公开(公告)号：US20140147022A1

公开(公告)日：2014-05-29

申请号：US13686737

申请日：2012-11-27

Applicant: Adobe Systems Incorporated

Inventor： Feng Zhou ,  Jon Brandt ,  Zhe Lin

IPC: G06K9/00

CPC classification number: G06K9/00281

Abstract: Systems and methods are discussed to localize facial landmarks using a test facial image and a set of training images. The landmarks can be localized on a test facial image using training facial images. A plurality of candidate landmark locations on the test facial image can be determined. A subset of the training facial images with facial features similar to the facial features in the test facial image can be identified. A plurality of shape constraints can be determined for each test facial image in the subset of test facial images. These shape constraints graphically relate to one landmark location from a linear combination of the other landmark locations in the test facial image. Shape constraints can be determined for every landmark within each test facial image. A candidate landmark can be chosen from the plurality of candidate landmarks using the shape constraints.

Abstract translation: 讨论系统和方法以使用测试面部图像和一组训练图像来定位面部地标。 可以使用训练面部图像将地标定位在测试面部图像上。 可以确定测试面部图像上的多个候选标记位置。 可以识别训练面部图像的一部分，其面部特征与测试面部图像中的面部特征相似。 可以在测试面部图像的子集中的每个测试面部图像确定多个形状约束。 这些形状约束图形地涉及来自测试面部图像中的其他地标位置的线性组合的一个地标位置。 每个测试面部图像中的每个地标可以确定形状约束。 可以使用形状约束从多个候选地标中选择候选地标。

公开(公告)号：US09152847B2

公开(公告)日：2015-10-06

申请号：US13686737

申请日：2012-11-27

Applicant: Adobe Systems Incorporated

Inventor： Feng Zhou ,  Jon Brandt ,  Zhe Lin

IPC: G06K9/00

CPC classification number: G06K9/00281

Abstract: Systems and methods are discussed to localize facial landmarks using a test facial image and a set of training images. The landmarks can be localized on a test facial image using training facial images. A plurality of candidate landmark locations on the test facial image can be determined. A subset of the training facial images with facial features similar to the facial features in the test facial image can be identified. A plurality of shape constraints can be determined for each test facial image in the subset of test facial images. These shape constraints graphically relate to one landmark location from a linear combination of the other landmark locations in the test facial image. Shape constraints can be determined for every landmark within each test facial image. A candidate landmark can be chosen from the plurality of candidate landmarks using the shape constraints.

Abstract translation: 讨论系统和方法以使用测试面部图像和一组训练图像来定位面部地标。 可以使用训练面部图像将地标定位在测试面部图像上。 可以确定测试面部图像上的多个候选标记位置。 可以识别训练面部图像的一部分，其面部特征与测试面部图像中的面部特征相似。 可以在测试面部图像的子集中的每个测试面部图像确定多个形状约束。 这些形状约束图形地涉及来自测试面部图像中的其他地标位置的线性组合的一个地标位置。 每个测试面部图像中的每个地标都可以确定形状约束。 可以使用形状约束从多个候选地标中选择候选地标。