Patents by Inventor Kshitiz Garg
Kshitiz Garg 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: 20150156419Abstract: Users are provided with feedback regarding blurriness of an image in real-time. When an image is received, a blur score is automatically generated in addition to a visual that indicates the extent of blurriness across the picture. The blur score is calculated by aggregating an image_blur_score and optionally a motion_blur_score. A user can also be provided with suggestions on improving image sharpness and help in determining if another image needs to be taken.Type: ApplicationFiled: December 2, 2013Publication date: June 4, 2015Applicant: YAHOO! INC.Inventors: Gaurav Aggarwal, Nikhil Rasiwasia, Kshitiz Garg, Vijay Mahadevan
-
Patent number: 8577150Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, processing the image to generate intrinsic images including a material image and an illumination image, and detecting and removing specularity as a function of the intrinsic images.Type: GrantFiled: March 18, 2011Date of Patent: November 5, 2013Assignee: Tandent Vision Science, Inc.Inventor: Kshitiz Garg
-
Patent number: 8577135Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, assembling a feature vector for the image file, the feature vector containing information regarding a likelihood that a selected region of the image file is specular, providing a classifier derived from a computer learning technique, computing a classification score for the selected region of the image file, as a function of the feature vector and the classifier and classifying the region as being specular, as a function of the classification score.Type: GrantFiled: November 17, 2009Date of Patent: November 5, 2013Assignee: Tandent Vision Science, Inc.Inventors: Kshitiz Garg, Neil Alldrin
-
Patent number: 8452109Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, assembling a feature vector for the image file, the feature vector containing information regarding a likelihood that a selected pair of regions of the image file are of a same intrinsic characteristic, for example, a same texture, providing a classifier derived from a computer learning technique, computing a classification score for the selected pair of regions of the image file, as a function of the feature vector and the classifier and classifying the regions as being of the same intrinsic characteristic, as a function of the classification score.Type: GrantFiled: January 11, 2010Date of Patent: May 28, 2013Assignee: Tandent Vision Science, Inc.Inventors: Neil Alldrin, Kshitiz Garg, Andrew Neil Stein, Kristin Jean Dana, Bruce Allen Maxwell, Casey Arthur Smith, Youngrock Yoon, Besma Roui Abidi
-
Publication number: 20130071033Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, providing a multi-class classifier trained to identify edges in an image relative to computer actions to be taken in respect to the respective edges, determined as a function of illumination effects in the image and utilizing the multi-class classifier to classify edges in the image, for identification of computer actions to be taken in respect to the edges in the image.Type: ApplicationFiled: September 21, 2011Publication date: March 21, 2013Applicant: Tandent Vision Science, Inc.Inventors: Andrew Neil Stein, Kshitiz Garg
-
Publication number: 20120237128Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, processing the image to generate intrinsic images including a material image and an illumination image, and detecting and removing specularity as a function of the intrinsic images.Type: ApplicationFiled: March 18, 2011Publication date: September 20, 2012Applicant: Tandent Vision Science, Inc.Inventor: Kshitiz Garg
-
Publication number: 20110222742Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, identifying shadow edges in the image, computing gradient information for the image and modifying the gradient information relative to the shadow edges for improved performance of computer functionality in an image processing operation.Type: ApplicationFiled: March 10, 2010Publication date: September 15, 2011Applicant: Tandent Vision Science, Inc.Inventors: Andrew Neil Stein, Neil Alldrin, Kshitiz Garg
-
Publication number: 20110170768Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, assembling a feature vector for the image file, the feature vector containing information regarding a likelihood that a selected pair of regions of the image file are of a same intrinsic characteristic, for example, a same texture, providing a classifier derived from a computer learning technique, computing a classification score for the selected pair of regions of the image file, as a function of the feature vector and the classifier and classifying the regions as being of the same intrinsic characteristic, as a function of the classification score.Type: ApplicationFiled: January 11, 2010Publication date: July 14, 2011Applicant: Tandent Vision Science, Inc.Inventors: Neil Alldrin, Kshitiz Garg, Andrew Neil Stein, Kristin Jean Dana, Bruce Allen Maxwell, Casey Arthur Smith, Youngrock Yoon, Besma Roui Abidi
-
Publication number: 20110116710Abstract: In a first exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, assembling a feature vector for the image file, the feature vector containing information regarding a likelihood that a selected region of the image file is specular, providing a classifier derived from a computer learning technique, computing a classification score for the selected region of the image file, as a function of the feature vector and the classifier and classifying the region as being specular, as a function of the classification score.Type: ApplicationFiled: November 17, 2009Publication date: May 19, 2011Applicant: Tandent Vision Science, Inc.Inventors: Kshitiz Garg, Neil Alldrin
-
Patent number: 7783183Abstract: Systems and methods for reducing the visibility of rain in acquired images are provided. One or more inputs relating the scene desired to be acquired by the user are used to retrieve camera settings that will reduce the visibility of rain in acquired images. Additionally, features relating to the scene may be automatically determined and used alone, or in combination with user inputs, to retrieve camera settings. The acquired images may be part of a video. Another feature of the invention is its use as a rain gauge. The camera settings are adjusted to enhance the visibility of rain, then one or more images are acquired and analyzed for the amount and size of raindrops. From this analysis the rain rate can be determined.Type: GrantFiled: December 22, 2009Date of Patent: August 24, 2010Assignee: The Trustees of Columbia University in the City of New YorkInventors: Kshitiz Garg, Shree K. Nayar
-
Publication number: 20100157076Abstract: Systems and methods for reducing the visibility of rain in acquired images are provided. One or more inputs relating the scene desired to be acquired by the user are used to retrieve camera settings that will reduce the visibility of rain in acquired images. Additionally, features relating to the scene may be automatically determined and used alone, or in combination with user inputs, to retrieve camera settings. The acquired images may be part of a video. Another feature of the invention is its use as a rain gauge. The camera settings are adjusted to enhance the visibility of rain, then one or more images are acquired and analyzed for the amount and size of raindrops. From this analysis the rain rate can be determined.Type: ApplicationFiled: December 22, 2009Publication date: June 24, 2010Applicant: The Trustees of Columbia University in the City of New YorkInventors: Kshitiz Garg, Shree K. Nayar
-
Patent number: 7660517Abstract: Systems and methods for reducing the visibility of rain in acquired images are provided. One or more inputs relating the scene desired to be acquired by the user are used to retrieve camera settings that will reduce the visibility of rain in acquired images. Additionally, features relating to the scene may be automatically determined and used alone, or in combination with user inputs, to retrieve camera settings. The acquired images may be part of a video. Another feature of the invention is its use as a rain gauge. The camera settings are adjusted to enhance the visibility of rain, then one ore more images are acquired and analyzed for the amount and size of raindrops. From this analysis the rain rate can be determined.Type: GrantFiled: March 16, 2006Date of Patent: February 9, 2010Assignee: The Trustees of Columbia University in the City of New YorkInventors: Kshitiz Garg, Shree K. Nayar
-
Publication number: 20070053671Abstract: Systems and methods for reducing the visibility of rain in acquired images are provided. One or more inputs relating the scene desired to be acquired by the user are used to retrieve camera settings that will reduce the visibility of rain in acquired images. Additionally, features relating to the scene may be automatically determined and used alone, or in combination with user inputs, to retrieve camera settings. The acquired images may be part of a video. Another feature of the invention is its use as a rain gauge. The camera settings are adjusted to enhance the visibility of rain, then one ore more images are acquired and analyzed for the amount and size of raindrops. From this analysis the rain rate can be determined.Type: ApplicationFiled: March 16, 2006Publication date: March 8, 2007Inventors: Kshitiz Garg, Shree Nayar