Library VisionTools
Category | Tool | Descpription | |
|---|---|---|---|
Reads a single 1D/2D code from the image – supports formats such as UPC, EAN, Code 39, QR, and others. | |||
Reads a Data Matrix code from the image – a two-dimensional code consisting of black and white squares arranged in a grid pattern. | |||
Detects and reads text in the image – Optical Character Recognition (OCR) for text extraction. | |||
Applies the Sobel operator – computes the gradient magnitude and emphasizes edges and intensity variations. | |||
Applies the Canny edge detection algorithm – detects edges based on intensity gradients in the image. | |||
Applies the Laplace operator – computes the second derivative and enhances areas with rapid intensity changes. | |||
Detects and outlines contours (white areas) in a binary image – output is sorted by size (from largest to smallest). | |||
Detects and outlines contours (white areas) in binary images – requires white objects; output is sorted from largest to smallest. | |||
Displays contours on an image – facilitates the identification of object or region outlines. Prerequisite: prior contour detection using “Find Contours.” | |||
Retrieves contours from a polyline array based on an index range – index is based on the distance from the image origin (0,0). Prerequisite: prior contour detection using “Find Contours.” | |||
Filters contours by area – sorted from largest to smallest area. Prerequisite: prior contour detection using “Find Contours.” | |||
Converts contours into a binary image (region) – can be used as a mask for further processing. Prerequisite: prior contour detection using “Find Contours.” | |||
Encloses an outline in a single box. | |||
Encloses a contour in a single circle. | |||
Determines deviations from the target value in the image – highlights areas that differ from the expected pattern. | |||
Adjusts the contrast and brightness of an image – enhances the display and visibility of details. | |||
Sharpens an image by increasing the contrast between neighboring pixels – enhances details and clarity. | |||
Adjusts the gamma value of the image – controls brightness and contrast for optimized display. | |||
Subtracts pixel values of one image from another – highlights differences between the two images. | |||
Raises pixel values to a power – increases or decreases brightness to enhance contrast or emphasize details. | |||
Applies an average filter – smooths the image and reduces noise or grainy structures. | |||
Applies a bilateral filter – smooths the image while preserving edges by considering spatial distance and intensity differences. | |||
Applies a Gaussian filter – smooths the image by averaging pixel values within a Gaussian kernel size. | |||
Applies a median filter – reduces noise by replacing each pixel with the median of its neighborhood. | |||
Scales the width and height of an image by different factors – allows for non-proportional resizing. | |||
Scales an image uniformly in both directions – maintaining the aspect ratio. | |||
Resizes an image to specified dimensions – width and height are adjusted precisely. | |||
Shifts an image horizontally and/or vertically – freed areas are filled with black pixels. | |||
Flips an image horizontally or vertically – creates a mirror image along the chosen axis. | |||
Rotates an image by a specified angle – rotation is performed around the center point. | |||
Removes the so-called fisheye effect from the image – corrects extreme wide-angle distortions. | |||
It improves local contrast by dividing the image into smaller regions and calculating histograms for each. A contrast-limited histogram correction is then applied. | |||
Measures similarities and differences between histograms. | |||
Improves the contrast of an image by stretching the histogram and making better use of the brightness values. | |||
Increases contrast without altering image properties. A low-contrast image is thus stretched across the entire area. | |||
It checks the pixel distribution. It finds the target image in the region where the color distribution most closely matches the reference image. | |||
Uniform distribution of pixel values over a defined area without changing the histogram. | |||
Compares two images and highlights differences – deviations appear dark, similarities lighter. | |||
Converts an RGB image to grayscale – based on brightness, simplifying color-independent image processing. | |||
Crops an image by coordinates – defined by the top-left and bottom-right corners, extracting the desired area. | |||
Crops an image based on a defined shape – selectively extracts the area within that shape. | |||
Draws a line on the image – useful for marking, highlighting, or annotating in image processing tasks. | |||
Enables drawing shapes on the image – ideal for highlighting or marking specific areas. | |||
Draws an ellipse on the image – useful for annotation, highlighting, or marking specific image areas. | |||
Limits the image area to a shape without cropping – pixels outside the shape are blacked out, coordinates remain unchanged. | |||
Calculates the mean of all pixels – provides information about the average brightness or color intensity in the image. | |||
Calculates the standard deviation of pixel values – indicates how much brightness or color varies or spreads within the image. | |||
Determines the smallest pixel value in the image – indicates the darkest or lowest intensity area within the entire image. | |||
Determines the highest pixel value in the image – indicates the brightest or most intense area within the entire image. | |||
Draws text at a specified position on the image – non-displayable characters are replaced with question marks. | |||
Provides metadata about the input image – determines image type, width, and height. | |||
Determines the RGB color channels of an image – returns one value per channel. | |||
Determines the hue, saturation, and brightness of an RGB image – by converting it to the HSV color space and splitting the channels. | |||
Creates a color image by combining individual images for the red, green, and blue channels. | |||
Calculates the histogram of an image. Supports grayscale (mono), RGB and HSV channels. | |||
Determines the intersection point of two segments in the image – optionally displaying the measurement result. | |||
Detects edges in the image – marks strong brightness or color changes, usually at object boundaries or prominent structures. | |||
Detects a circle within a region. Smallest, Fitting, Mean, or Largest Circle can be selected. | |||
Measures the shortest, average, and longest distance between two segments – useful for analyzing spatial relationships. | |||
Measures the distance between a point and a line segment – selectable: shortest distance, or distance to the segment’s start or end point. | |||
Measures the distance between a point and a line – useful for precise positioning relative to the line. | |||
Measures the angle between two lines – measured counterclockwise from a reference line. | |||
Measures the distance between two lines – useful for analyzing parallelism or spacing within the image. | |||
Measures the angle between two lines – based on a reference line, measured counterclockwise. | |||
Measures the angle between a line and a side of a non-rectangular rectangle counterclockwise. | |||
Measures the angle between two vectors – measured counterclockwise starting from the reference vector. | |||
Reduces white areas by removing edge pixels – useful for separating connected objects or removing small spots. | |||
Expands white areas by turning edge pixels white – fills gaps and connects broken object parts in the image. | |||
Applies erosion followed by dilation – smooths contours, removes noise, and reliably separates overlapping objects. | |||
Applies dilation followed by erosion – closes gaps, connects object parts, and smooths white areas in the image. | |||
Calculates the difference between dilation and erosion – highlights object contours and aids in edge detection. | |||
Calculates the difference between the original image and the opening operation – highlights small bright details such as fine structures or noise. | |||
Calculates the difference between the closing operation and the original image – highlights small dark details such as spots or objects against a bright background. | |||
Detects specific pixel patterns using two structuring elements – ideal for precise shape and pattern recognition in the image. | |||
Calculates the area of each white region in the binary image – provides quantitative size information about objects in the image. | |||
Detects and quantifies connected regions – groups of connected pixels with the same value are considered as individual objects. | |||
Counts black pixels in the image – useful for determining the size or extent of black areas. | |||
Detects and counts individual regions – connected pixels with the same value are identified as separate objects. | |||
Counts white pixels in the image – useful for determining the size or extent of white areas. | |||
Merges two regions into one connected region – useful for object recognition, merging, or segmentation evaluation. | |||
Combines two binary regions using a logical OR – white areas from both images are merged and preserved. | |||
Subtracts one region from another (Region1 – Region2) – useful for isolating differences or overlaps. | |||
Compares the intersection of two regions – useful for identifying common areas or features in segmentations. | |||
Inverts the pixels of a region – typically white to black and vice versa – for highlighting or creating a negative image. | |||
Converts a binary region into a grayscale image. | |||
Selects regions based on area, index, height, or width within a specified value range. | |||
Identifies the largest contiguous region – ideal for extracting dominant objects or relevant image areas. | |||
Calculates the smallest circle that completely encloses a region – useful for shape analysis and measurement. | |||
Calculates the smallest rectangle that completely encloses a region – useful for analysis and measurement. | |||
Returns the width and height of a region based on the input. | |||
Sorts regions by X, Y, width, height or area – with specific sorting direction depending on the feature. | |||
Sorts contours by X, Y, length, or area; the number of returned contours can be limited. | |||
Sorts an array of edges based on a specific feature. | |||
Cuts a region into a specific shape. | |||
Reduziert den Bereich einer Region auf eine bestimmte Form, jedoch ohne dabei die Region abzuschneiden. | |||
Encloses an area within a single circle. | |||
Encloses an area within a single rectangle. | |||
Adaptive Thresholding adjusts the threshold locally – ideal for uneven lighting, significantly improves detection accuracy. | |||
Sets pixels below the threshold to zero, and above to 255, i.e. white. | |||
This node specifically isolates image areas whose pixels lie in a defined color range. | |||
| Sets pixels below the threshold to zero, leaving others unchanged to preserve detail. |