-
公开(公告)号：US20140355821A1
公开(公告)日：2014-12-04
申请号：US13909838
申请日：2013-06-04
Applicant: Apple Inc.
Inventor： Jan Erik Solem , Jerome Piovano , Michael Rousson
CPC classification number: G06T7/0046 , G06K9/00281 , G06K9/469 , G06K9/621 , G06T7/75 , G06T2207/20081 , G06T2207/30201
Abstract: Techniques are provided to improve the performance and accuracy of landmark point detection using a Constrained Local Model. The accuracy of feature filters used by the model may be improved by supplying positive and negative sets of image data from training image regions of varying shapes and sizes to a linear support vector machine training algorithm. The size and shape of regions within which a feature filter is to be applied may be determined based on a variance in training image data for a landmark point with which the feature filter is associated. A sample image may be normalized and a confidence map generated for each landmark point by applying the feature filters as a convolution on the normalized image. A vector flow map may be pre-computed to improve the efficiency with which a mean landmark point is adjusted toward a corresponding landmark point in a sample image.
Abstract translation: 提供了技术来提高使用约束局部模型的地标点检测的性能和准确性。 模型使用的特征滤波器的精度可以通过从不同形状和尺寸的训练图像区域向线性支持向量机训练算法提供正和负的图像数据组来提高。 可以基于与特征滤波器相关联的地标点的训练图像数据的方差来确定要应用特征滤波器的区域的大小和形状。 可以对样本图像进行归一化，并通过将特征滤波器作为在归一化图像上的卷积应用来为每个地标点生成置信图。 可以预先计算矢量流程图，以提高将样本图像中的平均地标点调整到对应的地标点的效率。
-
公开(公告)号：US09208567B2
公开(公告)日：2015-12-08
申请号：US13909838
申请日：2013-06-04
Applicant: Apple Inc.
Inventor： Jan Erik Solem , Jerome Piovano , Michael Rousson
CPC classification number: G06T7/0046 , G06K9/00281 , G06K9/469 , G06K9/621 , G06T7/75 , G06T2207/20081 , G06T2207/30201
Abstract: Techniques are provided to improve the performance and accuracy of landmark point detection using a Constrained Local Model. The accuracy of feature filters used by the model may be improved by supplying positive and negative sets of image data from training image regions of varying shapes and sizes to a linear support vector machine training algorithm. The size and shape of regions within which a feature filter is to be applied may be determined based on a variance in training image data for a landmark point with which the feature filter is associated. A sample image may be normalized and a confidence map generated for each landmark point by applying the feature filters as a convolution on the normalized image. A vector flow map may be pre-computed to improve the efficiency with which a mean landmark point is adjusted toward a corresponding landmark point in a sample image.
Abstract translation: 提供了技术来提高使用约束局部模型的地标点检测的性能和准确性。 模型使用的特征滤波器的精度可以通过从不同形状和尺寸的训练图像区域向线性支持向量机训练算法提供正和负的图像数据组来提高。 可以基于与特征滤波器相关联的地标点的训练图像数据的方差来确定要应用特征滤波器的区域的大小和形状。 可以对样本图像进行归一化，并通过将特征滤波器作为在归一化图像上的卷积应用来为每个地标点生成置信图。 可以预先计算矢量流程图，以提高将样本图像中的平均地标点调整到对应的地标点的效率。
-
Search Results
2
records
(took 0.008 seconds)
