-
公开(公告)号：US20240273944A1
公开(公告)日：2024-08-15
申请号：US18236142
申请日：2023-08-21
Applicant: REALTEK SEMICONDUCTOR CORP.
Inventor： Chien-Hao Chen , Chih-Wei Wu , Shih-Tse Chen
CPC classification number: G06V40/172 , G06V10/82
Abstract: A training system, a training method, and a recognition system are provided. The training method is used to train a neural network module including: an encoder module, a shared decoder module, a synthesis module, and a classification module. The training method includes performing in a training epoch: repeatedly executing: taking a training image from a training set as an input image, obtaining a first loss based on training feature images of the training image and the feature images corresponding to the training image, and obtaining a second loss based on a classification marker of the training image and a classification generated by the classification module in correspondence with the training image; and updating first parameters and second parameters based on an average value of all the first losses and an average value of all the second losses obtained in the preceding step and an update algorithm.
-
公开(公告)号：US20230070321A1
公开(公告)日：2023-03-09
申请号：US17567147
申请日：2022-01-02
Applicant: Realtek Semiconductor Corp.
Inventor： Chien-Hao Chen , Shih-Tse Chen
IPC: G06V10/774 , G06V10/24 , G06V40/16 , G06V10/778
Abstract: A method for training a deep learning network for face recognition includes: utilizing a face landmark detector to perform face alignment processing on at least one captured image, thereby outputting at least one aligned image; inputting the at least one aligned image to a teacher model to obtain a first output vector; inputting the at least one captured image a student model corresponding to the teacher module to obtain a second output vector; and adjusting parameter settings of the student model according to the first output vector and the second output vector.
-
公开(公告)号：US11847821B2
公开(公告)日：2023-12-19
申请号：US17567147
申请日：2022-01-02
Applicant: Realtek Semiconductor Corp.
Inventor： Chien-Hao Chen , Shih-Tse Chen
IPC: G06V10/00 , G06V10/774 , G06V10/778 , G06V40/16 , G06V10/24
CPC classification number: G06V10/774 , G06V10/242 , G06V10/778 , G06V40/161
Abstract: A method for training a deep learning network for face recognition includes: utilizing a face landmark detector to perform face alignment processing on at least one captured image, thereby outputting at least one aligned image; inputting the at least one aligned image to a teacher model to obtain a first output vector; inputting the at least one captured image a student model corresponding to the teacher module to obtain a second output vector; and adjusting parameter settings of the student model according to the first output vector and the second output vector.
-
公开(公告)号：US11495006B2
公开(公告)日：2022-11-08
申请号：US16865409
申请日：2020-05-03
Applicant: Realtek Semiconductor Corp.
Inventor： Chao-Hsun Yang , Shang-Lun Chan , Shih-Tse Chen , Chien-Hao Chen
Abstract: An object detection method and an associated electronic device are provided, wherein the object detection method includes: utilizing an image processing circuit to determine whether motion occurs in an image to generate a determination result; selectively utilizing a specific bounding box to identify a target object to generate an identification result according to the determination result, wherein the specific bounding box represents a location of the target object in a previous image; and selectively updating information of the specific bounding box according to the identification result.
-
公开(公告)号：US20240273887A1
公开(公告)日：2024-08-15
申请号：US18216147
申请日：2023-06-29
Applicant: REALTEK SEMICONDUCTOR CORP.
Inventor： Chih-Wei Wu , Chien-Hao Chen , Wei-Hsiang Shen , Shih-Tse Chen
IPC: G06V10/82 , G06V10/774
CPC classification number: G06V10/82 , G06V10/774
Abstract: A neural network system and a signal processing method are provided. The neural network system includes at least one processing unit and a neural network module. The signal processing method includes: inputting a neural network input to the neural network module by the processing unit to generate an input at a previous layer of each convolutional transformer layer; performing pointwise convolution on the input by a key embedding layer based on key convolutional kernels to output a key tensor; performing convolution on the input by a value embedding layer based on value convolutional kernels to output a value tensor; performing a convolution on the cascading tensor of a first tensor and the key tensor by an attention embedding layer based on attention convolution kernels to output an attention tensor; and outputting an output tensor based on the attention tensor and the value tensor by an output module.
-
Patent Agency Ranking
公开(公告)号：US12131488B2
公开(公告)日：2024-10-29
申请号：US17686379
申请日：2022-03-03
Applicant: Realtek Semiconductor Corp.
Inventor： Chih-Wei Wu , Chien-Hao Chen , Chao-Hsun Yang , Shih-Tse Chen
IPC: G06T7/246
CPC classification number: G06T7/251 , G06T2207/30196
Abstract: A method used for object tracking includes: using a specific object model to generate a first vector of a first ratio object and a second vector of a second ratio object of an image in an object detection bounding box of a specific frame; generating an identity label of an object within the bounding box according to the first vector, the second vector, and M first ratio reference vectors and M second ratio reference vectors stored in an object vector database.
-
公开(公告)号：US11734956B2
公开(公告)日：2023-08-22
申请号：US17523930
申请日：2021-11-11
Applicant: Realtek Semiconductor Corp.
Inventor： Chien-Hao Chen , Chao-Hsun Yang , Shih-Tse Chen
CPC classification number: G06V40/172 , G06F18/22 , G06V10/761
Abstract: The present invention provides a processing circuit applied to a face recognition system, which includes a characteristic value calculation module, a determination circuit and a threshold value calculation module. The characteristic value calculation module is used to receive an image and process the image to generate a specific characteristic value; when the face recognition system operates in a face recognition phase, the determination circuit calculates multiple differences each between the specific characteristic value and one of multiple reference characteristic values, and determines whether at least one of the multiple differences is lower than a threshold value to generate a determination result; and when the face recognition system operates in a face registration phase, the threshold value calculation module determines a new threshold value according to differences between the specific characteristic value and the multiple reference values, for updating the threshold value used by the determination circuit.
-
公开(公告)号：US20230154017A1
公开(公告)日：2023-05-18
申请号：US17686379
申请日：2022-03-03
Applicant: Realtek Semiconductor Corp.
Inventor： Chih-Wei Wu , Chien-Hao Chen , Chao-Hsun Yang , Shih-Tse Chen
IPC: G06T7/246
CPC classification number: G06T7/251 , G06T2207/30196
Abstract: A method used for object tracking includes: using a specific object model to generate a first vector of a first ratio object and a second vector of a second ratio object of an image in an object detection bounding box of a specific frame; generating an identity label of an object within the bounding box according to the first vector, the second vector, and M first ratio reference vectors and M second ratio reference vectors stored in an object vector database.
-
公开(公告)号：US20220318543A1
公开(公告)日：2022-10-06
申请号：US17523930
申请日：2021-11-11
Applicant: Realtek Semiconductor Corp.
Inventor： Chien-Hao Chen , Chao-Hsun Yang , Shih-Tse Chen
Abstract: The present invention provides a processing circuit applied to a face recognition system, which includes a characteristic value calculation module, a determination circuit and a threshold value calculation module. The characteristic value calculation module is used to receive an image and process the image to generate a specific characteristic value; when the face recognition system operates in a face recognition phase, the determination circuit calculates multiple differences each between the specific characteristic value and one of multiple reference characteristic values, and determines whether at least one of the multiple differences is lower than a threshold value to generate a determination result; and when the face recognition system operates in a face registration phase, the threshold value calculation module determines a new threshold value according to differences between the specific characteristic value and the multiple reference values, for updating the threshold value used by the determination circuit.
-
公开(公告)号：US12125306B2
公开(公告)日：2024-10-22
申请号：US17685383
申请日：2022-03-03
Applicant: Realtek Semiconductor Corp.
Inventor： Chien-Hao Chen , Chao-Hsun Yang , Chih-Wei Wu , Shih-Tse Chen
Abstract: A method of performing person re-identification includes: obtaining a person feature vector according to an extracted image containing a person; obtaining state information of the person according to a state of the person in the extracted image; comparing the person feature vector with a plurality of registered person feature vectors in a database; when the person feature vector successfully matches a first registered person feature vector of the plurality of registered person feature vectors, identifying the person as a first identity corresponding to the first registered person feature vector; and selectively utilizing the person feature vector to update one of the first registered person feature vector and at least one second registered person feature vector that correspond to the first identity according to the state information.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.016 seconds)
