Advance Ultravision - Blog: Halcon

Showing posts with label Halcon. Show all posts

Tutorial: Working with XLDs - MVTec HALCON

In this tutorial, you will work with XLDs in MVTec HALCON. XLDs, or extended line descriptions, comprise contours, polygons, and parallels. XLD contours are used and returned by many HALCON operators, so that’s the focus of this video.

First, we look at an application where we want to find a line and check its width. Then, we try to learn more about the circle sector in an image. In these two applications, we will get to know many different functionalities concerning XLDs, like the detection of lines and edges, attributes, the union and segmentation of XLDs, and the selection of XLDs according to features, fitting geometric primitives, and more.

0:00 Introduction to XLDs in MVTec HALCON

1:00 XLD contours attributes

1:27 The first application

3:17 The second application

About Us:

Advance Ultravision is the main distributor of Industrial Machine Vision products and components in Malaysia. We specialized in Machine Vision software such as Machine Learning, Deep Learning, Machine Vision Software Library, and 3D Machine Vision.

More information at advanceultravision.com

Curated By:

Vincent Hua is a Malaysia-based Machine Vision sales engineer, an ex-Machine Vision cum Automated Machine software engineer. Specialized in a machine vision system for Semiconductor / Electronics / Automotive sector.

Deep Learning Classification - MVTec Halcon(Deep Learning, Machine Vision Library)

With the MVTec Deep Learning Tool, it’s possible to train a deep-learning-based classification model from scratch.

First, we import images of your application – using the folder structure, the Deep Learning Tool can assign labels automatically. We can then review our data by filtering the images according to these labels.

After that, we train the model using transfer learning and pre-trained networks provided by MVTec.

Lastly, we can review the trained model in detail, using a confusion matrix, heatmaps, and more. Deep Learning Tool(version 0.5) used in this video.

Get more information at MVTec deep learning tool

About Us:

More information at advanceultravision.com

MVTec Software GmbH is a leading international manufacturer of software for machine vision used in all demanding areas of imaging like the semiconductor industry, surface inspection, automatic optical inspection systems, quality control, metrology, medicine, or surveillance. In particular, software by MVTec enables new automation solutions for the Industrial Internet of Things by providing modern technologies like 3D vision, deep learning, and embedded vision.

Visit mvtec.com to learn more about us.

Curated By:

Webinar: MVTec HALCON 20.11 New Features - MVTec Halcon

In this webinar, Mario Bohnacker, Technical Product Manager HALCON at MVTec, talks about all improvements and new features in HALCON 20.11.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

Deep Learning with Densely Segmented Supermarket Dataset - MVTec Halcon

The Densely Segmented Supermarket (D2S) dataset is a benchmark for instance-aware semantic segmentation in an industrial domain. It contains 21,000 high-resolution images with pixel-wise labels of all object instances.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

Introduction to image filters with MVTec HALCON - MVTec Halcon

In this tutorial, you’ll learn about some of the most commonly used image filters in MVTec HALCON, how they work, and what they can be used for. First, we’ll have a look at some smoothing filters, in particular mean_image and median_image, and how filter masks work.

Then, you’ll get to know some arithmetic filters, like sub_image, invert_image, and scale_image. Next, we have a look at many different applications that we can solve with these filters. Lastly, you’ll learn about what to look out for when using filters on images with reduced domains.

0:28 How mean_image and median_image work

2:26 Some examples for arithmetic filters

2:57 Application examples

5:25 Reduced domains and image filters

In this tutorial, HALCON 20.05 is used.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

MVTec HALCON 20.11 New Features - MVTec Halcon

In this video you learn all about the new features in MVTec HALCON 20.11, released on November 20, 2011.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

HDevelop Tutorial 03: Visualization - MVTec Halcon

There are many ways to improve the visualization of your HDevelop programs. In this tutorial, you will learn about look-up tables, how to format you messages, and more.

Please contact Advance Ultravision Sdn. Bhd. to download the corresponding example program.

Content

0:14 A bad example

0:56 Look-up tables

1:35 “Record Interactions”

2:24 A Graphics window that adapts its aspect ratio

2:58 Formatting your messages I

3:45 Colors, fill and margin

4:16 “Insert Code”

4:49 Formatting your messages II

In this video, HALCON 12.0.1 is used.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

HDevelop Tutorial 04: Working with regions - MVTec Halcon

Regions are a very powerful tool when working with MVTec HALCON. In this video, we learn how to segment an image using the Gray Histogram tool. The resulting region is then processed with morphology to separate touching objects. Lastly, using the features of the regions, like for example the circularity, we cluster different objects in separate regions.

Please contact Advance Ultravision Sdn. Bhd. to download the corresponding example program.

It includes a small exercise: Instead of using the region features, we want to use the gray value information of the image.

Content

0:28 Segmentation: Separate background and foreground

0:48 Gray Histogram

2:26 Morphology: Process geometrical structures

3:28 Separate touching objects using morphology

4:22 Use region features to select certain regions

In this video, HALCON 13.0.1 is used.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

HDevelop Tutorial 01: GUI and Navigation - MVTec HALCON

Let’s take a look at the user interface of HDevelop, HALCON’s interactive development environment. You will also learn to navigate through a program.

You can download the corresponding example program here: https://www.mvtec.com/news-press/video/detail/hdevelop-tutorial-01-gui-and-navigation/

Content

0:32 Graphics Window

0:59 Program Window & Navigation

2:42 Variable Window

3:17 Operator Window

In this video, you will get to know the most important windows of HDevelop, namely the Graphics Window, the Program Window, the Operator Window and the Variable Window. Moreover, you will learn how to go through your program step by step and how to use the Program Counter and Breakpoints.

In this video, HALCON 12.0.1 is used, it can be easily adaptable for latest Halcon version.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

HDevelop Tutorial 02: Variables – MVTec HALCON

HDevelop features two types of variables: iconic variables, which consist of images, regions, and contours, and control variables, which consist of numbers, strings, and handles.

You can download the corresponding example program here: https://www.mvtec.com/news-press/video/detail/hdevelop-tutorial-02-variables-mvtec-halcon/

Content

1:11 Iconic variables

2:38 Control variables

3:26 Tuples and arrays

You will learn how to access all the important information about the variables your program uses. Additionally, you will learn about tuples and arrays and how to use them intelligently to avoid loops in your program.

In this video, HALCON 12 is used. The code can be easily adaptable to latest Halcon version.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

MVTec HALCON 20.05 New Features - MVTec Halcon

This video presents the main new features in HALCON 20.05, the new Progress version of MVTec HALCON released on May 20, 2020.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

Embedded Vision as a strategic choice - MVTec Halcon

In this webinar, held by MVTec, you get interesting insights of embedded vision.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

A fully automated dispense and labeling system for pharmaceutical products - MVTec HALCON

MVTec’s Certified Integration Partner Crave Technical developed a vision system for an automatic unit-of-use dispense and labeling system for pharmaceutical products. HALCON is used in this system for object detection, bar & data code reading as well as hand-eye-calibration for robots that pick the boxes from a conveyor and then position them for the scanning of the code.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

Draw oriented rectangles with the MVTec Deep Learning Tool - MVTec Halcon

Many computer programs often offer the option to draw axis-aligned rectangles but not to draw oriented rectangles. Thus, we developed a method that enables you to label training data for deep learning efficiently with oriented rectangles.

This video shows you how to do this with the MVTec Deep Learning Tool. In this video, version 0.2 of the Deep Learning Tool is used.

Free Download: Deep Learning Tool here: https://www.mvtec.com/products/deep-learning-tool/

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

Shrimp Sorting - MVTec Halcon

MVTec HALCON makes shrimp sorting fast and efficient. The shrimp sorting system from De Boer RVS uses our machine vision software HALCON to distinguish relevant catch (shrimps) from not-relevant by-catch in real-time.

As a consequence of this highly efficient sorting, this application does not only improve the fishing outcome, but also helps to protect the environment, as the alive by-catch is conveyed back to the sea immediately.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

Sweet Pepper Robot detects and picks ripe crops - MVTec Halcon

The Wageningen University & Research (WUR) in the Netherlands developed a greenhouse harvesting robot, which is able to pick ripe crops. The shape- and color-based detection algorithm for this task was implemented using MVTec HALCON.

The organization
The WUR Agro Food Robotics initiative is a joint program by several research groups of the Wageningen University & Research. The program tries to bring new knowledge to practice by carrying out feasibility studies, functional designs, prototype development, testing, validation and by supporting new product implementations.

The challenges
In the past decades the food production in greenhouses has been confronted with the increasing size of production facilities, increasing labor demands and increasing product quality demands by the consumers. Many operations are still done manually, for example the harvesting.

However, the availability of a skilled workforce that accepts repetitive tasks in the harsh greenhouse climate conditions is decreasing rapidly. Robotics and sensing technologies are an alternative solution, which makes crop production more efficient and more sustainable.

The solution
Within the scope of the the European research project "Clever Robots for Crops" (CROPS), later the "Sweet Pepper Robot"-project (SWEEPER), the WUR developed a robot to pick sweet peppers. The prototype comprises the following modules: a tool to cut and catch the pepper; a combined color and 3D camera; an industrial six degrees of freedom robot arm, computers and electronics, all assembled on a battery powered platform that moves the robot autonomously through the greenhouse.

Once the camera system has found a ripe pepper, the robotic arm positions the tool on top of the crop stem. The arm then moves the tool a few centimeters down with a vibrating knife and cuts off the pepper crop near the main plant stem.

Object detection with MVTec HALCON
A central function in the SWEEPER robot is detection of ripe crops. For successful operation, the 3D location of each crop must be determined with high accuracy. The chosen solution is based on an RGB-D camera that simultaneously reports color and depth information.

Using this camera and a custom built LED-based flash-light illumination system, RGB images of the plant are acquired from both overview distance and close range. In order to facilitate high frame-rate operation, a straight forward shape- and color-based detection algorithm was implemented using HALCON. The algorithm scans each acquired image for regions matching the target color thresholds.

Detected regions are refined by removing detections exceeding predefined minimum/maximum sizes. To further remove misdetections additional shape parameters are calculated. Finally, depth information from the camera is used to compute the volume of the detected regions. This information is then used to further prune false detections, avoid non-harvestable crop clusters, and define harvest priorities.

The exact 3D location of the point of mass is calculated using the depth information extracted from the detected region and a standard procedure of pixel-to-world transformation of the region. Given the subsets of regions that are classified as peppers to be harvested, a methodology for harvesting sequencing was defined. The robot arm then approaches the target by visual-servo control that keeps the target in the middle of the images until it is reached.

You can download the full success story here.

Find more information about Halcon here: https://mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/

Halcon Deep Learning Sample Application - Teknix(South Korea), MVTec Halcon

Find more information about Halcon Deep Learning here: https://www.mvtec.com/services-solutions/technologies/deep-learning/

Find more information about Machine Vision here: http://advanceultravision.com/

Latest Camera Interface Revisions & Maintenance Releases - MVTec Halcon

The following HALCON interfaces have recently been updated:

USB3Vision 13.0.8

GigEVision2 13.0.4

GenICamTL 13.0.6

Hilscher-cifX 13.0.3

OPC_UA 13.0.7

AlkUSB3 13.0.1

You can download the latest interface here: https://www.mvtec.com/products/interfaces/

Find more information about Machine Vision here: http://advanceultravision.com/

How to integrate HDevEngine into a C++/C# application - MVTec Halcon

In this tutorial, you will learn how to integrate machine vision code that you developed with HDevelop into an existing C++ or C# Visual Studio application. For this, we use the Library Project Export, which simplifies the usage of HDevEngine.

Thus, you can use HDevelop procedures as simple as HALCON operators in your C++ or C# application code.

1:01 How to structure your HDevelop code
1:51 The ‘Export Library Project’ dialog
3:00 Configure Visual Studio to use HALCON
3:45 Integrate the exported HDevelop functionality
4:53 Easily adapt the machine vision code in HDevelop

In this video, HALCON 19.05 is used. You can download the used application here:
https://www.mvtec.com/news-press/video/detail/hdevengine-poject-library-export

Find more information about Machine Vision here: http://advanceultravision.com/

Edge-supported Surface-based 3D-Matching with MVTec HALCON

In this tutorial, you will learn how to extend the functionality of surface-based matching with MVTec HALCON by also using edges of objects in the 3D scene.

Using the procedure debug_find_surface_model, we will optimize the used parameters and check the matching result.

0:54 Train 3D edges
1:53 Requirements on XYZ-mappings
2:25 Checking the 3D edges and the viewpoint
3:41 Further functionality, using 2D images

In this video, a preview version of HALCON 19.05 is used. You can download the used program here: https://www.mvtec.com/news-press/video/detail/surface-based-matching-with-halcon-3

Find more information about Halcon here: https://www.mvtec.com

Find more information about Machine Vision here: http://advanceultravision.com/