Computer Vision

Locates a specified number of the strongest transitions between dark and bright pixels along a given path (without a scan map).

Very fast object detection (or presence verification) when the expected number of edges is clearly defined.

Locates a specified number of multiple pairs of opposite edges across a given path (without a scan map).

Very fast detection (or presence verification) of multiple pairs of opposite edges.

Locates multiple dark or bright pixel peaks along a given path (without a scan map).

Very fast detection of multiple thin structures like wires or scale marks - usually for counting or distance measurements.

Locates the strongest transition between dark and bright pixels along a given path (without a scan map).

Very fast detection of an object (e.g. horizontal displacement of a bottle) and simple measurements (e.g. liquid level in a bottle).

Locates the strongest pair of edges across a given path (without a scan map).

Very fast detection or measurement of an object defined by a pair of opposite edges.

Locates a specified number of the strongest high or low peaks of surface height along a given path.

Locates multiple changes of surface height along a given path.

Locates multiple pairs of changes of surface height along a given path.

Locates the strongest high or low peak of surface height along a given path.

Extracts subpixel-precise paths that represent continuous edges.

Consistent detection of contours of variable or unpredictable shape, e.g. screw thread outline or a custom piece of textile.

Extracts a pixel-precise region of continuous edges.

Consistent detection of pixels that belong to contours of variable or unpredictable shape, e.g. screw thread outline or a custom piece of textile.

Extracts subpixel-precise paths that represent bright or dark thin lines.

Consistent detection of thin structures like scratches, cracks or lines.

Translates an array of bar widths to sequence of digits or text in accordance to the selected barcode standard.

Decoding of barcodes whose bars have been measured in a non-standard way.

Determines the position of a single barcode on the input image.

Detection of a barcode, but without actual recognition. Usually followed by a RecognizeBarcode filter.

Detects and recognizes a single barcode on the input image.

To be used as an easy all-in-one solution for typical barcode reading applications.

Select a subset of the given points that forms a grid and assign 2D indices to them.

Recognition of a custom regular grid for the purpose of camera calibration.

Finds the camera intrinsic parameters from the input arrays of annotated image coordinates. Uses pinhole camera model (perspective camera).

Camera calibration, image to world coordinates transformations.

Finds the image to world plane transformation matrix. World plane origin and axes are unspecified. Useful for image rectification or distance measurements.

Image rectification, distance measurements.

Finds the image to world plane transformation matrix. Image and their corresponding world points are directly specified (no grid needed).

Image to world coordinates transformations.

Finds the image to world plane transformation matrix, with world origin and axes specified in the image coordinates. Note that this is a filter for rather rarely seen special cases and it is usually better to use the CalibrateWorldPlane_Labeled filter.

Image to world coordinates transformations.

Computes a spatial map for transforming distorted images to rectified images defined in world coordinate plane. Allows for flexible definition of output geometry.

Image undistortion, perspective removal, image stitching.

Computes a spatial map for transforming distorted images to rectified images defined in world coordinate plane. Defines the output geometry in pixels.

Image undistortion, perspective removal.

Detects a chessboard calibration grid on the image, and returns calibration points where 4 chessboard squares meet.

Camera calibration, image to world coordinates transformations.

Generates artificial points for camera calibration. Doesn't support distortion.

Calibration testing.

Finds the world coordinates of image Edge.

Undistortion, image to world coordinate transformation.

Finds the world coordinates of image Gap.

Undistortion, image to world coordinate transformation.

Finds the world coordinates of image Path.

Undistortion, image to world coordinate transformation.

Finds the world coordinates of image Point.

Undistortion, image to world coordinate transformation.

Finds the world coordinates of image Ridge.

Undistortion, image to world coordinate transformation.

Finds the world coordinates of image Segment.

Undistortion, image to world coordinate transformation.

Finds the world coordinates of image Stripe.

Undistortion, image to world coordinate transformation.

Shifts world plane along its normal vector.

Image to world coordinates transformations.

Finds the image coordinates of world plane Edge.

World coordinate to image transformation

Finds the image coordinates of world plane Gap.

World coordinate to image transformation

Finds the image coordinates of world plane Path.

World coordinate to image transformation

Finds the image coordinates of world plane Point.

World coordinate to image transformation

Finds the image coordinates of world plane Ridge.

World coordinate to image transformation

Finds the image coordinates of world plane Segment.

World coordinate to image transformation

Finds the image coordinates of world plane Stripe.

World coordinate to image transformation

Translates a matrix of 0 or 1 values to a text in accordance to how QR codes are encoded.

Decoding of QR codes whose black and white segments have been determined in a non-standard way.

Detects and recognizes several PDF417 codes.

Detects and recognizes one Data Matrix code.

Detects and recognizes a single QR code on the input image.

Filters the frequencies in a frequency domain image suppressing the elements of too low or too high frequency.

Computes the phase of each frequency domain image pixel.

Finds lines in an image using Hough Transform.

Finds a specified shape in an image using Hough Transform.

This is an old algorithm for template matching. Quite slow.

Finds the strongest circle of a given radius in the input image.

Detection of a circular or close-to-circular object like a hole, pin, pill or particle.

Verifies object presence by analysing pixel intensities in the specified region.

Quick and easy presence verification, e.g. for missing caps, screws, labels.

Compares an image with a multi-image model using an ensemble of image features approach.

Finding general object defects by analyzing brightness deviations from a template image.

Compares an image with a template image considered to have no defects.

Finding general object defects by analyzing brightness deviations from a template image.

Creates golden template for application in CompareGoldenTemplate_Edges filter.

Detects corners using corner response method.

Detection of characteristic points on an image.

Finds line peaks on an image.

Created for applications with laser line detection.

Computes the shape of the image object using surface normals.

Computes surface normals using four images with light source in different places.

Segments an image into blobs by color-based thresholding.

Segments an image into blobs by dynamic thresholding.

Segments an image by binarizing it with many different thresholds and by looking which blobs appear "stable".

Most frequently used for finding correspondence points between two images.

Segments an image into blobs using image edges as their borders.

Detection of objects of undefined shape, but characterized by good contrast to the background and fairly uniform internal brightness.

Segments an image into blobs examining differences between pixels values.

Detection of objects of undefined shape, but characterized by uniform brightness and good contrast to the background.

Computes dark or bright watershed basins of an image.

A classic algorithm, useful for segmentation of ball-shaped objects like plant seeds, cells or fruits.

Returns fields of OcrCandidate structure.

Splits an array of blobs by distance to computed base lines.

Converts OcrMlpModel(old type) to OcrModel.

Converts OcrModel to OcrSvmModel.

Ready-to-use tool for reading text from images using the OCR technique.

Splits the input region into a fixed-size array of regions corresponding to individual characters.

Text segmentation when the number of characters is known, usually followed by a RecognizeCharacters filter.

Trains an OCR multilayer perceptron classifier.

Loads images and regions, extracts knowledge from it, and initializes OrganicModel, which can be then trained and used to classify new images.

Trains OrganicModel, which has to be previously initialized with LoadOrganicTrainingData.

Segments a point cloud into planes.

Segments a surface into planes.

Translates, rotates and scales the given contour set to the edges of the input image with subpixel precision.

Fine-tune results of edge-based template matching.

Performs a series of 1D ridge detections and finds an arc that best matches the detected points.

Precise detection of a thin arciform line, whose rough location is known beforehand.

Performs a series of 1D edge detections and finds a circle that best matches the detected points.

Precise detection of a circular object or hole, whose rough location is known beforehand.

Performs a series 1D stripe detections and finds a circle that best matches the detected points.

Precise detection of ring-shaped objects, whose rough location is known beforehand.

Performs a series of 1D ridge detections and creates a path from the detected points.

Tracing of a thin line, whose rough location and shape is known beforehand.

Performs a series of 1D edge detections and finds a segment that best matches the detected points.

Precise detection of a straight edge, whose rough location is known beforehand.

Performs a series of 1D stripe detections and finds a segment that best matches the detected points.

Precise detection of a straight stripe, whose rough location is known beforehand.

Performs a series of 1D ridge detections in 3D and finds a circle that best matches the detected points.

Precise detection of a circular object or hole, whose rough location is known beforehand.

Performs a series of 1D edge detections in 3D and creates a path from the detected points.

Tracing of an object contour, whose rough location and shape is known beforehand.

Performs a series of 1D stripe detections in 3D and creates a path from the detected points.

Tracing of a stripe, whose rough location and shape is known beforehand.

Performs a series of 1D ridge detections in 3D and finds a segment that best matches the detected points.

Precise detection of a thin straight line, whose rough location is known beforehand.

Limits the size of the EdgeModel objects created by CreateEdgeModel filter.

Creates a model for NCC or SAD template matching.

Dynamic creation of models in the runtime environment (normally they are created interactively in Studio).

Improves accuracy of single object matching by adding a subpixel-precise adjustment.

Usually used after an edge-based template matching tool.

Finds all occurrences of a predefined template on an image by analysing the normalized correlation between pixel values.

Detection of objects with blurred or unclear edges. Often one of the first filters in a program.

Finds a single occurrence of a predefined template on an image by comparing object edges.

Detection of an object whose outlines are sharp and rigid. Often one of the first filters in a program.

Finds a single occurrence of a predefined template on an image by analysing the Square Average Difference between pixel values.

Almost always inferior to NCC, so rarely used in real applications.

Combines results from multiple LocateSingleObject instances.

Creates histogram and map of Linear Binary Patterns (with radius 1 and size 8) of provided image.