Monday, 25 April 2016 16:06
Ranklets: Orientation selective non-parametric features for image analysis
Ranklets: Orientation selective non-parametric features for image analysis
Dr. Fabrizio Smeraldi (Queen Mary, University of London)
Department Of Engineering, Aula Magna, 04 May 2016, 4pm
Dr. Fabrizio Smeraldi (Queen Mary, University of London)
Department Of Engineering, Aula Magna, 04 May 2016, 4pm
Published in
Research
Friday, 13 March 2015 21:59
Italian patent granted for innovative image acquisition system
The Italian patent and trademark office recently approved a patent application about an innovative apparatus for acquiring a plurality of surface images of at least one body and related methods. The invention, which is the result of a cooperation between the Department of Engineering, Mondial Marmi Srl and colleagues from the University of Vigo (Spain) is composed of optical means for image acquisition and one dome-shaped illuminator provided with one inferior basement to integrally hold the object to acquire. On top of the dome is a rotatable device for revolving the optical means about a rotation axis in a controlled manner. The apparatus is particularly suitable for acquiring images of industrial and hand-made products such as - but not limited to - natural stone, wood, ceramics, textiles, etc.

Reference: Apparato per acquisire una pluralità di immagini di almeno un corpo e relativo metodo (Apparatus to acquire a plurality of images of at least one body and related method), IT patent no. 001413266, filed on July 25, 2012; granted on January 16, 2015. Assignee: Mondial Marmi Srl. Inventors: F. Bianconi, A. Fernández, E. González and S.A. Saetta.

Reference: Apparato per acquisire una pluralità di immagini di almeno un corpo e relativo metodo (Apparatus to acquire a plurality of images of at least one body and related method), IT patent no. 001413266, filed on July 25, 2012; granted on January 16, 2015. Assignee: Mondial Marmi Srl. Inventors: F. Bianconi, A. Fernández, E. González and S.A. Saetta.
Published in
Research
Thursday, 12 February 2015 10:12
Image features based on visual perception for discriminating between tumour epithelium and stroma
The tumour-stroma ratio (TSR) is an independent prognostic factor in a wide number of oncologic diseases. Accurate and reproducible estimation of TSR therefore plays a central role in patient stratification and follow-up. The use of features directly related to human perception makes it possible to evaluate the tissue's appearance on the basis of a set of meaningful parameters. In this work we proposed and evaluated the capability of the following five visual features to correctly discriminate epithelium from stroma in digitised tissue micro-arrays of colorectal cancer: coarseness, contrast, directionality, line-likeliness and roughness. The experiments demonstrated that the proposed approach can correctly discriminate epithelium from stroma with state-of-the-art accuracy.

Epithelium

Stroma

Epithelium

Stroma
Source:
F Bianconi, A. Álvarez-Larrán and A. Fernández, Discrimination between tumour epithelium and stroma via perception-based features, Neurocomputing, 154:119-126,2015.
Published in
Research