公开(公告)号：US09940577B2

公开(公告)日：2018-04-10

申请号：US14793157

申请日：2015-07-07

Applicant: ADOBE SYSTEMS INCORPORATED

Inventor： Hailin Jin ,  Jonathan Krause ,  Jianchao Yang

IPC: G06K9/62 ,  G06N3/08 ,  G06N99/00 ,  G06F17/30 ,  G06K9/00 ,  G06K9/46

CPC classification number: G06N3/088 ,  G06F17/30247 ,  G06K9/00362 ,  G06K9/4628 ,  G06K9/6218 ,  G06K9/627 ,  G06N99/005

Abstract: Embodiments of the present invention relate to finding semantic parts in images. In implementation, a convolutional neural network (CNN) is applied to a set of images to extract features for each image. Each feature is defined by a feature vector that enables a subset of the set of images to be clustered in accordance with a similarity between feature vectors. Normalized cuts may be utilized to help preserve pose within each cluster. The images in the cluster are aligned and part proposals are generated by sampling various regions in various sizes across the aligned images. To determine which part proposal corresponds to a semantic part, a classifier is trained for each part proposal and semantic part to determine which part proposal best fits the correlation pattern given by the true semantic part. In this way, semantic parts in images can be identified without any previous part annotations.