Patent
Face recognition method based on online learning
Lu Shengli,Pang Wei,Zhou Shihao,Xiang Jiaqi,Li Yufeng,Fan Xuemei +5 more
- 04 Jan 2019
4
TL;DR: In this paper, an on-line learning face recognition method, belonging to the technical field of calculation and calculation, in particular to the computer vision technical fields of face recognition, is described.
read more
Abstract: The invention discloses an on-line learning face recognition method, belonging to the technical field of calculation and calculation, in particular to the computer vision technical field of face recognition. The method trains the facial feature extractor by using the external data set, extracting reference features corresponding to each member of the local dataset to form a reference feature space, comparing a feature vector of a sample to be tested with a reference feature to determine a reference feature that is most similar to the feature vector of the sample to be tested, when the reference feature which is most similar to the eigenvector of the sample to be tested meets the threshold requirement, taking the identity of the member whose reference feature is most similar to the eigenvector of the sample to be tested as the identity of the sample to be tested, otherwise, the message that the identification of the sample to be tested fails is returned, and the reference feature spaceis updated according to the difference between the predicted feature vector of the sample to be tested and the real feature vector corresponding to the predicted feature vector in the reference feature space, so as to adapt to the change of the facial feature over time, especially in the case of frequently changing the members.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Data updating method and device, electronic equipment and storage medium
Zhao Hongbin,Jiang Wenzhong,Liu Yi +2 more
- 22 Oct 2019
TL;DR: In this paper, the authors proposed a data updating method, which consists of the steps of obtaining a first image of a target object, and obtaining a second image feature from a local face database; performing similarity comparison on the first image feature and the second image features to obtain a comparison result; under the condition that the comparison result is greater than a feature updating threshold, obtaining a difference feature of the difference feature, and taking the difference features as a dynamic updating feature, to obtain updated feature data of the target object.
3
Patent
Identity recognition system, client, server and method
TL;DR: In this article, an identity recognition system, a client, a server and a method is described, which consists of an image collection module used for obtaining a to-be-used image; a feature extraction module used to perform image feature extraction on the to be-utilized image by utilizing a feature extract model locally stored in the client to determine features of the to-Be-utilised image.
2
Patent
Sample collection method and system based on feature space
Xu Huayong
- 20 Aug 2019
TL;DR: In this article, a sample collection method based on a feature space is proposed, and the method comprises the steps: determining a first feature extraction algorithm, and constructing the first feature space; obtaining a first to-be-processed sample; extracting a feature vector of the first to be-processing sample; calculating the similarity between the feature vector and the feature vectors of each sample in the feature space, and recording the maximum value as the maximum values of first similarity; judging whether the first similarity maximum value is smaller than a preset first similarity threshold value or not; when it
Patent
Online learning facial recognition method
Lu Shengli,Pang Wei,Zhou Shihao,Xiang Jiaqi,Li Yufeng,Fan Xuemei +5 more
- 02 Jan 2020
TL;DR: In this paper, the authors proposed an online learning facial recognition method in the technical field of computation and calculation, and in particular in particular the technical domain of computer vision for facial recognition.
References
Patent
Face identification method and apparatus
Luo Jinwen,Hou Wendi,Yang Song +2 more
- 12 Oct 2016
TL;DR: In this paper, a face identification method using a convolution neural network model is described, which includes the steps of extracting face characteristic vectors of a face image to be identified by using a CNN model.
63
Patent
Vehicle detection method based on convolutional neural network
Ye Mao,Li Xudong,Li Tao,Fu Min,Xiao Huaqiang,Wang Mengwei +5 more
- 10 Sep 2014
TL;DR: In this article, a vehicle detection method based on a convolutional neural network was proposed, which consists of collecting vehicle and non-vehicle samples and classifying the vehicle samples, the step S1 of preprocessing the samples, step S2 of training a CNN vehicle detector, and step S4 calculating an average similarity table of a characteristic pattern, the phase S5 of constructing a similarity characteristic pattern set, the stage S6 of obtaining a CNN-OP vehicle detector and phase S7 of obtaining detection images, phase S8 of constructing an image pyramid for the detection
46
Patent
Acquisition method and device for face database
Huang Ling,Zhou Longsha +1 more
- 20 Mar 2013
TL;DR: In this article, an acquisition method and device for a face database is presented, which consists of the following steps: obtaining the characteristics of a face to be tested under the current circumstances, comparing the face characteristics with that of the face saved in the face database, prompting the tester to make a judgment on the face attributes with the highest similarity in the current face database.
11
Patent
KNN classification-based optimization method
Liu Chuan,Wang Wenyong,Gou Ling +2 more
- 31 May 2017
TL;DR: In this article, an additional bias parameter is added for each category, so that the purpose of improving classification accuracy can be achieved, and the method comprises the steps of introducing a bias parameter b for each categories to adjust maximum similarity based on a conventional KNN classification method; and correcting the parameter b from a training sample through a learning algorithm.
1