Con esta herramienta te facilitamos un acceso a todas las ofertas y demandas de tecnología europeas y a búsquedas de socios para participar en propuestas europeas de I+D publicadas en la red Enterprise Europe Network, pudiendo filtrar los resultados para facilitar las búsquedas más acordes con tus necesidades.

¿Quieres recibir estos listados de oportunidades de colaboración en tu correo de forma periódica y personalizada? Date de alta en nuestro Boletín

Para optimizar los resultados de la búsqueda, se recomienda utilizar términos en inglés.

Sistema de reconocimiento óptico/inteligente de caracteres


Oferta Tecnológica
Un centro español de investigación de Tecnologías de la Información y Comunicación ofrece un sistema de reconocimiento óptico/inteligente de caracteres para extraer datos de documentos en papel. Este sistema obtiene datos impresos y manuscritos de numerosos tipos de documentos, que posteriormente son procesados digitalmente. El sistema facilita los procesos de gestión de información con organismos. El centro de investigación busca socios con el fin de implantar el sistema a clientes finales e industrias que necesiten digitalización y establecer acuerdos de comercialización con asistencia técnica, licencia o servicio.


Optical/intelligent character recognition system
A Spanish ICT research center offers an optical/intelligent character recognition system to extract data out of documents on paper. It gets printed and handwritten data from many kinds of documents, to be later digitally processed. It eases information management processes within organizations. They look for partners to deploy the system into final clients, industries needing digitalization, via a commercial agreement with technical assistance, a license agreement or a services agreement.
Nowadays electronic media stand in coexistence with legacy paper formats for the task of capturing data from big numbers of subjects, in situations such as exams, surveys, registrations, etc. Although paper is currently on its way to extinction, it is still very used in many information acquisition methodologies, both in public and private environments.

Even though there are several laws in place covering the use of electronic documents as truly original copies of the paper ones (thus allowing paper destruction), which promote and regulate this transition, there are still advantages offered by paper (simplicity, easy manipulation, low cost...), that in many instances still outweigh the disadvantages (storing space, almost impossible search for contents, etc.).

This is leading to a slow evolution, rather than to a fast-paced one.

Companies not willing to give up on the many advantages of digital media, turn to optical/intelligent character recognition solutions (OCR), in order to transfer the information on paper to their online data repositories. This way, data becomes more manageable, more searchable, and easier to store, retrieve and back up.

The proposed OCR works with structured and unstructured texts, combining handwritten with digital characters and allowing the user the configuration of the area where the characters are present. Modelling language techniques allow this OCR to increase the precision and the speed in the process.
The system can be trained with different language corpus.

These are functionalities that the state of the art is not covering good enough.

A Spanish ICT research center has developed one of these solutions and would like to be connected to potential collaborators of any of its application fields, that can be, for instance:
- Accounting: Expenses sheets, bills, financial records, purchase orders, invoices.
- Customer services: Customer orders, warranty claims, service requests, query forms, work permits.
- Human resources: Applications for employees, performance appraisals, vacation requests, consent forms.
- Marketing: Surveys, market research forms, event registration, product evaluations, forms of access, general questionnaires.
- Production: Job reports, requirement forms, transportation, document outsourcing, Quality Assurance.
- Public Administration: License applications, census forms, tax forms, vehicle records, building permits, concessions.
- Education: Applications for students, test correction, scholarships, enrollment, registration, concessions.
- Health: Claim forms, prescriptions, medical records, patient admissions, records.
- Pharmacy: Questionnaires for clinical trials, patient surveys, research forms.
- Financial: Loan applications, credit reports, bill registration, bank transfers.
- Insurance: Claim forms, requests for quotes, reimbursement forms.

The research organization looks for partners willing to understand the product added value and deploy it in final clients: companies from any industry with digitalization needs. Different types of co-operation are possible:
- Commercial agreement with technical assistance, in which the research organization will assist the company that acquires the system to adapt it to specific needs and in its deployment.
- License agreement, in which the partner (software companies or document management companies) will integrate the software library into their own IT applications for digitalization and/or commercialize and deploy the complete solution in final clients, with or without the support of the research organization
- Services agreement, to provide the interested partner a specific analysis/action with the system in their documents.
Advantages and Innovations:
The product offered by the Spanish research center is a smart solution for data extraction out of documents on paper. The Optical/Intelligent Character Recognition system is able of extract printed and handwritten data from different kinds of documents, for its posterior digital processing. Furthermore, the product allows an efficient integration of paper within the information management processes that current organizations demand today.

High volume of documents can be managed via this system, without the cost of manually introducing its contents in the company´s data workflow. This means big cost cuts, both in time and resources.

The extremely low error rates, achieved by the advanced string correction algorithms built in the system, sharply reduce the amounts of user interaction needed throughout the manual data validation stage.

Some of its characteristics are the following:
- Own Intellectual Property -Y- Technology for intelligent text data extraction and document processing
- Easy integration with other document management systems or business intelligence tools
- Interoperability: export to many well-established formats (XML, CSV, TXT)
- Modularity: isolated software modules used for each different tasks, such as template definition, batch process management and scheduling, plus guided manual output validation
- High accuracy rates achieved thanks to advanced OCR algorithms combined with unique Language Model Technology
- Crossplatform support: available for GNU/Linux and MS Windows (XP, Vista, 7) 32 bit platforms.

The main advantages that can be highlighted are:
- Sharp reduction in labour, time and money expenses
- High volumes not a problem
- Decrease of errors in processed information
- Accuracy rates of 95% for handwritten contents, even higher for printed text
Stage of Development:
Already on the market

Partner sought

Type and Role of Partner Sought:
Type of partner sought: industry / company.
Activity of the partner: software development, sales and/or distribution of documental management tools.
Role of the partner: deploy the product in the final clients assessing them for the best use.
Potential partners can be resellers and distributors willing to understand the product added value and deploy it in final clients.


Type and Size of Client:
R&D Institution
Already Engaged in Trans-National Cooperation:
Languages Spoken:


Technology Keywords:
01003006 Computer Software
01003008 Data Processing / Data Interchange, Middleware
01003012 Imaging, Image Processing, Pattern Recognition