Patents by Inventor Zhijun DU

Zhijun DU 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).

  • Publication number: 20180293997
    Abstract: Methods, systems, and computer-readable storage media for voice denoising. Implementations include actions of performing a mathematical transform on each frame signal in an audio signal segment to generate multiple power spectra. Each power spectrum corresponds to a respective frame signal. Power value variances corresponding to frame signals at various frequencies are determined. A noise signal is identified in each frame signal based on the power value variance. The identified noise signal is removed from each frame signal of the plurality of frame signals.
    Type: Application
    Filed: April 12, 2018
    Publication date: October 11, 2018
    Applicant: Alibaba Group Holding Limited
    Inventor: Zhijun Du
  • Patent number: 10087125
    Abstract: Disclosed in the present invention are a chromium-free gas phase fluorination catalyst and an application thereof. The precursor of the related chromium-free gas phase fluorination catalyst consists of a compound containing iron element, a compound containing rare earth metal element and a compound containing element A, wherein element A is one selected from Ca, Al, Mg and Ti, the precursor is subjected to roasting and fluorination treating to obtain the chromium-free gas phase fluorination catalyst. The precursor of the catalyst is roasted at 400-500° C. and fluoridized with hydrogen fluoride at 350-450° C. to obtain the chromium-free gas phase fluorination catalyst. The catalyst has characteristics of being chromium-free and environment-friendly, good catalytic activity and long life etc. The catalyst can be used for preparing hydrofluoroolefins or hydrochlorofluoroolefins from halohydrocarbons.
    Type: Grant
    Filed: November 7, 2017
    Date of Patent: October 2, 2018
    Assignee: XI'AN MODERN CHEMISTRY RESEARCH INSTITUTE
    Inventors: Jian Lu, Bo Wang, Yue Qin, Wei Mao, Liangang Kou, Zhenhua Zhang, Fei He, Wei Zhang, Hui Ma, Yangbo Ma, Zhijun Hao, Chunying Li, Yongmei Du, Fengxian Li, Sheng Han
  • Publication number: 20180260614
    Abstract: A first face region within a first image is determined. The first face region includes a location of a face within the first image. Based on the determined first face region within the first image, a predicted face region within a second image is determined. A first region of similarity within the predicted face region is determined. The first region of similarity has at least a predetermined degree of similarity to the first face region within the first image. Whether a second face region is present within the second image is determined. The location of the face within the second image is determined based on the first region of similarity, the determination of whether the second face region is present within the second image, and a face region selection rule.
    Type: Application
    Filed: May 11, 2018
    Publication date: September 13, 2018
    Applicant: Alibaba Group Holding Limited
    Inventors: Nan Wang, Zhijun Du, Yu Zhang
  • Publication number: 20180174599
    Abstract: An audio recognition method may comprising performing diffusion processing on a plurality of first feature points in a spectrogram of a to-be-recognized audio file to obtain a feature point map; searching in a spectrogram of a target audio file to determine whether the spectrogram of the target audio file comprises second feature points that respectively correspond to the diffused first feature points in the feature point map; and in response to determining that the spectrogram of the target audio file comprises the second feature points, determining that the to-be-recognized audio file is a part of the target audio file.
    Type: Application
    Filed: February 15, 2018
    Publication date: June 21, 2018
    Inventor: ZHIJUN DU
  • Publication number: 20180018800
    Abstract: A method for synthesizing images includes selecting a background image from a plurality of source images and selecting one or more foreground elements from a plurality of source files. The foreground elements include at least one of a foreground image or a foreground text. The method further includes dividing at least a portion of the selected background image to one or more sub-regions for displaying the one or more selected foreground elements, each sub-region is used for displaying at least one foreground element. The method further includes determining a display format and a display location for each of the one or more foreground elements and synthesizing the one or more foreground elements to the corresponding one or more sub-regions of the background image based on the display format and the display location.
    Type: Application
    Filed: September 26, 2017
    Publication date: January 18, 2018
    Applicant: Alibaba Group Holding Limited
    Inventors: Yu Zhang, Zhijun Du, Nan Wang, Wei Ding, Qiang He
  • Publication number: 20180018801
    Abstract: A request is received for an image to be presented on a client computing device, where the image is synthesized by shared images and dedicated images dedicated to the client computing device. A first one or more source files are identified for generating the shared images that are used by the client computing device and one or more other client computing devices. The shared images are generated based on the first one or more source files. A second one or more source files are identified for generating the dedicated images. A configuration file is generated that includes instructions for the client computing device to synthesize the shared images and the second one or more source files to the requested image. The shared images, the second one or more source files, and the configuration file are sent to the client computing device.
    Type: Application
    Filed: September 26, 2017
    Publication date: January 18, 2018
    Applicant: Alibaba Group Holding Limited
    Inventors: Zhijun Du, Sanping Li, Nan Wang, Qiang He, Yanjun Zhao, Zhenqiang Lao, Jie Shi, Weixing Wang
  • Patent number: 9836640
    Abstract: A face detector training method, a face detection method, and apparatuses are provided. In the present invention, during a training phase, a flexible block based local binary pattern feature and a corresponding second classifier are constructed, appropriate second classifiers are searched for to generate multiple first classifiers, and multiple layers of first classifiers that are obtained by using a cascading method form a final face detector; and during a detection phase, face detection is performed on a to-be-detected image by using a first classifier or a face detector that is learned during a training process, so that a face is differentiated from a non-face, and a face detection result is combined and output.
    Type: Grant
    Filed: February 16, 2015
    Date of Patent: December 5, 2017
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Yu Zhang, Zhenhua Chai, Zhijun Du
  • Publication number: 20170180362
    Abstract: A method, an apparatus, a terminal, and a server for identity authentication are disclosed. The method includes: receiving dynamic face authentication prompt information sent by a server during identity authentication of a user; obtaining gesture recognition information of the dynamic face authentication prompt information by recognizing a facial gesture presented by the user; and sending the gesture recognition information to the server to enable the server to confirm that the identity authentication is successful for the user in response to verifying that the gesture recognition information is consistent with the dynamic face authentication prompt information. Using the embodiments of the present application, a highly secure authentication can be performed on an identity of a user through dynamic face authentication.
    Type: Application
    Filed: March 2, 2017
    Publication date: June 22, 2017
    Inventor: Zhijun DU
  • Patent number: 9582710
    Abstract: Embodiments of the present invention disclose methods for generating a strong classifier for face detection. The methods include determining, according to a size of a prestored image training sample, a parameter of weak classifier of the image training sample, obtaining a sketch value of each of the weak classifiers of the image training sample, calculating a weighted classification error of each of the weak classifiers according to the sketch value and an initial weight of the image training sample, obtaining at least one optimal weak classifier according to the weighted classification error, and generating a strong classifier for face detection according to the optimal weak classifiers. The embodiments of the present invention further disclose an apparatus for generating a strong classifier for face detection. The embodiments of the present invention have advantages of improving robustness of code against noise and reducing a false detection rate of face detection.
    Type: Grant
    Filed: December 2, 2014
    Date of Patent: February 28, 2017
    Assignee: Huawei Technologies Co., Ltd.
    Inventors: Yu Zhang, Zhijun Du, Minjie Wang
  • Publication number: 20160313468
    Abstract: Methods of forming a geologic map usable for identifying prospective resource accumulations beneath the earth-surface are disclosed herein. The methods include obtaining a seismic stratigraphic structure of a subsurface region of the earth, determining a plurality of potential resistivity boundaries from the seismic stratigraphic structure, obtaining an electromagnetic data set resulting from an electromagnetic data acquisition of the subsurface region, recovering a resistivity map of the subsurface region by performing an inversion process guided by the seismic information, and resolving a geologic map from the resistivity map.
    Type: Application
    Filed: April 7, 2016
    Publication date: October 27, 2016
    Inventors: Zhijun DU, Md. Anwar Hossain BHUIYAN, Eivind Rødnes VESTERÅS, Allan John McKAY
  • Publication number: 20150235074
    Abstract: A face detector training method, a face detection method, and apparatuses are provided. In the present invention, during a training phase, a flexible block based local binary pattern feature and a corresponding second classifier are constructed, appropriate second classifiers are searched for to generate multiple first classifiers, and multiple layers of first classifiers that are obtained by using a cascading method form a final face detector; and during a detection phase, face detection is performed on a to-be-detected image by using a first classifier or a face detector that is learned during a training process, so that a face is differentiated from a non-face, and a face detection result is combined and output.
    Type: Application
    Filed: February 16, 2015
    Publication date: August 20, 2015
    Inventors: Yu Zhang, Zhenhua Chai, Zhijun Du
  • Publication number: 20150154441
    Abstract: Embodiments of the present invention disclose methods for generating a strong classifier for face detection. The methods include determining, according to a size of a prestored image training sample, a parameter of weak classifier of the image training sample, obtaining a sketch value of each of the weak classifiers of the image training sample, calculating a weighted classification error of each of the weak classifiers according to the sketch value and an initial weight of the image training sample, obtaining at least one optimal weak classifier according to the weighted classification error, and generating a strong classifier for face detection according to the optimal weak classifiers. The embodiments of the present invention further disclose an apparatus for generating a strong classifier for face detection. The embodiments of the present invention have advantages of improving robustness of code against noise and reducing a false detection rate of face detection.
    Type: Application
    Filed: December 2, 2014
    Publication date: June 4, 2015
    Inventors: Yu ZHANG, Zhijun DU, Minjie WANG