06-06-2013 дата публикации
Номер: US20130142423A1
Принадлежит:
The disclosure relates to a system and a method for generating clothing feature data representative of at least one clothing feature of a piece of clothing being worn by the person in a set of images, and training a discriminative clothing classifier using the clothing feature data to provide a personal clothing model that corresponds to the piece of clothing. The personal clothing model can be used to identify additional images in which the person appears. 17407423004041250. A method performed using a physical computer system () comprising at least one processor () for generating a personal clothing model ( , ) for use in classifying an image ( , ) comprising:{'b': 16', '740', '52', '52, 'generating (), using the computer system (), clothing feature data representative of at least one clothing feature using clothing region data representative of clothing regions () detected in each image of a subset of images from a collection of images, each clothing region () being associated with a same clothing worn by a same person that appears in each image of the subset of images; and'}{'b': 18', '740', '300', '404', '300', '404', '12', '50, 'training (), using the computer system (), a discriminative clothing classifier using the clothing feature data to generate at least one personal clothing model (, ), wherein the at least one personal clothing model (, ), for use in classifying the image (, ), corresponds to the clothing.'}2300404. The method of claim 1 , further comprising using the at least one personal clothing model ( claim 1 , ) to classify an additional image in the collection of images that is not contained in the subset.3300404350300404352354300404. The method of claim 2 , wherein the using the at least one personal clothing model ( claim 2 , ) to classify an additional image in the collection of images comprises computing () a similarity score between the at least one personal clothing model ( claim 2 , ) and clothing feature data extracted from image data ...
Подробнее