Patents by Inventor Zicheng Liu
Zicheng 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).
-
Publication number: 20050129315Abstract: Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.Type: ApplicationFiled: February 1, 2005Publication date: June 16, 2005Applicant: Microsoft CorporationInventors: Zicheng Liu, Zhengyou Zhang, Michael Cohen, Charles Jacobs
-
Publication number: 20050114124Abstract: A method and system use an alternative sensor signal received from a sensor other than an air conduction microphone to estimate a clean speech value. The estimation uses either the alternative sensor signal alone, or in conjunction with the air conduction microphone signal. The clean speech value is estimated without using a model trained from noisy training data collected from an air conduction microphone. Under one embodiment, correction vectors are added to a vector formed from the alternative sensor signal in order to form a filter, which is applied to the air conductive microphone signal to produce the clean speech estimate. In other embodiments, the pitch of a speech signal is determined from the alternative sensor signal and is used to decompose an air conduction microphone signal. The decomposed signal is then used to determine a clean signal estimate.Type: ApplicationFiled: November 26, 2003Publication date: May 26, 2005Applicant: Microsoft CorporationInventors: Zicheng Liu, Michael Sinclair, Alejandro Acero, Xuedong Huang, James Droppo, Li Deng, Zhengyou Zhang, Yanli Zheng
-
Publication number: 20050078124Abstract: A method and system uses geometry-driven feature point analysis to synthesize images including for example facial expressions. Given the feature point positions (geometry) of an expression, the method automatically synthesizes the corresponding expression image, which has photorealistic and natural looking expression details.Type: ApplicationFiled: October 14, 2003Publication date: April 14, 2005Applicant: Microsoft CorporationInventors: Zicheng Liu, Baining Guo, Heung-Yeung Shum, Qingshan Zhang
-
Publication number: 20050074145Abstract: Systems and methods to estimate head motion between two images of a face are described. In one aspect, locations of a plurality of distinct facial features in the two images are identified. The locations correspond to a number of unknowns that are determined upon estimation of head motion. The number of unknowns are determined by a number of equations. The identified locations are converted into a set of physical face parameters based on the symmetry of the distinct facial features. The set of physical face parameters reduce the number of unknowns as compared to the number of equations used to determine the unknowns. An inequality constraint is added to a particular face parameter of the physical face parameters, such that the particular face parameter is constrained within a predetermined minimum and maximum value. The inequality constraint is converted to an equality constraint using a penalty function. Head motion is estimated from identified points in the two images.Type: ApplicationFiled: December 1, 2004Publication date: April 7, 2005Applicant: Microsoft CorporationInventors: Zicheng Liu, Zhengyou Zhang
-
Publication number: 20050065802Abstract: A system and method for automatically determining if a remote client is a human or a computer. A set of HIP design guidelines which are important to ensure the security and usability of a HIP system are described. Furthermore, one embodiment of this new HIP system and method is based on human face and facial feature detection. Because human face is the most familiar object to all human users the embodiment of the invention employing a face is possibly the most universal HIP system so far.Type: ApplicationFiled: September 19, 2003Publication date: March 24, 2005Applicant: Microsoft CorporationInventors: Yong Rui, Zicheng Liu
-
Publication number: 20050053277Abstract: Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.Type: ApplicationFiled: October 19, 2004Publication date: March 10, 2005Applicant: Microsoft CorporationInventors: Zicheng Liu, Zhengyou Zhang, Michael Cohen, Charles Jacobs
-
Publication number: 20050047630Abstract: Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.Type: ApplicationFiled: October 18, 2004Publication date: March 3, 2005Applicant: Microsoft CorporationInventors: Zicheng Liu, Zhengyou Zhang, Michael Cohen, Charles Jacobs
-
Publication number: 20050033571Abstract: The present invention combines a conventional audio microphone with an additional speech sensor that provides a speech sensor signal based on an input. The speech sensor signal is generated based on an action undertaken by a speaker during speech, such as facial movement, bone vibration, throat vibration, throat impedance changes, etc. A speech detector component receives an input from the speech sensor and outputs a speech detection signal indicative of whether a user is speaking. The speech detector generates the speech detection signal based on the microphone signal and the speech sensor signal.Type: ApplicationFiled: August 7, 2003Publication date: February 10, 2005Applicant: Microsoft CorporationInventors: Xuedong Huang, Zicheng Liu, Zhengyou Zhang, Michael Sinclair, Alejandro Acero
-
Publication number: 20050031195Abstract: A system and method for automatically modeling a three dimensional object, such as a face, from a single image. The system and method according to the invention can construct one or more three dimensional (3D) face models using a single image. Although use of a frontal image simplifies the processing, the system and method according to the invention can also generate a 3D model from a non-frontal image (e.g., an image where the object to be modeled has an out of plane rotation, such a face that is turned to one side to some extent). The system is fully automatic. It is fast compared to the other modeling systems. Furthermore, it is very robust. It can be used to construct personalized models for games, on-line chat, and so on. It can also be used as a tool to generate a database of faces with various poses which are needed to train most face recognition systems.Type: ApplicationFiled: August 8, 2003Publication date: February 10, 2005Applicant: Microsoft CorporationInventor: Zicheng Liu
-
Publication number: 20050027515Abstract: The present invention combines a conventional audio microphone with an additional speech sensor that provides a speech sensor signal based on an input. The speech sensor signal is generated based on an action undertaken by a speaker during speech, such as facial movement, bone vibration, throat vibration, throat impedance changes, etc. A speech detector component receives an input from the speech sensor and outputs a speech detection signal indicative of whether a user is speaking. The speech detector generates the speech detection signal based on the microphone signal and the speech sensor signal.Type: ApplicationFiled: July 29, 2003Publication date: February 3, 2005Applicant: Microsoft CorporationInventors: Xuedong Huang, Zicheng Liu, Zhengyou Zhang, Michael Sinclair, Alejandro Acero
-
Publication number: 20050008196Abstract: The system provides improved procedures to estimate head motion between two images of a face. Locations of a number of distinct facial features are identified in two images. The identified locations can correspond to the eye corners, mouth corners and nose tip. The locations are converted into as a set of physical face parameters based on the symmetry of the identified distinct facial features. The set of physical parameters reduces the number of unknowns as compared to the number of equations used to determine the unknowns. An initial head motion estimate is determined by: (a) estimating each of the set of physical parameters, (b) estimating a first head pose transform corresponding to the first image, and (c) estimating a second head pose transform corresponding to the second image. The head motion estimate can be incorporated into a feature matching algorithm to refine the head motion estimation and the physical facial parameters.Type: ApplicationFiled: August 4, 2004Publication date: January 13, 2005Applicant: Microsoft CorporationInventors: Zicheng Liu, Zhengyou Zhang
-
Patent number: 6828972Abstract: A system and method for mapping facial expressions. Facial expressions exhibit not only facial feature motions, but also subtle changes in illumination and appearance (e.g., facial creases and wrinkles). These details are important visual cues, but they are difficult to synthesize. Traditional expression mapping techniques consider feature motions while the details in illumination changes are ignored. A novel technique for facial expression mapping is presented. The illumination change of one person's expression is captured in what is called expression ratio image (ERI). Together with geometric warping, an ERI is mapped to any other person's face image to generate more expressive facial expressions.Type: GrantFiled: April 24, 2002Date of Patent: December 7, 2004Assignee: Microsoft Corp.Inventors: Zhengyou Zhang, Zicheng Liu, Ying Shan
-
Publication number: 20040233197Abstract: A system and method for compressing digital pen stroke data utilizing curve simplification. Digital pen stroke images (ink images) generate a relatively large amount of data to preserve the ink image generated on a device. Current ink compression algorithms utilize lossless compression algorithm that have limited success. The invention provides a lossy compression algorithm to reduce the amount of data required to store and transmit ink data. The invention utilizes a two-part algorithm to reduce and compress the number of data points representing the ink data. The invention also utilizes curve splines to reconstruct and smooth the lossy ink data image.Type: ApplicationFiled: May 19, 2003Publication date: November 25, 2004Inventors: Zicheng Liu, Henrique S. Malvar, Zhengyou Zhang
-
Publication number: 20040218827Abstract: A system and method for facilitating low bandwidth video image transmission in video conferencing systems. A target is acquired (video image of a person's head) and processed to identify one or more sub-regions (e.g., background, eyes, mouth and head). The invention incorporates a fast feature matching methodology to match a current sub-region with previously stored sub-regions. If a match is found, an instruction is sent to the receiving computer to generate the next frame of video data from the previously stored blocks utilizing a texture synthesis technique. The invention is applicable for video conferencing in low bandwidth environments.Type: ApplicationFiled: May 2, 2003Publication date: November 4, 2004Inventors: Michael Cohen, Zicheng Liu, Zhen Wen, Ke Zheng
-
Publication number: 20040213453Abstract: Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.Type: ApplicationFiled: May 14, 2004Publication date: October 28, 2004Applicant: Microsoft CorporationInventors: Zicheng Liu, Zhengyou Zhang, Michael F. Cohen, Charles E. Jacobs
-
Publication number: 20040213438Abstract: Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.Type: ApplicationFiled: May 14, 2004Publication date: October 28, 2004Applicant: Microsoft CorporationInventors: Zicheng Liu, Zhengyou Zhang, Michael F. Cohen, Charles E. Jacobs
-
Publication number: 20040208344Abstract: Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.Type: ApplicationFiled: May 14, 2004Publication date: October 21, 2004Applicant: Microsoft CorporationInventors: Zicheng Liu, Zhengyou Zhang, Michael F. Cohen, Charles E. Jacobs
-
Patent number: 6807290Abstract: Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.Type: GrantFiled: January 4, 2001Date of Patent: October 19, 2004Assignee: Microsoft CorporationInventors: Zicheng Liu, Zhengyou Zhang, Michael F. Cohen, Charles E. Jacobs
-
Publication number: 20040061787Abstract: The present invention includes a foveated wide-angle imaging system and method for capturing a wide-angle image and for viewing the captured wide-angle image in real time. In general, the foveated wide-angle imaging system includes a foveated wide-angle camera system having multiple cameras for capturing a scene and outputting raw output images, a foveated wide-angle stitching system for generating a stitch table, and a real-time wide-angle image correction system that creates a composed warp table from the stitch table and processes the raw output images using the composed warp table to correct distortion and perception problems. The foveated wide-angle imaging method includes using a foveated wide-angle camera system to capture a plurality of raw output images, generating a composed warp table, and processing the plurality of raw output images using the composed warp table to generate a corrected wide-angle image for viewing.Type: ApplicationFiled: September 30, 2002Publication date: April 1, 2004Inventors: Zicheng Liu, Michael Cohen
-
Publication number: 20040056857Abstract: A system and method for mapping facial expressions. Facial expressions exhibit not only facial feature motions, but also subtle changes in illumination and appearance (e.g., facial creases and wrinkles). These details are important visual cues, but they are difficult to synthesize. Traditional expression mapping techniques consider feature motions while the details in illumination changes are ignored. A novel technique for facial expression mapping is presented. The illumination change of one person's expression is captured in what is called expression ratio image (ERI).Type: ApplicationFiled: April 24, 2002Publication date: March 25, 2004Inventors: Zhengyou Zhang, Zicheng Liu, Ying Shan