Search
Woodspect

Multi-sensor Quality Control
system based on
machine learning algorithms
(Deep Learning AI)

  • About
  • Advantages
  • Defects detected
  • Technical Data
  • Gallery
  • Brochure
WOODSPECT - wood quality control
WoodSpect is a cutting edge, fully automated machine vision system based on neural networks (deep learning AI), dedicated to global manufacturers of furniture, wood flooring, windows, facades, wooden construction materials and wood-based materials (cardboard).

WoodSpect's defect detection accuracy reaches up to 98-99%, depending on the application.

WoodSpect combines innovative optics with advanced automation and factory IT. Thus it is able to replace manual inspection of products, increasing quality control efficiency.

The system helps automate quality control processes on production lines from raw material to finished board.

The flexibility of the Woodspect systems (customized hardware and personalized "learning" proprietary software KSM Vision based on AI) allows it to be applied to the needs of different types of wood-based products, including but not limited to:
- laths, lamellas
- boards (including glued laminated wood)
- plywood
- floor panels
- windows, doors
- wooden constructions
- cardboard

WoodSpect's AI-driven algorithm for detecting defects in wood products achieves a high efficiency of 98-99%, with a low number of samples classified incorrectly.

WoodSpect - similarly to other KSM Vision systems - is tailored to corporate requirements, in terms of IT systems: data exchange, user rights management, reporting.

Ideal customers for WoodSpect are major global players in wood manufacturing seeking automated vision control solutions to optimize their production processes.
Advantages:
- wood defect classification accuracy of 98% (compared to 90% accuracy of manual classification)
- user-friendly interface allowing visualization of results in graphical form
- easy integration of the system into the existing production line
- centralized qualitative and quantitative product control

Options:
- preview of quality control statistics for each product with visualization of rejected products
- access to in-depth quality control statistics by time, product, shift, lumber supplier
- defined trend values and alarms
- detailed reporting
- mobile system management module

What do you gain?
- guaranteed consumer satisfaction
- solving labor shortages by introducing automated machine vision based on artificial intelligence in place of manual inspection
- strengthening brand reputation and trust - consistently delivering quality products
- avoiding problems and rising costs in the downstream woodworking process (log > lamella > press > machining > varnishing > packaging > finished product > customer return / lost customer)
KSM Vision AI-driven Woodspect can distinguish a crack from a saw mark, or a resin pocket - from resin overgrowth.

Woodspect systems provide full detection of the the natural wood-based products on the sides and on the surface of products, including:
- cracks
- resin pockets
- rotten, cracked or falling knots
- mechanical damage (including cavities)
- discoloration (blue stains)
- defects in geometry
Woodspect is based on two measurement technologies: a 3D scanner, based on the laser triangulation method, and a color scanner using an RGB linear camera.

Woodspect offers two groups of applications, which can be distinguished according to the measurement method:

- Detection of defects on raw boards - algorithms based on neural networks make it possible to detect defects such as resin pockets, broken knots, mechanical damage. This type of quality control can be used i.a. to eliminate defects at lamella mandrel joints and automate the repair of the top surface of products.

- Precise measurement of 3D geometry - by using the laser triangulation method, it enables accurate measurement of the surface of boards after mechanical processing. This type of quality control can be used, i.a. to detect the volume of defects, which enables automation of the puttying process.

Configurable interface and database
Based on the production specification system interface can be adjusted, including automatic system set-up with data upload by higher-order system (e.g. MES) and additional data upload by line operator. Data collected by the system can be automatically uploaded to higher-order system.

They have already trusted us

  • In our opinion, the use of neural networks and the function of classifying detected defects distinguish the KSM Vision solution from competitive solutions, and the effectiveness achieved by the system ensures quality control at the level of systems of leading manufacturers.
    MLEKOVITA, 1 of 100 biggest Polish private companies 2022 according to Forbes
    M.A. Engineer Dariusz Sapiński,
    President of the Board
  • When designing the solution, KSM Vision showed great flexibility in adapting the system to the expectations of the BIOFARM Production Department. (...) Since the implementation of BLISPECT vision technology on the 1st BIOFARM production line almost two years ago, the KSM Vision Service Department has been available to BIOFARM employees with a good reaction time.
    BIOFARM Jarosław Pieczuro,
    President of the Board
  • KSM Vision Sp. z o. o. has developed a system for quality control of glass vials for pills. (...) A big advantage of the system is the use of machine learning algorithms, which allows easy adjustment of the system.
    ADAMED Group Dariusz Stępień,
    Dyrektor ds. Infrastruktury i Mediów

Our R&D on the solutions with the use of neural network potential are backed by our renowned partners: