Patents by Inventor Rujie Liu

Rujie Liu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10885308
    Abstract: A method and apparatus for evaluating an illumination condition in a face image is provided by decomposing a face image into illumination feature components and face feature components; extracting determined areas in the face image; calculating a maximum luminance feature, a minimum luminance feature and an illumination direction feature according to the decomposed illumination feature components in the determined areas. The illumination condition in the face image is evaluated according to the maximum luminance feature, the minimum luminance feature and the illumination direction feature.
    Type: Grant
    Filed: October 12, 2018
    Date of Patent: January 5, 2021
    Assignee: FUJITSU LIMITED
    Inventors: Pingping Lu, Rujie Liu
  • Publication number: 20200410290
    Abstract: An information processing apparatus includes a processor to input each sample image into feature extracting components to obtain at least two features of the sample image, and to cause a classifying component to calculate a classification loss of the sample image based on the at least two features; extract, from each pair of features, a plurality of sample pairs for calculating mutual information between each pair of features; input the plurality of sample pairs into a machine learning architecture corresponding to each pair of features, to calculate an information loss between each pair of features.
    Type: Application
    Filed: June 24, 2020
    Publication date: December 31, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Wei SHEN, Rujie LIU
  • Patent number: 10878284
    Abstract: The method for training an image model, in each round of training performed with respect to each sample image: inputs an image obtained by cropping the sample image by an object extraction component obtained through a previous round of training, as a scale-adjusted sample image, into the image model, wherein the object extraction component is used for extracting concerned objects in sample images at respective scales; inputs a feature of the scale-adjusted sample image into a local classifier in the image model respectively, performs category prediction with respect to feature points in the feature, so as to obtain a local prediction result, and updates the object extraction component based on the local prediction result; performs object level category prediction for the scale-adjusted sample image based on the feature and the updated object extraction component; and trains the image model based on a category prediction result of the scale-adjusted sample image.
    Type: Grant
    Filed: March 12, 2019
    Date of Patent: December 29, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Wei Shen, Rujie Liu
  • Publication number: 20200334490
    Abstract: The application relates to an image processing apparatus, and a training method and training apparatus for training the image processing apparatus. The training apparatus comprises: a feature map extracting unit to extract feature maps of support images and a query image; a refining unit to determine, with respect to each support image, a matching feature vector, based on the feature maps; and a joint training unit to use a training image as the query image to execute joint training, such that it is capable of determining a matching support image and a matching location with respect to a new query image, the training image matching a specific support image. The image processing apparatus trained through the above training technique is capable of simultaneously determining a matching support image among a plurality of support images respectively belonging to different classes which matches a query image, and determining a matching location.
    Type: Application
    Filed: January 17, 2020
    Publication date: October 22, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Wei SHEN, Rujie LIU
  • Patent number: 10810765
    Abstract: An image processing apparatus and an image processing method where the apparatus includes: a self-encoder configured to perform self-encoding on an input image to generate multiple feature maps; a parameter generator configured to generate multiple convolution kernels for a convolution neural network based on the multiple feature maps; and an outputter configured to generate, by using the convolution neural network, an output result of the input image based on the input image and the multiple convolution kernels. With the image processing apparatus and the image processing method according to the present disclosure, an accuracy of processing an image by using the CNN network can be improved.
    Type: Grant
    Filed: September 20, 2018
    Date of Patent: October 20, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Wei Shen, Rujie Liu
  • Patent number: 10796205
    Abstract: A multi-view vector processing method and a multi-view vector processing device are provided. A multi-view vector x represents an object containing information on at least two non-discrete views. A model of the multi-view vector, where the model includes at least components of: a population mean ? of the multi-view vector, view component of each view of the multi-view vector and noise is established. The population mean ?, parameters of each view component and parameters of the noise , are obtained by using training data of the multi-view vector x. The device includes a processor and a storage medium storing program codes, and the program codes implements the aforementioned method when being executed by the processor.
    Type: Grant
    Filed: May 4, 2018
    Date of Patent: October 6, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Ziqiang Shi, Liu Liu, Rujie Liu
  • Publication number: 20200302246
    Abstract: An information processing method includes: inputting sample image into a machine learning architecture to obtain a first feature, and causing a first classifier to calculate a first classification loss; calculating a second feature based on the first feature and a predetermined first mask, and inputting the second feature into the first classifier to calculate an entropy loss; calculating a second mask based on the first mask and the entropy loss to maximize the entropy loss; obtaining an adversarial feature based on the first feature and the second mask, where the adversarial feature is complementary to the second feature; causing, by training the first classifier and the second classifier in association with each other, the second classifier to calculate a second classification loss based on the adversarial feature; and adjusting parameters of the machine learning architecture, the first classifier and the second classifier, to obtain a trained machine learning architecture.
    Type: Application
    Filed: January 16, 2020
    Publication date: September 24, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Wei SHEN, Rujie LIU
  • Patent number: 10776918
    Abstract: The present application relates to method and device for determining image similarity that includes: dividing a target image into multiple regions based on positions of pixels relative to a reference point in the target image, and dividing a reference image into multiple regions based on positions of pixels relative to a reference point in the reference image; determining, based on feature points in the target image and feature points in the reference image as well as the regions obtained by dividing the target image and the regions obtained by dividing the reference image, similarity between a distribution of the feature points in the target image and a distribution of the feature points in the reference image. According to the method of the present application, the similarity is described more reasonably.
    Type: Grant
    Filed: November 17, 2017
    Date of Patent: September 15, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Mengjiao Wang, Rujie Liu
  • Patent number: 10769499
    Abstract: A method and apparatus for removing black eyepits and sunglasses in first actual scenario data having an image containing a face acquired from an actual scenario, to obtain second actual scenario data; counting a proportion of wearing glasses in the second actual scenario data; dividing original training data composed of an image containing a face into wearing-glasses and not-wearing-glasses first and second training data, where a proportion of wearing glasses in the original training data is lower than a proportion in the second actual scenario data; generating wearing-glasses third training data based on glasses data and the second training data; generating fourth training data in which a proportion of wearing glasses is equal to the proportion of wearing glasses in the second actual scenario data, based on the third training data and the original training data; and training a face recognition model based on the fourth training data.
    Type: Grant
    Filed: November 2, 2018
    Date of Patent: September 8, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Meng Zhang, Rujie Liu, Jun Sun
  • Publication number: 20200265220
    Abstract: An apparatus and method for training a classification model and an apparatus for classifying with a classification model are disclosed. The apparatus for training a classification model comprises: a local area obtainment unit to, obtain predetermined local area of each sample image; a feature extraction unit to, with respect to each sample image, set corresponding numbers of feature extraction layers for the global area and each predetermined local area, to extract a global feature of the global area and a local feature of each predetermined local area, wherein the global area and the predetermined local areas share at least one feature extraction layer in which the global feature and each local feature are combined; and a loss determination unit to calculate a loss function of the sample image based on combined features of each sample image, and to train the classification model based on the loss function.
    Type: Application
    Filed: January 9, 2020
    Publication date: August 20, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Meng Zhang, Rujie Liu
  • Publication number: 20200265308
    Abstract: The present disclosure relates to a model optimization method, a data identification method and a data identification device. A method for optimizing a data identification model comprises: acquiring a loss function of a data identification model to be optimized; calculating weight vectors in the loss function which correspond to classes; performing normalization processing on the weight vectors; updating the loss function by increasing an included angle between any two of the weight vectors; optimizing the data identification model to be optimized based on the updated loss function.
    Type: Application
    Filed: January 21, 2020
    Publication date: August 20, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Mengjiao Wang, Rujie Liu
  • Publication number: 20200265272
    Abstract: An apparatus for training a classification model includes: a feature extraction unit configured to set, with respect to each training set of a first predetermined number of training sets, feature extraction layers, and extract features of a sample image, where at least two of the training sets at least partially overlap; a feature fusion unit configured to set, with respect to training set, feature fusion layers, and perform a fusion on the extracted features of the sample image; and a loss determination unit configured to set, with respect to training set, a loss determination layer, calculate a loss function of the sample image based on the fused feature of the sample image, and train a classification model based on the loss function. The first predetermined number of training sets share at least one layer of feature fusion layers and feature extraction layers set with respect to each training set.
    Type: Application
    Filed: January 7, 2020
    Publication date: August 20, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Meng Zhang, Rujie Liu
  • Publication number: 20200234068
    Abstract: An apparatus for training a classifying model comprises: a first obtaining unit configured to input a sample image to a first machine learning framework, to obtain a first classification probability and a first classification loss; a second obtaining unit configured to input a second image to a second machine learning framework, to obtain a second classification probability and a second classification loss, the two machine learning frameworks having identical structures and sharing identical parameters; a similarity loss calculating unit configured to calculate a similarity loss related to a similarity between the first classification probability and the second classification probability; a total loss calculating unit configured to calculate the sum of the similarity loss, the first classification loss and the second classification loss, as a total loss; and a training unit configured to adjust parameters of the two machine learning frameworks to obtain a trained classifying model.
    Type: Application
    Filed: January 8, 2020
    Publication date: July 23, 2020
    Applicant: FUJITSU LIMITED
    Inventors: Meng Zhang, Rujie Liu
  • Patent number: 10657969
    Abstract: An identity verification method and an identity verification apparatus based on a voiceprint are provided. The identity verification method based on a voiceprint includes: receiving an unknown voice; extracting a voiceprint of the unknown voice using a neural network-based voiceprint extractor which is obtained through pre-training; concatenating the extracted voiceprint with a pre-stored voiceprint to obtain a concatenated voiceprint; and performing judgment on the concatenated voiceprint using a pre-trained classification model, to verify whether the extracted voiceprint and the pre-stored voiceprint are from a same person. With the identity verification method and the identity verification apparatus, a holographic voiceprint of the speaker can be extracted from a short voice segment, such that the verification result is more robust.
    Type: Grant
    Filed: January 9, 2018
    Date of Patent: May 19, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Ziqiang Shi, Liu Liu, Rujie Liu
  • Publication number: 20200134506
    Abstract: A method of training a student model corresponding to a teacher model is provided. The teacher model is obtained through training by taking first input data as input data and taking a corresponding output data as an output target. The method comprises training the student model by taking second input data as input data and taking the corresponding output data as an output target. The second input data is data obtained due to changing of the first input data.
    Type: Application
    Filed: October 2, 2019
    Publication date: April 30, 2020
    Applicant: Fujitsu Limited
    Inventors: Mengjiao WANG, Rujie LIU
  • Patent number: 10552712
    Abstract: The disclosure relates to a training device and method for an image processing device and an image processing device. The training device is used for training first and second image processing units, comprising: a training unit to input a first realistic image without a specific feature into the first image processing unit to generate a first generated image with the specific feature through first image processing, and to input a second realistic image with the specific feature into the second image processing unit to generate a second generated image without the specific feature through second image processing; and a classifying unit performing classification processing to discriminate realistic and generated images, wherein the training unit performs first training processing of training the classifying unit based on the realistic and generated images, and performs second training processing of training the first and second image processing units based on the training result.
    Type: Grant
    Filed: December 15, 2017
    Date of Patent: February 4, 2020
    Assignee: FUJITSU LIMITED
    Inventors: Wei Shen, Rujie Liu
  • Publication number: 20190392248
    Abstract: The present disclosure relates to an information processing method and an information processing apparatus. The information processing method according to the present disclosure performs training on a classification model by using a plurality of training samples, and comprises the steps of: adjusting a distribution of feature vectors of the plurality of training samples in a feature space based on a typical sample in the plurality of training samples; and performing training on the classification model by using the adjusted feature vectors of the plurality of training samples. Through the technology according to the present disclosure, it is possible to perform pre-adjustment on training samples before training, such that it is possible to reduce discrimination between training samples belonging to a same class and increase discrimination between training samples belonging to different classes in the training process.
    Type: Application
    Filed: June 24, 2019
    Publication date: December 26, 2019
    Applicant: FUJITSU LIMITED
    Inventors: Meng ZHANG, Rujie LIU
  • Publication number: 20190385086
    Abstract: There are provided a method of knowledge transferring, an information processing apparatus and a storage medium. The method of knowledge transferring includes: obtaining a first model which has been trained in advance with respect to a predetermined task; and training a second model with respect to the predetermined task by utilizing a comprehensive loss function, such that the second model has knowledge of the first model. The comprehensive loss function is based on a first loss function weighted by accuracy of an output result of the first model for a training sample in regard to the predetermined task, and a second loss function. The first loss function represents a difference between processing results of the second model and the first model for the training sample. The second loss function represents accuracy of an output result of the second model for the training sample in regard to the predetermined task.
    Type: Application
    Filed: June 12, 2019
    Publication date: December 19, 2019
    Applicant: FUJITSU LIMITED
    Inventors: Mengjiao WANG, Rujie LIU
  • Publication number: 20190286940
    Abstract: The method for training an image model, in each round of training performed with respect to each sample image: inputs an image obtained by cropping the sample image by an object extraction component obtained through a previous round of training, as a scale-adjusted sample image, into the image model, wherein the object extraction component is used for extracting concerned objects in sample images at respective scales; inputs a feature of the scale-adjusted sample image into a local classifier in the image model respectively, performs category prediction with respect to feature points in the feature, so as to obtain a local prediction result, and updates the object extraction component based on the local prediction result; performs object level category prediction for the scale-adjusted sample image based on the feature and the updated object extraction component; and trains the image model based on a category prediction result of the scale-adjusted sample image.
    Type: Application
    Filed: March 12, 2019
    Publication date: September 19, 2019
    Applicant: FUJITSU LIMITED
    Inventors: Wei SHEN, Rujie LIU
  • Patent number: 10410345
    Abstract: An image processing device and an image processing method are provided. The image processing device includes: an acquisitor configured to acquire multiple slice images arranged in an order; a selector configured to detect the multiple slice images sequentially, to determine a reference slice image and a reference trachea region in the reference slice image; and a branch point determiner configured to determine, with a region growing method, trachea regions of slice images following the reference slice image sequentially by using the reference trachea region as a seed region, and determine connectivity of the trachea regions, until a branch point slice image is determined, where a trachea region of the branch point slice image includes two disconnected regions. With the image processing device and the image processing method, manual intervention can be reduced and a position of the branch point can be determined more accurately.
    Type: Grant
    Filed: November 30, 2017
    Date of Patent: September 10, 2019
    Assignee: FUJITSU LIMITED
    Inventors: Mengjiao Wang, Rujie Liu