-
公开(公告)号：US20200057883A1
公开(公告)日：2020-02-20
申请号：US16665060
申请日：2019-10-28
Inventor： Yanhao Ge , Jilin Li , Chengjie Wang
Abstract: A face attribute recognition method, electronic device, and storage medium. The method may include obtaining a face image, inputting the face image into an attribute recognition model, performing a forward calculation on the face image using the attribute recognition model to obtain a plurality of attribute values according to different types of attributes, and outputting the plurality of attribute values, the plurality of attribute values indicating recognition results of a plurality of attributes of the face image. The attribute recognition model may be obtained through training based on a plurality of sample face images, a plurality of sample attribute recognition results of the plurality of sample face images, and the different types of attributes.
-
公开(公告)号：US10438077B2
公开(公告)日：2019-10-08
申请号：US15728178
申请日：2017-10-09
Inventor： Chengjie Wang , Jilin Li , Feiyue Huang , Yongjian Wu
Abstract: A face liveness detection method includes outputting a prompt to complete one or more specified actions in sequence within a specified time period, obtaining a face video, detecting a reference face image frame in the face video using a face detection method, locating a facial keypoint in the reference face image frame, tracking the facial keypoint in one or more subsequent face image frames, determining a state parameter of one of the one or more specified actions using a continuity analysis method according to the facial keypoint, and determining whether the one of the one or more specified actions is completed according to a continuity of the state parameter.
-
公开(公告)号：US10410053B2
公开(公告)日：2019-09-10
申请号：US15715579
申请日：2017-09-26
Inventor： Chengjie Wang , Hui Ni , Jilin Li
Abstract: A method for detecting an information card in an image is provided. The method includes performing a line detection to obtain two endpoints of a line segment corresponding to each of four sides of the information card; generating, a linear equation of the side; obtaining coordinates of four intersection points of the four sides of the information card; mapping the coordinates of the four intersection points to four corners of a rectangular box of the information card, to obtain a perspective transformation matrix; performing perspective transformation on image content encircled by four straight lines represented by the four linear equations to provide transformed image content; forming a gradient template according to a layout of information content on the information card; and using the gradient template to match with the transformed image content and determining whether the image content is a correct information card.
-
公开(公告)号：US10395095B2
公开(公告)日：2019-08-27
申请号：US15703826
申请日：2017-09-13
Inventor： Shouhong Ding , Jilin Li , Chengjie Wang , Feiyue Huang , Yongjian Wu , Guofu Tan
Abstract: Face model matrix training method, apparatus, and storage medium are provided. The method includes: obtaining a face image library, the face image library including k groups of face images, and each group of face images including at least one face image of at least one person, k>2, and k being an integer; separately parsing each group of the k groups of face images, and calculating a first matrix and a second matrix according to parsing results, the first matrix being an intra-group covariance matrix of facial features of each group of face images, and the second matrix being an inter-group covariance matrix of facial features of the k groups of face images; and training face model matrices according to the first matrix and the second matrix.
-
公开(公告)号：US20170372459A1
公开(公告)日：2017-12-28
申请号：US15699691
申请日：2017-09-08
CPC classification number: G06T5/005 , G06K9/00281 , G06T7/12 , G06T7/13 , G06T2200/24 , G06T2207/10024 , G06T2207/30201 , H04N5/23219 , H04N5/2621
Abstract: The method provided in the present disclosure includes: obtaining an image photographed by a camera, and performing face detection on the image by using a face detection algorithm, to obtain a face pixel set from the image; positioning a facial feature contour mask over the face pixel set, to obtain a to-be-examined pixel set from the face pixel set, the to-be-examined pixel set including: a plurality of pixels within an image area except pixels masked by the facial feature contour mask in the face pixel set; performing edge contour detection on the to-be-examined pixel set, and extracting one or more blemish regions from the to-be-examined pixel set, to obtain a to-be-retouched pixel set, the to-be-retouched pixel set including: a plurality of pixels within an image area belonging to the blemish regions; and retouching all pixels in the to-be-retouched pixel set, to obtain a retouched pixel set.
-
Patent Agency Ranking
36.发明授权公开(公告)号：US12299963B2
公开(公告)日：2025-05-13
申请号：US18051323
申请日：2022-10-31
Inventor： Keke He , Junwei Zhu , Hui Ni , Yun Cao , Xu Chen , Ying Tai , Chengjie Wang , Jilin Li , Feiyue Huang
IPC: G06V10/00 , G06V10/75 , G06V10/774 , G06V10/776 , G06V10/82 , G06V40/16
Abstract: An image processing method includes performing additional image feature extraction on a training source face image to obtain a source additional image feature, performing identity feature extraction on the training source face image to obtain a source identity feature, inputting a training template face image into an encoder in a to-be-trained face swapping model to obtain a face attribute feature, inputting the source additional image feature, the source identity feature, and the face attribute feature into a decoder in the face swapping model for decoding to obtain a decoded face image, obtaining a target model loss value based on an additional image difference between the decoded face image and a comparative face image, and adjusting the model parameters of the encoder and the decoder based on the target model loss value to obtain the trained face swapping model.
-
37.发明授权公开(公告)号：US12260615B2
公开(公告)日：2025-03-25
申请号：US18072272
申请日：2022-11-30
Inventor： Bo Li , Jianghe Xu , Shuang Wu , Shouhong Ding , Jilin Li
IPC: G06V10/764 , G06F21/56 , G06V10/44 , G06V10/74 , G06V10/774 , G06V10/776 , G06V10/80
Abstract: An image attack detection method includes: acquiring an image-to-be-detected, and performing global classification recognition based on the image-to-be-detected to obtain a global classification recognition result; performing local image extraction randomly based on the image-to-be-detected to obtain a target number of local images, the target number being obtained by calculation according to a defensive rate of a reference image corresponding to the image-to-be-detected; performing local classification recognition based on the target number of local images respectively to obtain respective local classification recognition results, and fusing the respective local classification recognition results to obtain a target classification recognition result; and detecting a similarity between the target classification recognition result and the global recognition result, and determining the image-to-be-detected as an attack image when the target classification recognition result and the global classification recognition result are dissimilar.
-
38.发明公开公开(公告)号：US20230259739A1
公开(公告)日：2023-08-17
申请号：US18302265
申请日：2023-04-18
Inventor： Boshen ZHANG , Yabiao Wang , Chengjie Wang , Jilin Li , Feiyue Huang
Abstract: Disclosed herein are an image detection method and apparatus, a computer-readable storage medium, and a computer device. The method includes iteratively training a plurality of neural network models to obtain a plurality of trained neural network model; and performing detection on an image to be detected using the trained plurality of neural network models to obtain a detection result. Each iteration of training includes: for each of a plurality of sample images, separately inputting the sample image into the neural network models to obtain a fuzzy probability value set, and calculating, based on the fuzzy probability value set and preset label information of the sample image, a loss parameter of the sample image; selecting target sample images based on a distribution of loss parameters of the plurality of sample images; and updating the plurality of neural network models based on the target sample images.
-
公开(公告)号：US11436435B2
公开(公告)日：2022-09-06
申请号：US16985170
申请日：2020-08-04
Inventor： Anping Li , Shaoxin Li , Chao Chen , Pengcheng Shen , Shuang Wu , Jilin Li
Abstract: This application relates to a model training method. The method includes retrieving a current group of training samples, the training samples being based on a training set; obtaining first sample features of training samples in the current group of training samples based on a to-be-trained model; and obtaining, center features respectively corresponding to the training samples; obtaining feature distribution parameters corresponding to the training samples, the feature distribution parameter corresponding to each training sample being obtained by collecting statistics on second sample features of training samples in the training set that belong to the same classification category, and the second sample feature of each training sample being generated by a trained model; obtaining, based on the center features and the feature distribution parameters, a comprehensive loss parameter corresponding to the current group of training samples; and adjusting model parameters of the to-be-trained model based on the comprehensive loss parameter.
-
公开(公告)号：US11335124B2
公开(公告)日：2022-05-17
申请号：US16927812
申请日：2020-07-13
Inventor： Anping Li , Shaoxin Li , Chao Chen , Pengcheng Shen , Jilin Li
Abstract: This application relates to a face recognition method performed at a computer server. After obtaining a to-be-recognized face image, the server inputs the to-be-recognized face image into a classification model. The server then obtains a recognition result of the to-be-recognized face image through the classification model. The classification model is obtained by inputting a training sample marked with class information into the classification model, outputting an output result of the training sample, calculating a loss of the classification model in a training process according to the output result, the class information and model parameters of the classification model, and performing back propagation optimization on the classification model according to the loss.
-
-
-
-
-
-
-
-
-
Search Results
47
records
(took 0.019 seconds)
