LumiScan Ecosystem: Object Shape Detection

LumiScan Object Finder

Finds known parts in the camera image by their shape – robust to changing light and surfaces.

LumiScan Object Finder locates known objects in a camera image by their shape. This machine vision app matches the edges of an object's outline rather than its brightness, which makes it tolerant of changing light and surface finish: a shiny part and a matte one present the same outline.

You teach an object directly from the live camera image, with one view per orientation or working distance. The app reports every match with position, size, score and object name – for presence checks, robot picks and sorting mixed parts on a belt.

Features

Shape-based matching on the object outline
Teaching from the live camera image – no file transfer, no image editor
Several views per object for different orientations or distances
Every match with position, size, score and object name
Objects taught once are available to all modules

Typical applications

Presence and count checks
Position feedback for robot picks
Sorting mixed parts on a conveyor
Orientation checks before an assembly step

Integration

ctrlX OS (ctrlX CORE or ctrlX IPC) with the ctrlX Data Layer
Windows 11 or Ubuntu 24.04 with LumiScan Keryx
Control from a ctrlX PLC on the same device, or via OPC UA on a PC
Images from LumiScan Cam Driver for GenICam cameras on the same device
Matches drawn on the image in LumiScan Cockpit

All apps in the ecosystem

Frequently asked questions

How does Object Finder find parts?

By their shape: it matches the edges of the object outline rather than its brightness. That makes it tolerant of changing light and surface finish – a shiny part and a matte one present the same outline.

How do we teach an object?

Directly from the live camera image, in the lighting the installation will use – no file transfer, no image editor. You can store several views per object for different orientations or working distances; an object taught once is available to all modules.

What does Object Finder report?

Every match with position, size, score and object name – for presence and count checks, robot picks, sorting mixed parts on a conveyor and orientation checks.

Object Finder or Template Finder?

Template Finder compares a small picture of the part and also reports scale and rotation. Object Finder compares the outline, which is more robust when light or surface finish change. Both are taught from the live camera image.

Does Object Finder run on ctrlX OS and on a PC?

Yes. On ctrlX OS (ctrlX CORE or ctrlX IPC) it uses the ctrlX Data Layer; on a PC with Windows 11 or Ubuntu 24.04 it uses LumiScan Keryx. Node addresses, types and behaviour are the same on both, so a program written against one works against the other. On a PC, a PLC controls it via OPC UA.

Where does the app get its images from?

It does not talk to a camera itself. It reads the image node of another app on the same device, normally LumiScan Cam Driver for GenICam cameras. Supported pixel formats are Mono8, Mono12, RGB8, RGB12, BGR8, BGR12 and the common Bayer 8/12-bit formats.

Interested in LumiScan Object Finder?

Tell us briefly about your application – we will get back to you within one business day with a quote.

Request a quote