Patents by Inventor Gene Goebel
Gene Goebel 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: 20240087075Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating and decoding watermarks. An image and a data item is received. The encoder generates a first watermark and then a second watermark is generated using multiple first watermarks. The second watermark is used to watermark the image by overlaying the second watermark over the image. To decode the watermark, presence of a watermark is determined on a portion of an image. A distortion model determines distortions in the image and modifies the portion of the image based on the predicted distortions. The modified portion is decoded using the decoder to obtain a predicted first data item that is further used to validate the watermark based on the first data item.Type: ApplicationFiled: January 11, 2022Publication date: March 14, 2024Inventors: Xiyang Luo, Feng Yang, Elnaz Barshan Tashnizi, Dake He, Ryan Matthew Haggarty, Michael Gene Goebel
-
Publication number: 20240070467Abstract: Systems, devices, methods and instructions are described for detecting GAN generated images. On embodiment involves receiving an images, generating co-occurrence matrices on color channels of the image, generating analysis of the image by using a convolutional neural network trained to analyze image features of the images based on the generated co-occurrence matrices and determining whether the image is a GAN generated image based on the analysis.Type: ApplicationFiled: October 26, 2023Publication date: February 29, 2024Inventors: Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Tejaswi Nanjundaswamy, Michael Gene Goebel, Bangalore S. Manjunath, Shivkumar Chandrasekaran
-
Patent number: 11854113Abstract: Systems and methods herein describe accessing an image, generating a resized image, generating an image feature vector by applying an image classification neural network to the resized image, generating analysis of the image by processing the image feature vector using a machine-learning classifier trained to analyze the image feature vector, and based on the analysis, determining an event that is attributed to the image.Type: GrantFiled: November 3, 2020Date of Patent: December 26, 2023Assignee: Mayachitra, Inc.Inventors: Lakshmanan Nataraj, Michael Gene Goebel, Bangalore S. Manjunath, Shivkumar Chandrasekaran
-
Patent number: 11842471Abstract: Systems and methods herein describe a metadata verification system that is configured to access a digital satellite image, generate a first discrete Fourier transform (DFT) pattern based on an ortho-rectified digital satellite image, generate a second DFT pattern based on rational polynomial coefficient (RPC) data of the digital satellite image, compare the first DFT pattern to the second DFT pattern, generate a score based on the comparison, and generate a determination of whether the digital satellite image has been manipulated based on the score.Type: GrantFiled: June 9, 2021Date of Patent: December 12, 2023Assignee: Mayachitra, Inc.Inventors: Chandrakanth Gudavalli, Michael Gene Goebel, Tejaswi Nanjundaswamy, Lakshmanan Nataraj, Shivkumar Chandrasekaran, Bangalore S. Manjunath
-
Patent number: 11836634Abstract: Systems, devices, methods and instructions are described for detecting GAN generated images. On embodiment involves receiving an images, generating co-occurrence matrices on color channels of the image, generating analysis of the image by using a convolutional neural network trained to analyze image features of the images based on the generated co-occurrence matrices and determining whether the image is a GAN generated image based on the analysis.Type: GrantFiled: June 7, 2022Date of Patent: December 5, 2023Assignee: Mayachitra, Inc.Inventors: Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Tejaswi Nanjundaswamy, Michael Gene Goebel, Bangalore S. Manjunath, Shivkumar Chandrasekaran
-
Publication number: 20230362399Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for jointly training an encoder that generates a watermark and a decoder that decodes a data item encoded within the watermark. The training comprises obtaining a plurality of training images and data items. For each training image, a first watermark is generated using an encoder and a subsequent second watermark is generated by tiling two or more first watermarks. The training image is watermarked using the second watermark to generate a first error value and distortions are added to the watermarked image. A distortion detector predicts the distortions based on which the distorted image is modified. The modified image is decoded by the decoder to generate a predicted data item and a second error value. The training parameters of the encoder and decoder are adjusted based on the first and the second error value.Type: ApplicationFiled: January 11, 2022Publication date: November 9, 2023Inventors: Xiyang Luo, Feng Yang, Elnaz Barshan Tashnizi, Dake He, Ryan Matthew Haggarty, Michael Gene Goebel
-
Publication number: 20220398709Abstract: Systems and methods herein describe a metadata verification system that is configured to access a digital satellite image, generate a first discrete Fourier transform (DFT) pattern based on an ortho-rectified digital satellite image, generate a second DFT pattern based on rational polynomial coefficient (RPC) data of the digital satellite image, compare the first DFT pattern to the second DFT pattern, generate a score based on the comparison, and generate a determination of whether the digital satellite image has been manipulated based on the score.Type: ApplicationFiled: June 9, 2021Publication date: December 15, 2022Inventors: Chandrakanth Gudavalli, Michael Gene Goebel, Tejaswi Nanjundaswamy, Lakshmanan Nataraj, Shivkumar Chandrasekaran, Bangalore S. Manjunath
-
Publication number: 20220318569Abstract: Systems, devices, methods and instructions are described for detecting GAN generated images. On embodiment involves receiving an images, generating co-occurrence matrices on color channels of the image, generating analysis of the image by using a convolutional neural network trained to analyze image features of the images based on the generated co-occurrence matrices and determining whether the image is a GAN generated image based on the analysis.Type: ApplicationFiled: June 7, 2022Publication date: October 6, 2022Inventors: Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Tejaswi Nanjundaswamy, Michael Gene Goebel, Bangalore S. Manjunath, Shivkumar Chandrasekaran
-
Patent number: 11429812Abstract: Systems, devices, methods and instructions are described for detecting GAN generated images. On embodiment involves receiving an images, generating co-occurrence matrices on color channels of the image, generating analysis of the image by using a convolutional neural network trained to analyze image features of the images based on the generated co-occurrence matrices and determining whether the image is a GAN generated image based on the analysis.Type: GrantFiled: February 26, 2020Date of Patent: August 30, 2022Assignee: Mayachitra, Inc.Inventors: Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Tejaswi Nanjundaswamy, Michael Gene Goebel, Bangalore S. Manjunath, Shivkumar Chandrasekaran
-
Publication number: 20210209425Abstract: Systems and methods herein describe accessing an image, generating a resized image, generating an image feature vector by applying an image classification neural network to the resized image, generating analysis of the image by processing the image feature vector using a machine-learning classifier trained to analyze the image feature vector, and based on the analysis, determining an event that is attributed to the image.Type: ApplicationFiled: November 3, 2020Publication date: July 8, 2021Inventors: Lakshmanan Nataraj, Michael Gene Goebel, Bangalore S. Manjunath, Shivkumar Chandrasekaran
-
Publication number: 20210209415Abstract: Systems, devices, methods and instructions are described for detecting GAN generated images. On embodiment involves receiving an images, generating co-occurrence matrices on color channels of the image, generating analysis of the image by using a convolutional neural network trained to analyze image features of the images based on the generated co-occurrence matrices and determining whether the image is a GAN generated image based on the analysis.Type: ApplicationFiled: February 26, 2020Publication date: July 8, 2021Inventors: Lakshmanan Nataraj, Tajuddin Manhar Mohammed, Tejaswi Nanjundaswamy, Michael Gene Goebel, Bangalore S. Manjunath, Shivkumar Chandrasekaran
-
Patent number: 9012387Abstract: Resist stripping agents useful for fabricating circuits and/or forming electrodes on semiconductor devices for semiconductor integrated circuits and/or liquid crystals with reduced metal and metal alloy etch rates (particularly copper etch rates and TiW etch rates), are provided with methods for their use. The preferred stripping agents contain low concentrations of resorcinol or a resorcinol derivative, with or without an added copper salt, and with or without an added amine to improve solubility of the copper salt. Further provided are integrated circuit devices and electronic interconnect structures prepared according to these methods.Type: GrantFiled: August 15, 2013Date of Patent: April 21, 2015Assignee: Dynaloy, LLCInventors: John Atkinson, Kimberly Dona Pollard, Gene Goebel
-
Publication number: 20130334679Abstract: Resist stripping agents useful for fabricating circuits and/or forming electrodes on semiconductor devices for semiconductor integrated circuits and/or liquid crystals with reduced metal and metal alloy etch rates (particularly copper etch rates and TiW etch rates), are provided with methods for their use. The preferred stripping agents contain low concentrations of resorcinol or a resorcinol derivative, with or without an added copper salt, and with or without an added amine to improve solubility of the copper salt. Further provided are integrated circuit devices and electronic interconnect structures prepared according to these methods.Type: ApplicationFiled: August 15, 2013Publication date: December 19, 2013Applicant: Dynaloy, LLCInventors: John Atkinson, Kimberly Dona Pollard, Gene Goebel
-
Patent number: 8551682Abstract: Resist stripping agents useful for fabricating circuits and/or forming electrodes on semiconductor devices for semiconductor integrated circuits and/or liquid crystals with reduced metal and metal alloy etch rates (particularly copper etch rates and TiW etch rates), are provided with methods for their use. The preferred stripping agents contain low concentrations of resorcinol or a resorcinol derivative, with or without an added copper salt, and with or without an added amine to improve solubility of the copper salt. Further provided are integrated circuit devices and electronic interconnect structures prepared according to these methods.Type: GrantFiled: October 30, 2007Date of Patent: October 8, 2013Assignee: Dynaloy, LLCInventors: John M. Atkinson, Kimberly Dona Pollard, Gene Goebel
-
Patent number: 7632796Abstract: Improved stripper solutions for removing photoresists from substrates are provided that typically have freezing points below about +15° C. and high loading capacities. The stripper solutions comprise dimethyl sulfoxide, a quaternary ammonium hydroxide, and an alkanolamine having at least two carbon atoms, at least one amino substituent and at least one hydroxyl substituent, the amino and hydroxyl substituents attached to two different carbon atoms. Some formulation can additionally contain a secondary solvent. Methods for use of the stripping solutions are additionally provided.Type: GrantFiled: October 28, 2005Date of Patent: December 15, 2009Assignee: Dynaloy, LLCInventors: Michael T. Phenis, Lauri Kirby Kirkpatrick, Raymond Chan, Diane Marie Scheele, Kimberly Dona Pollard, Gene Goebel
-
Publication number: 20090186793Abstract: Improved dry stripper solutions for removing one, two or more photoresist layers from substrates are provided. The stripper solutions comprise dimethyl sulfoxide, a quaternary ammonium hydroxide, and an alkanolamine, an optional secondary solvent and less than about 3 wt. % water and/or a dryness coefficient of at least about 1. Methods for the preparation and use of the improved dry stripping solutions are additionally provided.Type: ApplicationFiled: October 24, 2006Publication date: July 23, 2009Inventors: Michael T. Phenis, Lauri Renee Johnson, Raymond Chan, Diane Marie Scheele, Kimberly Dona Pollard, Gene Goebel