Patents by Inventor Animesh Khemka
Animesh Khemka 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: 20240155253Abstract: A method of compression includes compressing a captured image from a first bit-depth at which it was captured to a second bit-depth that is less than the first bit-depth. The compression comprises applying, according to a power curve, a first compression amount to a first region of the captured image having a first pixel value; and applying, according to the power curve, a second compression amount to a second part of the captured image having a higher second pixel value, wherein the first compression amount is lower than the second compression amount.Type: ApplicationFiled: January 16, 2024Publication date: May 9, 2024Inventors: Animesh Khemka, Sean Midthun Pieper
-
Patent number: 11917307Abstract: A method of decompression includes decompressing a compressed image according to a power curve to generate a partially decompressed image, wherein the compressed image is decompressed from a second bit depth that is lower than a first bit-depth at which the image was generated.Type: GrantFiled: January 6, 2023Date of Patent: February 27, 2024Assignee: Nvidia CorporationInventors: Animesh Khemka, Sean Midthun Pieper
-
Patent number: 11908104Abstract: In order to more accurately white balance an image, weightings can be determined for pixels of an image when computing an illuminant color value of the image and/or a scene. The weightings can be based at least in part on the Signal-to-Noise Ratio (SNR) of the pixels. The SNR may be actual SNR or SNR estimated from brightness levels of the pixels. SNR weighting (e.g., SNR adjustment) may reduce the effect of pixels with high noise on the computed illuminant color value. For example, one or more channel values of the illuminant color value can be determined based on the weightings and color values of the pixels. One or more color gain values can be determined based on the one or more channel values of the illuminant color value and used to white balance the image.Type: GrantFiled: September 6, 2022Date of Patent: February 20, 2024Assignee: NVIDIA CorporationInventors: Hamidreza Mirzaei Domabi, Eric Dujardin, Animesh Khemka, Yining Deng
-
Publication number: 20230141489Abstract: A method of decompression includes decompressing a compressed image according to a power curve to generate a partially decompressed image, wherein the compressed image is decompressed from a second bit depth that is lower than a first bit-depth at which the image was generated.Type: ApplicationFiled: January 6, 2023Publication date: May 11, 2023Inventors: Animesh Khemka, Sean Midthun Pieper
-
Publication number: 20230065993Abstract: Apparatuses, systems, and techniques to receive, at one or more processor associated with an image signal processing (ISP) pipeline, a compressed image generated by an image sensor, wherein the compressed image is captured at a first bit-depth associated with the image sensor and is compressed to a second bit-depth that is lower than the first bit-depth, and wherein the ISP is associated with a third bit-depth that is lower than the first bit-depth and higher than the second bit-depth; and decompress the compressed image according to a power curve to generate a partially decompressed image having the third bit-depth, wherein a plurality of regions of the partially decompressed image are decompressed at separate decompression amounts based on a corresponding pixel value of each region of the plurality of regions.Type: ApplicationFiled: August 30, 2021Publication date: March 2, 2023Inventors: Animesh Khemka, Sean Midthun Pieper
-
Patent number: 11582431Abstract: Apparatuses, systems, and techniques to receive, at one or more processor associated with an image signal processing (ISP) pipeline, a compressed image generated by an image sensor, wherein the compressed image is captured at a first bit-depth associated with the image sensor and is compressed to a second bit-depth that is lower than the first bit-depth, and wherein the ISP is associated with a third bit-depth that is lower than the first bit-depth and higher than the second bit-depth; and decompress the compressed image according to a power curve to generate a partially decompressed image having the third bit-depth, wherein a plurality of regions of the partially decompressed image are decompressed at separate decompression amounts based on a corresponding pixel value of each region of the plurality of regions.Type: GrantFiled: August 30, 2021Date of Patent: February 14, 2023Assignee: NVIDIA CORPORATIONInventors: Animesh Khemka, Sean Midthun Pieper
-
Publication number: 20220414831Abstract: In order to more accurately white balance an image, weightings can be determined for pixels of an image when computing an illuminant color value of the image and/or a scene. The weightings can be based at least in part on the Signal-to-Noise Ratio (SNR) of the pixels. The SNR may be actual SNR or SNR estimated from brightness levels of the pixels. SNR weighting (e.g., SNR adjustment) may reduce the effect of pixels with high noise on the computed illuminant color value. For example, one or more channel values of the illuminant color value can be determined based on the weightings and color values of the pixels. One or more color gain values can be determined based on the one or more channel values of the illuminant color value and used to white balance the image.Type: ApplicationFiled: September 6, 2022Publication date: December 29, 2022Inventors: Hamidreza Mirzaei Domabi, Eric Dujardin, Animesh Khemka, Yining Deng
-
Patent number: 11436704Abstract: In order to more accurately white balance an image, weightings can be determined for pixels of an image when computing an illuminant color value of the image and/or a scene. The weightings can be based at least in part on the Signal-to-Noise Ratio (SNR) of the pixels. The SNR may be actual SNR or SNR estimated from brightness levels of the pixels. SNR weighting (e.g., SNR adjustment) may reduce the effect of pixels with high noise on the computed illuminant color value. For example, one or more channel values of the illuminant color value can be determined based on the weightings and color values of the pixels. One or more color gain values can be determined based on the one or more channel values of the illuminant color value and used to white balance the image.Type: GrantFiled: January 14, 2020Date of Patent: September 6, 2022Assignee: NVIDIA CorporationInventors: Hamidreza Mirzaei Domabi, Eric Dujardin, Animesh Khemka, Yining Deng
-
Publication number: 20200226720Abstract: In order to more accurately white balance an image, weightings can be determined for pixels of an image when computing an illuminant color value of the image and/or a scene. The weightings can be based at least in part on the Signal-to-Noise Ratio (SNR) of the pixels. The SNR may be actual SNR or SNR estimated from brightness levels of the pixels. SNR weighting (e.g., SNR adjustment) may reduce the effect of pixels with high noise on the computed illuminant color value. For example, one or more channel values of the illuminant color value can be determined based on the weightings and color values of the pixels. One or more color gain values can be determined based on the one or more channel values of the illuminant color value and used to white balance the image.Type: ApplicationFiled: January 14, 2020Publication date: July 16, 2020Inventors: Hamidreza Mirzaei Domabi, Eric Dujardin, Animesh Khemka, Yining Deng
-
Publication number: 20160259758Abstract: A spatially varying PSF may be applied in a camera simulator by multiplying a fixed weight map by its impact region. Next, Fast Fourier Transform (FFT) both IWk and Ak, multiply the FFT results element by element and do an inverse FFT (IFFT) to bring the results back to spatial domain. The output image is exactly the same as the outcome of direct approach with the same interpolation method for spatially varying PSF. However, the operation now will be significantly faster in some embodiments.Type: ApplicationFiled: March 4, 2015Publication date: September 8, 2016Inventors: Animesh Khemka, Chyuan-Tyng Wu
-
Publication number: 20110184684Abstract: This application presents a new system and method for image acquisition of internal human tissue, including but not limited to the prostate, as well as a system and method for the guidance and positioning of medical devices relative to the internal tissue. In the presented systems and methods, ultrasound scanned data (e.g., 2-D B-mode images) are acquired freehand absent a mechanical armature that constrains an ultrasound acquisition probe in a known spatial framework. To allow for reconstruction of the scanned data into a 3-D image, multiple tracker sensors that provide position/location information are used with a freehand acquisition probe (e.g., handheld ultrasound probe). The position of such tracker sensors can be calculated when disposed in an electromagnetic field.Type: ApplicationFiled: March 7, 2011Publication date: July 28, 2011Applicant: EIGEN, INC.Inventors: Lu Li, Animesh Khemka
-
Patent number: 7942060Abstract: Provided herein are devices and methods for mounting variously configured medical imaging probes for imaging applications. In one aspect, a holding device allows for interfacing/holding most conventional ultrasound probes such that the probes may be attached to a positioning device using a common interface. As ultrasound probes come in various sizes and lengths, the device may adjust to different lengths, widths and shapes of different probes. Hence, the device may work in a substantially universal manner while securely holding probes with little wobble or other problems.Type: GrantFiled: March 26, 2007Date of Patent: May 17, 2011Assignee: Eigen, Inc.Inventors: Jasjit Suri, Kanwar Suri, Animesh Khemka, Dinesh Kumar
-
Patent number: 7832114Abstract: Provided herein are devices and methods for mounting variously configured medical imaging probes to a tracker assembly for imaging applications. In one aspect, a tracker assembly provides multiple degrees of freedom for positioning a probe relative to a patient and/or maintaining a probe in a desired location for imaging purposes. The tracker generates location information that may be utilized as frame of reference information for acquired images. In another aspect a holding device allows for interfacing/holding differently configured probes in a common orientation to a predetermined frame of reference.Type: GrantFiled: September 5, 2007Date of Patent: November 16, 2010Assignee: Eigen, LLCInventors: Jasjit S. Suri, Dinesh Kumar, Animesh Khemka
-
Publication number: 20090227874Abstract: Provided herein are devices and methods for mounting variously configured medical imaging probes (“ultrasound probes”) to a positioning device for imaging applications. One aspect provides a probe holder that has a recessed surface adapted to securely support a particular ultrasound probe for interfacing the probe with a positioning device. Another aspect provides a probe holder that interconnects with a flexible joint to allow the probe holder to securely support a variety of different ultrasound probes and interface those probes with a positioning device.Type: ApplicationFiled: November 6, 2008Publication date: September 10, 2009Applicant: EIGEN, INC.Inventors: Jasjit S. Suri, Dinesh Kumar, Animesh Khemka
-
Publication number: 20080249403Abstract: Provided herein are devices and methods for mounting variously configured medical imaging probes to a tracker assembly for imaging applications. In one aspect, a tracker assembly provides multiple degrees of freedom for positioning a probe relative to a patient and/or maintaining a probe in a desired location for imaging purposes. The tracker generates location information that may be utilized as frame of reference information for acquired images. In another aspect a holding device allows for interfacing/holding differently configured probes in a common orientation to a predetermined frame of reference.Type: ApplicationFiled: September 5, 2007Publication date: October 9, 2008Inventors: Jasjit S. Suri, Dinesh Kumar, Animesh Khemka
-
Publication number: 20080221453Abstract: Provided herein are devices and methods for mounting variously configured medical imaging probes for imaging applications. In one aspect, a holding device allows for interfacing/holding most conventional ultrasound probes such that the probes may be attached to a positioning device using a common interface. As ultrasound probes come in various sizes and lengths, the device may adjust to different lengths, widths and shapes of different probes. Hence, the device may work in a substantially universal manner while securely holding probes with little wobble or other problems.Type: ApplicationFiled: March 26, 2007Publication date: September 11, 2008Inventors: Jasjit Suri, Kanwar Suri, Animesh Khemka, Dinesh Kumar