Get in touch
Case Study
August 10, 2023

AI & ML Solution for a Facade Building Company

Federmeister GmbH

Federmeister GmbH

AWS, AL & ML, Construction, APAC
AI & ML Solution for a Facade Building Company


AI & ML Solution for a Facade Building Company

Federmeister specializes in the renovation of building facades. With a set of experienced workforce, they are called a specialist company in the market for quality in all trades: from planning to execution on the construction site. Federmeister has developed a digital platform for customers to quickly upload their requirements and get a customized quote for the desired services. They provide personal advice to customers with facade experts. Currently, they operate in four regions Rhine-Main metropolitan, Central Germany, Rhine-Neckar metropolitan and Stuttgart) In the near future, the rollout to the whole of Germany is planned.


At present, customers upload images on the platform to request a quote on the desired services. Once Federmeister’s backend team receives the information, they evaluate the requested services by using a third-party tool to re-create the image in different formats and calculate the cost of the services. This process takes an average of 8 hours in conversion which will help to plan and calculate the total cost and send the quote. When the inquiries are high on certain days, the actual deadline for sharing quotes with the customer is hard to achieve.


  • Built an application to compare the area with the predefined fixed values (with reference sheet) and calculate a quote. It will enable customers to upload correct images of their facades to the given web application.
  • Ability to detect objects and classify correctly and provide an accurate bounding box for the detected object.
  • The developed machine learning engine will detect and classify the door, windows, and facade. A customized algorithm is developed specifically to identify the doors, windows, and facades and trained on the engine.
  • The ML engine detects the image and measures the area of the objects (door, windows, and facade) with the predefined fixed values (with a given reference sheet) and calculates a quote based on the measurements.
  • The required measurement method & quote formulas will be prefixed in the system backend. The output will be given in the desired format requested by the client.

Business Outcome

  • Each component of the facade like windows, doors, and wall are trained with a large number of datasets (shared from Federmeister) to give high accuracy.
  • Time taken for quote generation reduced drastically from 2 weeks to 8 hours. This reduced the manual effort being put in and increased operational efficiency.
  • Gives the capacity to change in size or scale without worrying about the workload.
  • We expect the solution to achieve 80% accuracy in identifying the facade (door, window, wall). We will measure the objects with pre-defined values, and give the cost calculation as output in the desired format.

Federmeister GmbH

Sehr service-orientiertes Team. Steuern Prozesse und anfallenden Tätigkeiten sehr gründlich und zuverlässig. Regelmäßige Updates und Kommunikation, man ist immer im Bilde über anfallende Schritte. Toller Partner, jederzeit sehr zu empfehlen.

Daniel Herr

Federmeister GmbH

About AnkerCloud

Ankercloud helps you grow and maximize your cloud potential

Ankercloud has been delivering AI & ML projects utilizing AWS services & helping clients across the globe. Ankercloud is a preferred partner for AWS with a long experience of delivering ML solutions on multi-cloud platforms. A team of professionals closely discuss the requirements & architect the solution approach in an agile model of project delivery. Hands-on consulting approach is encouraged at all levels within the organization to gain the customers trust and respect. This provides Ankercloud with a competitive edge in the partner ecosystem as a preferred choice.

Learn More
Success stories

Success stories

Get in touch

The Ankercloud Team loves to listen!

Talk to us

Get in touch.
The Ankercloud Team loves to listen

Thank you!

Your submission has been received!

Oops! Something went wrong while submitting the form.