-
公开(公告)号：US20190122329A1
公开(公告)日：2019-04-25
申请号：US15792506
申请日：2017-10-24
Applicant: VMAXX, Inc.
Inventor： Jinjun Wang , Qiqi Hou
Abstract: A face replacement system for replacing a target face with a source face can include a facial landmark determination model having a cascade multichannel convolutional neural network (CMC-CNN) to process both the target and the source face. A face warping module is able to warp the source face using determined facial landmarks that match the determined facial landmarks of the target face, and a face selection module is able to select a facial region of interest in the source face. An image blending module is used to blend the target face with the selected source region of interest.
-
公开(公告)号：US20180114056A1
公开(公告)日：2018-04-26
申请号：US15792487
申请日：2017-10-24
Applicant: VMAXX, Inc.
Inventor： Jinjun Wang , Shun Zhang , Rui Shi
CPC classification number: G06K9/00288 , G06K9/00228 , G06K9/00275 , G06K9/00295 , G06K9/4628 , G06K9/6244 , G06K9/6269 , G06K9/6271
Abstract: A facial recognition method using online sparse learning includes initializing target position and scale, extracting positive and negative samples, and extracting high-dimensional Haar-like features. A sparse coding function can be used to determine sparse Haar-like features and form a sparse feature matrix, and the sparse feature matrix in turn is used to classify targets.
-
公开(公告)号：US20180114055A1
公开(公告)日：2018-04-26
申请号：US15792408
申请日：2017-10-24
Applicant: VMAXX. Inc.
Inventor： Jinjun Wang , Sanpin Zhou
Abstract: A visual recognition system to process images includes a global sub-network including a convolutional layer and a first max pooling layer. A local sub-network is connected to receive data from the global sub-network, and includes at least two convolutional layers, each connected to a max pooling layer. A fusion network is connected to receive data from the local sub-network, and includes a plurality of fully connected layers that respectively determine local feature maps derived from images. A loss layer is connected to receive data from the fusion network, set filter parameters, and minimize ranking error.
-
公开(公告)号：US10860863B2
公开(公告)日：2020-12-08
申请号：US15792557
申请日：2017-10-24
Applicant: VMAXX, Inc.
Inventor： Jinjun Wang , Rui Shi , Shun Zhang
Abstract: A non-hierarchical and iteratively updated tracking system includes a first module for creating an initial trajectory model for multiple targets from a set of received image detections. A second module is connected to the first module to provide identification of multiple targets using a target model, and a third module is connected to the second module to solve a joint object function and maximal condition probability for the target module. A tracklet module can update the first module trajectory module, and after convergence, output a trajectory model for multiple targets.
-
公开(公告)号：US10755082B2
公开(公告)日：2020-08-25
申请号：US15792408
申请日：2017-10-24
Applicant: VMAXX, Inc.
Inventor： Jinjun Wang , Sanpin Zhou
Abstract: A visual recognition system to process images includes a global sub-network including a convolutional layer and a first max pooling layer. A local sub-network is connected to receive data from the global sub-network, and includes at least two convolutional layers, each connected to a max pooling layer. A fusion network is connected to receive data from the local sub-network, and includes a plurality of fully connected layers that respectively determine local feature maps derived from images. A loss layer is connected to receive data from the fusion network, set filter parameters, and minimize ranking error.
-
Patent Agency Ranking
公开(公告)号：US10733699B2
公开(公告)日：2020-08-04
申请号：US15792506
申请日：2017-10-24
Applicant: VMAXX, Inc.
Inventor： Jinjun Wang , Qiqi Hou
Abstract: A face replacement system for replacing a target face with a source face can include a facial landmark determination model having a cascade multichannel convolutional neural network (CMC-CNN) to process both the target and the source face. A face warping module is able to warp the source face using determined facial landmarks that match the determined facial landmarks of the target face, and a face selection module is able to select a facial region of interest in the source face. An image blending module is used to blend the target face with the selected source region of interest.
-
公开(公告)号：US20190122115A1
公开(公告)日：2019-04-25
申请号：US15792546
申请日：2017-10-24
Applicant: VMAXX, Inc.
Inventor： Jinjun Wang , Yudong Liang
Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
-
公开(公告)号：US10902243B2
公开(公告)日：2021-01-26
申请号：US15792487
申请日：2017-10-24
Applicant: VMAXX, Inc.
Inventor： Jinjun Wang , Shun Zhang , Rui Shi
Abstract: A facial recognition method using online sparse learning includes initializing target position and scale, extracting positive and negative samples, and extracting high-dimensional Haar-like features. A sparse coding function can be used to determine sparse Haar-like features and form a sparse feature matrix, and the sparse feature matrix in turn is used to classify targets.
-
公开(公告)号：US10540589B2
公开(公告)日：2020-01-21
申请号：US15792546
申请日：2017-10-24
Applicant: VMAXX, Inc.
Inventor： Jinjun Wang , Yudong Liang
Abstract: A system for image quality assessment of non-aligned images includes a first deep path portion of a convolutional neural network having a set of parameters and a second deep path portion of the convolutional neural network sharing a set of parameters with the first deep path convolutional neural network. Weights are shared between the first and second deep path convolutional neural networks to support extraction of a same set of features in each neural network pathway. Non-aligned reference and distorted images are respectively provided to the first and second deep paths of the convolutional neural network for processing. A concatenation layer is connected to both the first and second deep paths convolutional neural network, and a fully connected layer is connected to the concatenation layer to receive input from both the first and second deep paths of the convolutional neural network, generating an image quality assessment as a linear regressor and outputting an image quality score.
-
公开(公告)号：US20180114072A1
公开(公告)日：2018-04-26
申请号：US15792557
申请日：2017-10-24
Applicant: VMAXX, Inc.
Inventor： Jinjun Wang , Rui Shi , Shun Zhang
CPC classification number: G06K9/00771 , B25J9/1697 , G06K9/3241 , G06K9/6297 , G06T7/215 , G06T7/277 , G06T2207/20084 , G06T2207/30232 , G06T2207/30241 , H04N7/181 , H04N7/183
Abstract: A non-hierarchical and iteratively updated tracking system includes a first module for creating an initial trajectory model for multiple targets from a set of received image detections. A second module is connected to the first module to provide identification of multiple targets using a target model, and a third module is connected to the second module to solve a joint object function and maximal condition probability for the target module. A tracklet module can update the first module trajectory module, and after convergence, output a trajectory model for multiple targets.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.01 seconds)
