Machine
Learning

Who we are. What we do.

Abto Software started the science journey 15 years ago as a partner of Lausanne University in Switzerland. One of our first projects was to develop smart software for horizontal drilling. The solution was recognised as the world’s most advanced steering tool for laying pipes and the first guidance system not affected by magnetic interference.

Scientists and innovative decision makers across all industries come to us with their ambitious ideas. We build and train intelligent applications that help businesses improve safety of people’s homes, fight fraud, reduce number of traffic incidents, or simply bring color to your black and white photos.

LEARN MORE…

Machine Learning in Real-World Applications by Industry

Machine learning can provide insight for all businesses and industries, tackling challenges of text analysis and natural language processing, object recognition.

Government and Security

  • Thief detection
  • Face detection and recognition
  • Counterfeits detection
  • CV for blind people

Healthcare

  • Alerts and diagnostics in medical imaging
  • Skin disease detection and recognition
  • Real time laser control for eye surgery
  • Food calorie counter

Retail & Real Estate

  • Kitchen details, furniture recognition & classification
  • Automatic image annotation
  • Body measurement

Transportation

  • Vehicles recognition/detection
  • License plates recognition
  • Road traffic analyses

Projects

We gather relevant datasets and develop intelligent applications that can read, learn and advise like humans do.
Learn what problems Abto Software has helped solve for the clients today, and help us find your solution tomorrow.

Customer:

Tech company, Israel

Project challenges:

  • Camera software works in real-time environment under any conditions: illumination, weather, etc
  • Detect vehicle direction
  • High software performance, since in most cases the vehicle is a moving object
  • Powerful synergy with the client’s suite of vehicle recognition products
  • Poor input file resolution, usually because the plate is too far away, or blurry images, particularly motion blur
  • Simultaneous processing of multiple video streams from CCTV cameras on different devices

Technologies and Instruments:

  • The back-end development tech stack: PHP, Laravel, Node.js, Amazon Web Services: S3, RDS, SQS, SNS, Database: MySQL.
  • Web UI tech stack: AngularJS, HTML, CSS.
  • Data Modeling and Architecture: machine learning and image/video processing algorithms, Haar Cascades.

HIDE INFO

Customer:

R&D project

Key features:

  • 75% precision rate
  • identification of food items from consumer camera-enabled device
  • real-time calorie counting
  • simple, lean and intuitive interface
  • possibility to add and edit food composition

Technologies and Instruments:

  • Android, iOS, image processing, machine learning, feed-forward artificial neural networks, image segmentation and clustering (k-means)
  • MATLAB, C++, Python, OpenCV, Qt

Project challenges:

  • to train an accurate classification model based on an extensive food images database
  • to build a robust system with multi-view image variations
  • to implement computer vision technologies, clustering and machine learning for Android and iPhone devices

HIDE INFO

Customer:

Expert consulting company, US

Benefits:

  • Increased Conversions. Being a machine-learning based conversational dialog engine, the chatbot can communicate with any number of people at the same time, giving instant responses to the questions users present.
  • Higher engagement. Customers are twice more likely to interact with a website when you reach out with a proactive chat

Technologies and Instruments:

  • AAI, ChatScript, flask, gunicorn, machine learning algorithms, nginx, Python, scikit-learn

Project challenges:

  • Optimization of the dialogues and reactions to the users’ messages for meaningful conversations outcomes
  • Ensuring basic language understanding and specific scenarios
  • Personalization

HIDE INFO

Machine Learning Tools and Technologies

Machine learning algorithms, methods and tools we use to develop smart software that can recognize objects, features, and patterns within images, video, and written content generating highly intelligent and insightful data.

Supervised learning algorithms

  • Artificial neural networks
  • Decision tree learning
  • Learning classifier systems
  • Nearest neighbor algorithm
  • Support vector machines
  • Random forests
  • Ensembles of classifiers
  • Bayesian statistics
  • Naive bayes classifier
  • Convolutional neural networks

Unsupervised learning algorithms

  • Approaches for learning latent variable models such as
  • Expectation–maximization algorithm (EM)
  • Method of moments
  • Blind signal separation techniques, e.g.
  • Principal component analysis
  • Independent component analysis
  • Non-negative matrix factorization
  • Singular value decomposition
  • Сlustering
  • K-means
  • Mixture models
  • Hierarchical clustering
  • Anomaly detection

Tools

Investigation:

  • MATLAB
  • R
  • Python

Implementation:

  • C++
  • OpenCV
TESTIMONIALS

“It always was and is an excellent work together and we look forward to many years more. I definitely can recommend Abto for a nearshore center.”

We started to build a dedicated team in Lviv together with Abto Software 3 years ago. As a product vendor, we rely on resources that can build up knowledge about our products long-term. Abto was able to provide us with these services.

Andreas Meier

Head of Product Development at Skybow, Switzerland

“We rely a great deal on the IT services and expertise we receive from Abto.”

For us, it is one of our success factors to rely on a partner with a professional approach like Abto to be successful in our market segments. We are very pleased with the quality and timing that they provide.

Christian Baumann

CEO at X-smart AG, a Boost Group Company, Switzerland

“Such a good quality, paired with the promptness and a great price-performance ratio is very rare. But most of all we appreciate working with the great people of Abto Software.”

Abto Software specialists developed a huge and extremely flexible SharePoint Client App for a Swiss customer providing various IT services, including the development of software based on SharePoint and its extensions.

Philip Nussbaumer

Head of Products at Up-Great AG, Switzerland

“Working with a company like Abto makes dealing with the unexpected easier.”

Abto’s flexibility helps deal with unexpected situations, which often occur in business. Stakeholders change their minds or suffer unexpected business shocks.

Tony Clarey

Founder of an IT Consulting Company, USA

"We use the Simple Contacts HRM system for recruitment needs in our company."

“We have been using it for more than one year, and it helps us to manage our recruitment process, make different custom reports, analyze data for recruiting metrics.

I really like that the system is integrated with LinkedIn, and you can open candidates’ profiles with one click. The system helps with sending meeting requests, notifications and newcomer letters. I can easily open a vacancy in the system or attach a candidate to it. I see the target day and how many days vacancies are at work. These things I like the most.”

Iryna Cherkas

Head of Recruitment

SEE OUR CUSTOMERS

Contact us

Tell your idea, request a quote or ask us a question