AI@CIB:
Artificial intelligence business solutions for more efficient and automated work processes.

AI@CIB:
Artificial intelligence business solutions for more efficient and automated work processes.

OCR WITH HANDWRITING

BETTER READING WITH AI

ANONYMIZATION

AUTOCROPPING

ENTITY RECOGNITION

ACCESSIBILITY WITH AI

DOCUMENT CLASSIFICATION

SUPERRESOLUTION

OCR WITH HANDWRITING

BETTER READING WITH AI

ANONYMIZATION

AUTOCROPPING

ENTITY RECOGNITION

ACCESSIBILITY WITH AI

DOCUMENT CLASSIFICATION

SUPERRESOLUTION

OCR WITH HANDWRITING

BETTER READING WITH AI

ANONYMIZATION

AUTOCROPPING

ENTITY RECOGNITION

ACCESSIBILITY WITH AI

DOCUMENT CLASSIFICATION

SUPERRESOLUTION

Better with artificial intelligence!

For a long time, it was a dream of the future to automate tasks that require human-level intelligence. CIB implements this vision in the new solutions that facilitate our work on the basis of neural networks.

*CIB invests 12% of its revenue in research and development.

CIB deepER: The powerful AI OCR specialising in business documents masters handwriting on scans

CIB deepER is an artificial intelligence-based optical character recognition engine for recognising and extracting text from images and scanned documents.

It is one of the most powerful OCR engines in the German-speaking world and also supports English, Spanish and Portuguese.

The OCR can be individually trained and integrated for integration and use in dark processing.

CIB PoP: Data protection for your documents with anonymization and pseudonymization

With CIB PoP we remove sensitive data from documents. The context remains intact if the user so wishes. The anonymised documents can thus be used as the basis for further AI training and can be published or passed on in compliance with the GDPR.

The project, which was funded and developed in collaboration with Fraunhofer IAIS, developed our AI-supported, automatic anonymization and pseudonymization tools.

CIB recogNice: Dokumente mit KI automatisch klassifizieren, Prozesse erheblich beschleunigen

Our AI-based classification module determines the appropriate classes from the extracted text structure of a document. CIB recogNice can:

AI recognition for automatic data extraction from documents

CIB sherlock accurately extracts from a document all text data relevant for a given use case. This enables reliable and automated document processing with artificial intelligence.

CIB superResolution restores illegible text

Restores text on images, making scans, faxes or photos of documents legible

Our AI specially trained for document material, checks image material and automatically restores illegible text.

CIB autoCrop: Automatically crop document scans and accelerate business processes with AI!

The AI model CIB autoCrop recognises the page and automatically trims the edges of document scans.

CIB easyRead: Reading comfortably with AI on small screens for your scans and documents

CIB ridmi: Accessible reading and comprehension

CIB ridmi will enable barrier-free reading of scanned or photographed files.

Together with the app CIB doXisafe and the AI model CIB deepER , texts are extracted from images and prepared in an acce

Hilano

Protection of hypersensitive data

The HILANO project, which is funded by KMU Innovativ, ensures the manual anonymization of documents from the medical and legal sectors that are critical in terms of data protection.

A constantly learning AI recognizes sensitive data and makes suggestions to the human user. The user’s correction of these suggestions trains the AI on-premise, on what the company is looking for in anonymization. The data remains in the hands of the company at all times, which ensures data protection.

In cooperation with: GLANOS, Bucerius Law School, University of Hamburg

Recent case studies

Modern technologies, intelligent solutions

Our AI-team has extensive knowledge of many different approaches to creating neural networks with different frameworks.

Neuronal Networks:

Frameworks:

Networks

Current CIB AI research areas

We are researching these topics now and in the future with partners or as part of funding programmes.

Natural Language Processing

With our AI solutions, we support the creation and understanding of documents wherever possible.

Image manipulation

Whether scans or smartphone recordings, documents are increasingly transmitted as images. We are researching to ensure perfect digitization here as well.

Business management

Whether incoming mail management, document processing or BPM, CIB also conducts research to make everyday work easier. 

Always learning!

finetuning

Continous Learning

An AI can learn from mistakes. Through corrections, the training of the AI is adjusted and the new AI replaces the old one.

Federated Learning - Data protection matters

For the protection of critical data, we rely on decentralised AI training: data worth protecting remains on site, only the AI's learned knowledge is shared!

Your own AI

Your specific use case is not yet supported by AI? Our AIs can be retrained. Talk to us!

Mobil

Mobile AI

AI on the go? With today's computing power and the know-how of CIB no problem! Feel free to contact us about this possibility!

AI training for a good cause!

Crowdsource

CIB crowdsource

Through our crowdsourcing platform, anyone can help train our AI models.

We attach great importance to data protection: all data processed on the platform by the hardworking members of our community are irrevocably anonymized or were already free of real personal data.

For a good cause!

Of course, diligent helping is also rewarded: For each task, points are awarded that can be donated to certified charitable organizations.

Register now and join in!

Are you interested in implementing AI in your use cases?