Patents by Inventor Deepanshu Arora

Deepanshu Arora 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).

  • Document boundary detection using deep learning model and image processing algorithms
    Patent number: 10970847
    Abstract: Techniques are disclosed for document boundary detection (BD) from an input image using a combination of deep learning model and image processing algorithms. Quadrilaterals approximating the document boundaries in the input image are determined and rated separately using both these approaches: deep leaning using convolutional neural network (CNN) and heuristics using image processing algorithms. Thereafter, the best rated quadrilateral is selected from the quadrilaterals obtained from both the approaches.
    Type: Grant
    Filed: May 16, 2019
    Date of Patent: April 6, 2021
    Assignee: Adobe Inc.
    Inventors: Prasenjit Mondal, Anuj Shara, Ankit Bal, Deepanshu Arora, Siddharth Kumar
  • DOCUMENT BOUNDARY DETECTION USING DEEP LEARNING MODEL AND IMAGE PROCESSING ALGORITHMS
    Publication number: 20200364875
    Abstract: Techniques are disclosed for document boundary detection (BD) from an input image using a combination of deep learning model and image processing algorithms. Quadrilaterals approximating the document boundaries in the input image are determined and rated separately using both these approaches: deep leaning using convolutional neural network (CNN) and heuristics using image processing algorithms. Thereafter, the best rated quadrilateral is selected from the quadrilaterals obtained from both the approaches.
    Type: Application
    Filed: May 16, 2019
    Publication date: November 19, 2020
    Applicant: Adobe Inc.
    Inventors: Prasenjit Mondal, Anuj Shara, Ankit Bal, Deepanshu Arora, Siddharth Kumar
  • Removal of shadows from document images while preserving fidelity of image contents
    Patent number: 10559067
    Abstract: Techniques are disclosed for generating a shadow map of a digital image. In some examples, a method may include generating a shadow mask of a digital image, generating a dilated de-noised binarized gradient image based on the shadow mask, generating a binarized median-filtered gray image based on the digital image and the dilated de-noised binarized gradient image, and generating a shadow map based on the shadow mask and the binarized median-filtered gray image. The generated shadow map can then be used to remove shadows from the digital image without degrading the quality of the image content in the digital image.
    Type: Grant
    Filed: February 28, 2018
    Date of Patent: February 11, 2020
    Assignee: Adobe Inc.
    Inventors: Prasenjit Mondal, Ruppesh Nalwaya, Ram Bhushan Agrawal, Deepanshu Arora, Anuj Shara
  • REMOVAL OF SHADOWS FROM DOCUMENT IMAGES WHILE PRESERVING FIDELITY OF IMAGE CONTENTS
    Publication number: 20190266706
    Abstract: Techniques are disclosed for generating a shadow map of a digital image. In some examples, a method may include generating a shadow mask of a digital image, generating a dilated de-noised binarized gradient image based on the shadow mask, generating a binarized median-filtered gray image based on the digital image and the dilated de-noised binarized gradient image, and generating a shadow map based on the shadow mask and the binarized median-filtered gray image. The generated shadow map can then be used to remove shadows from the digital image without degrading the quality of the image content in the digital image.
    Type: Application
    Filed: February 28, 2018
    Publication date: August 29, 2019
    Applicant: Adobe Inc.
    Inventors: Prasenjit Mondal, Ruppesh Nalwaya, Ram Bhushan Agrawal, Deepanshu Arora, Anuj Shara