公开(公告)号：US09110501B2

公开(公告)日：2015-08-18

申请号：US13800486

申请日：2013-03-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sudha Velusamy ,  Viswanath Gopalakrishnan ,  Bilva Bhalachandra Navathe ,  Anshul Sharma

IPC: G06K9/00 ,  G06F3/01 ,  G06K9/46

CPC classification number: G06F3/011 ,  G06K9/00335 ,  G06K9/4642 ,  G06K2009/4666

Abstract: A method and system for detecting temporal segments of talking faces in a video sequence using visual cues. The system detects talking segments by classifying talking and non-talking segments in a sequence of image frames using visual cues. The present disclosure detects temporal segments of talking faces in video sequences by first localizing face, eyes, and hence, a mouth region. Then, the localized mouth regions across the video frames are encoded in terms of integrated gradient histogram (IGH) of visual features and quantified using evaluated entropy of the IGH. The time series data of entropy values from each frame is further clustered using online temporal segmentation (K-Means clustering) algorithm to distinguish talking mouth patterns from other mouth movements. Such segmented time series data is then used to enhance the emotion recognition system.

Abstract translation: 一种使用视觉提示来检测视频序列中的谈话面部的时间段的方法和系统。 该系统通过使用视觉线索对一系列图像帧中的说话和非说话段进行分类来检测通话段。 本公开通过首先定位脸部，眼睛以及因此嘴部区域来检测视频序列中的说话面部的时间片段。 然后，通过视觉特征的积分梯度直方图（IGH）对视频帧上的局部化口腔区进行编码，并使用IGH的评估熵进行量化。 来自每个帧的熵值的时间序列数据使用在线时间分割（K-Means clustering）算法进一步聚类，以区分说话嘴模式与其他口部动作。 然后使用这种分段时间序列数据来增强情绪识别系统。

公开(公告)号：US10958842B2

公开(公告)日：2021-03-23

申请号：US15708550

申请日：2017-09-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Raushan Kumar ,  Viswanath Gopalakrishnan ,  Biplab Chandra Das ,  Kiran Nanjunda Iyer

IPC: H04N5/232 ,  H04N1/00 ,  G06K9/00 ,  G06K9/62 ,  G06F3/0488 ,  G06F16/65 ,  G06F3/0482 ,  G06F3/0484 ,  G06F16/54 ,  H04N1/32 ,  H04N101/00

Abstract: A method and an electronic device for displaying images in a multi-dimensional mode based on personalized topics are provided. The method includes generating a plurality of personalized topics based on a plurality of images stored in the electronic device across a predetermined time period, and displaying the plurality of personalized topics along a timeline.

公开(公告)号：US09886762B2

公开(公告)日：2018-02-06

申请号：US14808014

申请日：2015-07-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Kiran Nanjunda Iyer ,  Raushan Kumar ,  Satish Lokkoju ,  Viswanath Gopalakrishnan ,  Viswanath Veera

IPC: G06T7/00 ,  G06F17/30 ,  G06K9/62 ,  G06T7/143 ,  G06T7/162

CPC classification number: G06T7/143 ,  G06F17/30268 ,  G06K9/6276 ,  G06K2209/27 ,  G06T7/11 ,  G06T7/162 ,  G06T2207/20104

Abstract: The present disclosure relates to image retrieval in an electronic device. An operating method of an electronic device includes determining an object included in an image and a position of extent occupied by the object in the image and retrieving at least one image including the object at the position from among a plurality of images.

公开(公告)号：US10521009B2

公开(公告)日：2019-12-31

申请号：US15597442

申请日：2017-05-17

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Kiran Nanjunda Iyer ,  Viswanath Gopalakrishnan ,  Kapil Soni ,  Satish Lokkoju

IPC: G06F3/01 ,  G06F3/0346 ,  G06F1/16 ,  G06F3/0354 ,  G06F3/0362 ,  G06F3/038

Abstract: A method, which facilitates interaction with virtual reality device, includes receiving a user input via a wearable device; extracting a parameter and a value of the parameter from the user input; transmitting the parameter and the value of the parameter to the VR device; identifying an action corresponding to the parameter and the value; and executing the action.

公开(公告)号：US20130271361A1

公开(公告)日：2013-10-17

申请号：US13800486

申请日：2013-03-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sudha Velusamy ,  Viswanath Gopalakrishnan ,  Bilva Bhalachandra Navathe ,  Anshul Sharma

IPC: G06F3/01

CPC classification number: G06F3/011 ,  G06K9/00335 ,  G06K9/4642 ,  G06K2009/4666

Abstract: A method and system for detecting temporal segments of talking faces in a video sequence using visual cues. The system detects talking segments by classifying talking and non-talking segments in a sequence of image frames using visual cues. The present disclosure detects temporal segments of talking faces in video sequences by first localizing face, eyes, and hence, a mouth region. Then, the localized mouth regions across the video frames are encoded in terms of integrated gradient histogram (IGH) of visual features and quantified using evaluated entropy of the IGH. The time series data of entropy values from each frame is further clustered using online temporal segmentation (K-Means clustering) algorithm to distinguish talking mouth patterns from other mouth movements. Such segmented time series data is then used to enhance the emotion recognition system.

Abstract translation: 一种使用视觉提示来检测视频序列中的谈话面部的时间段的方法和系统。 该系统通过使用视觉线索对一系列图像帧中的说话和非说话段进行分类来检测通话段。 本公开通过首先定位脸部，眼睛以及因此嘴部区域来检测视频序列中的说话面部的时间片段。 然后，通过视觉特征的积分梯度直方图（IGH）对视频帧上的局部化口腔区进行编码，并使用IGH的评估熵进行量化。 来自每个帧的熵值的时间序列数据使用在线时间分割（K-Means clustering）算法进一步聚类，以区分说话嘴模式与其他口部动作。 然后使用这种分段时间序列数据来增强情绪识别系统。