Omron Corporation

Yasuyuki Ikeda

Shiro Fujieda

Hiroshi Yano

Atsushi Taneno

Masashi Kurita

Masahiro Fujikawa

Yutaka Kato

Koji Shimada

Yuichi Doi

Kakuto Shirane

Katsuhiro Shimoda

Yoshihiro Moritoki

Kazushi Yoshioka

Yoshihisa Minato

Sakon Yamamoto

Yutaka Kiuchi

Toyoo Iida

Takeshi Yoshiura

Yukiko Yanagawa

Naoya Nakashita

Hiroyuki Hazeyama

Jaewook Hwang

Yukihiro Komatsu

Yuki Akatsuka

Kengo Ichimura

Reiji Takahashi

Kazuhiro Shono

Akira Ishida

An image inspection device includes: a divided image generation part for inputting a divided inspection image obtained by dividing an image of an inspection object and a surrounding-containing image that includes an image based on at least some of the surrounding images of the divided inspection image to a prelearned model having been trained so as to accept as inputs a divided good-article image obtained by dividing an image of a good-article inspection object and an image including an image based on at least some of the surrounding images of the divided good-article image and output a restored divided image; and an inspection part for performing inspection of the inspection object on the basis of the restored divided image generated by the divided image generation part.

Image inspection device, image inspection method, and prelearned model generation device

An inspection system includes: a light emitting device configured to illuminate a target object; a collimator lens arranged between the light emitting device and the target object; and an imaging device configured to image the target object. The light emitting device is capable of changing a light emission position. The inspection system further includes an image analysis unit configured to generate an analysis image in which a value of each pixel corresponds to a normal direction of a surface of the target object appearing in the pixel, by analyzing a plurality of captured images obtained individually from a plurality of times of imaging where the light emission positions are different from each other. As a result, time and effort in adjustment for inspection can be reduced, and defect detection accuracy is improved.

Inspection system and inspection method

A defect inspecting device including an acquisition unit, an image generating unit, an inspection unit, and a setting unit. The image generating unit generates one or more feature extraction images by applying to an inspection image a learned classifier. The inspection unit identifies a region corresponding to a defect based on one or more determination parameters and a binarized image generated based on the feature extraction image. The setting unit provisionally sets the determination parameters on premise of a post-adjustment from a user when a number of image data for learning corresponding to the features is less than a threshold value in a case where the region corresponding to the defect is identified based on the pre-learned features, and sets the determination parameters according to designation from the user in a case where the region corresponding to the defect is identified based on a feature other than the pre-learned features.

Defect inspecting device, defect inspecting method, and storage medium

This image processing device, by superimposing a defect imageon a background image, with the original image of an inspection subject as the background image, and performing image processing in which the display format of the defect imageor the display format of the background imageis altered, a plurality of composite imageshaving different ways of seeing the defect imagewith respect to the background imageare generated (step), the advisability of detecting the defect imagefrom each of the plurality of composite imagesis verified (step), the detectable rangeof the defect imageis estimated on the basis of the detection advisability verification results (step), and the detectable rangeis displayed (step).

Image processing device, image processing method, and image processing non-transitory computer readable medium for verifying detectable range of defect image

A convolutional neural network performs: a first masking process of masking a pixel region not to be inspected, by computing pixel values of corresponding pixels of an inspection image and of a mask image; an intermediate process for extracting a feature image from the inspection image that has been subjected to the first masking process; and a second masking process of masking the pixel region not to be inspected, by computing the pixel values of corresponding pixels of the inspection image that has been subjected to the intermediate process and of the mask image that has been subjected to a process identical to the intermediate process.

Image processing device, image processing method, and computer readable recording medium

An image generating part generating feature extraction images by applying an identification part, which has completed learning, that has executed learning in advance to extract features using learning image data to an inspection image, an inspection part specifying an area corresponding to a defect on the basis of judgment parameters for judging presence/absence of a defect in the inspection target object and a binary image generated on the basis of the feature extraction images, and a setting part calculating an image score based on a density of a color of pixels of a setting image using the setting image that is the binary image in which an area corresponding to the defect is specified and updating the judgment parameters such that a difference between an image score of the inside of the area and an image score of the outside of the area becomes relatively large are included.

Defect inspection device, defect inspection method, and computer readable recording medium

Provided is an image processing system which determines at least one object using a low function device and a high function device having higher calculation capacity than the low function device. The low function device includes a part configured to output a first determination result which identifies the objects by applying a first convolution neural network to captured images of the objects, and a part configured to output the captured image to the high function device when the first determination result meets a predetermined condition. The high function device includes a part configured to apply a second convolution neural network preliminarily learned from a sample which is at least partially common to the first neural network to the captured image and to output a second determination result which identifies the object.

Neural network image processing system

An image processing device includes: a feature detection image generating unit that generates multiple feature detection images corresponding to multiple classes by applying a convolutional neural network having the classes learned previously to an input image; a post-processing unit that generates a measurement result by performing a post-process on at least some feature detection images of the multiple feature detection images on the basis of a setting parameter; and a user interface unit that receives an input of the setting parameter while presenting a user at least one of at least some of the feature detection images which are generated by the feature detection image generating unit and the measurement result which is generated by causing the post-processing unit to perform the post-process using at least some of the feature detection images which are generated by the feature detection image generating unit.

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

The disclosure includes: a memory section, storing a learned model and an internal parameter set in the learned model; an acquisition section, acquiring an image of an inspection object photographed under predetermined conditions; a preprocessing section, generating a predetermined preprocessing filter according to a feature value in a preprocessing image being an image of the inspection object that is acquired by the acquisition section and that includes a defect, and a feature value corresponding to the internal parameter, and generating a preprocessed image by applying the generated preprocessing filter to an inspection image being an image of the inspection object that is acquired by the acquisition section and converting the inspection image; and an inspection section, inspecting the preprocessed image for presence or absence of the defect of the inspection object by using the stored learned model.

Defect inspection apparatus, defect inspection method, and non-transitory computer readable medium

An image processing device is connected to an imaging unit. The imaging unit has an overlapping region in an imaging range before and after continuous imaging. The image processing device includes: an interface that receives a plurality of captured images obtained by the imaging unit; a measurement unit configured to acquire a measurement result of a subject in the captured image by performing measurement processing to the captured image; a synthesis unit configured to generate a synthesized image by synthesizing the plurality of captured images such that the captured images overlap with one another within an overlapping range corresponding to the overlapping region in imaging order; and an output unit configured to output the synthesized image, information indicating the overlapping range correlated with the synthesized image, and information indicating the measurement result.

Image processing device and image processing program

An image processing apparatus, connected to an imaging part to capture an image of workpieces conveyed on a conveyer, includes an interface that receives a signal indicating a travel distance of the conveyer, an interface that communicates with a control device for controlling a moving machine disposed downstream of an imaging area of a imaging part, a positional information acquisition unit that processes the image captured by the imaging part and thereby acquiring positional information of a pre-registered workpiece in the image, a travel distance obtaining unit that obtains the travel distance of the conveyer synchronized with the control device, an initiating unit that initiates the capturing by the imaging part in response to an imaging command, and a transmission unit that transmits, to the control device, the positional information and the travel distance upon the capturing of the image used to acquire the positional information.

Image processing apparatus and image processing system for conveyor tracking

An area partitioning method for partitioning an image into a foreground and a background includes a foreground designation step of causing a user to designate a part of pixels in an area that should be the foreground in the image as a foreground designating pixel, an estimation step of estimating a foreground color distribution and a background color distribution based on a color of the foreground designating pixel designated by the user, and an area partition step of partitioning the image into a foreground area and a background area with the estimated foreground color distribution and the estimated background color distribution as a condition. The estimation step includes dividing the color distribution of the image into a plurality of clusters, and selecting at least one cluster having a large relationship with the foreground designating pixel designated by the user in the plurality of clusters as the foreground color distribution.

Method for partitioning area, and inspection device

An image processing method improves the extraction accuracy of objects other than symbols. The image processing method may include four processes. In the first process, an image is input. In the second process, a symbol in the image is read. In the third process, a mask area including the symbol is set. In the fourth process, an object located in an area other than the mark area in the image is recognized.

Method and apparatus for processing images, and storage medium storing the program

An image processing device includes: an image receiving part configured to receive an image of a target workpiece on a surface of a conveying path captured by means of the imaging unit; a position acquiring part configured to acquire a position of the target workpiece in the captured image; a tilt acquiring part configured to acquire, by using the position of the target workpiece in the captured image acquired by means of the position acquiring part, a tilt angle of an imaging plane of the imaging unit relative to the surface of conveying path; and an outputting part configured to output assistant information used for assisting in the adjustment of the posture of the imaging unit by using the acquired tilt angle.

A control system executes a first control operation, and then executes a second control operation. In the first control operation, the image processing section obtains the image data and specifies a position of a characteristic part. The control section determines a control instruction for accelerating an object to a predetermined first speed based on the specified position of the characteristic part and then decelerating the object to a predetermined second speed lower than the first speed, to move the object to an intermediate target position away from the final target position by a predetermined margin distance. In the second control operation, the image processing section obtains the image data during movement of the moving mechanism and specifies the position of the characteristic part, and the control section determines a control instruction for positioning the object to the final target position based on the specified position of the characteristic part.

Growing community of inventors

Ikeda, Japan

Yasuyuki Ikeda