Spin-offs and Patents

 



 

Visual Tagging Services S.L. was founded in July 2012 as a spin-off company from Universitat Autònoma de Barcelona and the Computer Vision Center, based on the results of several years of research of the ISE Lab on Object Detection and Image Understanding. The mission is to connect the images with its associated information using image analysis recognition technology.

http://www.visual-tagging.com/index.html

 

VisualCentury

Cloud Sizing Services S.L. was founded in December 2011 as a spin-off company from Universitat Autònoma de Barcelona and the Computer Vision Center. This company has developed Verisize, an application that gives you the right size for each garment in an easy and effective way. For its development we used an extensive database of different constitution types and applied algorithms and multiple regression techniques, achieving high accuracy. The mission is to provide apparel online shoppers with advanced technology solution to help them find their right size for any garment of any brand they wish to buy – in seconds and without measuring or using a size chart.

http://www.verisize.com/en/

Captura de pantalla 2014-10-10 a les 15.29.47


 

Patent: Method for Detecting Defects on Yarns 

Inventors:  F. Xavier Roca Marvà, Miguel Angel Viñas Redrejo, Jordi Gonzàlez Sabaté, Sílvia Sánchez Mayoral

Publication number: WO2012152336 A1 Publication type: Application Application number: PCT/EP2011/057719

Publication date: Nov 15, 2012 Filing date: May 12, 2011 Priority date: May 12, 2011

Applicant:  Centre De Visió Per Computador (CVC), Universitat Autònoma De Barcelona

Company exploiting it: Elastic Berger S.L.

AbstractIn a first aspect, the present invention provides a method for detecting defects on yarns arranged substantially in parallel from a grey scale image (10) of the yarns, said grey scale image being divided into one or more image sections; the method comprising for each image section (10): calculating a restrictive threshold and a less restrictive threshold from the image section (10); obtaining a restrictive image section (11) by applying the restrictive threshold to the image section (10); obtaining a less restrictive image section (12) by applying the less restrictive threshold to the image section (10). Said method further comprises: obtaining a differential image (13) from the obtained restrictive image sections (11) and the obtained less restrictive image sections (12); and detecting defects on the yarns by comparing (15) the pixels (16) of the differential image (13) representing existence of difference with predetermined defect patterns (14).