公开(公告)号：US06940454B2

公开(公告)日：2005-09-06

申请号：US09929516

申请日：2001-08-13

Applicant: Frank Paetzold ,  Ulrich F. Buddemeier ,  Yevgeniy V. Dzhurinskiy ,  Karin M. Derlich ,  Hartmut Neven

Inventor： Frank Paetzold ,  Ulrich F. Buddemeier ,  Yevgeniy V. Dzhurinskiy ,  Karin M. Derlich ,  Hartmut Neven

IPC: G06K9/00 ,  G06T7/20 ,  G06T13/00 ,  G06T15/00

CPC classification number: G06K9/00362 ,  G06K9/00228 ,  G06K9/00248 ,  G06K9/4619 ,  G06K9/469 ,  G06T7/246 ,  G06T7/262 ,  G06T2207/20064

Abstract: Facial animation values are generated using a sequence of facial image frames and synchronously captured audio data of a speaking actor. In the technique, a plurality of visual-facial-animation values are provided based on tracking of facial features in the sequence of facial image frames of the speaking actor, and a plurality of audio-facial-animation values are provided based on visemes detected using the synchronously captured audio voice data of the speaking actor. The plurality of visual facial animation values and the plurality of audio facial animation values are combined to generate output facial animation values for use in facial animation.

Abstract translation: 使用一系列面部图像帧和同步捕获的演讲者的音频数据来生成面部动画值。 在该技术中，基于对演讲者的面部图像帧的序列中的面部特征的跟踪来提供多个视觉动画值，并且基于使用检测到的视度来提供多个音频面部动画值 同步录制的演讲者的音频语音数据。 多个视觉面部动画值和多个音频面部动画值被组合以产生用于面部动画的输出面部动画值。

公开(公告)号：US06917703B1

公开(公告)日：2005-07-12

申请号：US09795665

申请日：2001-02-28

Applicant: Johannes B. Steffens ,  Hartwig Adam ,  Hartmut Neven

Inventor： Johannes B. Steffens ,  Hartwig Adam ,  Hartmut Neven

IPC: G06K9/00 ,  G06K9/62

CPC classification number: G06K9/00281

Abstract: The present invention may be embodied in a method, and in a related apparatus, for classifying a feature in an image frame. In the method, an original image frame having an array of pixels is transformed using Gabor-wavelet transformations to generate a transformed image frame. Each pixel of the transformed image is associated with a respective pixel of the original image frame and is represented by a predetermined number of wavelet component values. A pixel of the transformed image frame associated with the feature is selected for analysis. A neural network is provided that has an output and a predetermined number of inputs. Each input of the neural network is associated with a respective wavelet component value of the selected pixel. The neural network classifies the local feature based on the wavelet component values, and indicates a class of the feature at an output of the neural network.

Abstract translation: 本发明可以在用于对图像帧中的特征进行分类的方法和相关装置中实现。 在该方法中，使用Gabor小波变换来变换具有像素阵列的原始图像帧，以生成变换后的图像帧。 变换图像的每个像素与原始图像帧的相应像素相关联，并且由预定数量的小波分量值表示。 选择与特征相关联的变换图像帧的像素进行分析。 提供具有输出和预定数量的输入的神经网络。 神经网络的每个输入与所选择的像素的相应小波分量值相关联。 神经网络基于小波分量值对局部特征进行分类，并且在神经网络的输出处指示特征的类别。

公开(公告)号：US06714661B2

公开(公告)日：2004-03-30

申请号：US09915205

申请日：2001-07-24

Applicant: Ulrich F. Buddenmeier ,  Hartmut Neven

Inventor： Ulrich F. Buddenmeier ,  Hartmut Neven

IPC: G06K900

CPC classification number: G06K9/00228 ,  G06K9/00248 ,  G06T7/11 ,  G06T7/262 ,  G06T7/97 ,  G06T2207/20064 ,  G06T2207/30201

Abstract: The present invention is embodied in a method and system for customizing a visual sensor for facial feature tracking using a neutral face image of an actor. The method may include generating a corrector graph to improve the sensor's performance in tracking an actor's facial features.

Abstract translation: 本发明体现在使用演员的中性面部图像定制用于面部特征跟踪的视觉传感器的方法和系统中。 该方法可以包括生成校正图以改善传感器跟踪演员的面部特征的性能。

公开(公告)号：US06580811B2

公开(公告)日：2003-06-17

申请号：US09871370

申请日：2001-05-31

Applicant: Thomas Maurer ,  Egor Valerievich Elagin ,  Luciano Pasquale Agostino Nocera ,  Johannes Bernhard Steffens ,  Hartmut Neven

Inventor： Thomas Maurer ,  Egor Valerievich Elagin ,  Luciano Pasquale Agostino Nocera ,  Johannes Bernhard Steffens ,  Hartmut Neven

IPC: G06K900

CPC classification number: G06K9/00362 ,  G06K9/00228 ,  G06K9/00248 ,  G06K9/4619 ,  G06K9/469 ,  G06T7/246 ,  G06T7/262 ,  G06T2207/20064

Abstract: The present invention is embodied in an apparatus, and related method, for sensing a person's facial movements, features and characteristics and the like to generate and animate an avatar image based on facial sensing. The avatar apparatus uses an image processing technique based on model graphs and bunch graphs that efficiently represent image features as jets. The jets are composed of wavelet transforms processed at node or landmark locations on an image corresponding to readily identifiable features. The nodes are acquired and tracked to animate an avatar image in accordance with the person's facial movements. Also, the facial sensing may use jet similarity to determine the person's facial features and characteristic thus allows tracking of a person's natural characteristics without any unnatural elements that may interfere or inhibit the person's natural characteristics.

Abstract translation: 本发明体现在一种用于感测人的面部运动，特征和特征等的装置和相关方法，以基于面部感测来生成和动画化身图像。 头像装置使用基于模型图和图形图像的图像处理技术，其有效地将图像特征表示为射流。 射流由在节点处处理的小波变换组成，或者对应于容易识别的特征的图像上的地标位置。 获取并跟踪节点，以根据人的面部动作对化身图像进行动画化。 此外，面部感测可以使用射流相似度来确定人的面部特征和特征，从而允许跟踪人的自然特征，而不会有任何可能干扰或抑制人的自然特征的不自然的元素。

公开(公告)号：US06301370B1

公开(公告)日：2001-10-09

申请号：US09206195

申请日：1998-12-04

Applicant: Johannes Bernhard Steffens ,  Egor Valerievich Elagin ,  Luciano Pasquale Agostino Nocera ,  Thomas Maurer ,  Hartmut Neven

Inventor： Johannes Bernhard Steffens ,  Egor Valerievich Elagin ,  Luciano Pasquale Agostino Nocera ,  Thomas Maurer ,  Hartmut Neven

IPC: G06K900

CPC classification number: G06T7/262 ,  G06K9/00228 ,  G06K9/00248 ,  G06K9/00362 ,  G06T7/246 ,  G06T2207/10012 ,  H04N13/239 ,  H04N13/246 ,  H04N13/302 ,  H04N13/366 ,  H04N2013/0081

Abstract: The present invention is embodied in an apparatus, and related method, for detecting and recognizing an object in an image frame. The object may be, for example, a head having particular facial characteristics. The object detection process uses robust and computationally efficient techniques. The object identification and recognition process uses an image processing technique based on model graphs and bunch graphs that efficiently represent image features as jets. The jets are composed of wavelet transforms and are processed at nodes or landmark locations on an image corresponding to readily identifiable features. The system of the invention is particularly advantageous for recognizing a person over a wide variety of pose angles.

Abstract translation: 本发明体现在用于检测和识别图像帧中的对象的装置和相关方法中。 该物体可以是例如具有特定面部特征的头部。 物体检测过程使用鲁棒且计算有效的技术。 物体识别和识别过程使用基于模型图和束图的图像处理技术，其有效地将图像特征表示为喷射。 射流由小波变换组成，并在对应于容易识别的特征的图像上的节点或地标位置进行处理。 本发明的系统特别有利于在多种姿态角度识别人。