2D Target Object Recognition

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

■ If you are not sure which version of the product you are currently using, please feel free to contact Mech-Mind Technical Support.

Function

This Step integrates image preprocessing, 2D feature extraction, template matching, and deep learning visual processing functions for quick target object recognition and inspection.

Usage Scenario

This Step is suitable for four major scenarios: positioning and picking, placement correction, error-proofing check, and information reading. It can flexibly handle different target object types, placement methods, and inspection requirements. It is typically used in conjunction with the "2D Smart Camera" Step.

Input and Output

Input

Input port Data type Description

Camera Color Image

Image/Color

Original color image of the target object.

Output

Output port Data type Description

Target Object Names

String []

Names of the target objects.

Recognized Pose

Pose []

The 3D picking pose in the robot reference frame.

Matching Score (Optional)

Number []

Used for evaluating the quality of the matching result.

Blob Mask (Optional)

Image/Color/Mask

The mask image of the detected blobs.

Classification Judgment Result

String []

Classification judgment result, that is OK or NG.

Classification Status (Optional)

Bool []

Used to indicate whether classification is successful; 1 for success, 0 for failure.

Classification Confidence (Optional)

Number []

Confidence for each classification result.

Image with Result (Optional)

Image []

Image with recognition result.

Deformation Judgment Result

String

Deformation check result, OK or NG.

Deformation Check (Optional)

Bool

Used to indicate whether the target object passes the deformation check. 1 indicates pass, and 0 indicates fail.

Deformation Confidence (Optional)

Number

Confidence score of the deformation of the target object. A higher score indicates smaller deformation.

Deviation Judgment Result

String

Pose deviation check result, OK or NG.

Deviation Check (Optional)

Bool

Used to indicate whether the target object passes the pose deviation check. 1 indicates pass, and 0 indicates fail.

Angle Deviation (Optional)

Number

Angular deviation of the target object relative to the template.

Center X Offset (Optional)

Number

Offset of the object center point relative to the template center in the X direction.

Center Y Offset (Optional)

Number

Offset of the object center point relative to the template center in the Y direction.

Count Judgment Result

String

Used to indicate whether the number of matching results is within the specified range (OK/NG).

Count Check (Optional)

Bool

Used to indicate whether the match count falls within the specified range. 1 indicates the count meets the requirement, and 0 indicates it does not.

Match Count (Optional)

Number

The total number of matching results.

1D/2D Barcode Content

String

The content of each recognized 1D or 2D barcode.

1D/2D Barcode Verification Result

Bool

Indicates whether 1D/2D barcode verification is passed. Outputs true if verification passes, false otherwise.

Barcode Location (Optional)

Shape2D/Contour

The position of each recognized 1D or 2D barcode in the image.

Recognition Result

String []

Character recognition result.

Recognition Judgment Result (Optional)

String []

Recognition judgment result, that is OK or NG.

Recognition Status (Optional)

Bool []

Used to indicate whether recognition is successful; 1 for success, 0 for failure.

Parameter Description

Parameter Description

Select Target Object

Parameter description: Select a target object to recognize from the drop-down list. The target object must be added in the config wizard in advance.
Tuning instructions: Click Config wizard or the Config wizard button on the Step block to enter the 2D Target Object Recognition Tool. For detailed instructions, refer to 2D Target Object Recognition.

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.