公开(公告)号：US20200051306A1

公开(公告)日：2020-02-13

申请号：US16655686

申请日：2019-10-17

Applicant: INTEL CORPORATION

Inventor： Minje Park ,  Tae-Hoon Kim ,  Myung-Ho Ju ,  Jihyeon Yi ,  Xiaolu Shen ,  Lidan Zhang ,  Qiang Li

IPC: G06T13/40 ,  G06T7/73

Abstract: Avatar animation systems disclosed herein provide high quality, real-time avatar animation that is based on the varying countenance of a human face. In some example embodiments, the real-time provision of high quality avatar animation is enabled at least in part, by a multi-frame regressor that is configured to map information descriptive of facial expressions depicted in two or more images to information descriptive of a single avatar blend shape. The two or more images may be temporally sequential images. This multi-frame regressor implements a machine learning component that generates the high quality avatar animation from information descriptive of a subject's face and/or information descriptive of avatar animation frames previously generated by the multi-frame regressor. The machine learning component may be trained using a set of training images that depict human facial expressions and avatar animation authored by professional animators to reflect facial expressions depicted in the set of training images.

公开(公告)号：US20190304155A1

公开(公告)日：2019-10-03

申请号：US16172664

申请日：2018-10-26

Applicant: Intel Corporation

Inventor： Yikai Fang ,  Yangzhou Du ,  Qiang Eric Li ,  Xiaofeng Tong ,  Wenlong Li ,  Minje Park ,  Myung-Ho Ju ,  Jihyeon Kate Yi ,  Tae-Hoon Pete Kim

IPC: G06T13/40 ,  G06K9/00 ,  G06T5/00

Abstract: Examples of systems and methods for augmented facial animation are generally described herein. A method for mapping facial expressions to an alternative avatar expression may include capturing a series of images of a face, and detecting a sequence of facial expressions of the face from the series of images. The method may include determining an alternative avatar expression mapped to the sequence of facial expressions, and animating an avatar using the alternative avatar expression.

公开(公告)号：US10354364B2

公开(公告)日：2019-07-16

申请号：US14853272

申请日：2015-09-14

Applicant: Intel Corporation

Inventor： Sean Pyo ,  Sangyup Lee ,  Minje Park

IPC: G06T3/60 ,  G06T3/00 ,  G06T7/13

Abstract: Techniques related to automatic perspective control of images using vanishing points are discussed. Such techniques may include determining a perspective control vanishing point associated with the image based on lines detected within the image, rotating the image based on the perspective control vanishing point to generate an aligned image, and warping the aligned image based on aligning two lines of the detected lines that meet at the perspective control vanishing point.

公开(公告)号：US09977950B2

公开(公告)日：2018-05-22

申请号：US15008186

申请日：2016-01-27

Applicant: INTEL CORPORATION

Inventor： Hyungsoo Lee ,  Yeongjae Cheon ,  Sumin Lee ,  Minje Park

IPC: G06K9/00 ,  G06K9/62 ,  G06F17/30

CPC classification number: G06K9/00288 ,  G06F17/30256 ,  G06K9/00281 ,  G06K9/6215

Abstract: Techniques are provided for facial recognition using decoy-based matching of facial image features. An example method may include comparing extracted facial features of an input image, provided for recognition, to facial features of each of one or more images in a gallery of known faces, to select a closest gallery image. The method may also include calculating a first distance between the input image and the selected gallery image. The method may further include comparing the facial features of the input image to facial features of each of one or more images in a set of decoy faces, to select a closest decoy image and calculating a second distance between the input image and the selected decoy image. The method may further include recognizing a match between the input image and the selected gallery image based on a comparison of the first distance and the second distance.

公开(公告)号：US09679412B2

公开(公告)日：2017-06-13

申请号：US14443337

申请日：2014-06-20

Applicant: INTEL CORPORATION ,  Minje Park ,  Olivier Duchenne ,  Yeongjae Cheon ,  Tae-Hoon Kim ,  Xiaolu Shen ,  Yangzhou Du ,  Wooju Ryu ,  Myung-Ho Ju

Inventor： Minje Park ,  Olivier Duchenne ,  Yeongjae Cheon ,  Tae-Hoon Kim ,  Xiaolu Shen ,  Yangzhou Du ,  Wooju Ryu ,  Myung-Ho Ju

IPC: G06K9/00 ,  G06T17/20

CPC classification number: G06T17/205 ,  G06K9/00208 ,  G06K9/00214 ,  G06K9/00221 ,  G06K9/00248 ,  G06K9/00261 ,  G06K9/00281 ,  G06T7/251 ,  G06T17/20 ,  G06T2200/04 ,  G06T2207/30201

Abstract: Apparatuses, methods and storage medium associated with 3D face model reconstruction are disclosed herein. In embodiments, an apparatus may include a facial landmark detector, a model fitter and a model tracker. The facial landmark detector may be configured to detect a plurality of landmarks of a face and their locations within each of a plurality of image frames. The model fitter may be configured to generate a 3D model of the face from a 3D model of a neutral face, in view of detected landmarks of the face and their locations within a first one of the plurality of image frames. The model tracker may be configured to maintain the 3D model to track the face in subsequent image frames, successively updating the 3D model in view of detected landmarks of the face and their locations within each of successive ones of the plurality of image frames. In embodiments, the facial landmark detector may include a face detector, an initial facial landmark detector, and one or more facial landmark detection linear regressors. Other embodiments may be described and/or claimed.

公开(公告)号：US09390478B2

公开(公告)日：2016-07-12

申请号：US14491698

申请日：2014-09-19

Applicant: Intel Corporation

Inventor： Kanghee Lee ,  Sumin Lee ,  Minje Park ,  Tae-Hoon Kim

IPC: G06K9/00 ,  G06T5/00 ,  G06T5/20 ,  H04N9/64

CPC classification number: G06T5/002 ,  G06T5/20 ,  G06T7/90 ,  G06T2207/10004 ,  G06T2207/10024 ,  G06T2207/20028 ,  G06T2207/20182 ,  G06T2207/30088 ,  G06T2207/30201 ,  H04N9/643 ,  H04N9/646

Abstract: System, apparatus, method, and computer readable media for on-the-fly captured image data enhancement. An image or video stream is enhanced with a filter in concurrence with generation of the stream by a camera module. In one exemplary embodiment, HD image frames are filtered at a rate of 30 fps, or more, to enhance human skin tones with an edge-preserving smoothing filter. In embodiments, the smoothing filter is applied to an image representation of reduced resolution, reducing computational overhead of the filter. The filtered image is then upsampled and blended with a map that identifies edges to maintain an edge quality comparable to a smoothing filter applied at full resolution. A device platform including a camera module and comporting with the exemplary architecture may provide enhanced video camera functionality even at low image processing bandwidth.

Abstract translation: 用于即时拍摄图像数据增强的系统，装置，方法和计算机可读介质。 使用过滤器增强图像或视频流，同时由相机模块生成流。 在一个示例性实施例中，以30fps或更大的速率对HD图像帧进行滤波，以利用边缘保持平滑滤波器增强人体肤色。 在实施例中，平滑滤波器被应用于降低分辨率的图像表示，减少了滤波器的计算开销。 然后对经滤波的图像进行上采样并与识别边缘的映射混合，以保持与以全分辨率应用的平滑滤波器相当的边缘质量。 包括相机模块和与示例性架构相融合的设备平台即使在低图像处理带宽下也可以提供增强的摄像机功能。

公开(公告)号：US09384539B2

公开(公告)日：2016-07-05

申请号：US14883932

申请日：2015-10-15

Applicant: Intel Corporation

Inventor： Minje Park

IPC: G06K9/34 ,  G06T5/40 ,  G06T5/00 ,  G06K9/62 ,  G06T5/50 ,  G06T11/60 ,  H04N5/235

CPC classification number: G06T5/40 ,  G06K9/6212 ,  G06T5/002 ,  G06T5/009 ,  G06T5/50 ,  G06T11/60 ,  G06T2207/10016 ,  G06T2207/10144 ,  G06T2207/20208 ,  G06T2207/20212 ,  H04N5/2353

Abstract: There is provided a method of processing a digital image including: (a) obtaining a plurality of images; (b) converting the plurality of images into histograms; (c) setting one of the plurality of images as a reference image and another of the plurality of images as a comparison target image; (d) adjusting a distribution of the histogram of the reference image to match a distribution of the histogram of the comparison target image to produce an adjusted reference image; (e) comparing a difference between the adjusted reference image and the comparison target image to produce a masking image; (f) applying the masking image to the comparison target image to produce an adjusted comparison target image; and (g) combining the reference image and the adjusted comparison target image to produce a high dynamic range (HDR) image. Accordingly, even if there is a complex motion on a subject, a clear image without an image overlap or a ghost effect may be obtained when producing the HDR image.

Abstract translation: 提供了一种处理数字图像的方法，包括：（a）获得多个图像; （b）将所述多个图像转换为直方图; （c）将所述多个图像中的一个作为参考图像和所述多个图像中的另一个作为比较对象图像; （d）调整参考图像的直方图的分布以匹配比较对象图像的直方图的分布，以产生经调整的参考图像; （e）比较调整后的参考图像和比较对象图像之间的差异以产生掩蔽图像; （f）将掩蔽图像应用于比较对象图像，生成调整后的比较对象图像; 和（g）组合参考图像和经调整的比较对象图像以产生高动态范围（HDR）图像。 因此，即使在被摄体上存在复杂的运动，也可以在生成HDR图像时获得没有图像重叠的清晰图像或重影效果。

公开(公告)号：US20160063033A1

公开(公告)日：2016-03-03

申请号：US14939093

申请日：2015-11-12

Applicant: Intel Corporation

Inventor： Minje Park ,  Tae-Hoon Kim

IPC: G06F17/30 ,  G06K9/03 ,  H04N5/232 ,  G06K9/00

CPC classification number: G06F17/30247 ,  G06K9/00221 ,  G06K9/00241 ,  G06K9/00248 ,  G06K9/00281 ,  G06K9/00912 ,  G06K9/03 ,  G06K9/033 ,  G06K9/036 ,  H04N5/23219 ,  H04N5/23222

Abstract: According to a method for providing a notification on a face recognition environment of the present disclosure, the method includes obtaining an input image that is input in a preview state, comparing feature information for a face included in the input image with feature information for a plurality of reference images of people stored in a predetermined database to determine, in real-time, whether the input image satisfies a predetermined effective condition for photographing. The predetermined effective condition for photographing is information regarding a condition necessary for recognizing the face included in the input image at a higher accuracy level than a predetermined accuracy level. The method further includes providing a user with a predetermined feedback for photographing guidance that corresponds to whether the predetermined effective condition for photographing is satisfied. According to the method, a condition of a face image detected for face recognition is checked, and if there is an unsuitable element in recognizing the face, it is notified to a user such that an obstruction environment hindering the face recognition by the user is removed, for enhancing a success rate of the face recognition.

Abstract translation: 根据本公开的面部识别环境中提供通知的方法，所述方法包括：获取以预览状态输入的输入图像，将输入图像中包含的面部的特征信息与多个特征信息进行比较 存储在预定数据库中的人的参考图像实时地确定输入图像是否满足用于拍摄的预定有效条件。 用于拍摄的预定有效条件是关于以比预定精度水平更高的精度水平识别包含在输入图像中的面部所必需的条件的信息。 该方法还包括向用户提供与用于拍摄的预定有效条件是否被满足的拍摄引导的预定反馈。 根据该方法，对面部识别检测到的面部图像的条件进行检查，并且如果在识别脸部时存在不适合的元素，则将其通知给用户，使得妨碍用户的脸部识别的阻塞环境被去除 ，用于提高脸部识别的成功率。

公开(公告)号：US20230394802A1

公开(公告)日：2023-12-07

申请号：US18454654

申请日：2023-08-23

Applicant: Intel Corporation

Inventor： Evgeny Tsykunov ,  Wonju Lee ,  Minje Park

IPC: G06V10/774 ,  G06V10/77

CPC classification number: G06V10/774 ,  G06V10/7715

Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed to explain machine learning models. An example apparatus includes programmable circuitry to generate a bitmask having a kernel size, apply the bitmask to the input image to generate a first masked input image, and compute a first saliency score for a first pixel of an input image based on the first masked input image. Additionally, the example programmable circuitry is to compute a second saliency score for a second pixel of the input image based on an output generated by a machine learning model, the output based on a second masked input image. The example programmable circuitry is also to generate a saliency map for the input image based on the first saliency score and the second saliency score, the saliency map indicative of at least one feature of the input image that contributed to training of the machine learning model.

公开(公告)号：US10475225B2

公开(公告)日：2019-11-12

申请号：US15124811

申请日：2015-12-18

Applicant: INTEL CORPORATION

Inventor： Minje Park ,  Tae-Hoon Kim ,  Myung-Ho Ju ,  Jihyeon Yi ,  Xiaolu Shen ,  Lidan Zhang ,  Qiang Li

IPC: G06T13/40 ,  G06T7/73 ,  G06T17/20

Abstract: Avatar animation systems disclosed herein provide high quality, real-time avatar animation that is based on the varying countenance of a human face. In some example embodiments, the real-time provision of high quality avatar animation is enabled at least in part, by a multi-frame regressor that is configured to map information descriptive of facial expressions depicted in two or more images to information descriptive of a single avatar blend shape. The two or more images may be temporally sequential images. This multi-frame regressor implements a machine learning component that generates the high quality avatar animation from information descriptive of a subject's face and/or information descriptive of avatar animation frames previously generated by the multi-frame regressor. The machine learning component may be trained using a set of training images that depict human facial expressions and avatar animation authored by professional animators to reflect facial expressions depicted in the set of training images.