensional feature space, and linearly separating a set of the points ? (x1), that are specified by the high-dimensional feature vectors thus obtained, to thereby color-classify the class (C1) of the culture medium; and a identifying step for forming, by a classifier, feature vectors based on color data on individual inspection points within a region in the culture medium using image data obtained by capturing an image of the culture medium under cultivation, mapping the inspection points (xj), that are specified by the feature vectors, on a high-dimensional feature space, and determining whether or not the mapped points ? (xj), that are specified by the high-dimensional feature vectors thus obtained, b

Abstract: Colonies growing on a culture medium surface may be more accurately counted with reduced variation in the counts obtained by capturing a plurality of images of the entire culture medium surface, wherein successive images are captured following rotation of the culture medium surface relative to the image capture apparatus by n/360 degrees where n is the number of images to be captured; performing data processing on image data of the entire culture medium surface of the petri dish at each specified angle; and the number of colonies in the petri dish is calculated by performing numerical processing on the number of colonies counted separately at each specified angle.

Abstract: A method for detecting microorganisms, which comprises: a training step for forming, by a classifier, feature vectors based on color data on individual points within a subject region of training in a culture medium, mapping the points in the culture medium, that are specified by the feature vectors, on a high-dimensional feature space, and linearly separating a set of the points ? (x1), that are specified by the high-dimensional feature vectors thus obtained, to thereby color-classify the class (C1) of the culture medium; and a identifying step for forming, by a classifier, feature vectors based on color data on individual inspection points within a region in the culture medium using image data obtained by capturing an image of the culture medium under cultivation, mapping the inspection points (xj), that are specified by the feature vectors, on a high-dimensional feature space, and determining whether or not the mapped points ? (xj), that are specified by the high-dimensional feature vectors thus obtained, b

Abstract: Problem to be Solved There is provided a colony counting method capable of obtaining highly reliable and stable colony count values with easy and simple means by eliminating the variation in colony count due to image capturing conditions when the number of colonies is counted by performing data processing on an image obtained by image capturing means performing image capturing on a petri dish.