-
1.发明授权公开(公告)号：US12249183B2
公开(公告)日：2025-03-11
申请号：US17687432
申请日：2022-03-04
Applicant: CANON KABUSHIKI KAISHA
Inventor： Qiao Wang , Deyu Wang , Kotaro Kitajima , Naoko Watazawa , Tsewei Chen , Wei Tao , Dongchao Wen
Abstract: The present disclosure discloses an apparatus and a method for detecting a facial pose, an image processing system, and a storage medium. The apparatus comprises: an obtaining unit to obtain at least three keypoints of at least one face from an input image based on a pre-generated neural network, wherein coordinates of the keypoints obtained via a layer in the neural network for obtaining coordinates are three-dimensional coordinates; and a determining unit to determine, for the at least one face, a pose of the face based on the obtained keypoints, wherein the determined facial pose includes at least an angle. According to the present disclosure, the accuracy of the three-dimensional coordinates of the facial keypoints can be improved, thus the detection precision of a facial pose can be improved.
-
2.发明申请公开(公告)号：US20220366259A1
公开(公告)日：2022-11-17
申请号：US17765711
申请日：2020-10-30
Applicant: CANON KABUSHIKI KAISHA
Inventor： Deyu Wang , Tse-wei Chen , Dongchao Wen , Junjie Liu , Wei Tao
Abstract: Provided are a method, an apparatus and a system for training a neural network, and a storage medium storing instructions. The neural network comprises a first neural network and a second neural network, training of the first neural network has not yet completed and training of the second neural network does not start. The method comprises: obtaining a first output by subjecting a sample image to the current first neural network, and obtaining a second output by subjecting the sample image to the current second neural network; and updating the current first neural network according to a first loss function value, and updating the current second neural network according to a second loss function value. The performance of the second neural network can be improved, and the overall training time of the first neural network and the second neural network can be reduced.
-
公开(公告)号：US11170512B2
公开(公告)日：2021-11-09
申请号：US16733694
申请日：2020-01-03
Applicant: CANON KABUSHIKI KAISHA
Inventor： Zhiyuan Zhang , Yaohai Huang , Deyu Wang
Abstract: An image processing apparatus for extracting features from video frames of a video; and determining, for non-initial video frames, reference information of an object detected in a previous video frame thereof in a corresponding non-initial video frame with respect to object information of the object; and detecting an object from an initial video frame based on the features and detects an object from non-initial video frames based on the features and the determined reference information. The processing time of the object detection processing can be reduced, and the real-time requirements of object detection in the video can be better satisfied.
-
公开(公告)号：US20220309779A1
公开(公告)日：2022-09-29
申请号：US17703858
申请日：2022-03-24
Applicant: CANON KABUSHIKI KAISHA
Inventor： Deyu Wang , Dongchao Wen , Wei Tao , Lingxiao Yin
IPC: G06V10/96 , G06V10/82 , G06V10/766 , G06N3/08
Abstract: The invention provides a neural network training and application method, device and storage medium. The training method comprises: an obtaining step of obtaining a processing result and a loss function value of the processing result for at least one task after a sample image is processed in a neural network; wherein the neural network comprises at least one network structure; a determination step of determining importance of the processing result thereof based on the obtained loss function value; an adjustment step of adjusting a weight of the loss function for obtaining the loss function value based on the determined importance; and an update step of updating the neural network according to the loss function after the weight is adjusted.
-
5.发明申请公开(公告)号：US20220292878A1
公开(公告)日：2022-09-15
申请号：US17687432
申请日：2022-03-04
Applicant: CANON KABUSHIKI KAISHA
Inventor： Qiao Wang , Deyu Wang , Kotaro Kitajima , Naoko Watazawa , Tsewei Chen , Wei Tao , Dongchao Wen
Abstract: The present disclosure discloses an apparatus and a method for detecting a facial pose, an image processing system, and a storage medium. The apparatus comprises: an obtaining unit to obtain at least three keypoints of at least one face from an input image based on a pre-generated neural network, wherein coordinates of the keypoints obtained via a layer in the neural network for obtaining coordinates are three-dimensional coordinates; and a determining unit to determine, for the at least one face, a pose of the face based on the obtained keypoints, wherein the determined facial pose includes at least an angle. According to the present disclosure, the accuracy of the three-dimensional coordinates of the facial keypoints can be improved, thus the detection precision of a facial pose can be improved.
-
Patent Agency Ranking
6.发明公开公开(公告)号：US20240020519A1
公开(公告)日：2024-01-18
申请号：US18351417
申请日：2023-07-12
Applicant: CANON KABUSHIKI KAISHA
Inventor： Wei Tao , Tsewei Chen , Deyu Wang , Lingxiao Yin , Dongyue Zhao
IPC: G06N3/0495 , G06N3/084
CPC classification number: G06N3/0495 , G06N3/084
Abstract: The present disclosure provides training and application methods and apparatuses for a neural network model, and a storage medium. The training method includes: quantizing, in a forward transfer process, a network parameter represented by a continuous real value, and calculating a quantization error; determining, in a backward transfer process, a gradient of a weight in the neural network model; correcting the gradient of the weight based on the calculated quantization error, wherein the correcting includes correcting a magnitude of the gradient and correcting a direction of the gradient; and updating the neural network model according to the corrected gradient.
-
公开(公告)号：US20200219269A1
公开(公告)日：2020-07-09
申请号：US16733694
申请日：2020-01-03
Applicant: CANON KABUSHIKI KAISHA
Inventor： Zhiyuan Zhang , Yaohai Huang , Deyu Wang
Abstract: An image processing apparatus for extracting features from video frames of a video; and determining, for non-initial video frames, reference information of an object detected in a previous video frame thereof in a corresponding non-initial video frame with respect to object information of the object; and detecting an object from an initial video frame based on the features and detects an object from non-initial video frames based on the features and the determined reference information. The processing time of the object detection processing can be reduced, and the real-time requirements of object detection in the video can be better satisfied.
-
8.发明申请公开(公告)号：US20210334622A1
公开(公告)日：2021-10-28
申请号：US17230577
申请日：2021-04-14
Applicant: CANON KABUSHIKI KAISHA
Inventor： Wei Tao , Tsewei Chen , Dongchao Wen , Junjie Liu , Deyu Wang
Abstract: A method for generating a multilayer neural network including acquiring a multilayer neural network, wherein the multilayer neural network includes at least convolutional layers and quantization layers; generating, for each of the quantization layers in the multilayer neural network, quantization threshold parameters based on a quantization bit parameter and a learnable quantization interval parameter in the quantization layer; and updating the multilayer neural network to obtain a fixed-point neural network based on the generated quantization threshold parameters and operation parameters for each layer in the multilayer neural network.
-
9.发明申请公开(公告)号：US20210279574A1
公开(公告)日：2021-09-09
申请号：US17189014
申请日：2021-03-01
Applicant: CANON KABUSHIKI KAISHA
Inventor： Junjie Liu , Tsewei Chen , Dongchao Wen , Wei Tao , Deyu Wang
Abstract: A method of generating a quantized neural network comprises: determining, based on a floating-point weight in a neural network to be quantized, networks which correspond to the floating-point weights and are used for directly outputting quantized weights, respectively; quantizing, using the determined network, the floating-point weight corresponding to the network to obtain a quantized neural network; updating, based on a loss function value obtained via the quantized neural network, the determined network, the floating-point weight and the quantized weight in the quantized neural network.
-
10.发明申请公开(公告)号：US20210065011A1
公开(公告)日：2021-03-04
申请号：US17003384
申请日：2020-08-26
Applicant: CANON KABUSHIKI KAISHA
Inventor： Junjie Liu , Tsewei Chen , Dongchao Wen , Wei Tao , Deyu Wang
Abstract: A training and application method, apparatus, system and storage medium of a neural network model is provided. The training method comprises: determining a constraint threshold range according to the number of training iterations and a calculation accuracy of the neural network model, and constraining a gradient of a weight to be within the constraint threshold range, so that when the gradient of a low-accuracy weight is distorted due to a quantization error, the distortion of the gradient is corrected by the constraint of the gradient, thereby making the trained network model achieve the expected performance.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.016 seconds)
