<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Costa, a</style></author><author><style face="normal" font="default" size="100%">Pereira, H</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Quality characterization of wine cork stoppers using computer vision</style></title><secondary-title><style face="normal" font="default" size="100%">JOURNAL INTERNATIONAL DES SCIENCES DE LA VIGNE ET DU VIN</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">computer imaging</style></keyword><keyword><style  face="normal" font="default" size="100%">quality classes</style></keyword><keyword><style  face="normal" font="default" size="100%">wine cork stoppers</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2005</style></year></dates><publisher><style face="normal" font="default" size="100%">VIGNE ET VIN PUBLICATIONS INT</style></publisher><pub-location><style face="normal" font="default" size="100%">42 RUE MARSAN, 33300 BORDEAUX, FRANCE</style></pub-location><volume><style face="normal" font="default" size="100%">39</style></volume><pages><style face="normal" font="default" size="100%">209-218</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">Image analysis techniques were applied on the surface of wine cork stoppers (tops and lateral cylindrical surface) of seven commercial quality classes to characterize their porosity. An increasing trend from the best to the worst quality classes was found for features related to area of pores (i.e. maximum length and width or pore maximum area) and concentration variables (i.e. porosity coefficient or number of pores per 100 cm(2)). Shape variables were rather constant and mean values showed no differences between quality classes. Variation of the pores characteristics within each quality class was large especially in the mid-quality range. Therefore there were no statistically significant differences to allow the isolation of the all quality classes and overlapping was particularly important in the medium-quality classes. The reduction of grading into only three quality classes allowed to isolate statistically different subsets based on porosity coefficient and number of pores per 100 cm(2). These variables can be selected for further development into quality grades specification of wine cork stoppers.</style></abstract></record></records></xml>