Patents by Inventor Pankaj Kumar Bajpai
Pankaj Kumar Bajpai 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: 11790228Abstract: A learning-based model is trained using a plurality of attributes of media. Depth estimation is performed using the learning-based model. The depth estimation supports performing a computer vision task on the media. Attributes used in the depth estimation include scene understanding, depth correctness, and processing of sharp edges and gaps. The media may be processed to perform media restoration or the media quality enhancement. A computer vision task may include semantic segmentation.Type: GrantFiled: January 21, 2021Date of Patent: October 17, 2023Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Kunal Swami, Prasanna Vishnu Bondada, Pankaj Kumar Bajpai, Mahesh P J, Manoj Kumar
-
Publication number: 20220351334Abstract: A method for performing multi-functional image restoration by an electronic device with a trained Machine Learning (ML) model is provided. The method includes receiving an image and determining channels of the image, and determining whether a number of restructuring needed for the channels is one. When the restructuring needed for the channels not one, then the method includes restructuring each channel into a first channel set, generating first inferences of the image corresponding to each channel by feeding the first channel set to the trained ML model, and generating a final inference image by combining the first inferences. When the number of restructuring needed for the channels is one, then the method includes restructuring the channels into a second channel set, and generating a second inference of the image by feeding the second channel set to the trained ML model.Type: ApplicationFiled: April 28, 2022Publication date: November 3, 2022Inventors: Saikat Kumar DAS, Sai Kumar Reddy MANNE, Pankaj Kumar BAJPAI, Rishikesh JHA, Alok Shankarlal SHUKLA, Shashavali DOODEKULA, Siddharth Deepak ROHEDA
-
Patent number: 11233936Abstract: Embodiments herein disclose a method for recommending an image capture mode by an electronic device. The method includes identifying, by the electronic device, at least one ROI displayed in a camera preview of the electronic device for capturing an image in a non-ultra-wide image capture mode. Further, the method includes determining, by the electronic device, that the at least one ROI is suitable to capture in an ultra-wide image capture mode. Further, the method includes providing, by the electronic device, at least one recommendation to switch to the ultra-wide image capture mode from the non-ultra-wide image capture mode for capturing the image.Type: GrantFiled: July 19, 2019Date of Patent: January 25, 2022Assignee: Samsung Electronics Co., Ltd.Inventors: Swadha Jaiswal, Debayan Mukherjee, Mannu Amrit, Shivi Pal, Vibha Venkatesh Kulkarni, Pavan Sudheendra, Pankaj Kumar Bajpai, Balvinder Singh, Narasimha Gopalakrishna Pai, Sanjay Narasimha Murthy, Vineeth Thanikonda Munirathnam
-
Publication number: 20210224652Abstract: A learning-based model is trained using a plurality of attributes of media. Depth estimation is performed using the learning-based model. The depth estimation supports performing a computer vision task on the media. Attributes used in the depth estimation include scene understanding, depth correctness, and processing of sharp edges and gaps. The media may be processed to perform media restoration or the media quality enhancement. A computer vision task may include semantic segmentation.Type: ApplicationFiled: January 21, 2021Publication date: July 22, 2021Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: Kunal SWAMI, Prasanna Vishnu BONDADA, Pankaj Kumar BAJPAI, Mahesh P. J, Manoj KUMAR
-
Patent number: 11057553Abstract: A device and a method for capturing media by using a device including a plurality of flaps are provided. At least two flaps among the plurality of flaps each include at least one camera. The method includes analyzing preview images of the cameras based on a first media capture mode, adjusting a bend angle between the at least two flaps based on the analysis of the preview images to determine at least one baseline distance, and obtaining at least one media in the first capture mode at the at least one baseline distance.Type: GrantFiled: July 5, 2019Date of Patent: July 6, 2021Assignee: Samsung Electronics Co., Ltd.Inventors: Sourabh Singh Yadav, Pankaj Kumar Bajpai, Sarvesh, Pranav Prakash Deshpande, Lokesh Rayasandra Boregowda, Rituparna Sarkar
-
Publication number: 20200045225Abstract: Embodiments herein disclose a method for recommending an image capture mode by an electronic device. The method includes identifying, by the electronic device, at least one ROI displayed in a camera preview of the electronic device for capturing an image in a non-ultra-wide image capture mode. Further, the method includes determining, by the electronic device, that the at least one ROI is suitable to capture in an ultra-wide image capture mode. Further, the method includes providing, by the electronic device, at least one recommendation to switch to the ultra-wide image capture mode from the non-ultra-wide image capture mode for capturing the image.Type: ApplicationFiled: July 19, 2019Publication date: February 6, 2020Inventors: Swadha JAISWAL, Debayan MUKHERJEE, Mannu AMRIT, Shivi PAL, Vibha Venkatesh KULKARNI, Pavan SUDHEENDRA, Pankaj Kumar BAJPAI, Balvinder SINGH, Narasimha Gopalakrishna PAI, Sanjay Narasimha MURTHY, Vineeth Thanikonda MUNIRATHNAM
-
Publication number: 20200014831Abstract: A device and a method for capturing media by using a device including a plurality of flaps are provided. At least two flaps among the plurality of flaps each include at least one camera. The method includes analyzing preview images of the cameras based on a first media capture mode, adjusting a bend angle between the at least two flaps based on the analysis of the preview images to determine at least one baseline distance, and obtaining at least one media in the first capture mode at the at least one baseline distance.Type: ApplicationFiled: July 5, 2019Publication date: January 9, 2020Inventors: Sourabh Singh YADAV, Pankaj Kumar BAJPAI, SARVESH, Pranav Prakash DESHPANDE, Lokesh Rayasandra BOREGOWDA, Rituparna SARKAR
-
Patent number: 9958285Abstract: An electronic device and method for capturing an image are disclosed. The electronic device includes an image sensor configured to capture images, a location sensor configured to detect a location of the electronic device, and a processor. The processor may execute the method, which includes capturing a first image, and detecting a first location where the first image is captured, detecting, by a processor, a second location at which a second image is to be captured and generating guidance information for travel to the second location, and when a present location is within a predefined range of the second location, automatically capturing the second image.Type: GrantFiled: February 20, 2015Date of Patent: May 1, 2018Assignee: Samsung Electronics Co., Ltd.Inventors: Shin-Jun Lee, K Santle Camilus, Sumedh Mannar, Vijay A, Moo-Jung Kim, Amit Kumar, Sung-Dae Cho, Pankaj Kumar Bajpai, Piyush Gupta, Rahul Chouhan, Hyung-Suk Kim, Ki-Huk Lee
-
Patent number: 9542735Abstract: A method and a device to compose an image by eliminating one or more moving objects in a scene being captured are provided. The method includes capturing plurality of images, generating a background image with a plurality of stationary objects after aligning the plurality of captured images, selecting a base image from a plurality of the aligned images, wherein the base image is selected based on a highest similarity measure with the background image, identifying the at least one moving object in the base image, and eliminating said identified at least one moving object in the base image to compose said image.Type: GrantFiled: April 23, 2015Date of Patent: January 10, 2017Assignee: Samsung Electronics Co., Ltd.Inventors: Alok Shankarlal Shukla, Pankaj Kumar Bajpai, Kasireddy Viswanatha Reddy, Keyur Ruganathbhai Ranipa
-
Publication number: 20160065943Abstract: An apparatus and a method for displaying images in an electronic device are provided. The electronic device includes a processor that obtains an image and a depth map corresponding to the image, separates the image into one or more areas based on the depth map of the image, applies an effect, which is different from at least one of other areas, to at least one of the areas separated from the image, and connects the areas, to which the different effects have been applied, as a single image, and a display that displays the single image.Type: ApplicationFiled: September 3, 2015Publication date: March 3, 2016Inventors: Jong-Hwa YIM, Shin-Jun LEE, K Santle CAMILUS, Pankaj Kumar BAJPAI, Patil Mahesh MOHAN, Sourabh Singh YADAV, Hyung-Suk KIM, Jung-Eun LEE, Sung-Dae CHO, Jayakarthick S., Keyur Ruganathbhai RANIPA
-
Publication number: 20150319373Abstract: A method and a device to compose an image by eliminating one or more moving objects in a scene being captured are provided. The method includes capturing plurality of images, generating a background image with a plurality of stationary objects after aligning the plurality of captured images, selecting a base image from a plurality of the aligned images, wherein the base image is selected based on a highest similarity measure with the background image, identifying the at least one moving object in the base image, and eliminating said identified at least one moving object in the base image to compose said image.Type: ApplicationFiled: April 23, 2015Publication date: November 5, 2015Inventors: Alok Shankarlal SHUKLA, Pankaj Kumar BAJPAI, Kasireddy Viswanatha REDDY, Keyur Ruganathbhai RANIPA
-
Publication number: 20150233724Abstract: An electronic device and method for capturing an image are disclosed. The electronic device includes an image sensor configured to capture images, a location sensor configured to detect a location of the electronic device, and a processor. The processor may execute the method, which includes capturing a first image, and detecting a first location where the first image is captured, detecting, by a processor, a second location at which a second image is to be captured and generating guidance information for travel to the second location, and when a present location is within a predefined range of the second location, automatically capturing the second image.Type: ApplicationFiled: February 20, 2015Publication date: August 20, 2015Inventors: Shin-Jun LEE, K Santle CAMILUS, Sumedh MANNAR, Vijay A, Moo-Jung KIM, Amit KUMAR, Sung-Dae CHO, Pankaj Kumar BAJPAI, Piyush GUPTA, Rahul CHOUHAN, Hyung-Suk KIM, Ki-Huk LEE
-
Patent number: 9111329Abstract: Disclosed is a method and apparatus for generating fixed size compressed images. The method includes grouping member entities of the image into a plurality of groups based on each image features, each of the plurality of groups including member entities sharing common features; selecting at least one group representative from at least one of the plurality of groups; estimating final control parameters for each of the group representatives in an iterative manner; and compressing the image based on the estimated control parameters.Type: GrantFiled: December 26, 2012Date of Patent: August 18, 2015Assignee: Samsung Electronics Co., LtdInventor: Pankaj Kumar Bajpai
-
Publication number: 20150086127Abstract: A method and an image capturing device configured to generate a defocused image from a reference image and one or more of focal bracketed images to provide an artificially defocused blurred image. The artificially defocused blurred image is a fusion image composed by processing the reference image and one or more of focal bracketed images to provide a clear foreground with gradual blurred background based on a created depth map. The method is time efficient as it provides faster processing on a captured and down sampled reference image and one or more captured down sampled aligned focal bracketed images. The depth map created using region based segmentation reduces a misclassification at a time of classifying foreground-background and misclassification of pixels to provide fast, robust artificial blurring of background in the captured reference image.Type: ApplicationFiled: May 9, 2014Publication date: March 26, 2015Applicant: Samsung Electronics Co., LtdInventors: K. Santle Camilus, Sabari Raju Shanmugam, Jayakarthick S., Narasimha Gopalakrishna Pai, Pankaj Kumar Bajpai, Gaurav Kumar Jain