Detect and Fit Rectangle

You are currently viewing the documentation for a pre-release version (2.2.0). To access documentation for other versions, click the "Switch Version" button located in the upper-right corner of the page.

■ If you're unsure about the version of the product you are using, please contact Mech-Mind Technical Support for assistance.

Description

This Step detects the edges of a rectangle from an image and fits the rectangle.

rectangle demo

Usage Scenario

This Step is primarily used in scenarios such as detecting rectangular areas, reference frames, pads, and patch areas on workpieces, where there is a rigid requirement for rectangle positioning or dimensional measurement.

Basic Concepts

  • Caliper

    In image processing, a virtual measurement tool detects edges within a specified region. Adjusting its count, width, and length affects the accuracy and stability of edge detection.

  • Edge polarity

    It refers to the direction of grayscale change across an edge, e.g., dark-to-light or light-to-dark.

Input and Output

Input

Input port Data type Description

Image

Image

The image used for detecting rectangle-shaped edges.

Alignment Parameter Group

Pose2D

Used to adjust the target region’s pose in sync with the target object’s pose changes.

Output

Output port Data type Description

Rectangle Pose

Pose2D

The position and orientation of the fitted rectangle.

Center Point

Shape2D/Point

The geometric center of the fitted rectangle.

Center X

Number

The X coordinate of the center point of the fitted rectangle.

Center Y

Number

The Y coordinate of the center point of the fitted rectangle.

Rectangle Width

Number

The width of the fitted rectangle.

Rectangle Height

Number

The height of the fitted rectangle.

Rectangle Rotation Angle

Number

The rotation angle of the fitted rectangle, relative to the positive X-axis direction.

Fitted Rectangle

Shape2D/Rectangle

The rectangle obtained through fitting.

Parameter Description

Parameter Description

ROI Settings

You can draw a rectangular ROI. The system extracts multiple columns of pixels according to the caliper settings, and the detected edge points in each column will be used for rectangular fitting.

Edge Polarity

This parameter specifies the direction in which the grayscale values change at the edges.

Value list:

  • Dark-to-Bright: Detects edges where grayscale values increase from low to high, corresponding to a visual transition from dark to bright.

  • Bright-to-Dark: Detects edges where grayscale values decrease from high to low, corresponding to a visual transition from bright to dark.

  • Any: No limit on the direction of grayscale value change of the edge. Both types can be detected.

Filter Window Size

Specify the window size to be used when filtering each column of pixels in its direction. Filtering can reduce noise and improve the stability of edge detection results.

Edge Mode

Define the edge types to be retained in edge detection.

Value list: Best, First, Last.

Grayscale Change Threshold

This parameter specifies the minimum grayscale variation between adjacent pixels at the edge of an extracted pixel column required for edge point detection. Setting this parameter value properly can effectively filter out weak edges and noise.

Use Relative Threshold

Once selected, an edge point is detected only if the grayscale variation between adjacent pixels at the edge of a pixel column meets or exceeds the specified percentage of the maximum variation in that column. Once this parameter is selected, set Relative Threshold.

Max Distance Threshold

This parameter is used to set the maximum allowed distance from detected edge points to the fitted rectangle. Edge points with a distance less than or equal to this threshold are considered inliers.

Default value: 4 px

Min Fit Score

This parameter is used to determine the lowest score for determining whether the fitted result is acceptable. It is only used for result evaluation and will not affect the fitting process. The score equals the ratio of the number of inliers to the total number of edge points.

When high measurement accuracy is required, raise the Score Threshold. A typical value is 0.8 or above.

Default value: 0.7

Max Iterations

The maximum number of attempts the algorithm will make to fit an optimal plane. Iteration stops once this limit is reached.

When the target contour is complex or subject to high interference, increasing the number of iterations improves accuracy at the cost of increased processing time.

Default value: 1000

Is this page helpful?

You can give a feedback in any of the following ways:

We Value Your Privacy

We use cookies to provide you with the best possible experience on our website. By continuing to use the site, you acknowledge that you agree to the use of cookies. If you decline, a single cookie will be used to ensure you're not tracked or remembered when you visit this website.