Summary
- Profile Type
- Technology offer
- POD Reference
- TORO20230406014
- Term of Validity
- 25 May 2023 - 24 May 2025
- Company's Country
- Romania
- Type of partnership
- Commercial agreement with technical assistance
- Research and development cooperation agreement
- Targeted Countries
- All countries
Contact the EEN partner nearest to you for more information.
Find my local partner
General information
- Short Summary
- A Romanian research team has developed Quality Control Technologies based on Artificial Intelligence and Machine Learning to that privide Optical Character Recognition (OCR), Object Detection or Anomaly Detection. They would like to conclude to conclude commercial agreements with technical assistance and research and development cooperation.
- Full Description
-
The Romanian company, based in Transylvania, supports businesses in accessing novel solutions based on the most recent advances in Artificial Intelligence and Machine Learning:
● They design customized solutions based on cutting edge technologies
● Their software are easy to use with simple and intuitive user interfaces
● They focus on explainable models and effective visualization tools
The Romanian company has developed several products which can be modified and adjusted according to customer needs:
Optical Character Recognition (OCR)
● Robust models in the presence of characters with deformations, occlusions, and blurred images
● Stunning accuracy also with non-standards fonts and reflective surfaces, where traditional OCR fails.
● Optical Character Verification (OCV) based on user-defined patterns
● Possibility to refine the model online with annotated images for brilliant performances on the most difficult OCR scenarios
Object Detection
● Detect position and orientation of objects in images, train models with few images per class
● Pre-trained out-of-the-box models for generic object detection capable of identifying position and orientation of more than 600 objects in an image
● Robust models recognizing objects in the presence of rotations, deformations and partial occlusions
● Customized models trained using ad-hoc synthetic datasets for domain-specific object detection with superior performances on the most challenging tasks
● Zero-shot object detection allows to detect images of objects never seen in training
Anomaly Detection
● Detect anomalies in regular surfaces with regular patterns, such as cracks, defects, discoloration, also when they are unknown a priori
● Pre-trained out-of-the-box models capable of identifying anomalies in regular surfaces with regular patterns, such as cracks, defects, discoloration
● Customized models trained with only few images of flawless cases can successfully identify anomalous examples of unlikely appearance in images coming from specific domains
● Anomalous samples can be provided to the model to better discriminate anomalies and tune the sensitivity and determine the acceptable sample variability
● Anomalies are highlighted in the image with heatmaps to highlight missing or extra elements and support model explainability.
The company is looking for partners via commercial or outsourcing agreements. - Advantages and Innovations
-
● Learning background in Mathematical Engineering, Computer Science Engineering Automation and Computer Science and Medical AI
● Professional experience working in European-funded research projects in the field of Machine Learning and Deep Learning.
● Research experience gained during PhD in Information Technology, PhD in Theoretical and Computational Physics and postdoctoral research.
● Customized as well as out-of-the-box ultimate solutions continuously updated based on the most recent advances in Deep Learning
● Optimized models with top-rated performances without the need of long training sessions: by combining few-shot learning and online-learning our networks can increase their performance in shorter time and reach stunning accuracy even in extreme settings
● Reduced number of labels and images required in training, thanks to the use of unsupervised pre-training, semi-supervised and self-learning techniques
● Workflow designed for minimal latency built on optimized numerical libraries and dedicated GPU parallel programming
● Models deployed on the cloud or on edge devices.
● Possibility of integration of our runtime libraries in your favorite platform: LabView, Adaptive Vision, Visual Studio 2019 C++ / C#, Halcon, Nvidia Jetson, Customized Plugins. - Stage of Development
- Already on the market
- Sustainable Development Goals
- Goal 9: Industry, Innovation and Infrastructure
- IPR status
- No IPR applied
Partner Sought
- Expected Role of a Partner
-
*Commercial agreements with technical assistance:
International Manufacturing, Aerospace or Agrifood companies who want to use the products and need technical assistance in the process.
* Research and development cooperation agreements:
Research teams specialized in Artificial Intelligence and Machine Learning in order to further develop the technologies. - Type and Size of Partner
- Big company
- SME 50 - 249
- Type of partnership
- Commercial agreement with technical assistance
- Research and development cooperation agreement
Dissemination
- Technology keywords
- 01003003 - Artificial Intelligence (AI)
- Market keywords
- 02007021 - Other Artificial intelligence related
- 02007020 - Artificial intelligence programming aids
- 02007016 - Artificial intelligence related software
- Sector Groups Involved
- Electronics
- Aerospace and Defence
- Mobility - Transport - Automotive
- Agri-Food
- Targeted countries
- All countries