Patents by Inventor Rufeng Chu
Rufeng Chu 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: 10885644Abstract: Embodiments of the present application relate to a method, apparatus, and system for detecting a specified image identifier. The method includes retrieving a target image to be detected from a predetermined area, binarizing the target image to be detected to obtain a target binary image to be detected, calibrating connected domains of the target binary image to be detected, successively retrieving image features of candidate connected domains, and comparing the image features corresponding to the candidate connected domains to image features of a standard specified identifier image, wherein the candidate connected domains are determined based at least in part on the calibration of the connected domains, and determining a candidate connected domain as the location of the specified identifier image based at least in part on the comparison of the image features corresponding to the candidate connected domains to image features of the standard specified identifier image.Type: GrantFiled: June 11, 2019Date of Patent: January 5, 2021Assignee: BANMA ZHIXING NETWORK (HONGKONG) CO., LIMITEDInventors: Gang Cheng, Rufeng Chu, Lun Zhang
-
Publication number: 20190295267Abstract: Embodiments of the present application relate to a method, apparatus, and system for detecting a specified image identifier. The method includes retrieving a target image to be detected from a predetermined area, binarizing the target image to be detected to obtain a target binary image to be detected, calibrating connected domains of the target binary image to be detected, successively retrieving image features of candidate connected domains, and comparing the image features corresponding to the candidate connected domains to image features of a standard specified identifier image, wherein the candidate connected domains are determined based at least in part on the calibration of the connected domains, and determining a candidate connected domain as the location of the specified identifier image based at least in part on the comparison of the image features corresponding to the candidate connected domains to image features of the standard specified identifier image.Type: ApplicationFiled: June 11, 2019Publication date: September 26, 2019Inventors: Gang Cheng, Rufeng Chu, Lun Zhang
-
Patent number: 10360689Abstract: Embodiments of the present application relate to a method, apparatus, and system for detecting a specified image identifier. The method includes retrieving a target image to be detected from a predetermined area, binarizing the target image to be detected to obtain a target binary image to be detected, calibrating connected domains of the target binary image to be detected, successively retrieving image features of candidate connected domains, and comparing the image features corresponding to the candidate connected domains to image features of a standard specified identifier image, wherein the candidate connected domains are determined based at least in part on the calibration of the connected domains, and determining a candidate connected domain as the location of the specified identifier image based at least in part on the comparison of the image features corresponding to the candidate connected domains to image features of the standard specified identifier image.Type: GrantFiled: September 14, 2017Date of Patent: July 23, 2019Assignee: Alibaba Group Holding LimitedInventors: Gang Cheng, Rufeng Chu, Lun Zhang
-
Patent number: 10127309Abstract: Embodiments of the present invention provide an audio information retrieval method and device. The method includes acquiring a spectrogram of an audio clip, extracting a local feature of at least one energy extreme point in the spectrogram to use as a local feature sequence of the audio clip, and conducting an audio information retrieval according to the local feature sequence of the audio clip to acquire audio information. Embodiments of the present invention reduce the probability of a missed match (e.g., false negative) and improve the accuracy of audio information retrieval.Type: GrantFiled: May 11, 2016Date of Patent: November 13, 2018Assignee: Alibaba Group Holding LimitedInventors: Dong Yi, Yeming Xiao, Rong Liu, Lun Zhang, Rufeng Chu
-
Patent number: 10121099Abstract: An identification code-based three-dimensional interactive technique includes acquiring an image including an identification-coded real object, the image being taken by video-capable equipment, identifying an identification code from the identification-coded real object, obtaining object information corresponding to the identification code, acquiring a reference image associated with the identification code and feature points of the reference image, obtaining a position, an orientation, or a combination thereof on the video-capable equipment relative to the identification-coded real object based on the reference image and the feature points of the reference image, and conducting a three-dimensional interaction based on the position, the orientation, or a combination thereof of the video-capable equipment relative to the identification-coded real object and the object information corresponding to the identification code.Type: GrantFiled: June 9, 2017Date of Patent: November 6, 2018Assignee: Alibaba Group Holding LimitedInventors: Shiqi Zhou, Rufeng Chu, Lun Zhang
-
Publication number: 20180005390Abstract: Embodiments of the present application relate to a method, apparatus, and system for detecting a specified image identifier. The method includes retrieving a target image to be detected from a predetermined area, binarizing the target image to be detected to obtain a target binary image to be detected, calibrating connected domains of the target binary image to be detected, successively retrieving image features of candidate connected domains, and comparing the image features corresponding to the candidate connected domains to image features of a standard specified identifier image, wherein the candidate connected domains are determined based at least in part on the calibration of the connected domains, and determining a candidate connected domain as the location of the specified identifier image based at least in part on the comparison of the image features corresponding to the candidate connected domains to image features of the standard specified identifier image.Type: ApplicationFiled: September 14, 2017Publication date: January 4, 2018Inventors: Gang Cheng, Rufeng Chu, Lun Zhang
-
Patent number: 9811749Abstract: Determining a label from an image is disclosed, including: obtaining an image; determining a first portion of the image associated with a special mark; determining a second portion of the image associated with a label based at least in part on the first portion of the image associated with the special mark; and applying character recognition to the second portion of the image associated with the label to determine a value associated with the label.Type: GrantFiled: January 21, 2015Date of Patent: November 7, 2017Assignee: Alibaba Group Holding LimitedInventors: Lun Zhang, Rufeng Chu, Chunhui Zhang
-
Patent number: 9799119Abstract: Embodiments of the present application relate to a method, apparatus, and system for detecting a specified image identifier. The method includes retrieving a target image to be detected from a predetermined area, binarizing the target image to be detected to obtain a target binary image to be detected, calibrating connected domains of the target binary image to be detected, successively retrieving image features of candidate connected domains, and comparing the image features corresponding to the candidate connected domains to image features of a standard specified identifier image, wherein the candidate connected domains are determined based at least in part on the calibration of the connected domains, and determining a candidate connected domain as the location of the specified identifier image based at least in part on the comparison of the image features corresponding to the candidate connected domains to image features of the standard specified identifier image.Type: GrantFiled: July 28, 2015Date of Patent: October 24, 2017Assignee: Alibaba Group Holding LimitedInventors: Gang Cheng, Rufeng Chu, Lun Zhang
-
Publication number: 20170277989Abstract: An identification code-based three-dimensional interactive technique includes acquiring an image including an identification-coded real object, the image being taken by video-capable equipment, identifying an identification code from the identification-coded real object, obtaining object information corresponding to the identification code, acquiring a reference image associated with the identification code and feature points of the reference image, obtaining a position, an orientation, or a combination thereof on the video-capable equipment relative to the identification-coded real object based on the reference image and the feature points of the reference image, and conducting a three-dimensional interaction based on the position, the orientation, or a combination thereof of the video-capable equipment relative to the identification-coded real object and the object information corresponding to the identification code.Type: ApplicationFiled: June 9, 2017Publication date: September 28, 2017Inventors: Shiqi Zhou, Rufeng Chu, Lun Zhang
-
Patent number: 9704247Abstract: An identification code-based three-dimensional interactive technique includes acquiring an image including an identification-coded real object, the image being taken by video-capable equipment, identifying an identification code from the identification-coded real object, obtaining object information corresponding to the identification code, acquiring a reference image associated with the identification code and feature points of the reference image, obtaining a position, an orientation, or a combination thereof on the video-capable equipment relative to the identification-coded real object based on the reference image and the feature points of the reference image, and conducting a three-dimensional interaction based on the position, the orientation, or a combination thereof of the video-capable equipment relative to the identification-coded real object and the object information corresponding to the identification code.Type: GrantFiled: July 14, 2016Date of Patent: July 11, 2017Assignee: Alibaba Group Holding LimitedInventors: Shiqi Zhou, Rufeng Chu, Lun Zhang
-
Patent number: 9665787Abstract: A method of extracting particular information in a standard card is disclosed herein. The method includes: acquiring a card image of a standard card having particular information to be extracted; identifying an image region containing the particular information in the card image; and extracting and outputting the image region as an independent image. Thus, an image related to the part of the particular information only can be obtained from the standard card conveniently, quickly and accurately, thereby improving the working efficiency. In addition, the present disclosure further provides an apparatus of extracting particular information in a standard card and a method of inputting particular information of a standard card in a mobile terminal.Type: GrantFiled: May 4, 2015Date of Patent: May 30, 2017Assignee: Alibaba Group Holding LimitedInventors: Shiqi Zhou, Rufeng Chu
-
Publication number: 20160335347Abstract: Embodiments of the present invention provide an audio information retrieval method and device. The method includes acquiring a spectrogram of an audio clip, extracting a local feature of at least one energy extreme point in the spectrogram to use as a local feature sequence of the audio clip, and conducting an audio information retrieval according to the local feature sequence of the audio clip to acquire audio information. Embodiments of the present invention reduce the probability of a missed match (e.g., false negative) and improve the accuracy of audio information retrieval.Type: ApplicationFiled: May 11, 2016Publication date: November 17, 2016Inventors: Dong YI, Yeming XIAO, Rong LIU, Lun ZHANG, Rufeng CHU
-
Publication number: 20160321814Abstract: An identification code-based three-dimensional interactive technique includes acquiring an image including an identification-coded real object, the image being taken by video-capable equipment, identifying an identification code from the identification-coded real object, obtaining object information corresponding to the identification code, acquiring a reference image associated with the identification code and feature points of the reference image, obtaining a position, an orientation, or a combination thereof on the video-capable equipment relative to the identification-coded real object based on the reference image and the feature points of the reference image, and conducting a three-dimensional interaction based on the position, the orientation, or a combination thereof of the video-capable equipment relative to the identification-coded real object and the object information corresponding to the identification code.Type: ApplicationFiled: July 14, 2016Publication date: November 3, 2016Inventors: Shiqi Zhou, Rufeng Chu, Lun Zhang
-
Patent number: 9430835Abstract: An identification code-based three-dimensional interactive technique includes acquiring an image including an identification-coded real object, the image being taken by video-capable equipment, identifying an identification code from the identification-coded real object, obtaining object information corresponding to the identification code, acquiring a reference image associated with the identification code and feature points of the reference image, obtaining a position, an orientation, or a combination thereof on the video-capable equipment relative to the identification-coded real object based on the reference image and the feature points of the reference image, and conducting a three-dimensional interaction based on the position, the orientation, or a combination thereof of the video-capable equipment relative to the identification-coded real object and the object information corresponding to the identification code.Type: GrantFiled: October 16, 2015Date of Patent: August 30, 2016Assignee: Alibaba Group Holding LimitedInventors: Shiqi Zhou, Rufeng Chu, Lun Zhang
-
Publication number: 20160035097Abstract: An identification code-based three-dimensional interactive technique includes acquiring an image including an identification-coded real object, the image being taken by video-capable equipment, identifying an identification code from the identification-coded real object, obtaining object information corresponding to the identification code, acquiring a reference image associated with the identification code and feature points of the reference image, obtaining a position, an orientation, or a combination thereof on the video-capable equipment relative to the identification-coded real object based on the reference image and the feature points of the reference image, and conducting a three-dimensional interaction based on the position, the orientation, or a combination thereof of the video-capable equipment relative to the identification-coded real object and the object information corresponding to the identification code.Type: ApplicationFiled: October 16, 2015Publication date: February 4, 2016Inventors: Shiqi Zhou, Rufeng Chu, Lun Zhang
-
Publication number: 20160034783Abstract: Embodiments of the present application relate to a method, apparatus, and system for detecting a specified image identifier. The method includes retrieving a target image to be detected from a predetermined area, binarizing the target image to be detected to obtain a target binary image to be detected, calibrating connected domains of the target binary image to be detected, successively retrieving image features of candidate connected domains, and comparing the image features corresponding to the candidate connected domains to image features of a standard specified identifier image, wherein the candidate connected domains are determined based at least in part on the calibration of the connected domains, and determining a candidate connected domain as the location of the specified identifier image based at least in part on the comparison of the image features corresponding to the candidate connected domains to image features of the standard specified identifier image.Type: ApplicationFiled: July 28, 2015Publication date: February 4, 2016Inventors: Gang Cheng, Rufeng Chu, Lun Zhang
-
Patent number: 9195871Abstract: An identification code-based three-dimensional interactive technique includes acquiring an image including an identification-coded real object, the image being taken by video-capable equipment, identifying an identification code from the identification-coded real object, obtaining object information corresponding to the identification code, acquiring a reference image associated with the identification code and feature points of the reference image, obtaining a position, an orientation, or a combination thereof on the video-capable equipment relative to the identification-coded real object based on the reference image and the feature points of the reference image, and conducting a three-dimensional interaction based on the position, the orientation, or a combination thereof of the video-capable equipment relative to the identification-coded real object and the object information corresponding to the identification code.Type: GrantFiled: February 4, 2014Date of Patent: November 24, 2015Assignee: Alibaba Group Holding LimitedInventors: Shiqi Zhou, Rufeng Chu, Lun Zhang
-
Publication number: 20150199581Abstract: Determining a label from an image is disclosed, including: obtaining an image; determining a first portion of the image associated with a special mark; determining a second portion of the image associated with a label based at least in part on the first portion of the image associated with the special mark; and applying character recognition to the second portion of the image associated with the label to determine a value associated with the label.Type: ApplicationFiled: January 21, 2015Publication date: July 16, 2015Inventors: Lun Zhang, Rufeng Chu, Chunhui Zhang
-
Patent number: 8971620Abstract: Determining a label from an image is disclosed, including: obtaining an image; determining a first portion of the image associated with a special mark; determining a second portion of the image associated with a label based at least in part on the first portion of the image associated with the special mark; and applying character recognition to the second portion of the image associated with the label to determine a value associated with the label.Type: GrantFiled: September 9, 2013Date of Patent: March 3, 2015Assignee: Alibaba Group Holding LimitedInventors: Lun Zhang, Rufeng Chu, Chunhui Zhang
-
Publication number: 20140217178Abstract: An identification code-based three-dimensional interactive technique includes acquiring an image including an identification-coded real object, the image being taken by video-capable equipment, identifying an identification code from the identification-coded real object, obtaining object information corresponding to the identification code, acquiring a reference image associated with the identification code and feature points of the reference image, obtaining a position, an orientation, or a combination thereof on the video-capable equipment relative to the identification-coded real object based on the reference image and the feature points of the reference image, and conducting a three-dimensional interaction based on the position, the orientation, or a combination thereof of the video-capable equipment relative to the identification-coded real object and the object information corresponding to the identification code.Type: ApplicationFiled: February 4, 2014Publication date: August 7, 2014Inventors: Shiqi Zhou, Rufeng Chu, Lun Zhang