2. 150
CLIENTS
250+
PROJECTS
10YEARS
in software
development
business
180
EMPLOYEES
We are a global provider of software engineering services with expertise in
the field of computer vision, data science and science-intensive solutions
Representative
Office
2 Engineering
Centers
Microsoft
GOLD CERTIFIED
Partner
Joint projects with the largest Universities in Western Europe
3out of 4customers choose us
for long-term partnership
ABTO Software Facts
3. Our Expertise
• Image recognition and processing
• Video processing and analysis
• 3D data acquisition and scene reconstruction
• Structure from motion (SFM)
• Simultaneous localization and mapping (SLAM)
• Object counting and quantification
• Pattern recognition
• Facial detection and recognition
• Pose estimation and gesture recognition
• Eye & gaze tracking
• Optical character recognition (OCR)
• Machine learning techniques
• Interpretation of video and image content
based on learning from sample data
4. Online &
Social Media
Healthcare
Security &
Surveillance
Manufacturing
& Retail
Banking
& Finance
Education &
Learning
Construction
& Real Estate
Areas of Application
5. Healthcare
• Biometrics
• Medical image analysis
• Computer vision for sensory substitution
• Statistical data processing & modeling
Our Featured Solutions
ABTO Software created a software for blood
analysis on pathological tissues for breast
cancer treatment. The software works as a
framework for white blood cell segmentation
in microscopic blood images using digital
image processing. It makes possible to detect
certain image features on a sizable image from
a microscope, apply SVM classifier to calculate
input image features and create automatic
reports on blood cell characteristics.
6. Security & Surveillance
• Face recognition solution
• License plate recognition
• Vehicle detection and recognition
• Object tracking and counting
Our Featured Solutions
We created our own algorithm for facial
recognition based on individual features
recognition to verify personal data and identify
a person.
7. , ...)
Automated recognition and measurement of 3D
objects
Construction & Real Estate
Our Featured Solutions
We developed a Phantom Scanner, a solution
for enterprise needs that employs virtual
reality and natural scene annotation. With this
solution you can easily reconstruct a 3D scene
model of the room on any mobile device by
means of video and image processing, line and
feature points detection and homographic
matrix.
• 3D scanning and rendering of objects
• Creating 3D models from point-cloud data
• 3D reconstruction from multiple photos
• Processing image-distance data from depth
cameras
• Automated recognition and measurement
of 3D objects
8. Manufacturing & Retail
• 3D positioning, environment understanding
• Software for improving quality of blurred,
noisy captured images
• Self-driving vehicles
• Mobile robotics
• industrial vision systems
• active and real time vision
• hardware for vision and image processing
Object Counter is an automated counting
system, based on slit imaging, which separates,
detects the direction, and counts moving
objects. This non-intrusive solution requires
minimum additional resources with the
measurement accuracy 99,5% .
9. Government & Finance
• Facial recognition
• License plate recognition
• Handwritten text recognition
• Image fraud detection
• Software for improving quality of
• blurred, noisy captured images
Our Featured Solutions
We created an image fraud detection
software that allows for real-time content
recognition with simultaneous automated
image calibration and transfer of tags to
content publishers and providers.
10. Education & Learning
• Augmented and virtual reality software
• Application-specific gaze & eye tracking
systems
Our Featured Solutions
Our team developed a custom eye tracking
software that captures natural human
behavior and provides unbiased constant data
stream. The software is used in such areas as
psychology, education, marketing and other
fields that involve processing data of human
performance. It is a flexible suite perfect for
qualitative and quantitative research in real-
world environments (analysis programs) or in
the lab settings (scenarios for integration with
experiment centers).
11. Online & Social Media
• Machine learning
• Statistical estimation
• Mobile communications
Our Featured Solutions
We created a video editing app is a tool that
enables users to create, modify, and share clips
across multiple social media sites and
platforms online. Video analysis and object
tracking technology are applied to video items.
BotOrNot is our own mobile product that
allows detecting fake followers on Twitter with
high level of precision. Classification,
clustering, data processing, information
retrieval are effective in context of social
network analytics.
12. R&D Projects In Progress
• Predictive analytics
• Speech recognition
• Customer segmentation, Cross-sell,
Customer retention
• Demand forecasting
• Patient scorecards
• Digital health records
• Image analytics
13. Food Scanner and Recognition App
On My Plate is a mobile app which
recognizes and calculates calorie
intake from images of food items in
real-time. The solution employs
machine learning techniques and
helps maintain everyday healthy
lifestyle.
Machine Learning is a branch of artificial intelligence that builds systems which can learn from data. These systems can adapt to real-world usage and perform better than classic systems in many situations.
Recent advances in Machine Learning technology allows us to extract features embedded in images or videos and use them as input parameters for machine learning algorithms. These algorithms learn from the input parameters and make assessments, classifications, identifications, decisions or predictions.
During this learning process, a human trainer tags areas within multiple images and labels them according to his or her needs and goals.
Based on mathematical and statistical analysis, the software creates a learning database it can use later to label objects in a new set of images. This labeling, also known as recognition reflects the statistical likelihood that a given visual element has matched a label in the learning database.
<p>This learning process is useful for cases where the appearance of the features is not an exact match to a reference image even after the images have been processed and normalized.</p> <div class="cl"></div> <p>On the other hand, recognition of exact matches after normalization does not require Machine Learning.</p>
Machine Learning can identify objects in one specific image or recognize actions based on changes in the object's state over time.
The combination of learning algorithms, and features to be extracted, and the dataset used for learning is important to achieve the desired results because each type of classification can require its own features to be extracted and its own images for training.
For example, a system can learn to identify dogs and differentiate them from cats. Or, classify dogs by breed such as Chihuahua, Bulldog or Poodle. Or classify dogs and cats as four-legged animals. Or identify an individual dog.
We create practical ComputerVision applications using the latest research and breakthroughs in Machine Learning.