Mech-DLK User Manual

You are viewing an old version of the documentation. You can switch to the documentation of the latest version by clicking the top-right corner of the page.

What is Mech-DLK?

Mech-DLK is machine vision deep learning software independently developed by Mech-Mind. With a variety of built-in industry-leading deep learning algorithms, it can solve many problems that traditional machine vision cannot handle, such as highly difficult segmentation, positioning, and classification.

Through intuitive and simple UI interactions, even without programming or specialized deep learning knowledge, users can quickly implement model training and validation with Mech-DLK.

Basic: Single Algorithm Modules

The software contains the following algorithm modules. Click See more to learn about the features of relevant algorithm modules and use them according to actual needs.

instance segmentation icon
Instance Segmentation

Segments the contour of target objects and outputs the corresponding labels of the classes.

object detection icon
Object Detection

Detects the positions of all target objects and recognizes their categories at the same time.

classification icon
Classification

Recognizes object front and back faces, object orientations, and defect types and determines whether objects are missing, or whether objects are neatly arranged.

defect segmentation icon
Defect Segmentation

Detects and segments the defect regions in the image.

unsupervised segmentation icon
Unsupervised Segmentation

Judges whether an image is OK, NG, or Unknown according to set thresholds and displays the possible areas with defects.

fast positioning icon
Fast Positioning

Recognizes the object orientation in an image and corrects the image based on the recognition result.

text detection icon
Text Detection

Detects the text areas of an image.

text recognition icon
Text Recognition

Recognizes the characters in the text area.

Advanced: Cascade Algorithm Modules

In addition, the software allows for the cascading of algorithm modules to achieve a wider range of features.

It is recommended that users should thoroughly learn about the features of single algorithm modules before cascading them to meet actual needs. Please read the Cascade Modules section to view the common cascading combinations as well as the way to cascade modules.

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.