Omron Corporation

Shiro Fujieda

Yasuyuki Ikeda

Hiroshi Yano

Atsushi Taneno

Yutaka Kato

Yuji Suzuki

Yutaka Kiuchi

Yuki Taniyasu

Jaewook Hwang

Hiroyuki Hazeyama

Shohei Nakaoka

Kenichi Ukai

Toshihiko Matsumoto

Reiji Takahashi

Masanao Yoshino

Kazushi Yoshioka

An image processing system includes one or more processors that select one target algorithm from evaluation algorithms, calculate an evaluation value indicating adaptation to image measurement using the target algorithm and one or more evaluation images corresponding to an evaluation lighting pattern for each evaluation lighting pattern, and determine a lighting pattern to be used for the image measurement from evaluation lighting patterns based on the evaluation value.

Image processing system that performs image measurement on target and adjust at least one of emission intensity and emission color for lighting elements, setting method, and program

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

A method for cutting out, from a gray-scale image generated by capturing an image of a character string, each character in the character string for recognition, includes a first step of repeating projection processing for projecting a highest or lowest gray level in a line along a direction crossing the character string in the gray-scale image, onto an axis along the character string, with the lowest gray level selected when a character in the gray-scale image is darker than a background, the highest gray level selected when the character in the gray-scale image is brighter than the background, and a projection target position moved along the character string.

Method for cutting out character, character recognition apparatus using this method, and program

An image processing method of processing a gray-scale image of character strings arranged in a plurality of lines of text, for character recognition, includes setting at least a part of a range, in which the character strings in the gray-scale image area are distributed, as a search area, and setting, for each of a plurality of points arranged along one of two axes, representing coordinates in the image, corresponding to an arrangement of the line of text, a plurality of lines extending across the search area, with the point as a starting point, and accumulating, for each of the lines, pixel data in the line within the search area.

Image processing method for character recognition, character recognition apparatus using this method, and program

A character-recognition device and method for imaging a character string, generating a grayscale image that corresponds to the character string, cutting out, from the grayscale image, individual characters in the character string, obtaining a coincidence of a character image that is being focused on for each of model images of a plurality of kinds of characters by sequentially focusing on cut-out character images to match the cut-out character images against the model images, and recognizing characters corresponding to the cut-out character images based on each coincidence.

Character-recognition method and character-recognition device and program using said method

One of stereo cameras is set such that a front view of a support surface of a workpiece is imaged, an image produced by the camera is displayed, and a range of an area where measurement processing is enabled is assigned by a rectangular frame. A manipulation assigning an upper limit and a lower limit of a height measurement range is accepted. When each assignment is fixed, zero is set as a z-coordinate to each constituent pixel of an image to which the rectangular frame is set, and a z-coordinate based on the upper limit of the height measurement range and a z-coordinate based on the lower limit are set to coordinates corresponding to the rectangular frame. Perspective transformation of three-dimensional information produced by the setting is performed from a direction of a line of sight set by a user, a produced projection image is displayed on a monitor.

Method for displaying measurement effective area in three-dimensional visual sensor and three-dimensional visual sensor

A recognition processing method and an image processing device ends recognition of an object within a predetermined time while maintaining the recognition accuracy. The device extracts combinations of three points defining a triangle whose side length satisfy predetermined criterion values from feature points of the model of a recognition object, registers the extracted combinations as model triangles, and similarly extracts combinations of three points defining a triangle whose side lengths satisfy predetermined criterion values from feature points of the recognition object. The combinations are used as comparison object triangles and associated with the respective model triangles. The device calculates a transformation parameter representing the correspondence relation between each comparison object triangle and the corresponding model triangle using the coordinates of the corresponding points (A and A', B and B&#x2032;, and C and C&#x2032;), determines the goodness of fit of the transformation parameters on the relation between the feature points of the model and those of the recognition object. The object is recognized by specifying the transformation parameters representing the correspondence relation between the feature points of the model and those of the recognition object according to the goodness of fit determined for each association.

Computer implemented method for recognizing an object based on a correspondence relationship between object feature points and pre-registered model feature points

To easily generate model data having high recognition accuracy and being consistent with measurement conditions and installation environment of each of optical sensors. Basic model representing a range in which a workpiece can be optically recognized is inputted, and pieces of processing of imaging and measuring the workpiece under the same condition as that in an actual measurement and matching feature data of the workpiece obtained from this measurement with the basic model are executed for a plurality of number of cycles. Then, in the basic model, information is set as unnecessary information where the information cannot be associated with the feature data of the workpiece in all of the pieces of matching processing, or where the number of times or ratio the information cannot be associated is more than a predetermined reference value, or where the information cannot be associated with the feature data in any one of the pieces of executed matching processing. Then, the unnecessary information is deleted from the basic model, and information after each deletion is identified as model data to be registered and is registered to the memory.

Method for registering model data for optical recognition processing and optical sensor

A control processing unit simultaneously drives cameras to produce images of a measuring object, the control processing unit searches corresponding point on a comparative image produced by one of the cameras for a representative point in a reference image produced by the other camera, and the control processing unit computes a three-dimensional coordinate corresponding to a coordinate using the coordinate of each point correlated by the search. The control processing unit also obtains a shift amount at the corresponding point specified by the search to an epipolar line specified based on a coordinate of a representative point on the reference image side or a parameter indicating a relationship between the cameras, and the control processing unit supplies the shift amount as an evaluation value indicating accuracy of three-dimensional measurement along with three-dimensional measurement result.

Method and apparatus for performing three-dimensional measurement

Images of a work piece in which measurement object is restricted to a specific point or domain are taken by a camera which takes the image of the work piece from a front-view direction and a camera which takes the image from obliquely above, and a height of each measurement object region is measured. Each pixel of the front-view image used in measurement processing is virtually disposed in a three-dimensional coordinate system including x- and y-axes constituting a coordinate system of the image and a z-axis indicating the height, and a perspective transform is performed to produce a processing result image expressing measurement result. A measurement value is set as the z-coordinate at the pixel which is a height measurement object, and the z-coordinates of other pixels are set at other pixels. A mark for identifying a position and an auxiliary line indicating the height are set at measurement object points and measurement object region in the image.

Three-dimensional measurement method and three-dimensional measurement apparatus

In the present invention, whether three-dimensional measurement or checking processing with a model is properly performed by setting information and recognition processing result can easily be confirmed. After setting processing is performed to a three-dimensional visual sensor including a stereo camera, a real workpiece is imaged, the three-dimensional measurement is performed to an edge included in a produced stereo image, and restored three-dimensional information is checked with a three-dimensional model to compute a position of the workpiece and a rotation angle for an attitude indicated by the three-dimensional model. Thereafter, perspective transformation of the three-dimensional information on the edge obtained through measurement processing and the three-dimensional model to which coordinate transformation is already performed based on recognition result is performed into a coordinate system of a camera that performs the imaging, and projection images are displayed while being able to be checked with each other.

Three-dimensional recognition result displaying method and three-dimensional visual sensor

Enabling height recognition processing by setting a height of an arbitrary plane to zero for convenience of the recognition processing. A parameter for three-dimensional measurement is calculated and registered through calibration and, thereafter, an image pickup with a stereo camera is performed on a plane desired to be recognized as having a height of zero in actual recognition processing. Three-dimensional measurement using the registered parameter is performed on characteristic patterns (marks m, mand m) included in this plane. Based on a positional relationship between a plane defined as having a height of zero through the calibration and the plane expressed by the calculation equation, a transformation parameter (a homogeneous transformation matrix) for displacing points in the former plane into the latter plane is determined, and the registered parameter is changed using the transformation parameter.

Three-dimensional vision sensor

When computation of a three-dimensional measurement processing parameter is completed, accuracy of a computed parameter can easily be confirmed. After a parameter for three-dimensional measurement is computed through calibration processing using a calibration workpiece in which plural feature points whose positional relationship is well known can be extracted from an image produced by imaging, three-dimensional coordinate computing processing is performed using the computed parameter for the plural feature points included in the stereo image used to compute the parameter. Perspective transformation of each computed three-dimensional coordinate is performed to produce a projection image in which each post-perspective-transformation three-dimensional coordinate is expressed by a predetermined pattern, and the projection image is displayed on a monitor device.

Calibration apparatus and method for assisting accuracy confirmation of parameter for three-dimensional measurement

An edge code histogram of a model generated in a model image is registered. A target region with respect to the input image is set. An edge code histogram for the target region is generated. A relative positional relationship between the edge code histogram of the model and the edge code histogram for the target region is sequentially changed, and a degree of coincidence between the edge code histograms at each relative position is calculated. A possibility that the region that matches the model is contained in the set target region from the sequentially calculated degree of coincidence between the edge code histograms is evaluated. Then a candidate point having a possibility of matching the model in the input image is specified while sequentially changing the position of the target region with respect to the input image and repeating steps above for each target region.

Image processing method and image processing device

A computer displays an image of an object which has been created by photographing by a photographing portion in a setting mode. Further, height threshold-value data is received according to an input from outside through a key board. Based on height information detected from the image created by photographing and based on the received threshold-value data, a partial image having height information specified by the threshold-value data is extracted from the image created by photographing and then is displayed. In a driving mode, the computer displays an image acquired by photographing the object, and extracts a partial image having height information specified by the threshold-value data, based on the height information detected from the image created by photographing and the threshold-value data preliminarily-received in the setting mode. The image data extracted in the driving mode is utilized for inspections of defects in the object.

Growing community of inventors

Kyoto, Japan

Shiro Fujieda