Keyence Corporation

Masato Shimodaira

Ippei Yamauchi

Naoki Takayama

Kazuhito Saeki

Norimasa Mayumi

Tsuyoshi Yamagami

Tomotaka Shimano

When a normal inspection and an inspection through deep learning processing is applicable, high inspection accuracy is obtained while reducing a processing time. The normal inspection processing is applied to a newly acquired inspection target image, the non-defective product determination or the defective product determination is confirmed for the inspection target image having the characteristic amount with which the non-defective product determination or the defective product determination is executable based on the characteristic amount within the inspection target image and the threshold for confirming the non-defective product determination or the threshold for confirming the defective product determination. The deep learning processing is applied to the inspection target image having the characteristic amount with which the non-defective product determination or the defective product determination is not confirmable, and the non-defective product determination or the defective product determination is executed.

Image inspection apparatus

The robot simulation apparatus includes: a workpiece model setting unitthat sets a workpiece model obtained by forming a model of a three-dimensional shape of a workpiece; a bulk pile data generating unitthat generates virtual bulk pile data of a plurality of workpiece models piled up in a virtual work space as a virtually formed work space; a region estimating unitthat identifies an estimated region that is estimated to be three-dimensionally measurable by a sensor unit which is disposed above the work space, based on a position and a posture of each workpiece model in the bulk pile data; and a picking motion simulating unitthat executes a simulation for verifying the picking motion from the bulk pile of the workpiece models in the virtual work space, based on data of the estimated region identified by the region estimating unit

Robot simulation apparatus and robot simulation method

The robot simulation apparatus includes: a workpiece model setting unitthat sets a workpiece model; a posture condition setting unitthat sets a condition related to a posture taken by the workpiece model, as a posture condition, when the workpiece model set by the workpiece model setting unitis disposed in a virtual work space as a virtually formed work space; a bulk pile data generating unitthat generates bulk pile data of the plurality of workpiece models piled up in the virtual work space, in accordance with the posture condition set by the posture condition setting unit; and a picking motion simulating unitthat executes a picking motion simulation for verifying the picking motion of the workpiece models in the virtual work space, with respect to the bulk pile data generated by the bulk pile data generating unit

A robot setting apparatus includes a positioning unit that adjusts a position and an attitude of a workpiece model, and a grip position specifying unit that specifies a grip position at which the workpiece model is gripped by an end effector for at least one fundamental direction image in a state of displaying at least three height images in which the workpiece model positioned by the positioning unit on the virtual three-dimensional space is viewed from respective axis directions of three axes orthogonal to each other on the display unit as fundamental direction images.

Robot setting apparatus, robot setting method, robot setting program, computer readable recording medium, and apparatus storing program

A robot setting apparatus includes a grip reference point setting unit, a grip direction setting unit that defines a grip direction in which the end effector model grips the workpiece model, a workpiece side grip location designation unit that designates a grip position at which the end effector model grips the workpiece model in a state in which at least the workpiece model is displayed in an image display region, and a relative position setting unit that sets a relative position between the end effector model and the workpiece model such that the grip direction defined in the grip direction setting unit is orthogonal to a workpiece plane representing an attitude of the workpiece model displayed in the image display region, and the grip reference point is located at the grip position along the grip direction.

Robot setting apparatus and robot setting method

A workpiece model is created based on three-dimensionally measured data obtained by performing a three-dimensional measurement on a working space in which the workpieces are loaded in bulk. Holding data including a holding position of the workpiece model and a posture of a holding unit of a robot are set by setting a model coordinate system. The setting of the model coordinate system and the setting of the holding data are repeated while sequentially changing the posture of the workpiece, and multiple pieces of holding data are stored such that the multiple pieces of holding data correspond to the workpiece models. A three-dimensional search process is performed on the obtained three-dimensionally measured data, and an operation of the holding unit of the robot is controlled based on the holding data set to the workpiece model.

Image processing device, image processing method, and computer program

An exposure time is changed stepwise, a light receiving amount output from a light receiving section is obtained at each exposure time, which is changed stepwise, and height image data, in which each pixel value indicates a height of each portion of a surface of a measuring object, is generated based on the obtained light receiving amount. It is determined whether each pixel constituting each height image is valid or invalid based on the obtained light receiving amount. An exposure time, which corresponds to a height image in which the number of pixels determined to be valid satisfies a predetermined condition, is set as a set value.

Shape measuring device and shape measuring method

A three-dimensional image processing apparatus includes: a distance image generating part capable of generating a distance image based on a plurality of images captured in an image capturing part; a pattern generating part for generating a first projection pattern and a second projection pattern whose fringe direction is different from that of the first projection pattern as a plurality of projection patterns obtained by changing a fringe direction of a projection pattern; and an incorrect-height determining part for making comparison in height information of a corresponding portion of an inspection target between a first distance image, generated in the distance image generating part based on a first pattern projected image, and a second distance image, generated based on a second pattern projected image, to determine height information of a portion where a difference not smaller than a predetermined value has occurred as incorrect.

Three-dimensional image processing apparatus, three-dimensional image processing method, three-dimensional image processing program, computer-readable recording medium, and recording device

The present invention provides a defect detection apparatus for detecting a defect even on a uniformly continuous background pattern, a method used in the apparatus, and a computer program for making a computer execute processing in the method. A defect size is set and stored, and an instruction to a first direction in which a background pattern is uniformly continuous is accepted. A reduced image reduced in the first direction using an image reduction ratio according to the defect size is generated. A filter processing is executed in the first direction for removing a defect, and the reduced image that is subjected to the filter processing is enlarged in the first direction with an image enlargement ratio corresponding to the reciprocal of the reduction ratio to generate a first enlarged image. A difference image is generated by calculating a difference between the multi-valued image and the first enlarged image.

Defect detection apparatus, defect detection method, and computer program

An image processing apparatus capable of executing filter processing with a desired blurring degree selected in accordance with an application from a multi-valued image captured an object surface, the image processing apparatus comprises: a first filter processing device for executing smoothing processing on the multi-valued image, a second filter processing device for creating a reduced image reduced from the multi-valued image with an image reduction ratio, executing smoothing processing on the reduced image, and creating an enlarged image of the smoothed image enlarged with an image enlargement ratio corresponding to the image reduction ratio, and an image display device for displaying a processed image by the first filter processing device or the second filter processing device.

Image processing apparatus, image processing method, and computer program

There are provided an image generating apparatus and an image generating method, which are capable of generating an image with only a noise portion reliably deleted. A reduced image is generated by reducing the multi-valued image, smoothing processing is executed on the reduced image, an edge image is generated from the reduced image, edge angle information concerning edge angles is generated in pixel units from the edge image, a synthesizing rate of the multi-valued image and the smoothed reduced image is calculated in pixel units of the reduced image based upon the edge angle information. An enlarged image is generated by enlarging the smoothed reduced image to an identical scale, the synthesizing rate calculated in pixel units of the reduced image is converted into a synthesizing rate in pixel units of the enlarged image, and the multi-valued image and the enlarged image are synthesized based upon the converted synthesizing rate.

Image generating apparatus and method

The present invention provides a technique of accurately extracting areas of characters included in a captured image even in a case where noise or dirt of a relatively large area occurs in a background image. A pixel value integration evaluation value is obtained by integrating pixel values in a character extracting direction B at each of the pixel positions in a character string direction A of an image including a character string. A waveform of the value is expressed as waveform data. A first threshold and a second threshold are set for the waveform data. An area in which the waveform data exceeds the first threshold is set as a character candidate area. In a case where an area in which the pixel value integration evaluation value exceeds the second threshold exists in the character candidate areas, the character candidate area is regarded as a true character area and the characters are extracted.

Character extracting apparatus, method, and program

The present invention provides a technique of accurately extracting areas of characters included in a captured image even in a case where noise or dirt of a relatively large area occurs in a background image. An integrated pixel value is obtained by integrating pixel values in a character extracting direction B for pixel positions in a character string direction A of an image including a character string. A standard deviation value is calculated along the character extracting direction for pixel positions in a character string direction A. The integrated pixel value and the standard deviation value are combined for pixel positions in a character string direction A. A threshold is set automatically or manually. A part of pixel positions in a character string direction A having the combined value of the integrated pixel value and the standard deviation value higher than the threshold is recognized as a character area to be extracted.

There are provided a defect detection apparatus, a defect detection method, and a computer program, which are capable of setting an appropriate reference line with respect to a plurality of edge points, to accurately detect a defect based upon a difference of each edge point, and in which a plurality of edge points are detected from an image including an edge of the object, a representative edge point representing the edge points present within a reference range having a prescribed width is calculated in each shifted position of the reference range while the reference range is sequentially shifted, residuals between a plurality of calculated representative edge points and corresponding edge points are calculated, a position and a size of the defect are specified based upon the calculated residuals, and the residuals are weighted and a representative edge point is repeatedly calculated, to obtain an apparent approximate curve (representative-edge-point sequence).

Defect detection apparatus, defect detection method and computer program

There is provided a defect detection apparatus capable of highly accurately detecting a defect of a size not larger than a size desired by the user, in which the size setting device sets the defect size, the reduction ratio setting device sets an image reduction ratio based on the set defect size, the image reduction device generates a reduced image obtained by reducing the original multi-valued image, the filter processing device performs filter processing on the reduced image for removing a defect in the reduced image, the image enlarging device generates an enlarged image obtained by enlarging the reduced image, subjected to the filter processing, at an image enlargement ratio corresponding to the reciprocal of the image reduction ratio, and the difference calculating device generates a difference image obtained by performing a calculation of a difference between the original multi-valued image and the enlarged image.

Growing community of inventors

Osaka, Japan

Masato Shimodaira