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.

Caracterización automática y precisa de texturas de imágenes digitales

Resumen

Tipo:
Oferta Tecnológica
Referencia:
TOFR20160902001
Publicado:
26/09/2016
Caducidad:
26/09/2017
Resumen:
Un laboratorio de investigación francés ha desarrollado un sistema automático de caracterización de texturas que describe las fluctuaciones locales de la regularidad de texturas dentro de imágenes digitales. Esta innovación permite la clasificación y segmentación automática de texturas. El sistema utiliza una calculadora automática programable para estimar los índices locales mediante una nueva técnica basada en variaciones cuadráticas. Se buscan entidades especializadas en imágenes médicas, diseño gráfico, meteorología y ciencia de materiales con el fin de establecer acuerdos de licencia o cooperación en investigación.

Details

Tittle:
Automatic and accurate characterization of textures of digital images
Summary:
A French research laboratory has developed an automatic computation system of texture features describing local fluctuations of the texture regularity within digital images. That innovation enables automatic texture classification and segmentation. Entities dealing with medical imaging, graphic design, meteorology, material sciences are sought for license agreement or research cooperation agreement (possibly co-funded).
Description:
Images observed in nature or produced by instruments (including biological microscopes, medical imaging systems, spatial telescopes or industrial devices) often show textural aspects. The major issues in texture analysis are the segmentation and the classification of images, the detection of abnormalities and the 3D shapes of objects. Current global indexes calculation of the entire image does not allow performance regarding local fluctuations which are not evaluated, and low accuracy in case of image heterogeneity.

A French research laboratory proposes a method that enables the automatic computation of texture features and describes the local fluctuations of the texture regularity within digital images. The innovation uses a programmable automatic calculator for the estimation of local indexes using a new technique that is based on quadratic variations.
The benefits of the calculator for imaging systems are noise, scale and contrast robustness, with computation of the index fluctuations (both local and new global that combines the previous ones) and automatic texture classification and segmentation.

The main application domains are the medical imaging (radiographic texture analysis, Magnetic Resonance Imaging texture classification...) and also graphic design, meteorology, geosciences, material sciences...
License agreement or research cooperation agreement are expected. The laboratory is looking for a partner involved in a co-development. The images of the partner will be tested with the software in order to search for desired characteristics and if the Proof of concept is successful, a co-development program can be built for segmentation and classification of the images.
Advantages and Innovations:
Automatic calculation
Texture classification
Texture segmentation
Contrast invariance
Noise robustness
Stage of Development:
Available for demonstration
IPs:
Patents granted
CommeR Statunts Regarding IPR Status:
International patent

Partner sought

Type and Role of Partner Sought:
The laboratory is looking for Industries or research entities with activities dealing with texture feature issues (applications listed above).

License, research cooperation or technical cooperation agreements are expected.
The laboratory is looking for a partner involved in a co-development. The images of the partner will be tested with the software in order to search for desired characteristics and, if the proof of concept is successful, a co-development program can be built for segmentation and classification of the images.

Client

Type and Size of Client:
R&D Institution
Already Engaged in Trans-National Cooperation:
No
Languages Spoken:
English
French

Keywords

Technology Keywords:
01005003 Contenidos digitales, publicidad electrónica
01003012 Imaging, Image Processing, Pattern Recognition
01001002 Sistemas digitales, representación digital