Abstract: The invention alleviates a burden on a user relating to an image inspection device based on photometric stereo and multi-spectral imaging. An illumination device 3 has three or more illumination blocks that irradiate a workpiece 2 with illumination beams from different directions, respectively. A camera 4 generates images of the workpiece 2. An image processing device 5 irradiates the workpieces 2 sequentially with illumination beams from light emitting elements of different lighting colors and generates a plurality of spectral images. The image processing device 5 sequentially turns on the three or more illumination blocks in units of blocks and generates a plurality of direction images. The image processing device 5 generates a color inspection image based on the plurality of spectral images and executes color inspection. The image processing device 5 generates a shape inspection image based on the plurality of direction images and executes shape inspection.

Abstract: The invention alleviates a burden on a user relating to selection of a lighting color required for image inspection by multi-spectral imaging. A processor controls an illumination device to irradiate a setting target object individually with an illumination beam of each lighting color in a predetermined order, thereby generating a plurality of spectral images. The processor sets a combination of lighting colors recommended to illuminate an inspection target object based on the plurality of spectral images. An inspection unit inspects the inside of each inspection region in a plurality of inspection images generated for the inspection target object illuminated by illumination beams of lighting colors according to the set combination of recommended lighting colors.

Abstract: The invention reduces a variation of a result of image inspection by alleviating a burden on the user relating to designation of an extracted color. An image inspection device displays a color image of an inspection target object, receives designation of at least a foreground region, and extracts a foreground color and a background color as color information from the foreground region and a background region, respectively. The image inspection device calculates a distance between a color of each pixel of the color image and the foreground color in a color space, and generates a foreground distance image. Similarly, the image inspection device forms a background distance image. The image inspection device inspects the inspection target object using a foreground-background image created by combining the foreground distance image and the background distance image.

Abstract: The invention alleviates a burden on a user relating to an image inspection device based on photometric stereo and multi-spectral imaging. An illumination device 3 has three or more illumination blocks that irradiate a workpiece 2 with illumination beams from different directions, respectively. A camera 4 generates images of the workpiece 2. An image processing device 5 irradiates the workpieces 2 sequentially with illumination beams from light emitting elements of different lighting colors and generates a plurality of spectral images. The image processing device 5 sequentially turns on the three or more illumination blocks in units of blocks and generates a plurality of direction images. The image processing device 5 generates a color inspection image based on the plurality of spectral images and executes color inspection. The image processing device 5 generates a shape inspection image based on the plurality of direction images and executes shape inspection.

Abstract: The invention alleviates a burden on a user relating to selection of a lighting color required for image inspection by multi-spectral imaging. A processor controls an illumination device to irradiate a setting target object individually with an illumination beam of each lighting color in a predetermined order, thereby generating a plurality of spectral images. The processor sets a combination of lighting colors recommended to illuminate an inspection target object based on the plurality of spectral images. An inspection unit inspects the inside of each inspection region in a plurality of inspection images generated for the inspection target object illuminated by illumination beams of lighting colors according to the set combination of recommended lighting colors.

Abstract: The invention improves accuracy of image inspection for a moving workpiece in an image inspection device provided with a plurality of light sources having different lighting colors. A first movement correction image is acquired before acquiring spectral images for multi-spectral imaging. A second movement correction image is acquired after acquiring the spectral images for multi-spectral imaging. Positions of the workpiece in the spectral images are corrected based on the amount of change between a position of a characteristic of a workpiece in the first movement correction image and a position of the characteristic of the workpiece in a second movement correction image thereby creating an inspection image. Image inspection on the workpiece is executed using this inspection image.

Abstract: The invention reduces a variation of a result of image inspection by alleviating a burden on the user relating to designation of an extracted color. An image inspection device displays a color image of an inspection target object, receives designation of at least a foreground region, and extracts a foreground color and a background color as color information from the foreground region and a background region, respectively. The image inspection device calculates a distance between a color of each pixel of the color image and the foreground color in a color space, and generates a foreground distance image. Similarly, the image inspection device forms a background distance image. The image inspection device inspects the inspection target object using a foreground-background image created by combining the foreground distance image and the background distance image.

Abstract: An inspection apparatus includes: an imaging section for capturing a first reference image by simultaneously turning on three or more illumination sections, and a second reference image at imaging timing temporally after the first reference image; a tracking target image designating section for designating a tracking target image in the first reference image and is used for tracking a position of the workpiece; a corresponding position estimating section for searching a position of the tracking target image designated by the tracking target image designating section from the second reference image, and specifying a position including the tracking target image in the second reference image, to estimate a corresponding relation of pixels that correspond among each of the partial illumination images; and an inspection image generating section for generating an inspection image for photometric stereo based on the corresponding relation of each of the pixels of the partial illumination images.

Abstract: An inspection apparatus includes: an imaging section for capturing a first reference image by simultaneously turning on three or more illumination sections, and a second reference image at imaging timing temporally after the first reference image; a tracking target image designating section for designating a tracking target image in the first reference image and is used for tracking a position of the workpiece; a corresponding position estimating section for searching a position of the tracking target image designated by the tracking target image designating section from the second reference image, and specifying a position including the tracking target image in the second reference image, to estimate a corresponding relation of pixels that correspond among each of the partial illumination images; and an inspection image generating section for generating an inspection image for photometric stereo based on the corresponding relation of each of the pixels of the partial illumination images.

Abstract: There is provided a matching method, capable of positioning with higher accuracy at higher speed. The method includes the steps of: constructing a pattern model of a registered image in which a plurality of reference points are set on an extracted contour and a corresponding point search line having a predetermined length and passing through each reference point; acquiring an image and acquiring an initial position corresponding to the registered image to arrange the corresponding point search line of the pattern model; finding a corresponding point on the image corresponding to each reference point with regard to each corresponding point search line at a position along the corresponding point search line on the image; and regarding a relation between each reference point and the corresponding point as an evaluation value and performing fine positioning such that an accumulated value of the evaluation values becomes minimal or maximal.

Abstract: There is provided a pattern model creating method in image processing, which allows selection of an appropriate contour in accordance with an object image, the method being a pattern model creating method in image processing for positioning by searching an object to be searched that is similar to a pre-registered image out of an image to be searched by use of a pattern model corresponding to the registered image, the method including: extracting a plurality of edge points from the registered image; creating a plurality of continuous chains by coupling adjacent edge points among the plurality of extracted edge points; eliminating a chain with a length not larger than a predetermined length among the plurality of chains; selecting chains sequentially from the smallest chain among the remaining chains; and regarding aggregation of the selected chains as a contour extracted from the registered image, to construct a pattern model for positioning.

Abstract: There is provided a data compression method for increasing a reduction ratio, while keeping a sufficient characteristic amount, to seek speeding up of processing, the method being for compressing image data in pattern model positioning in image processing of searching out of an image to be searched and positioning a pattern model corresponding to a pre-registered image. The method includes the steps of: computing an edge strength image having edge strength information and an edge angle image having edge angle information with respect to each pixel constituting an image; transforming the edge angle image of each pixel into an edge angle bit image expressed by an edge angle bit indicating an angle with a pre-defined fixed width; and compressing the edge angle bit image to create an edge angle bit reduced image by taking a sum with respect to each edge angle bit.

Abstract: There is provided a data compression method for increasing a reduction ratio, while keeping a sufficient characteristic amount, to seek speeding up of processing, the method being for compressing image data in pattern model positioning in image processing of searching out of an image to be searched and positioning a pattern model corresponding to a pre-registered image. The method includes the steps of: computing an edge strength image having edge strength information and an edge angle image having edge angle information with respect to each pixel constituting an image; transforming the edge angle image of each pixel into an edge angle bit image expressed by an edge angle bit indicating an angle with a pre-defined fixed width; and compressing the edge angle bit image to create an edge angle bit reduced image by taking a sum with respect to each edge angle bit.

Abstract: There is provided a method for deciding an image data reduction ratio in image processing which enables performance of stable positioning even on an unclear image, the method being a method for deciding an image data reduction ratio in image processing where an object to be searched that is similar to a pre-registered image is searched to be positioned out of the image to be searched by use of a pattern model corresponding to the registered image, the method including the steps of: computing a sharpness of each edge point based on the edge points with reference to an edge image where the edge points are extracted from image date; and deciding an image data reduction ratio based on each edge sharpness such that positional accuracy of the edge points becomes higher than a predetermined value.

Abstract: There is provided a data compression method for increasing a reduction ratio, while keeping a sufficient characteristic amount, to seek speeding up of processing, the method being for compressing image data in pattern model positioning in image processing of searching out of an image to be searched and positioning a pattern model corresponding to a pre-registered image. The method includes the steps of computing an edge strength image having edge strength information and an edge angle image having edge angle information with respect to each pixel constituting an image; transforming the edge angle image of each pixel into an edge angle bit image expressed by an edge angle bit indicating an angle with a pre-defined fixed width; and compressing the edge angle bit image to create an edge angle bit reduced image by taking a sum with respect to each edge angle bit.

Abstract: There is provided a method for deciding an image data reduction ratio in image processing which enables performance of stable positioning even on an unclear image, the method being a method for deciding an image data reduction ratio in image processing where an object to be searched that is similar to a pre-registered image is searched to be positioned out of the image to be searched by use of a pattern model corresponding to the registered image, the method including the steps of: computing a sharpness of each edge point based on the edge points with reference to an edge image where the edge points are extracted from image date; and deciding an image data reduction ratio based on each edge sharpness such that positional accuracy of the edge points becomes higher than a predetermined value.

Abstract: There is provided a pattern model creating method in image processing, which allows selection of an appropriate contour in accordance with an object image, the method being a pattern model creating method in image processing for positioning by searching an object to be searched that is similar to a pre-registered image out of an image to be searched by use of a pattern model corresponding to the registered image, the method including: extracting a plurality of edge points from the registered image; creating a plurality of continuous chains by coupling adjacent edge points among the plurality of extracted edge points; eliminating a chain with a length not larger than a predetermined length among the plurality of chains; selecting chains sequentially from the smallest chain among the remaining chains; and regarding aggregation of the selected chains as a contour extracted from the registered image, to construct a pattern model for positioning.

Abstract: There is provided a matching method, capable of positioning with higher accuracy at higher speed. The method includes the steps of: constructing a pattern model of a registered image in which a plurality of reference points are set on an extracted contour and a corresponding point search line having a predetermined length and passing through each reference point; acquiring an image and acquiring an initial position corresponding to the registered image to arrange the corresponding point search line of the pattern model; finding a corresponding point on the image corresponding to each reference point with regard to each corresponding point search line at a position along the corresponding point search line on the image; and regarding a relation between each reference point and the corresponding point as an evaluation value and performing fine positioning such that an accumulated value of the evaluation values becomes minimal or maximal.

Abstract: There is provided a data compression method for increasing a reduction ratio, while keeping a sufficient characteristic amount, to seek speeding up of processing, the method being for compressing image data in pattern model positioning in image processing of searching out of an image to be searched and positioning a pattern model corresponding to a pre-registered image. The method includes the steps of computing an edge strength image having edge strength information and an edge angle image having edge angle information with respect to each pixel constituting an image; transforming the edge angle image of each pixel into an edge angle bit image expressed by an edge angle bit indicating an angle with a pre-defined fixed width; and compressing the edge angle bit image to create an edge angle bit reduced image by taking a sum with respect to each edge angle bit.

Abstract: An image processing apparatus for extracting edge points in an input image acquired by an image acquisition device is presented. The image processing apparatus includes an edge magnitude threshold value specifying device for specifying an edge magnitude as an edge magnitude threshold value from the data of the edge magnitude corresponding to a criterion edge magnitude value and the number of the edge points to be extracted. The apparatus also includes an edge point extractor for extracting a pixel having an edge magnitude corresponding to the edge magnitude threshold value as one of the edge points in each pixel of the input image. An image processing method for extracting edge points in an input image acquired by an image acquisition device is also discussed.