BACKGROUND

Images observed in nature or produced by instruments including biological microscopes, medical imaging systems, spatial telescopes or industrial devices often show textural aspects. Major issues in texture analysis are the segmentation and the classification of images, the detection of abnormalities and the 3D shapes of objects.

KEY BENEFITS vs. STATE OF THE ART

We propose 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 Hurst indexes using a new technique that is based on quadratic variations.

DEVELOPMENT STATUS

• Software beta version available for demonstration
• Demonstrated for breast cancer risk evaluation with mammograms

An anisotropic Brownian field texture

APPLICATIONS

•Medical imaging (radiographic texture analysis, MRI texture classification…) 

•Graphic design, meteorology, geosciences, material sciences