AugeLab Studio Manual
English
English
  • 👋Welcome to AugeLab Studio User Manual
  • 📘Introduction
    • AugeLab Studio
    • Key Features
    • Use Cases
    • System Requirements
  • 🚀Getting Started
    • Signing up
    • Installation
    • First Look
    • Simple Tour
    • Your Very First Project
      • Basics
      • Detection
      • Wrapping Up
    • More Local Examples
    • Further Reading
  • 🖥️AugeLab Studio Interface
    • Detailed Look
    • Scenario Area
    • Menu and Toolbar
    • Managing Projects
    • Installing AI and much more
      • Leverage AI with Module Downloader
  • 🧱Function Blocks
    • Block Structures
    • Sockets
    • Blocks Column
    • Connections
    • All Function Blocks
      • AI Blocks
        • Face Detection
        • Mask Detection
        • Object Detection - Custom
        • Object Detection
        • Pose Estimation
        • Safety Equipment Detection
        • Social Distance Detector
        • Super Resolution
        • Text Detection
        • OCR
      • CNN Blocks
        • Average Pooling 2D
        • Batch Normalization
        • Choose Folder 2D
        • Compile Model
        • Conv. Sep. Layer 2D
        • Conv. Trans. Layer 2D
        • Convolutional Layer 2D
        • Dropout Layer
        • Flatten Layer 2D
        • Fully Connected
        • Global Average Pooling 2D
        • Global Max Pooling 2D
        • Input Layer 2D
        • Loss CCE
        • Max Pooling 2D
        • Metrics Accuracy
        • Model EfficientNet
        • Model MobileNet
        • Model ResNet
        • Model VGG
        • Optimizer Adadelta
        • Optimizer Adagrad
        • Optimizer Adam
        • Optimizer Adamax
        • Optimizer FTRL
        • Optimizer Nadam
        • Optimizer RMSProp
        • Optimizer SGD
        • ReLU Layer
        • Softmax Layer
        • Training Parameters
      • Data/Logic
        • Flow Control
          • Batch Concatenation
          • Batch Processing
          • Debatch
          • Get Batch Size
          • HMI Background
          • Subsystem Enabled
          • Subsystem In
          • Subsystem Loop
          • Subsystem Out
          • Subsystem
        • logic
          • All True
          • And
          • Demux
          • Equals
          • Greater
          • Logic Operations
          • Mux
          • Not
          • Or
          • Set - Reset
          • Smaller
        • Mathmetical Operations
          • Add
          • Counter
          • Divide
          • Math Operations
          • Maximum
          • Minimum
          • Multiply
          • Not Equals
          • Round
          • Square Root
          • Subtract
          • Trigonometry
        • Data Operations
          • Data Memory
          • Data to JSON
          • Data Type Converter
          • Datetime Compare
          • Dictionary Operations
          • Exclude Nones
          • Find Substring
          • Get Element
          • Is None
          • List Operations
          • Parse Data Dictionary
          • Replace None
          • String Merge
          • String Operations
        • Referencing
          • Data Read Global
          • Data Read Local
          • Data Write Global
          • Data Write Local
          • Debug Input
          • Tag From
          • Tag To
        • Signal Operators
          • Delay Step
          • Edge Falling
          • Edge Rising
          • Multi Port Switch
          • OFF Delay
          • ON Delay
      • Image/Transformations
        • Analysis
          • Color Density Percentage
          • Get Dimension
          • Histogram On Curve
          • Histogram On Line
          • Image Color Match
          • Image Memory
          • Image Resolution and Channel Value
          • Maximum Images
          • Mean Value of Image
          • Measure Position Distance
          • Minimum Images
          • Non-zero of Image
          • Std. of Image
          • Structural Similarity
        • Transformation Filters
          • Auto Alignment
          • Auto Contrast
          • Color Quantizer and Clustering
          • Color Space
          • Contrast-Brightness-Gamma
          • Contrast Optimization
          • Deconvolution
          • Denoising
          • Distance Transformation
          • FloodFill
          • Grab Cut Algorithm
        • Color Filters
          • 2D Filter
          • Apply Mask
          • Bilateral Filter
          • Blur
          • Edge Filter
          • HSV Filter
          • Image Adaptive Threshold
          • Image Threshold
          • Invert Image
          • Morphological Transformations
          • Normalize Image
          • RGB Mask
          • RGB Set
          • Sobel Filter
        • Operations
          • Add Images Weighted
          • Add Images
          • Collage Images
          • Divide Images
          • Flip Image
          • Image AutoRotator
          • Image Concatenate
          • Image Resize
          • Image Resizer
          • Merge Channels
          • Multiply Images
          • Polar Transform
          • Rotate Image Angle
          • Slice Image
          • Split Image
          • Subtract Images
      • Detections/Shapes
        • Detectors
          • Barcode Reader
          • Blob Detector
          • Blur Detector
          • Circle Detector
          • Corner Detector
          • Custom CNN Model
          • Data Matrix Reader
          • Detect Reference
          • Feature Detector
          • Find Object - Multiple Image
          • Find Object
          • Find Reference
          • Harris Corner Filter
          • Line Detector
          • Match Shapes
          • Measure Object Distance
          • Shape Detector
        • Draw
          • Draw Detections
          • Draw Line
          • Draw Point
          • Draw Rectangle
          • Draw Result On Image
          • Write Date On Image
          • Write Text On Image
        • Roi Processing
          • Check Area (Polygon)
          • Check Area
          • Get Pixel Mouse
          • Get Pixel
          • Get ROI
          • Image ROI Center
          • Image ROI Polygon
          • Image ROI Select Multi
          • Image ROI Select
          • Image ROI
          • Perspective Transform
          • Rectangles in Rectangle
        • Shape Analysis
          • Approximate Contour
          • Choose Line
          • Contour to Image
          • Fill Contour
          • Find Contour
          • Hull Convex
          • Minimum Circle
          • Minimum Ellipse
          • Minimum Rectangle
          • Minimum Rotated Rectangle
          • Most Similar Shape
          • Point Polygon Test
      • Input/Output
        • Communication
          • Modbus Connect
          • Modbus Read
          • Modbus Write
          • MQTT Publish
          • MQTT Subscribe
          • OPC UA Client
          • OPC UA Read
          • OPC UA Write
          • REST API - Get
          • REST API - Post
          • Send Mail
          • Siemens S7 Connect
          • Siemens S7 Read
          • Siemens S7 Write
        • Data Inputs
          • Date-Time List
          • Date-Time
          • Headless Check
          • Keyboard/Barcode Reader
          • Logic Input
          • Number Input
          • Number Range
          • PWM (Pulse Width Modulation)
          • Rising Edge
          • String Input
          • Text
        • Image Inputs
          • Camera IP (ONVIF)
          • Camera IP
          • Camera USB External
          • Camera USB Vidgear
          • Camera USB
          • Load Image From Path
          • Load Image
          • Make Image
          • Pixel
          • Video
        • Outputs/Exports
          • CSV Export
          • Cycle Timer
          • File/Folder Operations
          • GPU Statistics
          • Image Logger
          • Image Write
          • Led Output
          • Multi Image Write
          • Output
          • Scope
          • Show Image
          • Stop
  • 📡Devices and Communication
    • Camera Usage
    • Communication Protocols
    • Further Reading
  • 🧩Example Projects
    • Demo Projects
    • Circumference Measurement
    • Object Counting
    • Tile Width Measurement
    • Human Detection
    • Object Detection
  • 🔑Key Features
    • Deploy Custom HMI Applications
    • Annotate Data for Object Detection
    • Train Custom AI Models
      • Choosing the Right Database
      • When to Stop Training
    • Create Plugins
      • Components
      • Coding Reference
    • Share Your Solutions with Community
    • Instal Python Packages
  • 📑FAQ
    • Contact Us
    • FAQ
    • Setting up a full project
  • Additional Resources
    • Training Schedule
    • Training Materials
    • AugeLab Experts
  • Appendix
    • Dictionary
    • References
Powered by GitBook
On this page
  • 1. WHAT IS RECIPE WINDOW
  • 2. HOW TO INSTALL / START RECIPE WINDOW
  • 3. USER INTERFACE
  • 4. RECIPE MODEL
  • 5. ADDITIONAL FEATURES
  • 6. TIPS

Was this helpful?

  1. Key Features

Deploy Custom HMI Applications

PreviousObject DetectionNextAnnotate Data for Object Detection

Last updated 8 months ago

Was this helpful?

1. WHAT IS RECIPE WINDOW

The Recipe Window lets you create and manage multiple image processing tasks (recipe rules) as a single application (recipe) through a simple user interface. You set up these recipes in AugeLab Studio during the project development phase, and you can later deploy or change them easily using the Recipe Window. This helps you develop, monitor, and test complex image processing projects without needing advanced technical skills.

2. HOW TO INSTALL / START RECIPE WINDOW

Recipe Window can be used as an external application (no need to open AugeLab Studio). Recipe Window can be installed by AugeLab Studio. Click "Tools -> Install Recipe Window" in menubar.

After installation, shortcut (AugeLab Studio - Recipe Window) will be created on desktop. With using these shortcut Recipe Window can be used as an external application (no need to open AugeLab Studio).

3. USER INTERFACE

There is three sub window in Recipe Window. There sub windows are:

  • EDITOR WINDOW

    • Recipe can be created / modified in this window.

  • VIEW WINDOW

    • Created recipes can be monitored in view window.

  • TEST WINDOW

    • Created recipes can be tested by given test images in this window.

3.1. EDITOR WINDOW

This is the editor window in Recipe Window app. In this window, user can create / modify recipe. Let's check how to use it step by step.

  1. LOAD MODEL BUTTON

  2. EDIT CAM CONFIG

    Cameras are used as image source for recipe rules. Each rule needs an image source to apply an image processing task. Before start to create a recipe camera config needs to be specified. This configuration can be set by Camera Configuration Window. All connected cameras listed on this window. Camera resolution and advanced settings (exposure, white balance, ... with CAM SETTING button) must be set for each camera. Frames can be checked via CHECK CAMERA button. If there is an issue about camera (such as connection issue) all connected cameras can be RESCAN or RELEASE with related buttons. After all configuration completed save config via SAVE CONFIG button.

  1. SELECT CAMERA

    As mentioned before, each recipe rule needs an image source(camera). Before creating a recipe rule a camera needs to be selected.

  2. SET RULE CONFIG

    After camera selection, a recipe rule type needs to be selected based on requirements. This recipe rules listed based on [recipe model]. A recipe can have multiple rules, each rule must have a unique name in order to distinguish between multiple rules.

  3. SET RULE IMAGE

    Image can be obtained with various ways in Recipe Window:

    • TAKE IMAGE button

      • Get and display an image from selected camera immediately.\

    • IMPORT IMAGE button

      • Image file can be also used instead of camera as image source.

      ⚠️ Image resolution must be same with camera resolution.

    • TAKE IMAGE WITH TRIGGER button

  4. SELECT AREA REGION

    User may need a specific area on camera frame/image to perform image processing tasks. After clicking SELECT AREA button user can specify this area on image with click and drag with mouse.

  5. SELECT OBJECT REGION

    User may need to create a reference image for some image processing tasks (such as finding and object). This reference object image can be specified with SELECT OBJECT button. After clicking this button user can specify object boundary on image with click and drag with mouse.

  6. RULE OPERATIONS

    Until now, we completed following steps:

    • camera config done

    • rule type and name defined

    With clicking ADD RULE button, all these configuration will be combined and added into recipe as rule.

    ** UPDATE RULE: click related rule in rule table, update a parameter (camera, rule type, object area, ...) and click UPDATE RULE button. ** DELETE RULE: click related rule in rule table, click DELETE RULE button.\

  7. SAVE RECIPE

    As a last step, all created rule configurations with related images and camera configuration needs to be saved as a file with SAVE RECIPE button.

3.2. VIEW WINDOW

On previous section, we check features of editor window and learn how to create new recipes. In View Window, these created recipes can be start as process and result can be checked as shown below.

Let's check how to use this View Window step by step:\

  1. Define Recipe Name and Run\

    At first step, recipe name need to be defined to run. If there is an available saved recipe with given name. When RUN button clicked, if all configuration is valid and trigger is true, model start to run and results shown as image and table view consecutively.\

  2. Check Results As mentioned on previous sections, a recipe may have multiple rules. As displayed in the image above, recipe named pi loaded and run. Since there is two rules in this recipe, there is two bordered image in displayed image.\

    In this example, there is error in circle measure rule in last run. To indicate error in user interface, there is red border on related rule image and also NOK indicator displayed on table view, also the rule name which is detected as NOK is displayed.\

    There is also a counter in table view to display how many product processed and how many product detected as NOK. In this example, there is 12 run which means 12 products triggered and processed and there is 1 product which is not valid for all recipe rules.\

    RESET BUTTON : Counter can be reset when reset button clicked. RELOAD RECIPE BUTTON : If there is any update on recipe, recipe can be reloaded with clicking this button so no need to restart application.

3.3. TEST WINDOW

Before to start run created recipe, users may need to test recipes. In Test Window, created recipes can be tested with given image files. User only needs to select an image folder which contains multiple images for each camera object in recipe. After loading images, images can be checked with clicking on image path which listed on the left side in a table view. If all images loaded properly, recipe can be run for each images with clicking RUN TEST button. After run completed, all input images replaced with result images so these image can be checked with clicking on it. Result image layout is same with in View Window, each rule indicated in a bordered view in main image.\

⚠️

  • Loaded images resolutions has to be same with camera resolution which defined in recipe. Loaded image resolutions can be checked bottom-left corner of the window.

  • If multiple cameras used for recipe, loaded image folders has to be separate for each camera and image counts has to be same in order to run model for each image pair successfully.

4. RECIPE MODEL

As mentioned before; a recipe consists multiple recipe rules and the recipe rule basically is an image processing procedure. This procedure is a combination of image processing tasks. There is a two default recipe rule in Recipe Window, but user is responsible to create their own procedures based on their needs.

Recipe model is a file which created in AugeLab Studio. The layout of this model file displayed in following image:

There is 4 section in model file:

  • Recipe Loader Plugin: This plugin file reads recipe file and get all configurations (camera config, rule data, ...), and send these data to other components.

  • Check Trigger Subsystem: This component get trigger rule (frame, configs) as input, creates a trigger signal which means camera detected related object and image processing tasks can start to process.

  • MAIN Subsystem: This component consists all image processing procedures and runs all procedures based on given inputs (rule data, trigger signal).

  • Check Result Subsystem: MAIN subsystem returns many outputs (images, signals, ...) for each rule. This component process all input data and returns images (one image for each rule) and signals (one signal for each rule).

User should modify only MAIN subsystem.

MAIN SUBSYSTEM

MAIN subsystem internal layout displayed in following image:

There is 2 section in this MAIN subsystem:

  • Rule subsystems: These subsystems is the main logic part of the recipe rule. These subsystems needs to be modified by user based on their needs. Steps to add new rule:

    • Copy-paste existing rule

    • Connect inputs (rule data) and outputs (collect images and signals)

    • Update rule subsystem

    Each rule block has two outputs: - Image: Contain result image of image processing procedure - Signal: Contain signal which represents NOK/OK status. Recipe Windows detects all rules and lists them as a table, so user can create recipe with using these rules. \

  • Collect Images & Collect Signals: This subsystem merges all images and signals from each rule subsystems.

5. ADDITIONAL FEATURES

5.1. HOW TO SIMULATE CAMERAS

SIMULATE USB CAMERAS

❗ These setting valid only for basic USB cameras.

In some cases, recipe needs to be updated even if required cameras not connected. In this case usb cameras can be simulated with config/sim_usb_cams.json file.

Recipe specific cameras can be simulated with copy-paste camera_config data from related recipe json file into config/sim_usb_cams.json as following.

Simulation can be disabled with deleting content (don't delete the file) of config/sim_usb_cams.json file.

Random image will be displayed in recipe window for selected camera. Image can be replaced with IMPORT IMAGE button.

❗ Imported image resolution should be same as camera resolution.

❗ Imported image can be seen only in EDITOR view (can be used to edit recipe rules). Random image will be used during running recipe scenario (VIEW window).

IP CAMERA

❗ These setting valid only for basic IP cameras.

If there is any connected IP cameras (basic IP camera, no external library), ip addresses needs to be added into config/ip_cam_config.json

json format:

{
  "192.168.5.200": {},
  "192.168.5.100": {},
  "192.168.5.50": {}
}

6. TIPS

6.1. KEYBOARD SHORTCUTS

  • Ctrl key focus on recipe name input (not working when already focused on image widget etc.)

  • Alt key changes tab view

  • R or S keys starts/stops scenario on view window

  • F11 to toggle trigger override (working only VIEW window)

  • Shift + L to toggle visibility of log window

Recipes created based on recipe model configuration. This model contains all image processing procedures, it is created in AugeLab Studio. This model file will be explained in detail in section.

A trigger must be defined in in order to get one image when related object detected to perform defined image processing task in model file. This buttons waits trigger then get and display the image.\

🔑
RECIPE MODEL
recipe model
RECIPE WINDOW INSTALLATION
RECIPE WINDOW USER INTERFACES
EDITOR WINDOW
CAMERA CONFIG WINDOW
VIEW WINDOW
TEST WINDOW
RECIPE MODEL LAYOUT
RECIPE WINDOW - MAIN SUBSYSTEM
USB CAMERA CONFIG SIMULATION
USB CAMERA SIMULATION